High-level prior-based loss functions for medical image segmentation: A survey
Today, deep convolutional neural networks (CNNs) have demonstrated state of the art performance for supervised medical image segmentation, across various imaging modalities and tasks. Despite early success, segmentation networks may still generate anatomically aberrant segmentations, with holes or i...
Uloženo v:
| Vydáno v: | Computer vision and image understanding Ročník 210; s. 103248 |
|---|---|
| Hlavní autoři: | , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier Inc
01.09.2021
Elsevier |
| Témata: | |
| ISSN: | 1077-3142, 1090-235X |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Today, deep convolutional neural networks (CNNs) have demonstrated state of the art performance for supervised medical image segmentation, across various imaging modalities and tasks. Despite early success, segmentation networks may still generate anatomically aberrant segmentations, with holes or inaccuracies near the object boundaries. To mitigate this effect, recent research works have focused on incorporating spatial information or prior knowledge to enforce anatomically plausible segmentation. If the integration of prior knowledge in image segmentation is not a new topic in classical optimization approaches, it is today an increasing trend in CNN based image segmentation, as shown by the growing literature on the topic. In this survey, we focus on high level prior, embedded at the loss function level. We categorize the articles according to the nature of the prior: the object shape, size, topology, and the inter-regions constraints. We highlight strengths and limitations of current approaches, discuss the challenge related to the design and the integration of prior-based losses, and the optimization strategies, and draw future research directions.
•Review of methods that incorporate prior knowledge in deep learning loss function for medical image segmentation•Understanding the mechanisms behind the design and implementation of prior based losses.•Categorization of prior-based losses according to the nature of the prior constraints.•Overview on:•The types of priors existing in the literature and how they are modeled.•The major challenges linked to the design of such prior-based losses.•Their common training and optimization strategies. |
|---|---|
| AbstractList | Today, deep convolutional neural networks (CNNs) have demonstrated state of the art performance for supervised medical image segmentation, across various imaging modalities and tasks. Despite early success, segmentation networks may still generate anatomically aberrant segmentations, with holes or inaccuracies near the object boundaries. To mitigate this effect, recent research works have focused on incorporating spatial information or prior knowledge to enforce anatomically plausible segmentation. If the integration of prior knowledge in image segmentation is not a new topic in classical optimization approaches, it is today an increasing trend in CNN based image segmentation, as shown by the growing literature on the topic. In this survey, we focus on high level prior, embedded at the loss function level. We categorize the articles according to the nature of the prior: the object shape, size, topology, and the inter-regions constraints. We highlight strengths and limitations of current approaches, discuss the challenge related to the design and the integration of prior-based losses, and the optimization strategies, and draw future research directions. Today, deep convolutional neural networks (CNNs) have demonstrated state of the art performance for supervised medical image segmentation, across various imaging modalities and tasks. Despite early success, segmentation networks may still generate anatomically aberrant segmentations, with holes or inaccuracies near the object boundaries. To mitigate this effect, recent research works have focused on incorporating spatial information or prior knowledge to enforce anatomically plausible segmentation. If the integration of prior knowledge in image segmentation is not a new topic in classical optimization approaches, it is today an increasing trend in CNN based image segmentation, as shown by the growing literature on the topic. In this survey, we focus on high level prior, embedded at the loss function level. We categorize the articles according to the nature of the prior: the object shape, size, topology, and the inter-regions constraints. We highlight strengths and limitations of current approaches, discuss the challenge related to the design and the integration of prior-based losses, and the optimization strategies, and draw future research directions. •Review of methods that incorporate prior knowledge in deep learning loss function for medical image segmentation•Understanding the mechanisms behind the design and implementation of prior based losses.•Categorization of prior-based losses according to the nature of the prior constraints.•Overview on:•The types of priors existing in the literature and how they are modeled.•The major challenges linked to the design of such prior-based losses.•Their common training and optimization strategies. |
| ArticleNumber | 103248 |
| Author | El Jurdi, Rosana Abdallah, Fahed Honeine, Paul Cheplygina, Veronika Petitjean, Caroline |
| Author_xml | – sequence: 1 givenname: Rosana orcidid: 0000-0003-0509-9620 surname: El Jurdi fullname: El Jurdi, Rosana email: rosana.el-jurdi@univ-rouen.fr organization: Normandie Univ, INSA Rouen, UNIROUEN, UNIHAVRE, LITIS, Rouen, France – sequence: 2 givenname: Caroline surname: Petitjean fullname: Petitjean, Caroline email: caroline.petitjean@univ-rouen.fr organization: Normandie Univ, INSA Rouen, UNIROUEN, UNIHAVRE, LITIS, Rouen, France – sequence: 3 givenname: Paul orcidid: 0000-0002-3042-183X surname: Honeine fullname: Honeine, Paul email: paul.honeine@univ-rouen.fr organization: Normandie Univ, INSA Rouen, UNIROUEN, UNIHAVRE, LITIS, Rouen, France – sequence: 4 givenname: Veronika orcidid: 0000-0003-0176-9324 surname: Cheplygina fullname: Cheplygina, Veronika email: v.cheplygina@tue.nl organization: Computer Science Department, IT University of Copenhagen, Denmark – sequence: 5 givenname: Fahed surname: Abdallah fullname: Abdallah, Fahed email: fahed.abdallah76@gmail.com organization: Université Libanaise, Hadath, Beyrouth, Lebanon |
| BackLink | https://normandie-univ.hal.science/hal-03410506$$DView record in HAL |
| BookMark | eNp9kD1PwzAQhi1UJNrCH2DyypDi80eSIpaqAopUwQISm-U659ZVmiA7jdR_T6LAwtDJp_P7-M7PhIyqukJCboHNgEF6v5_Z1h9nnHHoGoLL_IKMgc1ZwoX6GvV1liUCJL8ikxj3jAHIOYzJ28pvd0mJLZb0O_g6JBsTsaBlHSN1x8o2vq66qg70gIW3pqT-YLZII24PWDWmv3-gCxqPocXTNbl0pox483tOyefz08dylazfX16Xi3ViRZY3iUBpBBRQSGY3mROpcanlyjrLmNugc8gzzFgqHRjFZTFXfSIHtEqZTKGYkrvh3Z0pdbf3wYSTro3Xq8Va9z0mJDDF0ha6bD5kbeg-FdBp64e9m2B8qYHp3qHe696h7h3qwWGH8n_o36yz0OMAYSeg9Rh0tB4r2-kLaBtd1P4c_gPDsI2B |
| CitedBy_id | crossref_primary_10_1002_mp_18053 crossref_primary_10_1007_s10489_024_05378_1 crossref_primary_10_1038_s41598_025_00116_0 crossref_primary_10_1016_j_cviu_2023_103774 crossref_primary_10_1007_s11042_023_16416_4 crossref_primary_10_1186_s12880_025_01737_7 crossref_primary_10_1109_TMI_2023_3251368 crossref_primary_10_1016_j_neucom_2025_131346 crossref_primary_10_1007_s11042_023_16490_8 crossref_primary_10_1117_1_JMI_11_4_044002 crossref_primary_10_1016_j_media_2024_103189 crossref_primary_10_1002_eqe_3966 crossref_primary_10_1109_ACCESS_2022_3163711 crossref_primary_10_3390_rs13183562 crossref_primary_10_1016_j_cviu_2023_103765 crossref_primary_10_1117_1_JRS_17_038501 crossref_primary_10_1007_s12021_024_09683_5 crossref_primary_10_1016_j_mri_2025_110505 crossref_primary_10_3389_fnins_2023_1220172 crossref_primary_10_1109_JBHI_2023_3305377 crossref_primary_10_3389_fcomp_2022_805166 crossref_primary_10_1109_TIM_2025_3547079 crossref_primary_10_1016_j_engappai_2024_108389 crossref_primary_10_1016_j_compmedimag_2023_102246 crossref_primary_10_1016_j_cviu_2023_103918 crossref_primary_10_1016_j_media_2023_102863 crossref_primary_10_3390_math13152417 crossref_primary_10_1002_hbm_25899 crossref_primary_10_1109_TMI_2024_3469214 crossref_primary_10_1109_JBHI_2025_3528432 crossref_primary_10_1007_s10851_022_01102_1 crossref_primary_10_3390_s22020523 crossref_primary_10_3390_s22062084 crossref_primary_10_1109_TPAMI_2023_3289667 crossref_primary_10_1016_j_compmedimag_2025_102531 crossref_primary_10_1016_j_eswa_2024_123518 crossref_primary_10_1109_TNNLS_2022_3190836 crossref_primary_10_1007_s10851_024_01172_3 crossref_primary_10_1016_j_intonc_2025_06_007 crossref_primary_10_1016_j_optlastec_2024_111298 crossref_primary_10_1016_j_compbiomed_2023_107069 crossref_primary_10_3390_cancers15174389 crossref_primary_10_1016_j_patcog_2023_109925 crossref_primary_10_1016_j_cviu_2023_103744 crossref_primary_10_3390_biomedicines11102687 crossref_primary_10_1002_hcs2_119 crossref_primary_10_1016_j_compbiomed_2024_108137 crossref_primary_10_1016_j_compbiomed_2024_108613 crossref_primary_10_1109_TMI_2022_3224660 crossref_primary_10_1007_s11517_024_03018_x crossref_primary_10_1016_j_cviu_2025_104421 crossref_primary_10_7717_peerj_cs_1122 |
| Cites_doi | 10.1007/s11042-020-08898-3 10.1007/978-3-319-65981-7_12 10.3390/jimaging7020019 10.1109/ISBI48211.2021.9434088 10.1016/j.media.2017.07.005 10.1186/s12880-015-0068-x 10.1109/ICIP.2005.1530282 10.1006/cviu.1995.1004 10.1007/s12530-019-09297-2 10.1109/CVPR42600.2020.01243 10.1109/TMI.2018.2837502 10.1109/TIP.2019.2941265 10.1016/j.compbiomed.2018.05.018 10.1109/34.868688 10.1038/s41598-020-69920-0 10.1016/j.media.2019.101551 10.1109/BIBM47256.2019.8983121 10.1007/s11263-008-0163-3 10.1007/3-540-47967-8_6 10.1109/72.286888 10.1007/978-3-319-67558-9_3 10.1007/s10278-019-00227-x 10.1016/j.media.2009.05.004 10.1109/TMI.2017.2743464 10.1016/j.media.2019.02.009 10.1007/s11263-006-8711-1 10.1109/JSTSP.2020.3001502 10.1007/s11263-006-7934-5 10.3389/fcvm.2020.00025 10.1007/s00521-017-3158-6 10.1109/WACV.2018.00163 |
| ContentType | Journal Article |
| Copyright | 2021 Elsevier Inc. licence_http://creativecommons.org/publicdomain/zero |
| Copyright_xml | – notice: 2021 Elsevier Inc. – notice: licence_http://creativecommons.org/publicdomain/zero |
| DBID | AAYXX CITATION 1XC VOOES |
| DOI | 10.1016/j.cviu.2021.103248 |
| DatabaseName | CrossRef Hyper Article en Ligne (HAL) Hyper Article en Ligne (HAL) (Open Access) |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences Engineering Computer Science Mathematics Statistics |
| EISSN | 1090-235X |
| ExternalDocumentID | oai:HAL:hal-03410506v1 10_1016_j_cviu_2021_103248 S1077314221000928 |
| GroupedDBID | --K --M -~X .DC .~1 0R~ 1B1 1~. 1~5 29F 4.4 457 4G. 5GY 5VS 6TJ 7-5 71M 8P~ AABNK AACTN AAEDT AAEDW AAIAV AAIKC AAIKJ AAKOC AALRI AAMNW AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABEFU ABFNM ABJNI ABMAC ABXDB ABYKQ ACDAQ ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADFGL ADJOM ADMUD ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CAG COF CS3 DM4 DU5 EBS EFBJH EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HF~ HVGLF HZ~ IHE J1W JJJVA KOM LG5 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SDF SDG SDP SES SEW SPC SPCBC SSV SSZ T5K TN5 XPP ZMT ~G- 9DU AATTM AAXKI AAYWO AAYXX ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS SST ~HD 1XC VOOES |
| ID | FETCH-LOGICAL-c378t-3e4a31d1d40cb7f36af6c25cfc00fbeffe27e7064f1a524d956af681ec55a75e3 |
| ISICitedReferencesCount | 62 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000691812700007&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1077-3142 |
| IngestDate | Wed Nov 19 06:36:45 EST 2025 Sat Nov 29 07:05:59 EST 2025 Tue Nov 18 22:27:07 EST 2025 Fri Feb 23 02:42:16 EST 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Deep learning Anatomical constraint losses Convolutional neural networks Medical image segmentation Prior-based loss functions |
| Language | English |
| License | licence_http://creativecommons.org/publicdomain/zero/: http://creativecommons.org/publicdomain/zero |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c378t-3e4a31d1d40cb7f36af6c25cfc00fbeffe27e7064f1a524d956af681ec55a75e3 |
| ORCID | 0000-0002-3042-183X 0000-0003-0509-9620 0000-0003-0176-9324 0000-0003-0013-5370 |
| OpenAccessLink | https://normandie-univ.hal.science/hal-03410506 |
| ParticipantIDs | hal_primary_oai_HAL_hal_03410506v1 crossref_citationtrail_10_1016_j_cviu_2021_103248 crossref_primary_10_1016_j_cviu_2021_103248 elsevier_sciencedirect_doi_10_1016_j_cviu_2021_103248 |
| PublicationCentury | 2000 |
| PublicationDate | September 2021 2021-09-00 2021-09 |
| PublicationDateYYYYMMDD | 2021-09-01 |
| PublicationDate_xml | – month: 09 year: 2021 text: September 2021 |
| PublicationDecade | 2020 |
| PublicationTitle | Computer vision and image understanding |
| PublicationYear | 2021 |
| Publisher | Elsevier Inc Elsevier |
| Publisher_xml | – name: Elsevier Inc – name: Elsevier |
| References | Zotti, Luo, Humbert, Lalande, Jodoin (b91) 2017; 10663 Milnor (b56) 2016 Heimann, Meinzer (b28) 2009; 13 Mirikharaji, Hamarneh (b57) 2018 Zhou, Ruan, Canu (b90) 2019; 3–4 Trullo, R., Petitjean, C., Ruan, S., Dubray, B., Nie, D., Shen, D., 2017. Joint segmentation of multiple thoracic organs in CT Images with two collaborative deep architectures. In: MICCAI’17 Workshop Deep Learning in Medical Image Analysis. Ségonne, Fischl (b73) 2015 Baumgartner, Koch, Pollefeys, Konukoglu (b3) 2017 Hu, H., Zheng, Y., Zhou, Q., Xiao, J., Chen, S., Guan, Q., 2019. MC-Unet: Multi-scale Convolution Unet for Bladder Cancer Cell Segmentation in Phase-Contrast Microscopy Images. In: 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 1197-1199. Taha, Hanbury (b79) 2015; 15 El Jurdi, Petitjean, Honeine, Abdallah (b21) 2020; 14 Lei, Wang, Wan, Zhang, Meng, Nandi (b45) 2020 Ganaye, Sdika, Triggs, Benoit-Cattin (b24) 2019; 58 Peng, Kervadec, Dolz, Ayed, Pedersoli, Desrosiers (b64) 2020; 130 Xu, Pham, Prince (b84) 2000; 2 Kervadec, Dolz, Tang, Granger, Boykov, Ayed (b38) 2019; 54 Renard, Guedria, De Palma, Vuillerme (b69) 2020; 10 Boyd, Vandenberghe (b6) 2004 Ganaye (b23) 2019 Haque, Neubert (b26) 2020; 18 Chen, Qin, Qiu, Tarroni, Duan, Bai, Rueckert (b13) 2020; 7 Isensee, Jaeger, Full, Wolf, Engelhardt, Maier-Hein (b33) 2018 Kervadec, Dolz, Yuan, Desrosiers, Granger, Ayed (b40) 2019 Shit, S., Paetzold, J.C., Sekuboyina, A., Zhylka, A., Ezhov, I., Unger, A., Pluim, J.P.W., Tetteh, G., Menze, B.H., 2019. clDice - a Topology-preserving loss function for tubular structure segmentation. In: Medical Imaging Meets NeurIPS 2019 Workshop. Yu, C., Wang, J., Gao, C., Yu, G., Shen, C., Sang, N., 2020. Context prior for scene segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Lillo, Loh, Hui, Zak (b46) 1993; 4 Taghanaki, Abhishek, Cohen, Cohen-Adad, Hamarneh (b78) 2019 . Charoenphakdee, Lee, Sugiyama (b12) 2019 Rousson, M., Paragios, N., 2002. Shape priors for level set representations. in: European Conf. on Computer Vision, Vol. 2,, pp. 78–92. Dolz, Ben Ayed, Desrosiers (b19) 2017 Petit, Thome, Soler (b65) 2019 BenTaieb, Hamarneh (b4) 2016 Nosrati, Hamarneh (b60) 2016 Foulonneau, Charbonnier, Heitz (b22) 2009; 81 Grady (b25) 2012 Veksler (b81) 2008 Liu, Veksler, Samarabandu (b49) 2008 Slabaugh, G., Unal, G., 2005. Graph cuts segmentation using an elliptical shape prior. In: International Conference on Image Processing (ICIP), Vol. 2, pp. 1222–1225. Ravishankar, Venkataramani, Thiruvenkadam, Sudhakar, Vaidya (b66) 2017 Milletari, Navab, Ahmadi (b55) 2016 Meyer, Noblet, Mazzara, Lallement (b54) 2018; 98 Marquez-Neila, P., Salzmann, M., Fua, P., 2017. Imposing Hard Constraints on Deep Networks: Promises and Limitations. In: CVPR Workshop on Negative Results in Computer Vision. Hu, Li, Samaras, Chen (b30) 2019; 32 Hesamian, Jia, He, Kennedy (b29) 2019; 32 Cootes, Cooper, Taylor, Graham (b16) 1995; 61 Isensee, Petersen, Klein, Zimmerer, Jaeger, Kohl, Wasserthal, Koehler, Norajitra, Wirkert (b34) 2019 Jang, Hong, Ha, Kim, Chang (b35) 2018 Yue, Luo, Ye, Xu, Zhuang (b88) 2019 Vicente, Kolmogorov, Rother (b82) 2008 Kim, Ye (b41) 2020; 29 Chouzenoux, Corbineau, Pesquet (b14) 2019 El Jurdi, R., Petitjean, C., Honeine, P., Abdallah, F., 2019. Organ Segmentation in CT Images With Weak Annotations: A Preliminary Study. In: 27th GRETSI Symposium on Signal and Image Processing, Lille, France. Bernard, Lalande, Zotti, Cervenansky, Yang, Heng, Cetin, Lekadir, Camara, Gonzalez Ballester, Sanroma, Napel, Petersen, Tziritas, Grinias, Khened, Kollerathu, Krishnamurthi, Rohé, Pennec, Sermesant, Isensee, Jäger, Maier-Hein, Full, Wolf, Engelhardt, Baumgartner, Koch, Wolterink, Išgum, Jang, Hong, Patravali, Jain, Humbert, Jodoin (b5) 2018; 37 Ronneberger, Fischer, Brox (b71) 2015 Litjens, Kooi, Bejnordi, Setio, Ciompi, Ghafoorian, van der Laak, van Ginneken, Sánchez (b48) 2017; 42 Oda, Roth, Chiba, Sokolić, Kitasaka, Oda, Hinoki, Uchida, Schnabel, Mori (b61) 2018 Byrne, Clough, Montana, King (b8) 2021 Magadza, Viriri (b52) 2021; 7 Pathak, Krähenbühl, Darrell (b63) 2015 Lorenzo-Valdes, Sanchez-Ortiz, Mohiaddin, Rueckert (b51) 2002 Shi, Malik (b74) 2000; 22 Krithiga, Geetha (b42) 2020 Ayed, Li, Islam, Garvin, Chhem (b2) 2008 Hu, Wang, Fuxin, Samaras, Chen (b31) 2021 Lambert, Z., Petitjean, C., Guyader, C.L., 2021. A geometrically-constrained deep network for CT image segmentation. In: IEEE International Symposium on Biomedical Imaging (ISBI). (b59) 1999 Kuo, Angelova, Malik, Lin (b43) 2019 Clough, Byrne, Oksuz, Zimmer, Schnabel, King (b15) 2020 Arif, Rahman, Knapp, Slabaugh (b1) 2018 Lin, Goyal, Girshick, He, Dollár (b47) 2017 Oktay, Ferrante, Kamnitsas, Heinrich, Bai, Caballero, Cook, de Marvao, Dawes, O‘Regan, Kainz, Glocker, Rueckert (b62) 2018; 37 Jiang, Grigorev, Rho, Tian, Fu, Sori, Khan, Liu (b36) 2017; 29 Kervadec, Dolz, Wang, Granger, ben Ayed (b39) 2020 Yang, S., Kweon, J., Kim, Y.-H., 2019. Major vessel segmentation on X-ray coronary angiography using deep networks with a novel penalty loss function. In: International Conference on Medical Imaging with Deep Learning – Extended Abstract Track, London, UK Boykov, Funka-Lea (b7) 2006; 70 Long, Shelhamer, Darrell (b50) 2015 Cremers, Rousson, Deriche (b17) 2007; 72 Kervadec, Bouchtiba, Desrosiers, Granger, Dolz, Ben Ayed (b37) 2019; 102 Reddy, C., Gopinath, K., Lombaert, H., 2019. Brain tumor segmentation using topological loss in convolutional networks. In: MIDL, London, UK Yang, Bian, Yu, Ni, Heng (b85) 2018 Mosinska, Márquez-Neila, Kozinski, Fua (b58) 2018 Zhang, Petitjean, Ainouz (b89) 2020 Sudre, Li, Vercauteren, Ourselin, Cardoso (b77) 2017 Çiçek, Abdulkadir, Lienkamp, Brox, Ronneberger (b10) 2016; 9901 Debelee, Schwenker, Ibenthal, Yohannes (b18) 2020; 11 Havaei, Guizard, Larochelle, Jodoin (b27) 2016 Chahal, Pandey, Goel (b11) 2020; 79 Wang, P., Chen, P., Yuan, Y., Liu, D., Huang, Z., Hou, X., Cottrell, G., 2018. Understanding convolution for semantic segmentation. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1451–1460. Caliva, F., Iriondo, C., Martinez, A.M., Majumdar, S., Pedoia, V., 2019. Distance Map Loss Penalty Term for Semantic Segmentation. In: International Conference on Medical Imaging with Deep Learning – Extended Abstract Track,London, UK Rohlfing, Brandt, Menzel, Russakoff, Maurer (b70) 2005 Razzak, Naz, Zaib (b67) 2018 Baumgartner (10.1016/j.cviu.2021.103248_b3) 2017 10.1016/j.cviu.2021.103248_b87 10.1016/j.cviu.2021.103248_b44 Rohlfing (10.1016/j.cviu.2021.103248_b70) 2005 Lei (10.1016/j.cviu.2021.103248_b45) 2020 Meyer (10.1016/j.cviu.2021.103248_b54) 2018; 98 10.1016/j.cviu.2021.103248_b86 10.1016/j.cviu.2021.103248_b83 Mosinska (10.1016/j.cviu.2021.103248_b58) 2018 Veksler (10.1016/j.cviu.2021.103248_b81) 2008 (10.1016/j.cviu.2021.103248_b59) 1999 Petit (10.1016/j.cviu.2021.103248_b65) 2019 10.1016/j.cviu.2021.103248_b9 Ravishankar (10.1016/j.cviu.2021.103248_b66) 2017 Kervadec (10.1016/j.cviu.2021.103248_b40) 2019 Charoenphakdee (10.1016/j.cviu.2021.103248_b12) 2019 Heimann (10.1016/j.cviu.2021.103248_b28) 2009; 13 Taghanaki (10.1016/j.cviu.2021.103248_b78) 2019 Ganaye (10.1016/j.cviu.2021.103248_b24) 2019; 58 Zhang (10.1016/j.cviu.2021.103248_b89) 2020 Hu (10.1016/j.cviu.2021.103248_b30) 2019; 32 Dolz (10.1016/j.cviu.2021.103248_b19) 2017 Hu (10.1016/j.cviu.2021.103248_b31) 2021 Chouzenoux (10.1016/j.cviu.2021.103248_b14) 2019 Jiang (10.1016/j.cviu.2021.103248_b36) 2017; 29 Krithiga (10.1016/j.cviu.2021.103248_b42) 2020 10.1016/j.cviu.2021.103248_b53 Oda (10.1016/j.cviu.2021.103248_b61) 2018 Boykov (10.1016/j.cviu.2021.103248_b7) 2006; 70 Pathak (10.1016/j.cviu.2021.103248_b63) 2015 Milletari (10.1016/j.cviu.2021.103248_b55) 2016 Chahal (10.1016/j.cviu.2021.103248_b11) 2020; 79 Isensee (10.1016/j.cviu.2021.103248_b33) 2018 Nosrati (10.1016/j.cviu.2021.103248_b60) 2016 Peng (10.1016/j.cviu.2021.103248_b64) 2020; 130 Kervadec (10.1016/j.cviu.2021.103248_b38) 2019; 54 BenTaieb (10.1016/j.cviu.2021.103248_b4) 2016 Chen (10.1016/j.cviu.2021.103248_b13) 2020; 7 Oktay (10.1016/j.cviu.2021.103248_b62) 2018; 37 Debelee (10.1016/j.cviu.2021.103248_b18) 2020; 11 Sudre (10.1016/j.cviu.2021.103248_b77) 2017 Bernard (10.1016/j.cviu.2021.103248_b5) 2018; 37 10.1016/j.cviu.2021.103248_b20 Kervadec (10.1016/j.cviu.2021.103248_b39) 2020 Liu (10.1016/j.cviu.2021.103248_b49) 2008 Kervadec (10.1016/j.cviu.2021.103248_b37) 2019; 102 Taha (10.1016/j.cviu.2021.103248_b79) 2015; 15 Cremers (10.1016/j.cviu.2021.103248_b17) 2007; 72 Grady (10.1016/j.cviu.2021.103248_b25) 2012 Ronneberger (10.1016/j.cviu.2021.103248_b71) 2015 Byrne (10.1016/j.cviu.2021.103248_b8) 2021 Lillo (10.1016/j.cviu.2021.103248_b46) 1993; 4 Long (10.1016/j.cviu.2021.103248_b50) 2015 10.1016/j.cviu.2021.103248_b68 Cootes (10.1016/j.cviu.2021.103248_b16) 1995; 61 Hesamian (10.1016/j.cviu.2021.103248_b29) 2019; 32 Mirikharaji (10.1016/j.cviu.2021.103248_b57) 2018 Çiçek (10.1016/j.cviu.2021.103248_b10) 2016; 9901 Lorenzo-Valdes (10.1016/j.cviu.2021.103248_b51) 2002 Ganaye (10.1016/j.cviu.2021.103248_b23) 2019 Renard (10.1016/j.cviu.2021.103248_b69) 2020; 10 Kim (10.1016/j.cviu.2021.103248_b41) 2020; 29 El Jurdi (10.1016/j.cviu.2021.103248_b21) 2020; 14 Foulonneau (10.1016/j.cviu.2021.103248_b22) 2009; 81 Havaei (10.1016/j.cviu.2021.103248_b27) 2016 Ségonne (10.1016/j.cviu.2021.103248_b73) 2015 Jang (10.1016/j.cviu.2021.103248_b35) 2018 Yang (10.1016/j.cviu.2021.103248_b85) 2018 Zhou (10.1016/j.cviu.2021.103248_b90) 2019; 3–4 10.1016/j.cviu.2021.103248_b32 10.1016/j.cviu.2021.103248_b76 10.1016/j.cviu.2021.103248_b75 Lin (10.1016/j.cviu.2021.103248_b47) 2017 10.1016/j.cviu.2021.103248_b72 Isensee (10.1016/j.cviu.2021.103248_b34) 2019 Vicente (10.1016/j.cviu.2021.103248_b82) 2008 Zotti (10.1016/j.cviu.2021.103248_b91) 2017; 10663 Magadza (10.1016/j.cviu.2021.103248_b52) 2021; 7 Xu (10.1016/j.cviu.2021.103248_b84) 2000; 2 Yue (10.1016/j.cviu.2021.103248_b88) 2019 Litjens (10.1016/j.cviu.2021.103248_b48) 2017; 42 Razzak (10.1016/j.cviu.2021.103248_b67) 2018 Shi (10.1016/j.cviu.2021.103248_b74) 2000; 22 Arif (10.1016/j.cviu.2021.103248_b1) 2018 Kuo (10.1016/j.cviu.2021.103248_b43) 2019 10.1016/j.cviu.2021.103248_b80 Ayed (10.1016/j.cviu.2021.103248_b2) 2008 Clough (10.1016/j.cviu.2021.103248_b15) 2020 Milnor (10.1016/j.cviu.2021.103248_b56) 2016 Boyd (10.1016/j.cviu.2021.103248_b6) 2004 Haque (10.1016/j.cviu.2021.103248_b26) 2020; 18 |
| References_xml | – volume: 32 start-page: 5657 year: 2019 end-page: 5668 ident: b30 article-title: Topology-preserving deep image segmentation publication-title: Advances in Neural Information Processing Systems – year: 2020 ident: b42 article-title: Breast cancer detection, segmentation and classification on histopathology images analysis: A systematic review publication-title: Arch. Comput. Methods Eng. – start-page: 152 year: 2018 end-page: 160 ident: b85 article-title: Class-balanced deep neural network for automatic ventricular structure segmentation publication-title: STACOM@MICCAI – reference: Shit, S., Paetzold, J.C., Sekuboyina, A., Zhylka, A., Ezhov, I., Unger, A., Pluim, J.P.W., Tetteh, G., Menze, B.H., 2019. clDice - a Topology-preserving loss function for tubular structure segmentation. In: Medical Imaging Meets NeurIPS 2019 Workshop. – start-page: 12 year: 2018 end-page: 24 ident: b1 article-title: Shape-aware deep convolutional neural network for vertebrae segmentation publication-title: Computational Methods and Clinical Applications in Musculoskeletal Imaging – start-page: 642 year: 2002 end-page: 650 ident: b51 article-title: Atlas-based segmentation and tracking of 3D cardiac MR images using non-rigid registration publication-title: Proc. of Medical Image Computing and Computer-Assisted Intervention (MICCAI) – reference: Yu, C., Wang, J., Gao, C., Yu, G., Shen, C., Sang, N., 2020. Context prior for scene segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). – start-page: 460 year: 2016 end-page: 468 ident: b4 article-title: Topology aware fully convolutional networks for histology gland segmentation publication-title: MICCAI, Vol. 9901 – reference: Yang, S., Kweon, J., Kim, Y.-H., 2019. Major vessel segmentation on X-ray coronary angiography using deep networks with a novel penalty loss function. In: International Conference on Medical Imaging with Deep Learning – Extended Abstract Track, London, UK, – volume: 4 start-page: 931 year: 1993 end-page: 940 ident: b46 article-title: On solving constrained optimization problems with neural networks: a penalty method approach publication-title: IEEE Trans. Neural Netw. – start-page: 1796 year: 2015 end-page: 1804 ident: b63 article-title: Constrained convolutional neural networks for weakly supervised segmentation publication-title: ICCV – start-page: 3 year: 2021 end-page: 13 ident: b8 article-title: A persistent homology-based topological loss function for multi-class CNN segmentation of cardiac MRI publication-title: Statistical Atlases and Computational Models of the Heart. M&Ms and EMIDEC Challenges – reference: Rousson, M., Paragios, N., 2002. Shape priors for level set representations. in: European Conf. on Computer Vision, Vol. 2,, pp. 78–92. – reference: Slabaugh, G., Unal, G., 2005. Graph cuts segmentation using an elliptical shape prior. In: International Conference on Image Processing (ICIP), Vol. 2, pp. 1222–1225. – volume: 37 start-page: 2514 year: 2018 end-page: 2525 ident: b5 article-title: Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: Is the problem solved? publication-title: IEEE Trans. Med. Imaging – volume: 70 start-page: 109 year: 2006 end-page: 131 ident: b7 article-title: Graph cuts and efficient ND image segmentation publication-title: Int. J. Comput. Vis. – reference: Caliva, F., Iriondo, C., Martinez, A.M., Majumdar, S., Pedoia, V., 2019. Distance Map Loss Penalty Term for Semantic Segmentation. In: International Conference on Medical Imaging with Deep Learning – Extended Abstract Track,London, UK, – volume: 13 start-page: 543 year: 2009 end-page: 563 ident: b28 article-title: Statistical shape models for 3D medical image segmentation: A review publication-title: Med. Image Anal. – year: 2019 ident: b40 article-title: Constrained deep networks: Lagrangian optimization via log-barrier extensions – start-page: 9207 year: 2019 end-page: 9216 ident: b43 article-title: Shapemask: Learning to segment novel objects by refining shape priors publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision – volume: 10663 start-page: 73 year: 2017 end-page: 81 ident: b91 article-title: Gridnet with automatic shape prior registration for automatic MRI cardiac segmentation publication-title: Statistical Atlases and Computational Models of the Heart STACOM, Held in Conjunction with MICCAI, Quebec City, Canada – volume: 102 start-page: 285 year: 2019 end-page: 296 ident: b37 article-title: Boundary loss for highly unbalanced segmentation publication-title: Medical Imaging with Deep Learning – year: 2008 ident: b2 article-title: Area prior constrained level set evolution for medical image segmentation publication-title: Medical Imaging 2008: Image Processing, Vol. 6914 – volume: 79 start-page: 21771 year: 2020 end-page: 21814 ident: b11 article-title: A survey on brain tumor detection techniques for MR images publication-title: Multimedia Tools Appl. – year: 2017 ident: b3 article-title: An exploration of 2D and 3D deep learning techniques for Cardiac MR image segmentation publication-title: STACOM@MICCAI – reference: Lambert, Z., Petitjean, C., Guyader, C.L., 2021. A geometrically-constrained deep network for CT image segmentation. In: IEEE International Symposium on Biomedical Imaging (ISBI). – start-page: 228 year: 2018 end-page: 236 ident: b61 article-title: BESNet: Boundary-enhanced segmentation of cells in histopathological images publication-title: MICCAI – start-page: 737 year: 2018 end-page: 745 ident: b57 article-title: Star shape prior in fully convolutional networks for skin lesion segmentation publication-title: MICCAI, Vol. 11073 – start-page: 2999 year: 2017 end-page: 3007 ident: b47 article-title: Focal loss for dense object detection publication-title: ICCV – start-page: 961 year: 2019 end-page: 970 ident: b12 article-title: On symmetric losses for learning from corrupted labels publication-title: ICML, PMLR – start-page: 111 year: 2012 end-page: 135 ident: b25 article-title: Targeted image segmentation using graph methods publication-title: Image Processing and Analysis with Graphs – volume: 7 year: 2021 ident: b52 article-title: Deep learning for brain tumor segmentation: A survey of state-of-the-art publication-title: J. Imaging – volume: 11 start-page: 143 year: 2020 end-page: 163 ident: b18 article-title: Survey of deep learning in breast cancer image analysis publication-title: Evol. Syst. – volume: 58 year: 2019 ident: b24 article-title: Removing segmentation inconsistencies with semi-supervised non-adjacency constraint publication-title: Med. Image. Anal – reference: El Jurdi, R., Petitjean, C., Honeine, P., Abdallah, F., 2019. Organ Segmentation in CT Images With Weak Annotations: A Preliminary Study. In: 27th GRETSI Symposium on Signal and Image Processing, Lille, France. – volume: 22 start-page: 888 year: 2000 end-page: 905 ident: b74 article-title: Normalized cuts and image segmentation publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 22 year: 2019 ident: b34 article-title: NnU-Net: Self-adapting framework for U-net-based medical image segmentation publication-title: Bildverarbeitung FÜR Die Medizin 2019 – volume: 54 start-page: 88 year: 2019 end-page: 99 ident: b38 article-title: Constrained-CNN losses for weakly supervised segmentation publication-title: Med. Image Anal. – volume: 42 start-page: 60 year: 2017 end-page: 88 ident: b48 article-title: A survey on deep learning in medical image analysis publication-title: Med. Image Anal. – volume: 61 start-page: 38 year: 1995 end-page: 59 ident: b16 article-title: Active shape models - their training and application publication-title: Comput. Vis. Image Underst. – year: 2019 ident: b65 article-title: Biasing deep convnets for semantic segmentation of medical images with a prior-driven prediction function publication-title: Medical Imaging with Deep Learning – reference: Trullo, R., Petitjean, C., Ruan, S., Dubray, B., Nie, D., Shen, D., 2017. Joint segmentation of multiple thoracic organs in CT Images with two collaborative deep architectures. In: MICCAI’17 Workshop Deep Learning in Medical Image Analysis. – start-page: 3431 year: 2015 end-page: 3440 ident: b50 article-title: Fully convolutional networks for semantic segmentation publication-title: CVPR – start-page: 125 year: 2016 end-page: 148 ident: b27 article-title: Deep learning trends for focal brain pathology segmentation in MRI publication-title: Machine Learning for Health Informatics: State-of-the-Art and Future Challenges – start-page: 234 year: 2015 end-page: 241 ident: b71 article-title: U-Net: Convolutional networks for biomedical image segmentation publication-title: MICCAI – start-page: 488 year: 1999 end-page: 525 ident: b59 article-title: Penalty, barrier, and augmented Lagrangian methods publication-title: Numerical Optimization – start-page: 323 year: 2018 end-page: 350 ident: b67 article-title: Deep learning for medical image processing: Overview, challenges and the future publication-title: Lecture Notes in Computational Vision and Biomechanics – volume: 2 start-page: 129 year: 2000 end-page: 174 ident: b84 article-title: Image segmentation using deformable models publication-title: Handbook of Medical Imaging – volume: 10 start-page: 1 year: 2020 end-page: 16 ident: b69 article-title: Variability and reproducibility in deep learning for medical image segmentation publication-title: Sci. Rep. – start-page: 1 year: 2008 end-page: 8 ident: b82 article-title: Graph cut based image segmentation with connectivity priors publication-title: IEEE Computer Vision and Pattern Recognition (CVPR) – year: 2005 ident: b70 article-title: Quo vadis, atlas-based segmentation ? publication-title: The Handbook of Medical Image Analysis: Segmentation and Registration Models – volume: 130 start-page: 297 year: 2020 end-page: 308 ident: b64 article-title: Discretely-constrained deep network for weakly supervised segmentation publication-title: Neural Netw. Off. J. Int. Neural Netw. Soc. – year: 2004 ident: b6 article-title: Convex Optimization – volume: 7 start-page: 25 year: 2020 ident: b13 article-title: Deep learning for cardiac image segmentation: A review publication-title: Front. Cardiovasc. Med. – start-page: 1 year: 2008 end-page: 8 ident: b49 article-title: Graph cut with ordering constraints on labels and its applications publication-title: IEEE CVPR – start-page: 203 year: 2017 end-page: 211 ident: b66 article-title: Learning and incorporating shape models for semantic segmentation publication-title: MICCAI – year: 2021 ident: b31 article-title: Topology-aware segmentation using discrete Morse theory – year: 2017 ident: b77 article-title: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations publication-title: DLMIA/ML-CDS@MICCAI – volume: 15 start-page: 29 year: 2015 ident: b79 article-title: Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool publication-title: BMC Med. Imaging – reference: Reddy, C., Gopinath, K., Lombaert, H., 2019. Brain tumor segmentation using topological loss in convolutional networks. In: MIDL, London, UK, – volume: 3–4 year: 2019 ident: b90 article-title: A review: Deep learning for medical image segmentation using multi-modality fusion publication-title: Array – start-page: 120 year: 2018 end-page: 129 ident: b33 article-title: Automatic cardiac disease assessment on cine-MRI via time-series segmentation and domain specific features publication-title: Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges – start-page: 454 year: 2008 end-page: 467 ident: b81 article-title: Star shape prior for graph-cut image segmentation publication-title: ECCV – volume: 29 start-page: 1257 year: 2017 end-page: 1265 ident: b36 article-title: Medical image semantic segmentation based on deep learning publication-title: Neural Comput. Appl. – volume: 18 year: 2020 ident: b26 article-title: Deep learning approaches to biomedical image segmentation publication-title: Inform. Med. Unlocked – year: 2019 ident: b14 article-title: A proximal interior point algorithm with applications to image processing publication-title: J. Math. Imaging Vis. – year: 2020 ident: b39 article-title: Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervision publication-title: Medical Imaging with Deep Learning – start-page: 3136 year: 2018 end-page: 3145 ident: b58 article-title: Beyond the pixel-wise loss for topology-aware delineation publication-title: CVPR – volume: 72 start-page: 195 year: 2007 end-page: 215 ident: b17 article-title: A review of statistical approaches to level set segmentation: Integrating color, texture, motion and shape publication-title: Int. J. Comput. Vis. – volume: 81 start-page: 68 year: 2009 ident: b22 article-title: Multi-reference shape priors for active contours publication-title: Int. J. Comput. Vis. – volume: 37 start-page: 384 year: 2018 end-page: 395 ident: b62 article-title: Anatomically constrained neural networks (ACNNs): Application to cardiac image enhancement and segmentation publication-title: IEEE Trans. Med. Imaging – year: 2016 ident: b60 article-title: Incorporating prior knowledge in medical image segmentation: a survey – volume: 32 year: 2019 ident: b29 article-title: Deep learning techniques for medical image segmentation: Achievements and challenges publication-title: J. Digit Imaging – start-page: 559 year: 2019 end-page: 567 ident: b88 article-title: Cardiac segmentation from LGE mri using deep neural network incorporating shape and spatial priors publication-title: Medical Image Computing and Computer Assisted Intervention – MICCAI 2019 – volume: 29 start-page: 1856 year: 2020 end-page: 1866 ident: b41 article-title: Mumford-Shah Loss functional for image segmentation with deep learning publication-title: IEEE Trans. Image Process. – start-page: 2001 year: 2020 end-page: 2004 ident: b89 article-title: Kappa loss for skin lesion segmentation in fully convolutional network publication-title: IEEE ISBI – start-page: 161 year: 2018 end-page: 169 ident: b35 article-title: Automatic segmentation of LV and RV in cardiac MRI publication-title: MICCAI Workshop on Statistical Atlases and Computational Models of the Heart – start-page: 245 year: 2015 end-page: 262 ident: b73 article-title: Integration of topological constraints in medical image segmentation publication-title: Handbook of Biomedical Imaging: Methodologies and Clinical Research – reference: . – volume: 14 start-page: 1189 year: 2020 end-page: 1198 ident: b21 article-title: BB-UNet: U-net with bounding box prior publication-title: IEEE J. Sel. Top. Sign. Proces. – reference: Hu, H., Zheng, Y., Zhou, Q., Xiao, J., Chen, S., Guan, Q., 2019. MC-Unet: Multi-scale Convolution Unet for Bladder Cancer Cell Segmentation in Phase-Contrast Microscopy Images. In: 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 1197-1199. – year: 2020 ident: b45 article-title: Medical image segmentation using deep learning: A survey – start-page: 565 year: 2016 end-page: 571 ident: b55 article-title: V-NEt: Fully convolutional neural networks for volumetric medical image segmentation publication-title: 2016 Fourth International Conference on 3D Vision (3DV) – reference: Wang, P., Chen, P., Yuan, Y., Liu, D., Huang, Z., Hou, X., Cottrell, G., 2018. Understanding convolution for semantic segmentation. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1451–1460. – volume: 98 year: 2018 ident: b54 article-title: Survey on deep learning for radiotherapy publication-title: Comput. Biol. Med. – volume: 9901 start-page: 424 year: 2016 end-page: 432 ident: b10 article-title: 3D U-net: Learning dense volumetric segmentation from sparse annotation publication-title: MICCAI – year: 2019 ident: b23 article-title: A Priori Et Apprentissage Profond Pour La Segmentation En Imagerie Cérébrale – year: 2016 ident: b56 article-title: Morse Theory. (AM-51) – start-page: 755 year: 2017 end-page: 763 ident: b19 article-title: Unbiased shape compactness for segmentation publication-title: MICCAI – reference: Marquez-Neila, P., Salzmann, M., Fua, P., 2017. Imposing Hard Constraints on Deep Networks: Promises and Limitations. In: CVPR Workshop on Negative Results in Computer Vision. – year: 2019 ident: b78 article-title: Deep semantic segmentation of natural and medical images: A review – start-page: 1 year: 2020 ident: b15 article-title: A topological loss function for deep-learning based image segmentation using persistent homology publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 130 start-page: 297 year: 2020 ident: 10.1016/j.cviu.2021.103248_b64 article-title: Discretely-constrained deep network for weakly supervised segmentation publication-title: Neural Netw. Off. J. Int. Neural Netw. Soc. – start-page: 1 year: 2008 ident: 10.1016/j.cviu.2021.103248_b82 article-title: Graph cut based image segmentation with connectivity priors – volume: 79 start-page: 21771 issue: 29 year: 2020 ident: 10.1016/j.cviu.2021.103248_b11 article-title: A survey on brain tumor detection techniques for MR images publication-title: Multimedia Tools Appl. doi: 10.1007/s11042-020-08898-3 – start-page: 323 year: 2018 ident: 10.1016/j.cviu.2021.103248_b67 article-title: Deep learning for medical image processing: Overview, challenges and the future doi: 10.1007/978-3-319-65981-7_12 – start-page: 3136 year: 2018 ident: 10.1016/j.cviu.2021.103248_b58 article-title: Beyond the pixel-wise loss for topology-aware delineation – start-page: 755 year: 2017 ident: 10.1016/j.cviu.2021.103248_b19 article-title: Unbiased shape compactness for segmentation – year: 2019 ident: 10.1016/j.cviu.2021.103248_b14 article-title: A proximal interior point algorithm with applications to image processing publication-title: J. Math. Imaging Vis. – volume: 7 issue: 2 year: 2021 ident: 10.1016/j.cviu.2021.103248_b52 article-title: Deep learning for brain tumor segmentation: A survey of state-of-the-art publication-title: J. Imaging doi: 10.3390/jimaging7020019 – volume: 2 start-page: 129 year: 2000 ident: 10.1016/j.cviu.2021.103248_b84 article-title: Image segmentation using deformable models – ident: 10.1016/j.cviu.2021.103248_b44 doi: 10.1109/ISBI48211.2021.9434088 – volume: 42 start-page: 60 year: 2017 ident: 10.1016/j.cviu.2021.103248_b48 article-title: A survey on deep learning in medical image analysis publication-title: Med. Image Anal. doi: 10.1016/j.media.2017.07.005 – volume: 10663 start-page: 73 year: 2017 ident: 10.1016/j.cviu.2021.103248_b91 article-title: Gridnet with automatic shape prior registration for automatic MRI cardiac segmentation – start-page: 488 year: 1999 ident: 10.1016/j.cviu.2021.103248_b59 article-title: Penalty, barrier, and augmented Lagrangian methods – start-page: 2001 year: 2020 ident: 10.1016/j.cviu.2021.103248_b89 article-title: Kappa loss for skin lesion segmentation in fully convolutional network – volume: 102 start-page: 285 year: 2019 ident: 10.1016/j.cviu.2021.103248_b37 article-title: Boundary loss for highly unbalanced segmentation – year: 2005 ident: 10.1016/j.cviu.2021.103248_b70 article-title: Quo vadis, atlas-based segmentation ? – volume: 18 year: 2020 ident: 10.1016/j.cviu.2021.103248_b26 article-title: Deep learning approaches to biomedical image segmentation publication-title: Inform. Med. Unlocked – volume: 15 start-page: 29 year: 2015 ident: 10.1016/j.cviu.2021.103248_b79 article-title: Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool publication-title: BMC Med. Imaging doi: 10.1186/s12880-015-0068-x – year: 2017 ident: 10.1016/j.cviu.2021.103248_b3 article-title: An exploration of 2D and 3D deep learning techniques for Cardiac MR image segmentation – start-page: 125 year: 2016 ident: 10.1016/j.cviu.2021.103248_b27 article-title: Deep learning trends for focal brain pathology segmentation in MRI – start-page: 9207 year: 2019 ident: 10.1016/j.cviu.2021.103248_b43 article-title: Shapemask: Learning to segment novel objects by refining shape priors – start-page: 1 year: 2008 ident: 10.1016/j.cviu.2021.103248_b49 article-title: Graph cut with ordering constraints on labels and its applications – ident: 10.1016/j.cviu.2021.103248_b76 doi: 10.1109/ICIP.2005.1530282 – volume: 61 start-page: 38 issue: 1 year: 1995 ident: 10.1016/j.cviu.2021.103248_b16 article-title: Active shape models - their training and application publication-title: Comput. Vis. Image Underst. doi: 10.1006/cviu.1995.1004 – start-page: 460 year: 2016 ident: 10.1016/j.cviu.2021.103248_b4 article-title: Topology aware fully convolutional networks for histology gland segmentation – volume: 11 start-page: 143 issue: 1 year: 2020 ident: 10.1016/j.cviu.2021.103248_b18 article-title: Survey of deep learning in breast cancer image analysis publication-title: Evol. Syst. doi: 10.1007/s12530-019-09297-2 – year: 2021 ident: 10.1016/j.cviu.2021.103248_b31 – ident: 10.1016/j.cviu.2021.103248_b87 doi: 10.1109/CVPR42600.2020.01243 – volume: 37 start-page: 2514 issue: 11 year: 2018 ident: 10.1016/j.cviu.2021.103248_b5 article-title: Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: Is the problem solved? publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2018.2837502 – year: 2020 ident: 10.1016/j.cviu.2021.103248_b42 article-title: Breast cancer detection, segmentation and classification on histopathology images analysis: A systematic review publication-title: Arch. Comput. Methods Eng. – year: 2019 ident: 10.1016/j.cviu.2021.103248_b23 – volume: 29 start-page: 1856 year: 2020 ident: 10.1016/j.cviu.2021.103248_b41 article-title: Mumford-Shah Loss functional for image segmentation with deep learning publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2019.2941265 – year: 2004 ident: 10.1016/j.cviu.2021.103248_b6 – start-page: 161 year: 2018 ident: 10.1016/j.cviu.2021.103248_b35 article-title: Automatic segmentation of LV and RV in cardiac MRI – start-page: 642 year: 2002 ident: 10.1016/j.cviu.2021.103248_b51 article-title: Atlas-based segmentation and tracking of 3D cardiac MR images using non-rigid registration – volume: 98 year: 2018 ident: 10.1016/j.cviu.2021.103248_b54 article-title: Survey on deep learning for radiotherapy publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2018.05.018 – volume: 22 start-page: 888 issue: 8 year: 2000 ident: 10.1016/j.cviu.2021.103248_b74 article-title: Normalized cuts and image segmentation publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/34.868688 – start-page: 3431 year: 2015 ident: 10.1016/j.cviu.2021.103248_b50 article-title: Fully convolutional networks for semantic segmentation – volume: 10 start-page: 1 issue: 1 year: 2020 ident: 10.1016/j.cviu.2021.103248_b69 article-title: Variability and reproducibility in deep learning for medical image segmentation publication-title: Sci. Rep. doi: 10.1038/s41598-020-69920-0 – volume: 58 year: 2019 ident: 10.1016/j.cviu.2021.103248_b24 article-title: Removing segmentation inconsistencies with semi-supervised non-adjacency constraint publication-title: Med. Image. Anal doi: 10.1016/j.media.2019.101551 – start-page: 1796 year: 2015 ident: 10.1016/j.cviu.2021.103248_b63 article-title: Constrained convolutional neural networks for weakly supervised segmentation – start-page: 737 year: 2018 ident: 10.1016/j.cviu.2021.103248_b57 article-title: Star shape prior in fully convolutional networks for skin lesion segmentation – ident: 10.1016/j.cviu.2021.103248_b32 doi: 10.1109/BIBM47256.2019.8983121 – start-page: 22 year: 2019 ident: 10.1016/j.cviu.2021.103248_b34 article-title: NnU-Net: Self-adapting framework for U-net-based medical image segmentation – year: 2019 ident: 10.1016/j.cviu.2021.103248_b40 – year: 2016 ident: 10.1016/j.cviu.2021.103248_b60 – start-page: 12 year: 2018 ident: 10.1016/j.cviu.2021.103248_b1 article-title: Shape-aware deep convolutional neural network for vertebrae segmentation – volume: 81 start-page: 68 issue: 1 year: 2009 ident: 10.1016/j.cviu.2021.103248_b22 article-title: Multi-reference shape priors for active contours publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-008-0163-3 – year: 2017 ident: 10.1016/j.cviu.2021.103248_b77 article-title: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations – start-page: 120 year: 2018 ident: 10.1016/j.cviu.2021.103248_b33 article-title: Automatic cardiac disease assessment on cine-MRI via time-series segmentation and domain specific features – ident: 10.1016/j.cviu.2021.103248_b53 – start-page: 1 year: 2020 ident: 10.1016/j.cviu.2021.103248_b15 article-title: A topological loss function for deep-learning based image segmentation using persistent homology publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 3 year: 2021 ident: 10.1016/j.cviu.2021.103248_b8 article-title: A persistent homology-based topological loss function for multi-class CNN segmentation of cardiac MRI – start-page: 234 year: 2015 ident: 10.1016/j.cviu.2021.103248_b71 article-title: U-Net: Convolutional networks for biomedical image segmentation – ident: 10.1016/j.cviu.2021.103248_b20 – ident: 10.1016/j.cviu.2021.103248_b72 doi: 10.1007/3-540-47967-8_6 – year: 2020 ident: 10.1016/j.cviu.2021.103248_b45 – volume: 4 start-page: 931 issue: 6 year: 1993 ident: 10.1016/j.cviu.2021.103248_b46 article-title: On solving constrained optimization problems with neural networks: a penalty method approach publication-title: IEEE Trans. Neural Netw. doi: 10.1109/72.286888 – start-page: 245 year: 2015 ident: 10.1016/j.cviu.2021.103248_b73 article-title: Integration of topological constraints in medical image segmentation – ident: 10.1016/j.cviu.2021.103248_b9 – volume: 9901 start-page: 424 year: 2016 ident: 10.1016/j.cviu.2021.103248_b10 article-title: 3D U-net: Learning dense volumetric segmentation from sparse annotation – ident: 10.1016/j.cviu.2021.103248_b86 – start-page: 203 year: 2017 ident: 10.1016/j.cviu.2021.103248_b66 article-title: Learning and incorporating shape models for semantic segmentation – start-page: 152 year: 2018 ident: 10.1016/j.cviu.2021.103248_b85 article-title: Class-balanced deep neural network for automatic ventricular structure segmentation – start-page: 228 year: 2018 ident: 10.1016/j.cviu.2021.103248_b61 article-title: BESNet: Boundary-enhanced segmentation of cells in histopathological images – ident: 10.1016/j.cviu.2021.103248_b80 doi: 10.1007/978-3-319-67558-9_3 – volume: 32 year: 2019 ident: 10.1016/j.cviu.2021.103248_b29 article-title: Deep learning techniques for medical image segmentation: Achievements and challenges publication-title: J. Digit Imaging doi: 10.1007/s10278-019-00227-x – start-page: 565 year: 2016 ident: 10.1016/j.cviu.2021.103248_b55 article-title: V-NEt: Fully convolutional neural networks for volumetric medical image segmentation – volume: 13 start-page: 543 issue: 4 year: 2009 ident: 10.1016/j.cviu.2021.103248_b28 article-title: Statistical shape models for 3D medical image segmentation: A review publication-title: Med. Image Anal. doi: 10.1016/j.media.2009.05.004 – year: 2019 ident: 10.1016/j.cviu.2021.103248_b65 article-title: Biasing deep convnets for semantic segmentation of medical images with a prior-driven prediction function – volume: 37 start-page: 384 issue: 2 year: 2018 ident: 10.1016/j.cviu.2021.103248_b62 article-title: Anatomically constrained neural networks (ACNNs): Application to cardiac image enhancement and segmentation publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2017.2743464 – ident: 10.1016/j.cviu.2021.103248_b75 – start-page: 111 year: 2012 ident: 10.1016/j.cviu.2021.103248_b25 article-title: Targeted image segmentation using graph methods – volume: 54 start-page: 88 year: 2019 ident: 10.1016/j.cviu.2021.103248_b38 article-title: Constrained-CNN losses for weakly supervised segmentation publication-title: Med. Image Anal. doi: 10.1016/j.media.2019.02.009 – start-page: 2999 year: 2017 ident: 10.1016/j.cviu.2021.103248_b47 article-title: Focal loss for dense object detection – year: 2020 ident: 10.1016/j.cviu.2021.103248_b39 article-title: Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervision – volume: 72 start-page: 195 issue: 2 year: 2007 ident: 10.1016/j.cviu.2021.103248_b17 article-title: A review of statistical approaches to level set segmentation: Integrating color, texture, motion and shape publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-006-8711-1 – start-page: 454 year: 2008 ident: 10.1016/j.cviu.2021.103248_b81 article-title: Star shape prior for graph-cut image segmentation – volume: 14 start-page: 1189 issue: 6 year: 2020 ident: 10.1016/j.cviu.2021.103248_b21 article-title: BB-UNet: U-net with bounding box prior publication-title: IEEE J. Sel. Top. Sign. Proces. doi: 10.1109/JSTSP.2020.3001502 – year: 2019 ident: 10.1016/j.cviu.2021.103248_b78 – start-page: 961 year: 2019 ident: 10.1016/j.cviu.2021.103248_b12 article-title: On symmetric losses for learning from corrupted labels – volume: 70 start-page: 109 issue: 2 year: 2006 ident: 10.1016/j.cviu.2021.103248_b7 article-title: Graph cuts and efficient ND image segmentation publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-006-7934-5 – volume: 32 start-page: 5657 year: 2019 ident: 10.1016/j.cviu.2021.103248_b30 article-title: Topology-preserving deep image segmentation – ident: 10.1016/j.cviu.2021.103248_b68 – volume: 3–4 year: 2019 ident: 10.1016/j.cviu.2021.103248_b90 article-title: A review: Deep learning for medical image segmentation using multi-modality fusion publication-title: Array – year: 2016 ident: 10.1016/j.cviu.2021.103248_b56 – start-page: 559 year: 2019 ident: 10.1016/j.cviu.2021.103248_b88 article-title: Cardiac segmentation from LGE mri using deep neural network incorporating shape and spatial priors – volume: 7 start-page: 25 year: 2020 ident: 10.1016/j.cviu.2021.103248_b13 article-title: Deep learning for cardiac image segmentation: A review publication-title: Front. Cardiovasc. Med. doi: 10.3389/fcvm.2020.00025 – year: 2008 ident: 10.1016/j.cviu.2021.103248_b2 article-title: Area prior constrained level set evolution for medical image segmentation – volume: 29 start-page: 1257 year: 2017 ident: 10.1016/j.cviu.2021.103248_b36 article-title: Medical image semantic segmentation based on deep learning publication-title: Neural Comput. Appl. doi: 10.1007/s00521-017-3158-6 – ident: 10.1016/j.cviu.2021.103248_b83 doi: 10.1109/WACV.2018.00163 |
| SSID | ssj0011491 |
| Score | 2.5990243 |
| Snippet | Today, deep convolutional neural networks (CNNs) have demonstrated state of the art performance for supervised medical image segmentation, across various... |
| SourceID | hal crossref elsevier |
| SourceType | Open Access Repository Enrichment Source Index Database Publisher |
| StartPage | 103248 |
| SubjectTerms | Anatomical constraint losses Artificial Intelligence Computer Science Computer Vision and Pattern Recognition Computers and Society Convolutional neural networks Deep learning Engineering Sciences Machine Learning Mathematics Medical image segmentation Neural and Evolutionary Computing Prior-based loss functions Signal and Image processing Statistics |
| Title | High-level prior-based loss functions for medical image segmentation: A survey |
| URI | https://dx.doi.org/10.1016/j.cviu.2021.103248 https://normandie-univ.hal.science/hal-03410506 |
| Volume | 210 |
| WOSCitedRecordID | wos000691812700007&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1090-235X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0011491 issn: 1077-3142 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLbKxsN44DJAjJssxFuUKncnvFVlUzdKmcRAfYscx6EtaVa1SzV-EX-Tc2LnUhDTeODFal07SXu--tjH3_lMyFs_CLOEJRx1KgPTS2AcTFgWmkkoLe5ldhpUO6Zfx2wyCafT6LzX-1nnwmxzVhTh9XW0-q-mhjowNqbO_oO5m4tCBbwGo0MJZofyVoZH5oaZIxfIWK3nl2sTHVVq5OANDfRiivqG7MKl3qSZL5G4s5HfljoRqTBUDvSmXG93933rQyAMlZOuth6q7mU3S6ZlhBhnJUBQcbg3vODtUAwXXEgVfh2qs4NajF0Wcq5CrV3m4nAmV_kPPEiiYudKlPX9zrtxC8duiFk6mKY9f2fstRiGTJXYVl_qusgyHdefdgdsRxFh_xj8VRxi0RfbednHW6KigKOEPHeVtkeDz_H5-5N4fDr5sPtph544GoyhnPHctFwkw1rBFpbZ-w7zI_AA-4PT4-lZs2EFC01b0VvVd9D5WYpK-PsD_W0OdGdWR_Or2c3FQ3JfL0voQMHpEenJ4pA80EsUqh3ABqpqANR1h-ReR9IS3n1sdICh-QGuZZQU-GPyqUUm7SCTIjJpg0wKyKQambSCFu0ik76jnCpcPiFfTo4vhiNTn-dhCpeFV6YrPe7aqZ16loABwQ14FgjHF5mwrCxB_pLDJIM5cmZz3_FSWLpDi9CWwvc586X7lOwVAMBnhArfFp7rZVbCUZMviRIeZWkaptKzM5amR8Suf-FYaLF7PHMlj2tW4yJGq8RolVhZ5YgYTZ-Vknq5sbVfGy7Wk1U1CY0Bjjf2ewNWbm6A6u4AtBjrWpg9v02jF-Sg_V-9JHtX61K-InfFFuy6fq0B-gvU8sEY |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=High-level+prior-based+loss+functions+for+medical+image+segmentation+%3A+a+survey&rft.jtitle=Computer+vision+and+image+understanding&rft.au=El+Jurdi%2C+Rosana&rft.au=Petitjean%2C+Caroline&rft.au=Honeine%2C+Paul&rft.au=Cheplygina%2C+Veronika&rft.date=2021-09-01&rft.pub=Elsevier&rft.issn=1077-3142&rft.eissn=1090-235X&rft.volume=210&rft_id=info:doi/10.1016%2Fj.cviu.2021.103248&rft.externalDBID=HAS_PDF_LINK&rft.externalDocID=oai%3AHAL%3Ahal-03410506v1 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1077-3142&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1077-3142&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1077-3142&client=summon |