{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T07:07:44Z","timestamp":1775027264750,"version":"3.50.1"},"reference-count":33,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2021,8,28]],"date-time":"2021-08-28T00:00:00Z","timestamp":1630108800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["No. 2018R1C1B5047075"],"award-info":[{"award-number":["No. 2018R1C1B5047075"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>The aim of this study was to compare the performance of a deep-learning convolutional neural network (Faster R-CNN) model to detect imaging findings suggestive of idiopathic Parkinson\u2019s disease (PD) based on [18F]FP-CIT PET maximum intensity projection (MIP) images versus that of nuclear medicine (NM) physicians. The anteroposterior MIP images of the [18F]FP-CIT PET scan of 527 patients were classified as having PD (139 images) or non-PD (388 images) patterns according to the final diagnosis. Non-PD patterns were classified as overall-normal (ONL, 365 images) and vascular parkinsonism with definite defects or prominently decreased dopamine transporter binding (dVP, 23 images) patterns. Faster R-CNN was trained on 120 PD, 320 ONL, and 16 dVP pattern images and tested on the 19 PD, 45 ONL, and seven dVP patterns images. The performance of the Faster R-CNN and three NM physicians was assessed using receiver operating characteristics curve analysis. The difference in performance was assessed using Cochran\u2019s Q test, and the inter-rater reliability was calculated. Faster R-CNN showed high accuracy in differentiating PD from non-PD patterns and also from dVP patterns, with results comparable to those of NM physicians. There were no significant differences in the area under the curve and performance. The inter-rater reliability among Faster R-CNN and NM physicians showed substantial to almost perfect agreement. The deep-learning model accurately differentiated PD from non-PD patterns on MIP images of [18F]FP-CIT PET, and its performance was comparable to that of NM physicians.<\/jats:p>","DOI":"10.3390\/diagnostics11091557","type":"journal-article","created":{"date-parts":[[2021,8,29]],"date-time":"2021-08-29T21:45:16Z","timestamp":1630273516000},"page":"1557","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Faster Region-Based Convolutional Neural Network in the Classification of Different Parkinsonism Patterns of the Striatum on Maximum Intensity Projection Images of [18F]FP-CIT Positron Emission Tomography"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7191-0007","authenticated-orcid":false,"given":"Byung Wook","family":"Choi","sequence":"first","affiliation":[{"name":"Department of Nuclear Medicine, Daegu Catholic University Medical Center, Daegu Catholic University School of Medicine, Daegu 42472, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1959-8578","authenticated-orcid":false,"given":"Sungmin","family":"Kang","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine, Daegu Catholic University Medical Center, Daegu Catholic University School of Medicine, Daegu 42472, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hae Won","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Nuclear Medicine, Keimyung University Dongsan Hospital, Keimyung University School of Medicine, Daegu 42601, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oh Dae","family":"Kwon","sequence":"additional","affiliation":[{"name":"Department of Neurology, Daegu Catholic University Medical Center, Daegu Catholic University School of Medicine, Daegu 42472, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huy Duc","family":"Vu","sequence":"additional","affiliation":[{"name":"Department of Radiology, Daegu Catholic University Medical Center, Daegu Catholic University School of Medicine, Daegu 42472, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9491-1347","authenticated-orcid":false,"given":"Sung Won","family":"Youn","sequence":"additional","affiliation":[{"name":"Department of Radiology, Daegu Catholic University Medical Center, Daegu Catholic University School of Medicine, Daegu 42472, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,8,28]]},"reference":[{"key":"ref_1","first-page":"1189","article-title":"Parkinsonian syndromes","volume":"19","author":"Williams","year":"2013","journal-title":"Continuum"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"145","DOI":"10.33160\/yam.2018.09.001","article-title":"Role of Neuroimaging on Differentiation of Parkinson\u2019s Disease and Its Related Diseases","volume":"61","author":"Ogawa","year":"2018","journal-title":"Yonago Acta Med."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1202","DOI":"10.1136\/jnnp.2008.144501","article-title":"Changes in diagnosis with follow-up in an incident cohort of patients with parkinsonism","volume":"79","author":"Caslake","year":"2008","journal-title":"J. Neurol. Neurosurg. Psychiatry"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"566","DOI":"10.1212\/WNL.0000000000002350","article-title":"Accuracy of clinical diagnosis of Parkinson disease: A systematic review and meta-analysis","volume":"86","author":"Rizzo","year":"2016","journal-title":"Neurology"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1186\/s40035-017-0076-6","article-title":"Imaging biomarkers in Parkinson\u2019s disease and Parkinsonian syndromes: Current and emerging concepts","volume":"6","author":"Saeed","year":"2017","journal-title":"Transl. Neurodegener."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"S175","DOI":"10.1016\/j.jacr.2020.01.042","article-title":"ACR Appropriateness Criteria\u00ae Movement Disorders and Neurodegenerative Diseases","volume":"17","author":"Harvey","year":"2020","journal-title":"J. Am. Coll. Radiol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1007\/s00259-009-1267-x","article-title":"EANM procedure guidelines for brain neurotransmission SPECT using (123)I-labelled dopamine transporter ligands, version 2","volume":"37","author":"Darcourt","year":"2010","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"154","DOI":"10.2967\/jnumed.111.100784","article-title":"SNM practice guideline for dopamine transporter imaging with 123I-ioflupane SPECT 1.0","volume":"53","author":"Djang","year":"2012","journal-title":"J. Nucl. Med."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"399","DOI":"10.2967\/jnumed.111.095224","article-title":"Subregional patterns of preferential striatal dopamine transporter loss differ in Parkinson disease, progressive supranuclear palsy, and multiple-system atrophy","volume":"53","author":"Oh","year":"2012","journal-title":"J. Nucl. Med."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1007\/s00415-011-6163-1","article-title":"Visual assessment of dopaminergic degeneration pattern in 123I-FP-CIT SPECT differentiates patients with atypical parkinsonian syndromes and idiopathic Parkinson\u2019s disease","volume":"259","author":"Kahraman","year":"2012","journal-title":"J. Neurol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"939","DOI":"10.1002\/jmri.26534","article-title":"Deep learning in radiology: An overview of the concepts and a survey of the state of the art with focus on MRI","volume":"49","author":"Mazurowski","year":"2019","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_13","first-page":"564","article-title":"Intervertebral disc detection in X-ray images using faster R-CNN","volume":"2017","author":"Ruhan","year":"2017","journal-title":"Conf. Proc. IEEE Eng. Med. Biol. Soc."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"5135","DOI":"10.1158\/0008-5472.CAN-18-0494","article-title":"Identification of Metastatic Lymph Nodes in MR Imaging with Faster Region-Based Convolutional Neural Networks","volume":"78","author":"Lu","year":"2018","journal-title":"Cancer Res."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"796025","DOI":"10.1155\/2011\/796025","article-title":"Molecular SPECT Imaging: An Overview","volume":"2011","author":"Khalil","year":"2011","journal-title":"Int. J. Mol. Imaging"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"670","DOI":"10.1212\/01.wnl.0000324625.00404.15","article-title":"Second consensus statement on the diagnosis of multiple system atrophy","volume":"71","author":"Gilman","year":"2008","journal-title":"Neurology"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1591","DOI":"10.1002\/mds.26424","article-title":"MDS clinical diagnostic criteria for Parkinson\u2019s disease","volume":"30","author":"Postuma","year":"2015","journal-title":"Mov. Disord."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1002\/mds.26987","article-title":"Clinical diagnosis of progressive supranuclear palsy: The movement disorder society criteria","volume":"32","author":"Respondek","year":"2017","journal-title":"Mov. Disord."},{"key":"ref_19","unstructured":"Stoker, T.B., and Greenland, J.C. (2018). The Differential Diagnosis of Parkinson\u2019s Diseas. Parkinson\u2019s Disease: Pathogenesis and Clinical Aspects, Codon Publications."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1007\/s13139-012-0182-4","article-title":"Differential Diagnosis of Parkinsonism Using Dual-Phase F-18 FP-CIT PET Imaging","volume":"47","author":"Jin","year":"2013","journal-title":"Nucl. Med. Mol. Imaging"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Dutta, A., and Zisserman, A. (2019, January 21\u201325). The VIA Annotation Software for Images, Audio and Video. Proceedings of the 27th ACM International Conference on Multimedia, Nice, France.","DOI":"10.1145\/3343031.3350535"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1007\/s00259-014-2882-8","article-title":"Machine learning models for the differential diagnosis of vascular parkinsonism and Parkinson\u2019s disease using [(123)I]FP-CIT SPECT","volume":"42","author":"Lojo","year":"2015","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"887","DOI":"10.1097\/MNM.0000000000000890","article-title":"Artificial intelligence in the diagnosis of Parkinson\u2019s disease from ioflupane-123 single-photon emission computed tomography dopamine transporter scans using transfer learning","volume":"39","author":"Kim","year":"2018","journal-title":"Nucl. Med. Commun."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Shiiba, T., Arimura, Y., Nagano, M., Takahashi, T., and Takaki, A. (2020). Improvement of classification performance of Parkinson\u2019s disease using shape features for machine learning on dopamine transporter single photon emission computed tomography. PLoS ONE, 15.","DOI":"10.1371\/journal.pone.0228289"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1186\/s40658-016-0140-9","article-title":"CADA-computer-aided DaTSCAN analysis","volume":"3","author":"Augimeri","year":"2016","journal-title":"EJNMMI Phys."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"586","DOI":"10.1016\/j.nicl.2017.09.010","article-title":"Refining diagnosis of Parkinson\u2019s disease with deep learning-based interpretation of dopamine transporter imaging","volume":"16","author":"Choi","year":"2017","journal-title":"NeuroImage Clin."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1097\/MNM.0b013e32833b7ea4","article-title":"Interobserver reproducibility of the interpretation of I-123 FP-CIT single-photon emission computed tomography","volume":"31","author":"Tondeur","year":"2010","journal-title":"Nucl. Med. Commun."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1007\/s12149-011-0564-1","article-title":"Interobserver variability, and visual and quantitative parameters of (123)I-FP-CIT SPECT (DaTSCAN) studies","volume":"26","author":"Papathanasiou","year":"2012","journal-title":"Ann. Nucl. Med."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1088\/0031-9155\/51\/3\/007","article-title":"Comparison of region-of-interest analysis and human observers in the diagnosis of Parkinson\u2019s disease using [99mTc]TRODAT-1 and SPECT","volume":"51","author":"Acton","year":"2006","journal-title":"Phys. Med. Biol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"5971","DOI":"10.1118\/1.4742055","article-title":"Automatic assistance to Parkinson\u2019s disease diagnosis in DaTSCAN SPECT imaging","volume":"39","author":"Illan","year":"2012","journal-title":"Med. Phys."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Brahim, A., Ram\u00edrez, J., G\u00f3rriz, J.M., Khedher, L., and Salas-Gonzalez, D. (2015). Comparison between Different Intensity Normalization Methods in 123I-Ioflupane Imaging for the Automatic Detection of Parkinsonism. PLoS ONE, 10.","DOI":"10.1371\/journal.pone.0135107"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Chakraborty, S., Aich, S., and Kim, H. (2020). Detection of parkinson\u2019s disease from 3T T1 weighted MRI scans using 3D convolutional neural network. Diagnostics, 10.","DOI":"10.3390\/diagnostics10060402"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Chakraborty, S., Aich, S., and Kim, H. (2020). 3D textural, morphological and statistical analysis of voxel of interests in 3T MRI scans for the detection of Parkinson\u2019s disease using artificial neural networks. Healthcare, 8.","DOI":"10.3390\/healthcare8010034"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/11\/9\/1557\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:54:08Z","timestamp":1760165648000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/11\/9\/1557"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,28]]},"references-count":33,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2021,9]]}},"alternative-id":["diagnostics11091557"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics11091557","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,28]]}}}