Clinical application of deep learning-based synthetic CT from real MRI to improve dose planning accuracy in Gamma Knife radiosurgery: a proof of concept study

Dose planning for Gamma Knife radiosurgery (GKRS) uses the magnetic resonance (MR)-based tissue maximum ratio (TMR) algorithm, which calculates radiation dose without considering heterogeneous radiation attenuation in the tissue. In order to plan the dose considering the radiation attenuation, the C...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Biomedical Engineering Letters Jg. 12; H. 4; S. 359 - 367
Hauptverfasser:	Park, So Hee, Choi, Dong Min, Jung, In-Ho, Chang, Kyung Won, Kim, Myung Ji, Jung, Hyun Ho, Chang, Jin Woo, Kim, Hwiyoung, Chang, Won Seok
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Korea Springer Science and Business Media LLC 01.11.2022 The Korean Society of Medical and Biological Engineering Springer Nature B.V
Schlagworte:	Adenoma Algorithms Artificial intelligence Attenuation Biological and Medical Physics Biomedical Engineering and Bioengineering Biomedicine Biophysics Brain tumors Computed tomography Convolution Deep learning Engineering Feasibility studies Gamma Knife radiosurgery Health services Image acquisition Image contrast Image enhancement Machine learning Magnetic resonance imaging Medical and Radiation Physics Meningioma Metastases Neuro-oncology Original Original Article Pituitary Planning Radiation Radiation dosage Radiation effects Radiology Radiosurgery Synthetic CT Tumors Vascular diseases Deep learning Gamma Knife radiosurgery Neuro-oncology Synthetic CT Artificial intelligence
ISSN:	2093-9868, 2093-985X, 2093-985X
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Dose planning for Gamma Knife radiosurgery (GKRS) uses the magnetic resonance (MR)-based tissue maximum ratio (TMR) algorithm, which calculates radiation dose without considering heterogeneous radiation attenuation in the tissue. In order to plan the dose considering the radiation attenuation, the Convolution algorithm should be used, and additional radiation exposure for computed tomography (CT) and registration errors between MR and CT are entailed. This study investigated the clinical feasibility of synthetic CT (sCT) from GKRS planning MR using deep learning. The model was trained using frame-based contrast-enhanced T1-weighted MR images and corresponding CT slices from 54 training subjects acquired for GKRS planning. The model was applied prospectively to 60 lesions in 43 patients including benign tumor such as meningioma and pituitary adenoma, metastatic brain tumors, and vascular disease of various location for evaluating the model and its application. We evaluated the sCT and compared between treatment plans made with MR only (TMR 10 plan), MR and real CT (rCT; Convolution with rCT [Conv-rCT] plan), and MR and synthetic CT (Convolution with sCT [Conv-sCT] plan). The mean absolute error (MAE) of 43 sCT was 107.35 ± 16.47 Hounsfield units. The TMR 10 treatment plan differed significantly from plans made by Conv-sCT and Conv-rCT. However, the Conv-sCT and Conv-rCT plans were similar. This study showed the practical applicability of deep learning based on sCT in GKRS. Our results support the possibility of formulating GKRS treatment plans while considering radiation attenuation in the tissue using GKRS planning MR and no radiation exposure.
AbstractList	Dose planning for Gamma Knife radiosurgery (GKRS) uses the magnetic resonance (MR)-based tissue maximum ratio (TMR) algorithm, which calculates radiation dose without considering heterogeneous radiation attenuation in the tissue. In order to plan the dose considering the radiation attenuation, the Convolution algorithm should be used, and additional radiation exposure for computed tomography (CT) and registration errors between MR and CT are entailed. This study investigated the clinical feasibility of synthetic CT (sCT) from GKRS planning MR using deep learning. The model was trained using frame-based contrast-enhanced T1-weighted MR images and corresponding CT slices from 54 training subjects acquired for GKRS planning. The model was applied prospectively to 60 lesions in 43 patients including benign tumor such as meningioma and pituitary adenoma, metastatic brain tumors, and vascular disease of various location for evaluating the model and its application. We evaluated the sCT and compared between treatment plans made with MR only (TMR 10 plan), MR and real CT (rCT; Convolution with rCT [Conv-rCT] plan), and MR and synthetic CT (Convolution with sCT [Conv-sCT] plan). The mean absolute error (MAE) of 43 sCT was 107.35 ± 16.47 Hounsfield units. The TMR 10 treatment plan differed significantly from plans made by Conv-sCT and Conv-rCT. However, the Conv-sCT and Conv-rCT plans were similar. This study showed the practical applicability of deep learning based on sCT in GKRS. Our results support the possibility of formulating GKRS treatment plans while considering radiation attenuation in the tissue using GKRS planning MR and no radiation exposure.Dose planning for Gamma Knife radiosurgery (GKRS) uses the magnetic resonance (MR)-based tissue maximum ratio (TMR) algorithm, which calculates radiation dose without considering heterogeneous radiation attenuation in the tissue. In order to plan the dose considering the radiation attenuation, the Convolution algorithm should be used, and additional radiation exposure for computed tomography (CT) and registration errors between MR and CT are entailed. This study investigated the clinical feasibility of synthetic CT (sCT) from GKRS planning MR using deep learning. The model was trained using frame-based contrast-enhanced T1-weighted MR images and corresponding CT slices from 54 training subjects acquired for GKRS planning. The model was applied prospectively to 60 lesions in 43 patients including benign tumor such as meningioma and pituitary adenoma, metastatic brain tumors, and vascular disease of various location for evaluating the model and its application. We evaluated the sCT and compared between treatment plans made with MR only (TMR 10 plan), MR and real CT (rCT; Convolution with rCT [Conv-rCT] plan), and MR and synthetic CT (Convolution with sCT [Conv-sCT] plan). The mean absolute error (MAE) of 43 sCT was 107.35 ± 16.47 Hounsfield units. The TMR 10 treatment plan differed significantly from plans made by Conv-sCT and Conv-rCT. However, the Conv-sCT and Conv-rCT plans were similar. This study showed the practical applicability of deep learning based on sCT in GKRS. Our results support the possibility of formulating GKRS treatment plans while considering radiation attenuation in the tissue using GKRS planning MR and no radiation exposure. Dose planning for Gamma Knife radiosurgery (GKRS) uses the magnetic resonance (MR)-based tissue maximum ratio (TMR) algorithm, which calculates radiation dose without considering heterogeneous radiation attenuation in the tissue. In order to plan the dose considering the radiation attenuation, the Convolution algorithm should be used, and additional radiation exposure for computed tomography (CT) and registration errors between MR and CT are entailed. This study investigated the clinical feasibility of synthetic CT (sCT) from GKRS planning MR using deep learning. The model was trained using frame-based contrast-enhanced T1-weighted MR images and corresponding CT slices from 54 training subjects acquired for GKRS planning. The model was applied prospectively to 60 lesions in 43 patients including benign tumor such as meningioma and pituitary adenoma, metastatic brain tumors, and vascular disease of various location for evaluating the model and its application. We evaluated the sCT and compared between treatment plans made with MR only (TMR 10 plan), MR and real CT (rCT; Convolution with rCT [Conv-rCT] plan), and MR and synthetic CT (Convolution with sCT [Conv-sCT] plan). The mean absolute error (MAE) of 43 sCT was 107.35 ± 16.47 Hounsfield units. The TMR 10 treatment plan differed significantly from plans made by Conv-sCT and Conv-rCT. However, the Conv-sCT and Conv-rCT plans were similar. This study showed the practical applicability of deep learning based on sCT in GKRS. Our results support the possibility of formulating GKRS treatment plans while considering radiation attenuation in the tissue using GKRS planning MR and no radiation exposure.
Author	Myung Ji Kim Hwiyoung Kim Kyung Won Chang Jin Woo Chang Hyun Ho Jung In-Ho Jung Dong Min Choi So Hee Park Won Seok Chang
Author_xml	– sequence: 1 givenname: So Hee surname: Park fullname: Park, So Hee organization: Department of Neurosurgery, Brain Research Institute, Yonsei Medical Gamma Knife Center, Yonsei University College of Medicine – sequence: 2 givenname: Dong Min surname: Choi fullname: Choi, Dong Min organization: Center of Clinical Imaging Data Science, Department of Radiology, Yonsei University College of Medicine – sequence: 3 givenname: In-Ho surname: Jung fullname: Jung, In-Ho organization: Department of Neurosurgery, Brain Research Institute, Yonsei Medical Gamma Knife Center, Yonsei University College of Medicine – sequence: 4 givenname: Kyung Won surname: Chang fullname: Chang, Kyung Won organization: Department of Neurosurgery, Brain Research Institute, Yonsei Medical Gamma Knife Center, Yonsei University College of Medicine – sequence: 5 givenname: Myung Ji surname: Kim fullname: Kim, Myung Ji organization: Department of Neurosurgery, Korea University Medical Center, Korea University College of Medicine, Ansan Hospital – sequence: 6 givenname: Hyun Ho surname: Jung fullname: Jung, Hyun Ho organization: Department of Neurosurgery, Brain Research Institute, Yonsei Medical Gamma Knife Center, Yonsei University College of Medicine – sequence: 7 givenname: Jin Woo surname: Chang fullname: Chang, Jin Woo organization: Department of Neurosurgery, Brain Research Institute, Yonsei Medical Gamma Knife Center, Yonsei University College of Medicine – sequence: 8 givenname: Hwiyoung surname: Kim fullname: Kim, Hwiyoung email: hykim82@yuhs.ac organization: Center of Clinical Imaging Data Science, Department of Radiology, Yonsei University College of Medicine, Department of Biomedical System Informatics, Yonsei University College of Medicine – sequence: 9 givenname: Won Seok orcidid: 0000-0003-3145-4016 surname: Chang fullname: Chang, Won Seok email: changws0716@yuhs.ac organization: Department of Neurosurgery, Brain Research Institute, Yonsei Medical Gamma Knife Center, Yonsei University College of Medicine
BackLink	https://cir.nii.ac.jp/crid/1874242817407483520$$DView record in CiNii https://www.ncbi.nlm.nih.gov/pubmed/36238366$$D View this record in MEDLINE/PubMed
BookMark	eNp9kl9r1TAYxotM3Jz7Al5IQC-8qeZvk3ohyEHncCLIBO9CTvL2LKNNatKO9cv4Wc3Z2abuYqWkgT6_p0_6vE-rvRADVNVzgt8QjOXbTJhgvMaU1rgssr56VB1Q3LK6VeLn3t2-UfvVUc4XuFyCiJaxJ9U-ayhTrGkOqt-r3gdvTY_MOPZlM_kYUOyQAxhRDyYFHzb12mRwKC9hOofJW7Q6Q12KA0pQyK_fT9AUkR_GFC8BuZgBjb0JWxIZa-dk7IJ8QMdmGAz6EnwHKBnnY57TBtLyDhlU2PLVctsYLIwTytPslmfV4870GY5unofVj08fz1af69NvxyerD6e1FU071bITpGNWUSxwoyQnRra2EaRxRBoopwXSKufWDXfcYMAOBMWOY8NBKkKBHVbvd77jvB7AWQhTMr0ekx9MWnQ0Xv__JvhzvYmXuhUCt4QXg9c3Bin-miFPevDZQl9-A8Q5ayqpIKqVDBfpy3vSizinUI63VTFBOMFbwxf_JrqLcltdEaidwKaYc4JOWz9d11cC-l4TrLeDoneDosuM6OtB0VcFpffQW_cHIbaDchGHUtvf2A9Sr3ZU8L4E3K6kFEQ5VURyLLlipQr2B-GX3Gk
CitedBy_id	crossref_primary_10_3390_bioengineering10091078 crossref_primary_10_1016_j_radonc_2024_110387 crossref_primary_10_1016_j_ejmp_2024_104504 crossref_primary_10_1007_s13139_024_00861_6 crossref_primary_10_1088_2057_1976_add26b crossref_primary_10_1016_j_media_2025_103605 crossref_primary_10_1007_s13534_024_00430_y crossref_primary_10_1007_s40998_025_00808_3 crossref_primary_10_1055_a_2436_8444 crossref_primary_10_1016_j_phro_2024_100652
Cites_doi	10.1186/s13014-021-01794-6 10.1016/j.ijrobp.2009.10.017 10.1120/jacmp.v16i6.5530 10.1002/acm2.12554 10.1109/2945.556502 10.1118/1.4914158 10.1088/0031-9155/59/21/6595 10.1016/j.radonc.2019.03.026 10.3389/fonc.2019.00964 10.1002/mp.12155 10.1002/mp.13617 10.1016/j.ijrobp.2015.08.049 10.1002/acm2.12238 10.1109/CVPR.2017.632 10.1109/TBME.2018.2814538 10.1002/mp.14075 10.1002/mp.12964 10.1109/BIBM49941.2020.9313470 10.18637/jss.v086.i08 10.1088/0031-9155/58/23/8419 10.1002/mp.13047 10.3389/fninf.2013.00045 10.1002/mp.13663 10.1109/2945.620490 10.1007/s10278-017-0037-8 10.3389/fonc.2019.01333
ContentType	Journal Article
Contributor	Kim, Hwiyoung Myung Ji Kim Hwiyoung Kim Kyung Won Chang Jin Woo Chang Hyun Ho Jung In-Ho Jung Dong Min Choi So Hee Park Won Seok Chang
Contributor_xml	– sequence: 1 fullname: So Hee Park – sequence: 2 fullname: Dong Min Choi – sequence: 3 fullname: In-Ho Jung – sequence: 4 fullname: Kyung Won Chang – sequence: 5 fullname: Myung Ji Kim – sequence: 6 fullname: Hyun Ho Jung – sequence: 7 fullname: Jin Woo Chang – sequence: 8 fullname: Hwiyoung Kim – sequence: 9 fullname: Won Seok Chang – sequence: 10 fullname: Kim, Hwiyoung
Copyright	Korean Society of Medical and Biological Engineering 2022 Korean Society of Medical and Biological Engineering 2022.
Copyright_xml	– notice: Korean Society of Medical and Biological Engineering 2022 – notice: Korean Society of Medical and Biological Engineering 2022.
DBID	RYH AAYXX CITATION NPM 7X8 5PM
DOI	10.1007/s13534-022-00227-x
DatabaseName	CiNii Complete CrossRef PubMed MEDLINE - Academic PubMed Central (Full Participant titles)
DatabaseTitle	CrossRef PubMed MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic PubMed
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	Engineering
EISSN	2093-985X
EndPage	367
ExternalDocumentID	PMC9550914 36238366 10_1007_s13534_022_00227_x
Genre	Journal Article
GrantInformation_xml	– fundername: Korea Health Industry Development Institute grantid: HI21C1161 funderid: http://dx.doi.org/10.13039/501100003710 – fundername: Korea Medical Device Development Fund grantid: 202011D25 – fundername: Severance Hospital Research Fund for Clinical Excellence – fundername: ; – fundername: ; grantid: HI21C1161 – fundername: ; grantid: 202011D25
GroupedDBID	0R~ 0VY 203 29~ 30V 4.4 406 408 53G 8TC 96X AACDK AAHNG AAIAL AAJBT AAJKR AANZL AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAZMS ABAKF ABBRH ABDBE ABDZT ABECU ABFSG ABFTV ABJNI ABJOX ABKCH ABMQK ABQBU ABRTQ ABSXP ABTEG ABTHY ABTKH ABTMW ABXPI ACAOD ACDTI ACGFS ACHSB ACIWK ACKNC ACMLO ACOKC ACPIV ACPRK ACSTC ACZOJ ADHHG ADHIR ADKNI ADKPE ADRFC ADTPH ADURQ ADYFF ADZKW AEFQL AEGNC AEJHL AEJRE AEMSY AEOHA AEPYU AESKC AETCA AEVLU AEXYK AEZWR AFBBN AFDZB AFHIU AFOHR AFQWF AFWTZ AFZKB AGAYW AGDGC AGMZJ AGQEE AGQMX AGRTI AGWZB AGYKE AHAVH AHBYD AHKAY AHPBZ AHWEU AHYZX AIAKS AIGIU AIIXL AILAN AITGF AIXLP AJRNO AKLTO ALFXC ALMA_UNASSIGNED_HOLDINGS AMKLP AMXSW AMYLF AMYQR ATHPR AUKKA AXYYD AYFIA AYJHY BGNMA CSCUP DNIVK DPUIP EBLON EBS EIOEI ESBYG FERAY FIGPU FNLPD FRRFC FYJPI GGCAI GJIRD HMJXF HRMNR HYE I0C IKXTQ IWAJR IXD J-C JBSCW JZLTJ KOV LLZTM M4Y NPVJJ NQJWS NU0 O9J OK1 PT4 RLLFE ROL RPM RSV RYH S27 SEG SHX SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE SZN T13 TSG U2A UG4 UOJIU UTJUX UZXMN VFIZW W48 ZMTXR ~A9 -EM 2VQ AAAVM AARHV AAYTO AAYZH ADINQ AEBTG AFLOW AGJBK AHSBF AJBLW EJD FINBP FSGXE GGRSB GQ6 HF~ HZ~ O9- Z7X AAYXX CITATION NPM 7X8 5PM
ID	FETCH-LOGICAL-c569t-7f51f3c8205068741a79c6516d17ae362e198ddb64d4a0e0de520d40a4e7812e3
IEDL.DBID	RSV
ISICitedReferencesCount	12
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000812103800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2093-9868 2093-985X
IngestDate	Thu Aug 21 18:37:32 EDT 2025 Thu Oct 02 05:20:03 EDT 2025 Wed Sep 17 23:53:23 EDT 2025 Mon Jul 21 05:50:07 EDT 2025 Tue Nov 18 22:35:34 EST 2025 Sat Nov 29 02:18:44 EST 2025 Fri Feb 21 02:45:27 EST 2025 Mon Nov 10 09:09:02 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	false
IsScholarly	true
Issue	4
Keywords	Deep learning Gamma Knife radiosurgery Neuro-oncology Synthetic CT Artificial intelligence
Language	English
License	Korean Society of Medical and Biological Engineering 2022.
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c569t-7f51f3c8205068741a79c6516d17ae362e198ddb64d4a0e0de520d40a4e7812e3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0002-2717-0101 0000-0002-4135-5743 0000-0003-3145-4016
OpenAccessLink	https://cir.nii.ac.jp/crid/1874242817407483520
PMID	36238366
PQID	2723514104
PQPubID	2043953
PageCount	9
ParticipantIDs	pubmedcentral_primary_oai_pubmedcentral_nih_gov_9550914 proquest_miscellaneous_2725189730 proquest_journals_2723514104 pubmed_primary_36238366 crossref_citationtrail_10_1007_s13534_022_00227_x crossref_primary_10_1007_s13534_022_00227_x springer_journals_10_1007_s13534_022_00227_x nii_cinii_1874242817407483520
PublicationCentury	2000
PublicationDate	2022-11-01
PublicationDateYYYYMMDD	2022-11-01
PublicationDate_xml	– month: 11 year: 2022 text: 2022-11-01 day: 01
PublicationDecade	2020
PublicationPlace	Korea
PublicationPlace_xml	– name: Korea – name: Germany – name: Heidelberg
PublicationTitle	Biomedical Engineering Letters
PublicationTitleAbbrev	Biomed. Eng. Lett
PublicationTitleAlternate	Biomed Eng Lett
PublicationYear	2022
Publisher	Springer Science and Business Media LLC The Korean Society of Medical and Biological Engineering Springer Nature B.V
Publisher_xml	– name: Springer Science and Business Media LLC – name: The Korean Society of Medical and Biological Engineering – name: Springer Nature B.V
References	GuptaDKimMVinebergKABalterJMGeneration of synthetic CT images from MRI for treatment planning and patient positioning using a 3-channel U-net trained on sagittal imagesFront Oncol2019996410.3389/fonc.2019.00964 KazemifarSMcGuireSTimmermanRMRI-only brain radiotherapy: assessing the dosimetric accuracy of synthetic CT images generated using a deep learning approachRadiother Oncol2019136566310.1016/j.radonc.2019.03.026 AndreasenDVan LeemputKHansenRHAndersenJAEdmundJMPatch-based generation of a pseudo CT from conventional MRI sequences for MRI-only radiotherapy of the brainMed Phys20154241596160510.1118/1.4914158 Lerner M, Medin J, Jamtheim Gustafsson C, Alkner S, Siversson C, Olsson LE. Clinical validation of a commercially available deep learning software for synthetic CT generation for brain. Radiat Oncol. 2021;16(1):66. https://doi.org/10.1186/s13014-021-01794-6 Beare R, Lowekamp B, Yaniv Z. Image segmentation, registration and characterization in R with SimpleITK. J Stat Softw. 2018;86. https://doi.org/10.18637/jss.v086.i08 LeiYHarmsJWangTMRI-only based synthetic CT generation using dense cycle consistent generative adversarial networksMed Phys20194683565358110.1002/mp.13617 Emami H, Dong M, Nejad-Davarani SP, Glide-Hurst CK. Generating synthetic CTs from magnetic resonance images using generative adversarial networks. Med Phys. 2018; https://doi.org/10.1002/mp.13047 FallowsPWrightGHarroldNBownesPA comparison of the convolution and TMR10 treatment planning algorithms for Gamma Knife((R)) radiosurgeryJ Radiosurg SBRT201852157167 OsmancikovaPNovotnyJJrSolcJPipekJComparison of the convolution algorithm with TMR10 for Leksell gamma knife and dosimetric verification with radiochromic gel dosimeterJ Appl Clin Med Phys201819113814410.1002/acm2.12238 DinklaAMFlorkowMCMasperoMDosimetric evaluation of synthetic CT for head and neck radiotherapy generated by a patch-based three-dimensional convolutional neural networkMed Phys20194694095410410.1002/mp.13663 Mattes D, Haynor DR, Vesselle H, Lewellyn TK, Eubank W. Nonrigid multimodality image registration. Spie; 2001:1609–1620 Lowekamp BC, Chen DT, Ibanez L, Blezek D. The design of SimpleITK. Front Neuroinform. 2013;7:45. https://doi.org/10.3389/fninf.2013.00045 ParadisECaoYLawrenceTSAssessing the dosimetric accuracy of magnetic resonance-generated synthetic CT images for focal brain VMAT radiation therapyInt J Radiat Oncol Biol Phys20159351154116110.1016/j.ijrobp.2015.08.049 HsuSHCaoYHuangKFengMBalterJMInvestigation of a method for generating synthetic CT models from MRI scans of the head and neck for radiation therapyPhys Med Biol201358238419843510.1088/0031-9155/58/23/8419 Ganz JC. The history of the gamma knife. Elsevier; 2014 Isola P, Zhu J-Y, Zhou T, Efros AA. Image-to-image translation with conditional adversarial networks. 2017:1125–1134 NieDTrulloRLianJMedical image synthesis with deep convolutional adversarial networksIEEE Trans Biomed Eng201865122720273010.1109/TBME.2018.2814538 GudurMSHaraWLeQTWangLXingLLiRA unifying probabilistic Bayesian approach to derive electron density from MRI for radiation therapy treatment planningPhys Med Biol201459216595660610.1088/0031-9155/59/21/6595 Qiao Z, Qian Z, Tang H, et al. CorGAN: Context aware recurrent generative adversarial network for medical image generation. IEEE; 2020:1100–1103 LiuFYadavPBaschnagelAMMcMillanABMR-based treatment planning in radiation therapy using a deep learning approachJ Appl Clin Med Phys201920310511410.1002/acm2.12554 QiMLiYWuAMulti-sequence MR image-based synthetic CT generation using a generative adversarial network for head and neck MRI-only radiotherapyMed Phys20204741880189410.1002/mp.14075 LeeSWolbergGChwaK-YShinSYImage metamorphosis with scattered feature constraintsIEEE Trans Visual Comput Graph19962433735410.1109/2945.556502 LeeSWolbergGShinSYScattered data interpolation with multilevel B-splinesIEEE Trans Visual Comput Graph19973322824410.1109/2945.620490 UlinKUrieMMCherlowJMResults of a multi-institutional benchmark test for cranial CT/MR image registrationInt J Radiat Oncol Biol Phys20107751584158910.1016/j.ijrobp.2009.10.017 HanXMR-based synthetic CT generation using a deep convolutional neural network methodMed Phys20174441408141910.1002/mp.12155 WangYLiuCZhangXDengWSynthetic CT generation based on T2 weighted mri of nasopharyngeal carcinoma (NPC) Using a deep convolutional neural network (DCNN)Front Oncol20199133310.3389/fonc.2019.01333 XuAYBhatnagarJBednarzGGamma Knife radiosurgery with CT image-based dose calculationJ Appl Clin Med Phys201516611912910.1120/jacmp.v16i6.5530 Huang H, Yu PS, Wang C. An introduction to image synthesis with generative adversarial nets; 2018. arXiv preprint arXiv:180304469 Jang H, Liu F, Zhao G, Bradshaw T, McMillan AB. Technical note: deep learning based MRAC using rapid ultrashort echo time imaging. Med Phys. 2018; https://doi.org/10.1002/mp.12964 YanivZLowekampBCJohnsonHJBeareRSimpleITK image-analysis notebooks: a collaborative environment for education and reproducible researchJ Digit Imaging201831329030310.1007/s10278-017-0037-8 AY Xu (227_CR2) 2015; 16 D Andreasen (227_CR22) 2015; 42 D Gupta (227_CR8) 2019; 9 S Lee (227_CR19) 1997; 3 P Fallows (227_CR3) 2018; 5 S Lee (227_CR18) 1996; 2 P Osmancikova (227_CR4) 2018; 19 E Paradis (227_CR14) 2015; 93 227_CR21 227_CR20 Y Lei (227_CR7) 2019; 46 227_CR29 Z Yaniv (227_CR17) 2018; 31 227_CR28 Y Wang (227_CR10) 2019; 9 227_CR26 227_CR25 SH Hsu (227_CR24) 2013; 58 227_CR1 M Qi (227_CR9) 2020; 47 D Nie (227_CR27) 2018; 65 K Ulin (227_CR5) 2010; 77 AM Dinkla (227_CR11) 2019; 46 F Liu (227_CR13) 2019; 20 S Kazemifar (227_CR12) 2019; 136 227_CR30 X Han (227_CR6) 2017; 44 227_CR16 227_CR15 MS Gudur (227_CR23) 2014; 59
References_xml	– reference: HanXMR-based synthetic CT generation using a deep convolutional neural network methodMed Phys20174441408141910.1002/mp.12155 – reference: WangYLiuCZhangXDengWSynthetic CT generation based on T2 weighted mri of nasopharyngeal carcinoma (NPC) Using a deep convolutional neural network (DCNN)Front Oncol20199133310.3389/fonc.2019.01333 – reference: Lowekamp BC, Chen DT, Ibanez L, Blezek D. The design of SimpleITK. Front Neuroinform. 2013;7:45. https://doi.org/10.3389/fninf.2013.00045 – reference: Ganz JC. The history of the gamma knife. Elsevier; 2014 – reference: UlinKUrieMMCherlowJMResults of a multi-institutional benchmark test for cranial CT/MR image registrationInt J Radiat Oncol Biol Phys20107751584158910.1016/j.ijrobp.2009.10.017 – reference: LeeSWolbergGChwaK-YShinSYImage metamorphosis with scattered feature constraintsIEEE Trans Visual Comput Graph19962433735410.1109/2945.556502 – reference: GudurMSHaraWLeQTWangLXingLLiRA unifying probabilistic Bayesian approach to derive electron density from MRI for radiation therapy treatment planningPhys Med Biol201459216595660610.1088/0031-9155/59/21/6595 – reference: Lerner M, Medin J, Jamtheim Gustafsson C, Alkner S, Siversson C, Olsson LE. Clinical validation of a commercially available deep learning software for synthetic CT generation for brain. Radiat Oncol. 2021;16(1):66. https://doi.org/10.1186/s13014-021-01794-6 – reference: OsmancikovaPNovotnyJJrSolcJPipekJComparison of the convolution algorithm with TMR10 for Leksell gamma knife and dosimetric verification with radiochromic gel dosimeterJ Appl Clin Med Phys201819113814410.1002/acm2.12238 – reference: ParadisECaoYLawrenceTSAssessing the dosimetric accuracy of magnetic resonance-generated synthetic CT images for focal brain VMAT radiation therapyInt J Radiat Oncol Biol Phys20159351154116110.1016/j.ijrobp.2015.08.049 – reference: HsuSHCaoYHuangKFengMBalterJMInvestigation of a method for generating synthetic CT models from MRI scans of the head and neck for radiation therapyPhys Med Biol201358238419843510.1088/0031-9155/58/23/8419 – reference: FallowsPWrightGHarroldNBownesPA comparison of the convolution and TMR10 treatment planning algorithms for Gamma Knife((R)) radiosurgeryJ Radiosurg SBRT201852157167 – reference: NieDTrulloRLianJMedical image synthesis with deep convolutional adversarial networksIEEE Trans Biomed Eng201865122720273010.1109/TBME.2018.2814538 – reference: AndreasenDVan LeemputKHansenRHAndersenJAEdmundJMPatch-based generation of a pseudo CT from conventional MRI sequences for MRI-only radiotherapy of the brainMed Phys20154241596160510.1118/1.4914158 – reference: QiMLiYWuAMulti-sequence MR image-based synthetic CT generation using a generative adversarial network for head and neck MRI-only radiotherapyMed Phys20204741880189410.1002/mp.14075 – reference: Beare R, Lowekamp B, Yaniv Z. Image segmentation, registration and characterization in R with SimpleITK. J Stat Softw. 2018;86. https://doi.org/10.18637/jss.v086.i08 – reference: LeiYHarmsJWangTMRI-only based synthetic CT generation using dense cycle consistent generative adversarial networksMed Phys20194683565358110.1002/mp.13617 – reference: Jang H, Liu F, Zhao G, Bradshaw T, McMillan AB. Technical note: deep learning based MRAC using rapid ultrashort echo time imaging. Med Phys. 2018; https://doi.org/10.1002/mp.12964 – reference: Emami H, Dong M, Nejad-Davarani SP, Glide-Hurst CK. Generating synthetic CTs from magnetic resonance images using generative adversarial networks. Med Phys. 2018; https://doi.org/10.1002/mp.13047 – reference: LeeSWolbergGShinSYScattered data interpolation with multilevel B-splinesIEEE Trans Visual Comput Graph19973322824410.1109/2945.620490 – reference: KazemifarSMcGuireSTimmermanRMRI-only brain radiotherapy: assessing the dosimetric accuracy of synthetic CT images generated using a deep learning approachRadiother Oncol2019136566310.1016/j.radonc.2019.03.026 – reference: Qiao Z, Qian Z, Tang H, et al. CorGAN: Context aware recurrent generative adversarial network for medical image generation. IEEE; 2020:1100–1103 – reference: DinklaAMFlorkowMCMasperoMDosimetric evaluation of synthetic CT for head and neck radiotherapy generated by a patch-based three-dimensional convolutional neural networkMed Phys20194694095410410.1002/mp.13663 – reference: XuAYBhatnagarJBednarzGGamma Knife radiosurgery with CT image-based dose calculationJ Appl Clin Med Phys201516611912910.1120/jacmp.v16i6.5530 – reference: YanivZLowekampBCJohnsonHJBeareRSimpleITK image-analysis notebooks: a collaborative environment for education and reproducible researchJ Digit Imaging201831329030310.1007/s10278-017-0037-8 – reference: Isola P, Zhu J-Y, Zhou T, Efros AA. Image-to-image translation with conditional adversarial networks. 2017:1125–1134 – reference: Mattes D, Haynor DR, Vesselle H, Lewellyn TK, Eubank W. Nonrigid multimodality image registration. Spie; 2001:1609–1620 – reference: GuptaDKimMVinebergKABalterJMGeneration of synthetic CT images from MRI for treatment planning and patient positioning using a 3-channel U-net trained on sagittal imagesFront Oncol2019996410.3389/fonc.2019.00964 – reference: Huang H, Yu PS, Wang C. An introduction to image synthesis with generative adversarial nets; 2018. arXiv preprint arXiv:180304469 – reference: LiuFYadavPBaschnagelAMMcMillanABMR-based treatment planning in radiation therapy using a deep learning approachJ Appl Clin Med Phys201920310511410.1002/acm2.12554 – ident: 227_CR29 doi: 10.1186/s13014-021-01794-6 – ident: 227_CR1 – volume: 77 start-page: 1584 issue: 5 year: 2010 ident: 227_CR5 publication-title: Int J Radiat Oncol Biol Phys doi: 10.1016/j.ijrobp.2009.10.017 – volume: 16 start-page: 119 issue: 6 year: 2015 ident: 227_CR2 publication-title: J Appl Clin Med Phys doi: 10.1120/jacmp.v16i6.5530 – volume: 20 start-page: 105 issue: 3 year: 2019 ident: 227_CR13 publication-title: J Appl Clin Med Phys doi: 10.1002/acm2.12554 – volume: 2 start-page: 337 issue: 4 year: 1996 ident: 227_CR18 publication-title: IEEE Trans Visual Comput Graph doi: 10.1109/2945.556502 – volume: 42 start-page: 1596 issue: 4 year: 2015 ident: 227_CR22 publication-title: Med Phys doi: 10.1118/1.4914158 – volume: 59 start-page: 6595 issue: 21 year: 2014 ident: 227_CR23 publication-title: Phys Med Biol doi: 10.1088/0031-9155/59/21/6595 – volume: 136 start-page: 56 year: 2019 ident: 227_CR12 publication-title: Radiother Oncol doi: 10.1016/j.radonc.2019.03.026 – ident: 227_CR20 – volume: 9 start-page: 964 year: 2019 ident: 227_CR8 publication-title: Front Oncol doi: 10.3389/fonc.2019.00964 – volume: 44 start-page: 1408 issue: 4 year: 2017 ident: 227_CR6 publication-title: Med Phys doi: 10.1002/mp.12155 – volume: 46 start-page: 3565 issue: 8 year: 2019 ident: 227_CR7 publication-title: Med Phys doi: 10.1002/mp.13617 – volume: 93 start-page: 1154 issue: 5 year: 2015 ident: 227_CR14 publication-title: Int J Radiat Oncol Biol Phys doi: 10.1016/j.ijrobp.2015.08.049 – volume: 19 start-page: 138 issue: 1 year: 2018 ident: 227_CR4 publication-title: J Appl Clin Med Phys doi: 10.1002/acm2.12238 – ident: 227_CR21 doi: 10.1109/CVPR.2017.632 – volume: 65 start-page: 2720 issue: 12 year: 2018 ident: 227_CR27 publication-title: IEEE Trans Biomed Eng doi: 10.1109/TBME.2018.2814538 – volume: 47 start-page: 1880 issue: 4 year: 2020 ident: 227_CR9 publication-title: Med Phys doi: 10.1002/mp.14075 – volume: 5 start-page: 157 issue: 2 year: 2018 ident: 227_CR3 publication-title: J Radiosurg SBRT – ident: 227_CR28 doi: 10.1002/mp.12964 – ident: 227_CR30 doi: 10.1109/BIBM49941.2020.9313470 – ident: 227_CR25 – ident: 227_CR15 doi: 10.18637/jss.v086.i08 – volume: 58 start-page: 8419 issue: 23 year: 2013 ident: 227_CR24 publication-title: Phys Med Biol doi: 10.1088/0031-9155/58/23/8419 – ident: 227_CR26 doi: 10.1002/mp.13047 – ident: 227_CR16 doi: 10.3389/fninf.2013.00045 – volume: 46 start-page: 4095 issue: 9 year: 2019 ident: 227_CR11 publication-title: Med Phys doi: 10.1002/mp.13663 – volume: 3 start-page: 228 issue: 3 year: 1997 ident: 227_CR19 publication-title: IEEE Trans Visual Comput Graph doi: 10.1109/2945.620490 – volume: 31 start-page: 290 issue: 3 year: 2018 ident: 227_CR17 publication-title: J Digit Imaging doi: 10.1007/s10278-017-0037-8 – volume: 9 start-page: 1333 year: 2019 ident: 227_CR10 publication-title: Front Oncol doi: 10.3389/fonc.2019.01333
SSID	ssj0000515933
Score	2.3152351
Snippet	Dose planning for Gamma Knife radiosurgery (GKRS) uses the magnetic resonance (MR)-based tissue maximum ratio (TMR) algorithm, which calculates radiation dose...
SourceID	pubmedcentral proquest pubmed crossref springer nii
SourceType	Open Access Repository Aggregation Database Index Database Enrichment Source Publisher
StartPage	359
SubjectTerms	Adenoma Algorithms Artificial intelligence Attenuation Biological and Medical Physics Biomedical Engineering and Bioengineering Biomedicine Biophysics Brain tumors Computed tomography Convolution Deep learning Engineering Feasibility studies Gamma Knife radiosurgery Health services Image acquisition Image contrast Image enhancement Machine learning Magnetic resonance imaging Medical and Radiation Physics Meningioma Metastases Neuro-oncology Original Original Article Pituitary Planning Radiation Radiation dosage Radiation effects Radiology Radiosurgery Synthetic CT Tumors Vascular diseases
Title	Clinical application of deep learning-based synthetic CT from real MRI to improve dose planning accuracy in Gamma Knife radiosurgery: a proof of concept study
URI	https://cir.nii.ac.jp/crid/1874242817407483520 https://link.springer.com/article/10.1007/s13534-022-00227-x https://www.ncbi.nlm.nih.gov/pubmed/36238366 https://www.proquest.com/docview/2723514104 https://www.proquest.com/docview/2725189730 https://pubmed.ncbi.nlm.nih.gov/PMC9550914
Volume	12
WOSCitedRecordID	wos000812103800001&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: PRVAVX databaseName: SpringerLINK Contemporary 1997-Present customDbUrl: eissn: 2093-985X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000515933 issn: 2093-9868 databaseCode: RSV dateStart: 20110201 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwELZo4QAH3tBAWw0SN7AUx7HjcEMVBYSoUClob5HXdkqkbbLa7Fb0z_BbGTuP7UJBAinKJY7jTCaez4_5PkKes8STfLiElokTNJWpopprRlXuZR6mbJrxMohNZEdHajLJP_VJYe2w231Ykgw99TrZjQueUr_7PPDeUUSO1zHcKS_YcPz56ziz4lVLOg35BIfrNFdS9dkyV1ezEZG26qq6Cmz-vmfyl4XTEI8O7_zfm9wlt3v8Ca87h7lHrrn6Prl1iZXwAfnRc4XO4NLqNjQlWOfm0MtMnFIf_yy0FzVCSKwMDk7A56oAotAZfDx-D8sGqjBl4cA2rYN5r48E2pjVQpsLqGp4q8_ONHzwO2xgoW3VtF2e9ivQgPfiU_EwXW4lBC7ch-TL4ZuTg3e0l3GgRsh8SbNSsJIbhBoilgoRjM5yIwWTlmXaYQB1LFfWTmVqUx272DqRxDaNdeoyhB-OPyLbdVO7HQKc66lxKi6znKVow9wgQiplWepEK1HGEWHDpyxMz3HupTZmxZqd2du-QLMXwfbF94i8GO-Zdwwffy29hx6Clfuz1zNEiKNwVIdIzGNZbMHu4DtF3xu0RZIlPmECR74ReTZexv_YL87o2jWrUEYwlWOHG5HHnauNzUEbccWljEi24YRjAc8Rvnmlrr4FrvBceESIz305uOK6WX9-yyf_VvwpuZl4bw4pmrtke7lYuT1yw5wvq3axT7ayidoP_-hP2KczUA
linkProvider	Springer Nature
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3bbtQwELWgIEEfuBYItDBIvIGlJI4TmzdUUVq1XaGyoL5FXtuBSNtktdmt6M_wrYydy3ahIIEU5SWO40wmnuPLnEPIqyh2JB82pkVsOU3SRFDFVESFdDIPk2iSscKLTWSjkTg9lR-7pLCm3-3eL0n6nnqV7MY4S6jbfe557ygixxsJRizHmH_y6csws-JUS1oN-RiH61SKVHTZMldXsxaRrldleRXY_H3P5C8Lpz4e7d39vze5R-50-BPetQ5zn1yz1QOyeYmV8CH50XGFTuHS6jbUBRhrZ9DJTHylLv4ZaC4qhJBYGeyOweWqAKLQKRyfHMCihtJPWVgwdWNh1ukjgdJ6OVf6AsoKPqizMwWHbocNzJUp66bN034LCvBefCoeus2tBM-Fu0U-770f7-7TTsaBap7KBc0KHhVMI9TgYSoQwahM6pRHqYkyZTGA2kgKYyZpYhIV2tBYHocmCVViM4Qflj0iG1Vd2ScEGFMTbUVYZDJK0IZSI0Iq0qJQsRK8CAMS9Z8y1x3HuZPamOYrdmZn-xzNnnvb598D8nq4Z9YyfPy19A56CFbuzk7PECGOwFEdIjGHZbEF273v5F1v0ORxFruECRz5BuTlcBn_Y7c4oypbL30ZHgmJHW5AHreuNjQHbcQES9OAZGtOOBRwHOHrV6rym-cKl9whQnzum94VV83681s-_bfiL8it_fHxUX50MDp8Rm7HzrN9uuY22VjMl3aH3NTni7KZP_d_6k8IdTVM
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3bbtQwELWgIAQPXAsEWhgk3sBqEudi84YKC1VhVUFBfYu8vkCkbbLaZBH9Gb6VsZPN7kJBQkhRXuLYzmRiH8cz5xDyNIodyYeJqY1NSpMs4VQyGVEunMzDJJrkzHqxiXw85icn4mgti99Huy-3JLucBsfSVLV7M233VolvLGUJdZHongOPIoq8lLhAerde__h5-MviFEw6PfkYl-5U8Iz3mTPnV7MxO12syvI84Pl7_OQvm6h-bhrd-P-nukmu97gUXnaOdItcMNVtcm2NrfAO-dFziE5hbdcbagvamBn08hNfqJsXNTRnFUJLrAz2j8HlsACi0ym8_3AAbQ2l_5VhQNeNgVmvmwRSqcVcqjMoK3gjT08lHLrIG5hLXdZNl7_9AiTgvdgqHqrLuQTPkbtNPo1eH--_pb28A1VpJlqa2zSyTCEEScOMI7KRuVBZGmU6yqXBidVEgms9yRKdyNCE2qRxqJNQJiZHWGLYXbJV1ZW5T4AxOVGGhzYXUYI2FAqRk82slbHkqQ0DEi1fa6F67nMnwTEtVqzNzvYFmr3wti--B-TZcM-sY_74a-ld9Bas3J2dziFCH46rPURoDuNiD3aWflT0o0RTxHnsEilwRRyQJ8Nl_L7dpo2sTL3wZdKICxyIA3Kvc7uhO2gjxlmWBSTfcMihgOMO37xSlV89h7hIHVLEdp8v3XLVrT8_5YN_K_6YXDl6NSreHYwPH5KrsXNsn8W5Q7ba-cLsksvqW1s280f-o_0JRxU-MA
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=Clinical+application+of+deep+learning-based+synthetic+CT+from+real+MRI+to+improve+dose+planning+accuracy+in+Gamma+Knife+radiosurgery%3A+a+proof+of+concept+study&rft.jtitle=Biomedical+engineering+letters&rft.au=Park%2C+So+Hee&rft.au=Choi%2C+Dong+Min&rft.au=Jung+In-Ho&rft.au=Chang%2C+Kyung+Won&rft.date=2022-11-01&rft.pub=Springer+Nature+B.V&rft.issn=2093-9868&rft.eissn=2093-985X&rft.volume=12&rft.issue=4&rft.spage=359&rft.epage=367&rft_id=info:doi/10.1007%2Fs13534-022-00227-x&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2093-9868&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2093-9868&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2093-9868&client=summon