Deep reinforcement learning and convolutional autoencoders for anomaly detection of congenital inner ear malformations in clinical CT images

Detection of abnormalities within the inner ear is a challenging task even for experienced clinicians. In this study, we propose an automated method for automatic abnormality detection to provide support for the diagnosis and clinical management of various otological disorders. We propose a framewor...

Full description

Saved in:
Bibliographic Details
Published in:Computerized medical imaging and graphics Vol. 113; p. 102343
Main Authors: López Diez, Paula, Sundgaard, Josefine Vilsbøll, Margeta, Jan, Diab, Khassan, Patou, François, Paulsen, Rasmus R.
Format: Journal Article
Language:English
Published: United States Elsevier Ltd 01.04.2024
Subjects:
ISSN:0895-6111, 1879-0771, 1879-0771
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Detection of abnormalities within the inner ear is a challenging task even for experienced clinicians. In this study, we propose an automated method for automatic abnormality detection to provide support for the diagnosis and clinical management of various otological disorders. We propose a framework for inner ear abnormality detection based on deep reinforcement learning for landmark detection which is trained uniquely in normative data. In our approach, we derive two abnormality measurements: Dimage and Uimage. The first measurement, Dimage, is based on the variability of the predicted configuration of a well-defined set of landmarks in a subspace formed by the point distribution model of the location of those landmarks in normative data. We create this subspace using Procrustes shape alignment and Principal Component Analysis projection. The second measurement, Uimage, represents the degree of hesitation of the agents when approaching the final location of the landmarks and is based on the distribution of the predicted Q-values of the model for the last ten states. Finally, we unify these measurements in a combined anomaly measurement called Cimage. We compare our method’s performance with a 3D convolutional autoencoder technique for abnormality detection using the patch-based mean squared error between the original and the generated image as a basis for classifying abnormal versus normal anatomies. We compare both approaches and show that our method, based on deep reinforcement learning, shows better detection performance for abnormal anatomies on both an artificial and a real clinical CT dataset of various inner ear malformations with an increase of 11.2% of the area under the ROC curve. Our method also shows more robustness against the heterogeneous quality of the images in our dataset. •Congenital inner ear malformation detection is key for better development of children with severe hearing loss.•Anomaly detection with automated detection of congenital malformations of the inner ear.•Landmark localization with deep reinforcement learning for anomaly detection in CT images.•Trained only in normative data which is more accessible and easier to collect.•Evaluate and compare our method with a 3D convolutional autoencoder in two clinical datasets of artificial and real congenital inner ear malformations.
AbstractList AbstractDetection of abnormalities within the inner ear is a challenging task even for experienced clinicians. In this study, we propose an automated method for automatic abnormality detection to provide support for the diagnosis and clinical management of various otological disorders. We propose a framework for inner ear abnormality detection based on deep reinforcement learning for landmark detection which is trained uniquely in normative data. In our approach, we derive two abnormality measurements: Dimage and Uimage. The first measurement, Dimage, is based on the variability of the predicted configuration of a well-defined set of landmarks in a subspace formed by the point distribution model of the location of those landmarks in normative data. We create this subspace using Procrustes shape alignment and Principal Component Analysis projection. The second measurement, Uimage, represents the degree of hesitation of the agents when approaching the final location of the landmarks and is based on the distribution of the predicted Q-values of the model for the last ten states. Finally, we unify these measurements in a combined anomaly measurement called Cimage. We compare our method’s performance with a 3D convolutional autoencoder technique for abnormality detection using the patch-based mean squared error between the original and the generated image as a basis for classifying abnormal versus normal anatomies. We compare both approaches and show that our method, based on deep reinforcement learning, shows better detection performance for abnormal anatomies on both an artificial and a real clinical CT dataset of various inner ear malformations with an increase of 11.2% of the area under the ROC curve. Our method also shows more robustness against the heterogeneous quality of the images in our dataset.
Detection of abnormalities within the inner ear is a challenging task even for experienced clinicians. In this study, we propose an automated method for automatic abnormality detection to provide support for the diagnosis and clinical management of various otological disorders. We propose a framework for inner ear abnormality detection based on deep reinforcement learning for landmark detection which is trained uniquely in normative data. In our approach, we derive two abnormality measurements: D and U . The first measurement, D , is based on the variability of the predicted configuration of a well-defined set of landmarks in a subspace formed by the point distribution model of the location of those landmarks in normative data. We create this subspace using Procrustes shape alignment and Principal Component Analysis projection. The second measurement, U , represents the degree of hesitation of the agents when approaching the final location of the landmarks and is based on the distribution of the predicted Q-values of the model for the last ten states. Finally, we unify these measurements in a combined anomaly measurement called C . We compare our method's performance with a 3D convolutional autoencoder technique for abnormality detection using the patch-based mean squared error between the original and the generated image as a basis for classifying abnormal versus normal anatomies. We compare both approaches and show that our method, based on deep reinforcement learning, shows better detection performance for abnormal anatomies on both an artificial and a real clinical CT dataset of various inner ear malformations with an increase of 11.2% of the area under the ROC curve. Our method also shows more robustness against the heterogeneous quality of the images in our dataset.
Detection of abnormalities within the inner ear is a challenging task even for experienced clinicians. In this study, we propose an automated method for automatic abnormality detection to provide support for the diagnosis and clinical management of various otological disorders. We propose a framework for inner ear abnormality detection based on deep reinforcement learning for landmark detection which is trained uniquely in normative data. In our approach, we derive two abnormality measurements: Dimage and Uimage. The first measurement, Dimage, is based on the variability of the predicted configuration of a well-defined set of landmarks in a subspace formed by the point distribution model of the location of those landmarks in normative data. We create this subspace using Procrustes shape alignment and Principal Component Analysis projection. The second measurement, Uimage, represents the degree of hesitation of the agents when approaching the final location of the landmarks and is based on the distribution of the predicted Q-values of the model for the last ten states. Finally, we unify these measurements in a combined anomaly measurement called Cimage. We compare our method’s performance with a 3D convolutional autoencoder technique for abnormality detection using the patch-based mean squared error between the original and the generated image as a basis for classifying abnormal versus normal anatomies. We compare both approaches and show that our method, based on deep reinforcement learning, shows better detection performance for abnormal anatomies on both an artificial and a real clinical CT dataset of various inner ear malformations with an increase of 11.2% of the area under the ROC curve. Our method also shows more robustness against the heterogeneous quality of the images in our dataset. •Congenital inner ear malformation detection is key for better development of children with severe hearing loss.•Anomaly detection with automated detection of congenital malformations of the inner ear.•Landmark localization with deep reinforcement learning for anomaly detection in CT images.•Trained only in normative data which is more accessible and easier to collect.•Evaluate and compare our method with a 3D convolutional autoencoder in two clinical datasets of artificial and real congenital inner ear malformations.
Detection of abnormalities within the inner ear is a challenging task even for experienced clinicians. In this study, we propose an automated method for automatic abnormality detection to provide support for the diagnosis and clinical management of various otological disorders. We propose a framework for inner ear abnormality detection based on deep reinforcement learning for landmark detection which is trained uniquely in normative data. In our approach, we derive two abnormality measurements: Dimage and Uimage. The first measurement, Dimage, is based on the variability of the predicted configuration of a well-defined set of landmarks in a subspace formed by the point distribution model of the location of those landmarks in normative data. We create this subspace using Procrustes shape alignment and Principal Component Analysis projection. The second measurement, Uimage, represents the degree of hesitation of the agents when approaching the final location of the landmarks and is based on the distribution of the predicted Q-values of the model for the last ten states. Finally, we unify these measurements in a combined anomaly measurement called Cimage. We compare our method's performance with a 3D convolutional autoencoder technique for abnormality detection using the patch-based mean squared error between the original and the generated image as a basis for classifying abnormal versus normal anatomies. We compare both approaches and show that our method, based on deep reinforcement learning, shows better detection performance for abnormal anatomies on both an artificial and a real clinical CT dataset of various inner ear malformations with an increase of 11.2% of the area under the ROC curve. Our method also shows more robustness against the heterogeneous quality of the images in our dataset.Detection of abnormalities within the inner ear is a challenging task even for experienced clinicians. In this study, we propose an automated method for automatic abnormality detection to provide support for the diagnosis and clinical management of various otological disorders. We propose a framework for inner ear abnormality detection based on deep reinforcement learning for landmark detection which is trained uniquely in normative data. In our approach, we derive two abnormality measurements: Dimage and Uimage. The first measurement, Dimage, is based on the variability of the predicted configuration of a well-defined set of landmarks in a subspace formed by the point distribution model of the location of those landmarks in normative data. We create this subspace using Procrustes shape alignment and Principal Component Analysis projection. The second measurement, Uimage, represents the degree of hesitation of the agents when approaching the final location of the landmarks and is based on the distribution of the predicted Q-values of the model for the last ten states. Finally, we unify these measurements in a combined anomaly measurement called Cimage. We compare our method's performance with a 3D convolutional autoencoder technique for abnormality detection using the patch-based mean squared error between the original and the generated image as a basis for classifying abnormal versus normal anatomies. We compare both approaches and show that our method, based on deep reinforcement learning, shows better detection performance for abnormal anatomies on both an artificial and a real clinical CT dataset of various inner ear malformations with an increase of 11.2% of the area under the ROC curve. Our method also shows more robustness against the heterogeneous quality of the images in our dataset.
ArticleNumber 102343
Author López Diez, Paula
Paulsen, Rasmus R.
Patou, François
Margeta, Jan
Sundgaard, Josefine Vilsbøll
Diab, Khassan
Author_xml – sequence: 1
  givenname: Paula
  orcidid: 0000-0002-9346-743X
  surname: López Diez
  fullname: López Diez, Paula
  email: plodi@dtu.dk
  organization: Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark
– sequence: 2
  givenname: Josefine Vilsbøll
  surname: Sundgaard
  fullname: Sundgaard, Josefine Vilsbøll
  organization: Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark
– sequence: 3
  givenname: Jan
  surname: Margeta
  fullname: Margeta, Jan
  organization: KardioMe, Research & Development, Nova Dubnica, Slovakia
– sequence: 4
  givenname: Khassan
  surname: Diab
  fullname: Diab, Khassan
  organization: Tashkent International Clinic, Tashkent, Uzbekistan
– sequence: 5
  givenname: François
  surname: Patou
  fullname: Patou, François
  organization: Oticon Medical, Research & Technology group, Smørum, Denmark
– sequence: 6
  givenname: Rasmus R.
  surname: Paulsen
  fullname: Paulsen, Rasmus R.
  organization: Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark
BackLink https://www.ncbi.nlm.nih.gov/pubmed/38325245$$D View this record in MEDLINE/PubMed
BookMark eNqNkkuLFDEUhYOMOD2jf0Hizk21edRzoww9vmDAhSO4C6lbt5q0VUmbVA30f_BHe8ueERkQOptA-M7h5px7wc588MjYKynWUsjyzW4NYdyP2LnRbtdKqJzelc71E7aSddVkoqrkGVuJuimyUkp5zi5S2gkhlKjkM3aua60KlRcr9usacc8jOt-HCDiin_iANnrnt9z6jkPwd2GYJxe8Hbidp4AeQocxcVIQEkY7HHiHE8IC8dAvmi16N5HAeY-RkyEnjASjXaBE7xwG5x0Qs7nly0cwPWdPezskfHF_X7JvH97fbj5lN18-ft5c3WRQ5HLKoMk7Xfd1Z3PQVrTQCaEFYmPpSJC2L_JStRrauhGg26oUugfUtgRRCWz0JXt99N3H8HPGNJnRJcBhsB7DnIxqlG6kboqa0Jf36NxS4GYfadR4MA8JEtAcAYghpYj9X0QKs7RlduaftszSljm2Rdp3j7RAoS0BTdG64SSHzdEBKa47h9EkcFQQoZH6MF1wJ7m8feTy0M0PPGDahTlS-clIk5QR5uuyV8taqfzPSn0ng6v_G5w4xG_cs-eW
CitedBy_id crossref_primary_10_1007_s12530_024_09632_2
crossref_primary_10_3390_electronics13091654
crossref_primary_10_3390_info16090730
Cites_doi 10.1002/lio2.936
10.1145/2133360.2133363
10.3390/jcm11226640
10.1007/BF02291478
10.1016/j.compmedimag.2020.101770
10.1016/j.media.2022.102417
10.1109/TKDE.2019.2947676
10.1016/j.compmedimag.2017.04.002
10.1016/j.media.2022.102526
10.1007/s13369-019-03967-8
10.1038/s41598-021-00330-6
10.1016/j.media.2004.06.007
10.1109/TPAMI.2017.2782687
10.1006/cviu.1995.1004
10.1159/000095611
10.1016/j.media.2022.102475
10.1016/j.media.2020.101713
10.1016/j.media.2021.102345
10.1109/JBHI.2020.2964016
10.1016/j.compmedimag.2021.101888
10.1109/42.938237
10.1016/j.neuroimage.2006.01.015
10.1016/j.media.2022.102491
10.1016/j.compmedimag.2021.101940
10.1097/MAO.0000000000002204
10.1016/j.media.2019.01.010
10.4274/balkanmedj.2017.0367
10.1109/TKDE.2023.3270293
10.1016/j.ejmp.2020.01.027
10.1109/TPAMI.2022.3188763
10.1016/j.media.2021.102193
10.3390/audiolres11040047
10.1038/nrdp.2016.94
ContentType Journal Article
Copyright 2024 The Authors
The Authors
Copyright © 2024 The Authors. Published by Elsevier Ltd.. All rights reserved.
Copyright_xml – notice: 2024 The Authors
– notice: The Authors
– notice: Copyright © 2024 The Authors. Published by Elsevier Ltd.. All rights reserved.
DBID 6I.
AAFTH
AAYXX
CITATION
NPM
7X8
DOI 10.1016/j.compmedimag.2024.102343
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
PubMed
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList
PubMed

MEDLINE - Academic

Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 1879-0771
EndPage 102343
ExternalDocumentID 38325245
10_1016_j_compmedimag_2024_102343
S089561112400020X
1_s2_0_S089561112400020X
Genre Journal Article
GroupedDBID ---
--K
--M
.1-
.DC
.FO
.GJ
.~1
0R~
1B1
1P~
1RT
1~.
1~5
29F
4.4
457
4G.
53G
5GY
5RE
5VS
7-5
71M
8P~
9JM
9JN
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AATTM
AAXKI
AAXUO
AAYFN
AAYWO
ABBOA
ABBQC
ABFNM
ABJNI
ABMAC
ABMZM
ABWVN
ABXDB
ACDAQ
ACGFS
ACIEU
ACIUM
ACIWK
ACLOT
ACNNM
ACPRK
ACRLP
ACRPL
ACVFH
ACZNC
ADBBV
ADCNI
ADEZE
ADJOM
ADMUD
ADNMO
AEBSH
AEIPS
AEKER
AENEX
AEUPX
AEVXI
AFJKZ
AFPUW
AFRAH
AFRHN
AFTJW
AFXIZ
AGHFR
AGQPQ
AGUBO
AGYEJ
AHHHB
AHZHX
AIALX
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AJRQY
AJUYK
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
ANZVX
AOUOD
APXCP
ASPBG
AVWKF
AXJTR
AZFZN
BKOJK
BLXMC
BNPGV
CS3
DU5
EBS
EFJIC
EFKBS
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
GBOLZ
HEI
HLZ
HMK
HMO
HVGLF
HZ~
IHE
J1W
KOM
LX9
M29
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
ROL
RPZ
SAE
SBC
SDF
SDG
SDP
SEL
SES
SEW
SPC
SPCBC
SSH
SSV
SSZ
T5K
WUQ
Z5R
ZGI
~G-
~HD
AACTN
AFCTW
AFKWA
AJOXV
AMFUW
RIG
6I.
AAFTH
AAIAV
ABLVK
ABYKQ
AJBFU
LCYCR
9DU
AAYXX
CITATION
AGCQF
AGRNS
NPM
7X8
ID FETCH-LOGICAL-c541t-c94d38f8da4c3a0bcd0030ee9aaaa1c1af5462b3cb890c3b7603fce3a6c070e93
ISICitedReferencesCount 5
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001177077300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0895-6111
1879-0771
IngestDate Sat Sep 27 20:27:19 EDT 2025
Mon Jul 21 06:00:34 EDT 2025
Sat Nov 29 07:12:55 EST 2025
Tue Nov 18 21:49:53 EST 2025
Sat Mar 02 16:00:28 EST 2024
Tue Feb 25 19:59:04 EST 2025
Tue Oct 14 19:37:59 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Cochlear implant
Deep reinforcement learning
Computed tomography
Congenital malformation
Anomaly detection
Language English
License This is an open access article under the CC BY license.
Copyright © 2024 The Authors. Published by Elsevier Ltd.. All rights reserved.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c541t-c94d38f8da4c3a0bcd0030ee9aaaa1c1af5462b3cb890c3b7603fce3a6c070e93
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0002-9346-743X
OpenAccessLink https://www.clinicalkey.es/playcontent/1-s2.0-S089561112400020X
PMID 38325245
PQID 2923913958
PQPubID 23479
PageCount 1
ParticipantIDs proquest_miscellaneous_2923913958
pubmed_primary_38325245
crossref_primary_10_1016_j_compmedimag_2024_102343
crossref_citationtrail_10_1016_j_compmedimag_2024_102343
elsevier_sciencedirect_doi_10_1016_j_compmedimag_2024_102343
elsevier_clinicalkeyesjournals_1_s2_0_S089561112400020X
elsevier_clinicalkey_doi_10_1016_j_compmedimag_2024_102343
PublicationCentury 2000
PublicationDate 2024-04-01
PublicationDateYYYYMMDD 2024-04-01
PublicationDate_xml – month: 04
  year: 2024
  text: 2024-04-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Computerized medical imaging and graphics
PublicationTitleAlternate Comput Med Imaging Graph
PublicationYear 2024
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Wang, Zeng, Yu, Cheng, Liu, Zhou, Zhu, Kloft, Yin, Liao (b51) 2023; 45
Wang, Zhu, Lee, Elton, Shen, Tang, Peng, Lu, Summers (b52) 2022; 77
Chakravorti, Noble, Gifford, Dawant, O’Connell, Wang, Labadie (b9) 2019; 40
Escudé, James, Deguine, Cochard, Eter, Fraysse (b15) 2006; 11
Taboada-Crispi, Sahli, Orozco Monteagudo, Hernandez Pacheco, Falcon (b46) 2009
Welch, McIntosh, McNiven, Huang, Zhang, Wee, Traverso, O’Sullivan, Hoebers, Dekker, Jaffray (b54) 2020; 70
Liu, Ting, Zhou (b22) 2012; 6
Venkataramanan, Peng, Singh, Mahalanobis (b49) 2020
Pinaya, Graham, Gray, da Costa, Tudosiu, Wright, Mah, MacKinnon, Teo, Jager, Werring, Rees, Nachev, Ourselin, Cardoso (b35) 2022
Trier, Noe, Sørensen, Mosegaard (b47) 2008; 132
Atlason, Askell Love, Sigurdsson, Vilmundur Gudnason, Ellingsen (b4) 2019; vol. 10949
Zimmerer, Isensee, Petersen, Kohl, Maier-Hein (b60) 2019
Radutoiu, Patou, Margeta, Paulsen, López Diez (b38) 2022
Prastawa, Bullitt, Ho, Gerig (b37) 2004; 8
Chen, You, Tezcan, Konukoglu (b10) 2020; 64
Cootes, Taylor, Cooper, Graham (b11) 1995; 61
Wolleb, Bieder, Sandkühler, Cattin (b55) 2022
Sato, Hanaoka, Nomura, Takenaga, Miki, Yoshikawa, Hayashi, Abe (b40) 2018; vol. 10575
Dhanasingh, Weiss, Erhard, Altamimi, Roland, Hagr, Rompaey, de Heyning (b14) 2022
Ghesu, Georgescu, Zheng, Grbic, Maier, Hornegger, Comaniciu (b16) 2019; 41
Xu, Pang, Wang, Wang (b56) 2023
Dhanasingh, Erpenbeck, Assadi, Doyle, Roland, Hagr, Rompaey, de Heyning (b13) 2021; 11
Martins, Telea, Falcão (b28) 2020; 85
Gower (b17) 1975; 40
Paludetti, Conti, Di Nardo, De Corso, Rolesi, Picciotti, Fetoni (b32) 2012; 32
Leroy, Rueckert, Alansary (b21) 2020
Nazir, Shakil, Khurshid (b31) 2021; 91
López Diez, Juhl, Sundgaard, Diab, Margeta, Patou, Paulsen (b23) 2022; vol. 3
Schlegl, Seeböck, Waldstein, Schmidt-Erfurth, Langs (b42) 2017
Silva-Rodríguez, Naranjo, Dolz (b44) 2022; 80
Yushkevich, Piven, Cody Hazlett, Gimpel Smith, Ho, Gee, Gerig (b58) 2006; 31
Xu, Wang, Wei, Jian, Li, Liu (b57) 2023
Pawlowski, N., Lee, M.J., Rajchl, M., McDonagh, S.G., Ferrante, E., Kamnitsas, K., Cooke, S., Stevenson, S., Khetani, A., Newman, T., Zeiler, F.A., Digby, R., Coles, J.P., Rueckert, D., Menon, D.K., Newcombe, V.F.J., Glocker, B., 2018. Unsupervised Lesion Detection in Brain CT using Bayesian Convolutional Autoencoders. In: 1st Conference on Medical Imaging with Deep Learning. MIDL 2018.
Bekkouch, Maksudov, Kiselev, Mustafaev, Vrtovec, Ibragimov (b7) 2022; 78
Watkins (b53) 1989
Masci, Meier, Cireşan, Schmidhuber (b29) 2011
Pinaya, Tudosiu, Gray, Rees, Nachev, Ourselin, Cardoso (b36) 2022; 79
Arai, Chayama, Iyatomi, Oishi (b2) 2018
Baur, Wiestler, Albarqouni, Navab (b6) 2019
Margeta, Hussain, López Diez, Morgenstern, Demarcy, Wang, Gnansia, Martinez Manzanera, Vandersteen, Delingette, Buechner, Lenarz, Patou, Guevara (b27) 2022; 11
Astaraki, Smedby, Wang (b3) 2022; 80
Sennaroğlu, Bajin (b43) 2017; 34
Demarcy, Vandersteen, Guevara, Raffaelli, Gnansia, Ayache, Delingette (b12) 2017; 59
Sun, Wang, Huang, Ding, Greenspan, Paisley (b45) 2020; 24
Hariri, Kind, Brunner (b19) 2021; 33
Zhou, Le, Luu, V Nguyen, Ayache (b59) 2021; 73
Korver, Smith, Van Camp, Schleiss, Bitner-Glindzicz, Lustig, Usami, Boudewyns (b20) 2017; 3
Brotto, Sorrentino, Cenedese, Avato, Bovo, Trevisi, Manara (b8) 2021; 11
Allenby, Liang, Harvey, Woodruff, Prior, Winter, Alonso-Caneiro (b1) 2021; 89
López Diez, Sundgaard, Patou, Margeta, Paulsen (b25) 2021
Lopez Pinaya, Vieira, Garcia-Dias, Mechelli (b26) 2020
Van Leemput, Maes, Vandermeulen, Colchester, Suetens (b48) 2001; 20
Vlontzos, Alansary, Kamnitsas, Rueckert, Kainz (b50) 2019
López Diez, Sørensen, Sundgaard, Diab, Margeta, Patou, Paulsen (b24) 2022
Sajid, Hussain, Sarwar (b39) 2019; 44
Baur, Graf, Wiestler, Albarqouni, Navab (b5) 2020
Hainan, Jiang, Liu, Lu, Liang (b18) 2019
MONAI-Consortium (b30) 2022
Paszke, Gross, Massa, Lerer, Bradbury, Chanan, Killeen, Lin, Gimelshein, Antiga, Desmaison, Kopf, Yang, DeVito, Raison, Tejani, Chilamkurthy, Steiner, Fang, Bai, Chintala (b33) 2019; vol. 32
Schlegl, Seeböck, Waldstein, Langs, Schmidt-Erfurth (b41) 2019; 54
Baur (10.1016/j.compmedimag.2024.102343_b6) 2019
Liu (10.1016/j.compmedimag.2024.102343_b22) 2012; 6
Yushkevich (10.1016/j.compmedimag.2024.102343_b58) 2006; 31
Margeta (10.1016/j.compmedimag.2024.102343_b27) 2022; 11
Pinaya (10.1016/j.compmedimag.2024.102343_b36) 2022; 79
Wang (10.1016/j.compmedimag.2024.102343_b52) 2022; 77
Dhanasingh (10.1016/j.compmedimag.2024.102343_b13) 2021; 11
Paszke (10.1016/j.compmedimag.2024.102343_b33) 2019; vol. 32
Wolleb (10.1016/j.compmedimag.2024.102343_b55) 2022
Bekkouch (10.1016/j.compmedimag.2024.102343_b7) 2022; 78
Pinaya (10.1016/j.compmedimag.2024.102343_b35) 2022
Sato (10.1016/j.compmedimag.2024.102343_b40) 2018; vol. 10575
Paludetti (10.1016/j.compmedimag.2024.102343_b32) 2012; 32
Watkins (10.1016/j.compmedimag.2024.102343_b53) 1989
Escudé (10.1016/j.compmedimag.2024.102343_b15) 2006; 11
Dhanasingh (10.1016/j.compmedimag.2024.102343_b14) 2022
Martins (10.1016/j.compmedimag.2024.102343_b28) 2020; 85
Nazir (10.1016/j.compmedimag.2024.102343_b31) 2021; 91
Welch (10.1016/j.compmedimag.2024.102343_b54) 2020; 70
Trier (10.1016/j.compmedimag.2024.102343_b47) 2008; 132
Schlegl (10.1016/j.compmedimag.2024.102343_b41) 2019; 54
Radutoiu (10.1016/j.compmedimag.2024.102343_b38) 2022
Hariri (10.1016/j.compmedimag.2024.102343_b19) 2021; 33
Taboada-Crispi (10.1016/j.compmedimag.2024.102343_b46) 2009
Arai (10.1016/j.compmedimag.2024.102343_b2) 2018
Zhou (10.1016/j.compmedimag.2024.102343_b59) 2021; 73
Zimmerer (10.1016/j.compmedimag.2024.102343_b60) 2019
Demarcy (10.1016/j.compmedimag.2024.102343_b12) 2017; 59
Prastawa (10.1016/j.compmedimag.2024.102343_b37) 2004; 8
Baur (10.1016/j.compmedimag.2024.102343_b5) 2020
López Diez (10.1016/j.compmedimag.2024.102343_b25) 2021
Atlason (10.1016/j.compmedimag.2024.102343_b4) 2019; vol. 10949
Chakravorti (10.1016/j.compmedimag.2024.102343_b9) 2019; 40
Masci (10.1016/j.compmedimag.2024.102343_b29) 2011
Van Leemput (10.1016/j.compmedimag.2024.102343_b48) 2001; 20
Xu (10.1016/j.compmedimag.2024.102343_b57) 2023
Schlegl (10.1016/j.compmedimag.2024.102343_b42) 2017
Gower (10.1016/j.compmedimag.2024.102343_b17) 1975; 40
Lopez Pinaya (10.1016/j.compmedimag.2024.102343_b26) 2020
Sajid (10.1016/j.compmedimag.2024.102343_b39) 2019; 44
López Diez (10.1016/j.compmedimag.2024.102343_b23) 2022; vol. 3
Wang (10.1016/j.compmedimag.2024.102343_b51) 2023; 45
Ghesu (10.1016/j.compmedimag.2024.102343_b16) 2019; 41
Hainan (10.1016/j.compmedimag.2024.102343_b18) 2019
Brotto (10.1016/j.compmedimag.2024.102343_b8) 2021; 11
Silva-Rodríguez (10.1016/j.compmedimag.2024.102343_b44) 2022; 80
Chen (10.1016/j.compmedimag.2024.102343_b10) 2020; 64
MONAI-Consortium (10.1016/j.compmedimag.2024.102343_b30) 2022
Korver (10.1016/j.compmedimag.2024.102343_b20) 2017; 3
López Diez (10.1016/j.compmedimag.2024.102343_b24) 2022
10.1016/j.compmedimag.2024.102343_b34
Allenby (10.1016/j.compmedimag.2024.102343_b1) 2021; 89
Venkataramanan (10.1016/j.compmedimag.2024.102343_b49) 2020
Xu (10.1016/j.compmedimag.2024.102343_b56) 2023
Vlontzos (10.1016/j.compmedimag.2024.102343_b50) 2019
Astaraki (10.1016/j.compmedimag.2024.102343_b3) 2022; 80
Leroy (10.1016/j.compmedimag.2024.102343_b21) 2020
Cootes (10.1016/j.compmedimag.2024.102343_b11) 1995; 61
Sun (10.1016/j.compmedimag.2024.102343_b45) 2020; 24
Sennaroğlu (10.1016/j.compmedimag.2024.102343_b43) 2017; 34
References_xml – volume: 45
  start-page: 2952
  year: 2023
  end-page: 2969
  ident: b51
  article-title: E3Outlier: A self-supervised framework for unsupervised deep outlier detection
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 41
  start-page: 176
  year: 2019
  end-page: 189
  ident: b16
  article-title: Multi-scale deep reinforcement learning for real-time 3D-landmark detection in CT scans
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 40
  start-page: 617
  year: 2019
  ident: b9
  article-title: Further evidence of the relationship between cochlear implant electrode positioning and hearing outcomes
  publication-title: Otol. Neurotol.: Off. Publ. Am. Otol. Soc., Am. Neurotol. Soc. Eur. Acad. Otol. Neurotol.
– volume: 34
  year: 2017
  ident: b43
  article-title: Classification and current management of inner ear malformations
  publication-title: Balkan Med. J.
– volume: 3
  start-page: 1
  year: 2017
  end-page: 17
  ident: b20
  article-title: Congenital hearing loss
  publication-title: Nat. Rev. Dis. Primers
– start-page: 177
  year: 2020
  end-page: 186
  ident: b21
  article-title: Communicative reinforcement learning agents for landmark detection in brain images
  publication-title: Machine Learning in Clinical Neuroimaging and Radiogenomics in Neuro-Oncology
– volume: 64
  year: 2020
  ident: b10
  article-title: Unsupervised lesion detection via image restoration with a normative prior
  publication-title: Med. Image Anal.
– volume: 11
  start-page: 27
  year: 2006
  end-page: 33
  ident: b15
  article-title: The size of the cochlea and predictions of insertion depth angles for cochlear implant electrodes
  publication-title: Audiol. Neurotol.
– start-page: 105
  year: 2019
  ident: b18
  article-title: The Detection of Non-Polypoid Colorectal Lesions Using the Texture Feature Extracted from Intact Colon Wall: A Pilot Study
– start-page: 416
  year: 2022
  end-page: 424
  ident: b38
  article-title: Accurate localization of Inner Ear Regions of interests using deep reinforcement learning
  publication-title: Machine Learning in Medical Imaging
– volume: 89
  year: 2021
  ident: b1
  article-title: Detection of clustered anomalies in single-voxel morphometry as a rapid automated method for identifying intracranial aneurysms
  publication-title: Comput. Med. Imaging Graph.
– start-page: 718
  year: 2020
  end-page: 727
  ident: b5
  article-title: SteGANomaly: Inhibiting cyclegan steganography for unsupervised anomaly detection in brain MRI
  publication-title: Medical Image Computing and Computer Assisted Intervention
– year: 1989
  ident: b53
  article-title: Learning from Delayed Rewards
– volume: 40
  start-page: 33
  year: 1975
  end-page: 51
  ident: b17
  article-title: Generalized procrustes analysis
  publication-title: Psychometrika
– volume: 132
  start-page: 523
  year: 2008
  ident: b47
  article-title: The visible ear surgery simulator
  publication-title: Stud. Health Technol. Inf.
– volume: 33
  start-page: 1479
  year: 2021
  end-page: 1489
  ident: b19
  article-title: Extended isolation forest
  publication-title: IEEE Trans. Knowl. Data Eng.
– start-page: 289
  year: 2019
  end-page: 297
  ident: b60
  article-title: Unsupervised anomaly localization using variational auto-encoders
  publication-title: Medical Image Computing and Computer Assisted Intervention
– start-page: 146
  year: 2017
  end-page: 157
  ident: b42
  article-title: Unsupervised anomaly detection with generative adversarial networks to guide marker discovery
  publication-title: Information Processing in Medical Imaging
– volume: 79
  year: 2022
  ident: b36
  article-title: Unsupervised brain imaging 3D anomaly detection and segmentation with transformers
  publication-title: Med. Image Anal.
– start-page: 485
  year: 2020
  end-page: 503
  ident: b49
  article-title: Attention guided anomaly localization in images
  publication-title: Computer Vision – ECCV 2020
– volume: 31
  start-page: 1116
  year: 2006
  end-page: 1128
  ident: b58
  article-title: User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability
  publication-title: Neuroimage
– year: 2023
  ident: b57
  article-title: Fascinating supervisory signals and where to find them: Deep anomaly detection with scale learning
– volume: 6
  year: 2012
  ident: b22
  article-title: Isolation-based anomaly detection
  publication-title: ACM Trans. Knowl. Discov. Data
– volume: 59
  start-page: 1
  year: 2017
  end-page: 12
  ident: b12
  article-title: Automated analysis of human cochlea shape variability from segmented
  publication-title: Comput. Med. Imaging Graph.
– start-page: 193
  year: 2020
  end-page: 208
  ident: b26
  article-title: Chapter 11 - autoencoders
  publication-title: Machine Learning
– start-page: 519
  year: 2021
  end-page: 528
  ident: b25
  article-title: Facial and cochlear nerves characterization using deep reinforcement learning for landmark detection
  publication-title: Medical Image Computing and Computer Assisted Intervention
– volume: vol. 32
  year: 2019
  ident: b33
  article-title: PyTorch: An imperative style, high-performance deep learning library
  publication-title: Advances in Neural Information Processing Systems
– volume: 70
  start-page: 145
  year: 2020
  end-page: 152
  ident: b54
  article-title: User-controlled pipelines for feature integration and head and neck radiation therapy outcome predictions
  publication-title: Phys. Med.
– start-page: 697
  year: 2022
  end-page: 706
  ident: b24
  article-title: Deep reinforcement learning for detection of inner ear abnormal anatomy in computed tomography
  publication-title: Medical Image Computing and Computer Assisted Intervention
– year: 2023
  ident: b56
  article-title: Deep isolation forest for anomaly detection
  publication-title: IEEE Trans. Knowl. Data Eng.
– volume: 44
  start-page: 9249
  year: 2019
  end-page: 9261
  ident: b39
  article-title: Brain tumor detection and segmentation in MR images using deep learning
  publication-title: Arab. J. Sci. Eng.
– start-page: 262
  year: 2019
  end-page: 270
  ident: b50
  article-title: Multiple landmark detection using multi-agent reinforcement learning
  publication-title: Medical Image Computing and Computer Assisted Intervention
– start-page: 52
  year: 2011
  end-page: 59
  ident: b29
  article-title: Stacked convolutional auto-encoders for hierarchical feature extraction
  publication-title: Artificial Neural Networks and Machine Learning
– volume: 32
  start-page: 347
  year: 2012
  ident: b32
  article-title: Infant hearing loss: From diagnosis to therapy official report of XXI conference of Italian society of pediatric otorhinolaryngology
  publication-title: Acta Otorhinolaryngol. Italica
– volume: 54
  start-page: 30
  year: 2019
  end-page: 44
  ident: b41
  article-title: F-AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks
  publication-title: Med. Image Anal.
– volume: 24
  start-page: 2303
  year: 2020
  end-page: 2314
  ident: b45
  article-title: An adversarial learning approach to medical image synthesis for lesion detection
  publication-title: IEEE J. Biomed. Health Inf.
– volume: 20
  start-page: 677
  year: 2001
  end-page: 688
  ident: b48
  article-title: Automated segmentation of multiple sclerosis lesions by model outlier detection
  publication-title: IEEE Trans. Med. Imaging
– volume: vol. 3
  year: 2022
  ident: b23
  article-title: Deep reinforcement learning for detection of abnormal anatomies
  publication-title: Proceedings of the Northern Lights Deep Learning Workshop
– start-page: 35
  year: 2022
  end-page: 45
  ident: b55
  article-title: Diffusion models for medical anomaly detection
  publication-title: Medical Image Computing and Computer Assisted Intervention
– volume: 11
  year: 2021
  ident: b13
  article-title: A novel method of identifying inner ear malformation types by pattern recognition in the mid modiolar section
  publication-title: Sci. Rep.
– volume: 91
  year: 2021
  ident: b31
  article-title: Role of deep learning in brain tumor detection and classification (2015 to 2020): A review
  publication-title: Comput. Med. Imaging Graph.
– volume: 78
  year: 2022
  ident: b7
  article-title: Multi-landmark environment analysis with reinforcement learning for pelvic abnormality detection and quantification
  publication-title: Med. Image Anal.
– volume: 73
  year: 2021
  ident: b59
  article-title: Deep reinforcement learning in medical imaging: A literature review
  publication-title: Med. Image Anal.
– start-page: 161
  year: 2019
  end-page: 169
  ident: b6
  article-title: Deep autoencoding models for unsupervised anomaly segmentation in brain MR images
  publication-title: Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries
– volume: 80
  year: 2022
  ident: b3
  article-title: Prior-aware autoencoders for lung pathology segmentation
  publication-title: Med. Image Anal.
– start-page: 705
  year: 2022
  end-page: 714
  ident: b35
  article-title: Fast unsupervised brain anomaly detection and segmentation with diffusion models
  publication-title: Medical Image Computing and Computer Assisted Intervention
– volume: 77
  year: 2022
  ident: b52
  article-title: Global-local attention network with multi-task uncertainty loss for abnormal lymph node detection in MR images
  publication-title: Med. Image Anal.
– year: 2022
  ident: b14
  article-title: A novel three-step process for the identification of inner ear malformation types
  publication-title: Laryngosc. Investig. Otolaryngol.
– start-page: 5162
  year: 2018
  end-page: 5165
  ident: b2
  article-title: Significant dimension reduction of 3D brain MRI using 3D convolutional autoencoders
  publication-title: 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
– volume: vol. 10949
  start-page: 109491H
  year: 2019
  ident: b4
  article-title: Unsupervised brain lesion segmentation from MRI using a convolutional autoencoder
  publication-title: Medical Imaging 2019: Image Processing
– volume: 8
  start-page: 275
  year: 2004
  end-page: 283
  ident: b37
  article-title: A brain tumor segmentation framework based on outlier detection
  publication-title: Med. Image Anal.
– volume: 11
  start-page: 524
  year: 2021
  end-page: 536
  ident: b8
  article-title: Genetics of inner ear malformations: A review
  publication-title: Audiol. Res.
– volume: 11
  year: 2022
  ident: b27
  article-title: A web-based automated image processing research platform for cochlear implantation-related studies
  publication-title: J. Clin. Med.
– year: 2022
  ident: b30
  article-title: MONAI: Medical open network for AI
– volume: vol. 10575
  start-page: 388
  year: 2018
  end-page: 393
  ident: b40
  article-title: A primitive study on unsupervised anomaly detection with an autoencoder in emergency head CT volumes
  publication-title: Medical Imaging 2018: Computer-Aided Diagnosis
– volume: 85
  year: 2020
  ident: b28
  article-title: Investigating the impact of supervoxel segmentation for unsupervised abnormal brain asymmetry detection
  publication-title: Comput. Med. Imaging Graph.
– volume: 61
  start-page: 38
  year: 1995
  end-page: 59
  ident: b11
  article-title: Active shape models-their training and application
  publication-title: Comput. Vis. Image Underst.
– volume: 80
  year: 2022
  ident: b44
  article-title: Constrained unsupervised anomaly segmentation
  publication-title: Med. Image Anal.
– start-page: 426
  year: 2009
  end-page: 446
  ident: b46
  article-title: Anomaly detection in medical image analysis
  publication-title: Handbook of Research on Advanced Techniques in Diagnostic Imaging and Biomedical Applications
– reference: Pawlowski, N., Lee, M.J., Rajchl, M., McDonagh, S.G., Ferrante, E., Kamnitsas, K., Cooke, S., Stevenson, S., Khetani, A., Newman, T., Zeiler, F.A., Digby, R., Coles, J.P., Rueckert, D., Menon, D.K., Newcombe, V.F.J., Glocker, B., 2018. Unsupervised Lesion Detection in Brain CT using Bayesian Convolutional Autoencoders. In: 1st Conference on Medical Imaging with Deep Learning. MIDL 2018.
– year: 2022
  ident: 10.1016/j.compmedimag.2024.102343_b14
  article-title: A novel three-step process for the identification of inner ear malformation types
  publication-title: Laryngosc. Investig. Otolaryngol.
  doi: 10.1002/lio2.936
– volume: 6
  year: 2012
  ident: 10.1016/j.compmedimag.2024.102343_b22
  article-title: Isolation-based anomaly detection
  publication-title: ACM Trans. Knowl. Discov. Data
  doi: 10.1145/2133360.2133363
– volume: 11
  issue: 22
  year: 2022
  ident: 10.1016/j.compmedimag.2024.102343_b27
  article-title: A web-based automated image processing research platform for cochlear implantation-related studies
  publication-title: J. Clin. Med.
  doi: 10.3390/jcm11226640
– volume: 40
  start-page: 33
  issue: 1
  year: 1975
  ident: 10.1016/j.compmedimag.2024.102343_b17
  article-title: Generalized procrustes analysis
  publication-title: Psychometrika
  doi: 10.1007/BF02291478
– start-page: 519
  year: 2021
  ident: 10.1016/j.compmedimag.2024.102343_b25
  article-title: Facial and cochlear nerves characterization using deep reinforcement learning for landmark detection
– start-page: 262
  year: 2019
  ident: 10.1016/j.compmedimag.2024.102343_b50
  article-title: Multiple landmark detection using multi-agent reinforcement learning
– volume: vol. 10575
  start-page: 388
  year: 2018
  ident: 10.1016/j.compmedimag.2024.102343_b40
  article-title: A primitive study on unsupervised anomaly detection with an autoencoder in emergency head CT volumes
– start-page: 697
  year: 2022
  ident: 10.1016/j.compmedimag.2024.102343_b24
  article-title: Deep reinforcement learning for detection of inner ear abnormal anatomy in computed tomography
– volume: 85
  year: 2020
  ident: 10.1016/j.compmedimag.2024.102343_b28
  article-title: Investigating the impact of supervoxel segmentation for unsupervised abnormal brain asymmetry detection
  publication-title: Comput. Med. Imaging Graph.
  doi: 10.1016/j.compmedimag.2020.101770
– start-page: 193
  year: 2020
  ident: 10.1016/j.compmedimag.2024.102343_b26
  article-title: Chapter 11 - autoencoders
– start-page: 485
  year: 2020
  ident: 10.1016/j.compmedimag.2024.102343_b49
  article-title: Attention guided anomaly localization in images
– volume: 78
  year: 2022
  ident: 10.1016/j.compmedimag.2024.102343_b7
  article-title: Multi-landmark environment analysis with reinforcement learning for pelvic abnormality detection and quantification
  publication-title: Med. Image Anal.
  doi: 10.1016/j.media.2022.102417
– year: 2022
  ident: 10.1016/j.compmedimag.2024.102343_b30
– volume: 33
  start-page: 1479
  year: 2021
  ident: 10.1016/j.compmedimag.2024.102343_b19
  article-title: Extended isolation forest
  publication-title: IEEE Trans. Knowl. Data Eng.
  doi: 10.1109/TKDE.2019.2947676
– start-page: 146
  year: 2017
  ident: 10.1016/j.compmedimag.2024.102343_b42
  article-title: Unsupervised anomaly detection with generative adversarial networks to guide marker discovery
– start-page: 5162
  year: 2018
  ident: 10.1016/j.compmedimag.2024.102343_b2
  article-title: Significant dimension reduction of 3D brain MRI using 3D convolutional autoencoders
– start-page: 105
  year: 2019
  ident: 10.1016/j.compmedimag.2024.102343_b18
– start-page: 705
  year: 2022
  ident: 10.1016/j.compmedimag.2024.102343_b35
  article-title: Fast unsupervised brain anomaly detection and segmentation with diffusion models
– volume: 32
  start-page: 347
  issue: 6
  year: 2012
  ident: 10.1016/j.compmedimag.2024.102343_b32
  article-title: Infant hearing loss: From diagnosis to therapy official report of XXI conference of Italian society of pediatric otorhinolaryngology
  publication-title: Acta Otorhinolaryngol. Italica
– volume: 59
  start-page: 1
  year: 2017
  ident: 10.1016/j.compmedimag.2024.102343_b12
  article-title: Automated analysis of human cochlea shape variability from segmented μCT images
  publication-title: Comput. Med. Imaging Graph.
  doi: 10.1016/j.compmedimag.2017.04.002
– start-page: 718
  year: 2020
  ident: 10.1016/j.compmedimag.2024.102343_b5
  article-title: SteGANomaly: Inhibiting cyclegan steganography for unsupervised anomaly detection in brain MRI
– volume: vol. 3
  year: 2022
  ident: 10.1016/j.compmedimag.2024.102343_b23
  article-title: Deep reinforcement learning for detection of abnormal anatomies
– volume: 80
  year: 2022
  ident: 10.1016/j.compmedimag.2024.102343_b44
  article-title: Constrained unsupervised anomaly segmentation
  publication-title: Med. Image Anal.
  doi: 10.1016/j.media.2022.102526
– volume: 44
  start-page: 9249
  year: 2019
  ident: 10.1016/j.compmedimag.2024.102343_b39
  article-title: Brain tumor detection and segmentation in MR images using deep learning
  publication-title: Arab. J. Sci. Eng.
  doi: 10.1007/s13369-019-03967-8
– volume: 11
  year: 2021
  ident: 10.1016/j.compmedimag.2024.102343_b13
  article-title: A novel method of identifying inner ear malformation types by pattern recognition in the mid modiolar section
  publication-title: Sci. Rep.
  doi: 10.1038/s41598-021-00330-6
– volume: 8
  start-page: 275
  issue: 3
  year: 2004
  ident: 10.1016/j.compmedimag.2024.102343_b37
  article-title: A brain tumor segmentation framework based on outlier detection
  publication-title: Med. Image Anal.
  doi: 10.1016/j.media.2004.06.007
– volume: 41
  start-page: 176
  issue: 1
  year: 2019
  ident: 10.1016/j.compmedimag.2024.102343_b16
  article-title: Multi-scale deep reinforcement learning for real-time 3D-landmark detection in CT scans
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2017.2782687
– ident: 10.1016/j.compmedimag.2024.102343_b34
– volume: 61
  start-page: 38
  issue: 1
  year: 1995
  ident: 10.1016/j.compmedimag.2024.102343_b11
  article-title: Active shape models-their training and application
  publication-title: Comput. Vis. Image Underst.
  doi: 10.1006/cviu.1995.1004
– volume: 11
  start-page: 27
  issue: Suppl. 1
  year: 2006
  ident: 10.1016/j.compmedimag.2024.102343_b15
  article-title: The size of the cochlea and predictions of insertion depth angles for cochlear implant electrodes
  publication-title: Audiol. Neurotol.
  doi: 10.1159/000095611
– volume: 79
  year: 2022
  ident: 10.1016/j.compmedimag.2024.102343_b36
  article-title: Unsupervised brain imaging 3D anomaly detection and segmentation with transformers
  publication-title: Med. Image Anal.
  doi: 10.1016/j.media.2022.102475
– volume: 64
  year: 2020
  ident: 10.1016/j.compmedimag.2024.102343_b10
  article-title: Unsupervised lesion detection via image restoration with a normative prior
  publication-title: Med. Image Anal.
  doi: 10.1016/j.media.2020.101713
– volume: 77
  year: 2022
  ident: 10.1016/j.compmedimag.2024.102343_b52
  article-title: Global-local attention network with multi-task uncertainty loss for abnormal lymph node detection in MR images
  publication-title: Med. Image Anal.
  doi: 10.1016/j.media.2021.102345
– start-page: 52
  year: 2011
  ident: 10.1016/j.compmedimag.2024.102343_b29
  article-title: Stacked convolutional auto-encoders for hierarchical feature extraction
– volume: 24
  start-page: 2303
  issue: 8
  year: 2020
  ident: 10.1016/j.compmedimag.2024.102343_b45
  article-title: An adversarial learning approach to medical image synthesis for lesion detection
  publication-title: IEEE J. Biomed. Health Inf.
  doi: 10.1109/JBHI.2020.2964016
– volume: 89
  year: 2021
  ident: 10.1016/j.compmedimag.2024.102343_b1
  article-title: Detection of clustered anomalies in single-voxel morphometry as a rapid automated method for identifying intracranial aneurysms
  publication-title: Comput. Med. Imaging Graph.
  doi: 10.1016/j.compmedimag.2021.101888
– start-page: 161
  year: 2019
  ident: 10.1016/j.compmedimag.2024.102343_b6
  article-title: Deep autoencoding models for unsupervised anomaly segmentation in brain MR images
– volume: 20
  start-page: 677
  issue: 8
  year: 2001
  ident: 10.1016/j.compmedimag.2024.102343_b48
  article-title: Automated segmentation of multiple sclerosis lesions by model outlier detection
  publication-title: IEEE Trans. Med. Imaging
  doi: 10.1109/42.938237
– volume: 31
  start-page: 1116
  issue: 3
  year: 2006
  ident: 10.1016/j.compmedimag.2024.102343_b58
  article-title: User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability
  publication-title: Neuroimage
  doi: 10.1016/j.neuroimage.2006.01.015
– year: 2023
  ident: 10.1016/j.compmedimag.2024.102343_b57
– volume: 80
  year: 2022
  ident: 10.1016/j.compmedimag.2024.102343_b3
  article-title: Prior-aware autoencoders for lung pathology segmentation
  publication-title: Med. Image Anal.
  doi: 10.1016/j.media.2022.102491
– volume: 91
  year: 2021
  ident: 10.1016/j.compmedimag.2024.102343_b31
  article-title: Role of deep learning in brain tumor detection and classification (2015 to 2020): A review
  publication-title: Comput. Med. Imaging Graph.
  doi: 10.1016/j.compmedimag.2021.101940
– volume: vol. 32
  year: 2019
  ident: 10.1016/j.compmedimag.2024.102343_b33
  article-title: PyTorch: An imperative style, high-performance deep learning library
– volume: 40
  start-page: 617
  issue: 5
  year: 2019
  ident: 10.1016/j.compmedimag.2024.102343_b9
  article-title: Further evidence of the relationship between cochlear implant electrode positioning and hearing outcomes
  publication-title: Otol. Neurotol.: Off. Publ. Am. Otol. Soc., Am. Neurotol. Soc. Eur. Acad. Otol. Neurotol.
  doi: 10.1097/MAO.0000000000002204
– volume: 54
  start-page: 30
  year: 2019
  ident: 10.1016/j.compmedimag.2024.102343_b41
  article-title: F-AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks
  publication-title: Med. Image Anal.
  doi: 10.1016/j.media.2019.01.010
– volume: 34
  year: 2017
  ident: 10.1016/j.compmedimag.2024.102343_b43
  article-title: Classification and current management of inner ear malformations
  publication-title: Balkan Med. J.
  doi: 10.4274/balkanmedj.2017.0367
– start-page: 177
  year: 2020
  ident: 10.1016/j.compmedimag.2024.102343_b21
  article-title: Communicative reinforcement learning agents for landmark detection in brain images
– year: 1989
  ident: 10.1016/j.compmedimag.2024.102343_b53
– start-page: 35
  year: 2022
  ident: 10.1016/j.compmedimag.2024.102343_b55
  article-title: Diffusion models for medical anomaly detection
– year: 2023
  ident: 10.1016/j.compmedimag.2024.102343_b56
  article-title: Deep isolation forest for anomaly detection
  publication-title: IEEE Trans. Knowl. Data Eng.
  doi: 10.1109/TKDE.2023.3270293
– volume: 70
  start-page: 145
  year: 2020
  ident: 10.1016/j.compmedimag.2024.102343_b54
  article-title: User-controlled pipelines for feature integration and head and neck radiation therapy outcome predictions
  publication-title: Phys. Med.
  doi: 10.1016/j.ejmp.2020.01.027
– volume: 45
  start-page: 2952
  year: 2023
  ident: 10.1016/j.compmedimag.2024.102343_b51
  article-title: E3Outlier: A self-supervised framework for unsupervised deep outlier detection
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2022.3188763
– volume: vol. 10949
  start-page: 109491H
  year: 2019
  ident: 10.1016/j.compmedimag.2024.102343_b4
  article-title: Unsupervised brain lesion segmentation from MRI using a convolutional autoencoder
– volume: 73
  year: 2021
  ident: 10.1016/j.compmedimag.2024.102343_b59
  article-title: Deep reinforcement learning in medical imaging: A literature review
  publication-title: Med. Image Anal.
  doi: 10.1016/j.media.2021.102193
– start-page: 289
  year: 2019
  ident: 10.1016/j.compmedimag.2024.102343_b60
  article-title: Unsupervised anomaly localization using variational auto-encoders
– start-page: 416
  year: 2022
  ident: 10.1016/j.compmedimag.2024.102343_b38
  article-title: Accurate localization of Inner Ear Regions of interests using deep reinforcement learning
– start-page: 426
  year: 2009
  ident: 10.1016/j.compmedimag.2024.102343_b46
  article-title: Anomaly detection in medical image analysis
– volume: 11
  start-page: 524
  issue: 4
  year: 2021
  ident: 10.1016/j.compmedimag.2024.102343_b8
  article-title: Genetics of inner ear malformations: A review
  publication-title: Audiol. Res.
  doi: 10.3390/audiolres11040047
– volume: 132
  start-page: 523
  year: 2008
  ident: 10.1016/j.compmedimag.2024.102343_b47
  article-title: The visible ear surgery simulator
  publication-title: Stud. Health Technol. Inf.
– volume: 3
  start-page: 1
  issue: 1
  year: 2017
  ident: 10.1016/j.compmedimag.2024.102343_b20
  article-title: Congenital hearing loss
  publication-title: Nat. Rev. Dis. Primers
  doi: 10.1038/nrdp.2016.94
SSID ssj0002071
Score 2.4032319
Snippet Detection of abnormalities within the inner ear is a challenging task even for experienced clinicians. In this study, we propose an automated method for...
AbstractDetection of abnormalities within the inner ear is a challenging task even for experienced clinicians. In this study, we propose an automated method...
SourceID proquest
pubmed
crossref
elsevier
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 102343
SubjectTerms Anomaly detection
Cochlear implant
Computed tomography
Congenital malformation
Deep reinforcement learning
Internal Medicine
Other
Title Deep reinforcement learning and convolutional autoencoders for anomaly detection of congenital inner ear malformations in clinical CT images
URI https://www.clinicalkey.com/#!/content/1-s2.0-S089561112400020X
https://www.clinicalkey.es/playcontent/1-s2.0-S089561112400020X
https://dx.doi.org/10.1016/j.compmedimag.2024.102343
https://www.ncbi.nlm.nih.gov/pubmed/38325245
https://www.proquest.com/docview/2923913958
Volume 113
WOSCitedRecordID wos001177077300001&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: 1879-0771
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002071
  issn: 0895-6111
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1fb9MwELe6DU28IP6O8mfyJMRLlamJk8ZBvIyyCVAZSHRT3yzHdkanNi1LO419Br4i34W7xE5bsUnlgT5ElZWLI98v57P9uztCXmV-R2YZ014a-4EXhmnoSc1ST0eZjv2UG12yLU578fExHwySr43GbxcLczmK85xfXSXT_6pqaANlY-jsP6i7fig0wH9QOlxB7XBdS_HvjZm2LkyZEVWVm3-uNMSZDWLLL-0LYJ6A-WyCuSyRz2wZlZOxHP1saTMzyrmTIAP9YX2RVlmrq4Xpf-C2OvSxZNXWUZbdfms4BkNVLLu-rn7E8Bp83LE9H8Lb3IuVubOXyPc9PMR_x6bmGgyz3eiW81E9j2AQy5mUFTcfTzIy9JhPh6MiLSX5aMF5LPnulhZcfw7IBioN3XdYQdhmuwESLPNmKpvNY4zDqiq57Jsb2pyh99mSqcacFVWGqL9mkWpD4xxBMMXxgKHYx573FzKrmbuPv4ijk15P9A8H_dfTHx4WNcPDf1vhZYNsBXGUwLyxdfDxcPCpdhWCdrUj4N52m-wtCIi39H6bA3XbAql0lPr3yT27wqEHFTIfkIbJH5Ltz5bD8Yj8QoDSFYBSB1AKOKArAKXLAKUgQS1AaQ1QOsnoAqC0BCiFB9IVgEI7dQCl3T6tAPqYnBwd9rsfPFsTxFNR6M88lYSa8YxrGSom26nSOE0Zk0j4-cqXWRR2gpSplCdtxdK402aZMkx2FExuJmFPyGY-yc1TQnVHaxh01dFZGsYskD4sLYzBgmCaa5U2CXcDLZRNmI91W0bCMSPPxZKOBOpIVDpqkqAWnVZZY9YReuO0Kdx4wEQuAJXrCMc3CZvCWqZC-KIIRFt8a3OMZYdlVlgCcNAkb2tJ63VX3vS6He854AmYmfC4UeZmMi9EAGtHTDoc8SbZqRBZDwYDRyIKwujZGtLPyd3FZ_-CbM4u5uYluaMuZ8PiYpdsxAO-az-sP1sOGWo
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=Deep+reinforcement+learning+and+convolutional+autoencoders+for+anomaly+detection+of+congenital+inner+ear+malformations+in+clinical+CT+images&rft.jtitle=Computerized+medical+imaging+and+graphics&rft.au=L%C3%B3pez+Diez%2C+Paula&rft.au=Sundgaard%2C+Josefine+Vilsb%C3%B8ll&rft.au=Margeta%2C+Jan&rft.au=Diab%2C+Khassan&rft.date=2024-04-01&rft.issn=1879-0771&rft.eissn=1879-0771&rft.volume=113&rft.spage=102343&rft_id=info:doi/10.1016%2Fj.compmedimag.2024.102343&rft.externalDBID=NO_FULL_TEXT
thumbnail_m http://cvtisr.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fcdn.clinicalkey.com%2Fck-thumbnails%2F08956111%2Fcov200h.gif