{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T10:43:05Z","timestamp":1782384185540,"version":"3.54.5"},"reference-count":36,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T00:00:00Z","timestamp":1748649600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: 123I-FP-CIT dopamine transporter imaging is commonly used for the diagnosis of Parkinsonian syndromes in patients whose clinical presentation is atypical. Prolonged immobility, which can be difficult to maintain in this population, is required to perform SPECT acquisition. In this study we aimed to develop a Convolutional Neural Network (CNN) able to predict the outcome of the full examination based on the first acquired projection, and reliably detect normal patients. Methods: All 123I-FP-CIT SPECT performed in our center between June 2017 and February 2024 were included and split between a training and a validation set (70%\/30%). An additional 100 SPECT were used as an independent test set. Examinations were labeled by two independent physicians. A VGG16-like CNN model was trained to assess the probability of examination abnormality from the first acquired projection (anterior and posterior view at 0\u00b0), taking age into consideration. A threshold maximizing sensitivity while maintaining good diagnostic accuracy was then determined. The model was validated in the independent testing set. Saliency maps were generated to visualize the most impactful areas in the classification. Results: A total of 982 123I-FP-CIT SPECT were retrieved and labelled (training set: 618; validation set: 264; independent testing set: 100). The trained model achieved a sensibility of 98.0% and a negative predictive value of 96.3% (one false negative) while maintaining an accuracy of 75.0%. The saliency maps confirmed that the regions with the greatest impact on the final classification corresponded to clinically relevant areas (basal ganglia and background noise). Conclusions: Our results suggest that this trained CNN could be used to exclude presynaptic dopaminergic loss with high reliability from the first acquired projection. It could be particularly useful in patients with compliance issues. Confirmation with images from other centers will be necessary.<\/jats:p>","DOI":"10.3390\/diagnostics15111407","type":"journal-article","created":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T03:19:38Z","timestamp":1748834378000},"page":"1407","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Prediction of 123I-FP-CIT SPECT Results from First Acquired Projections Using Artificial Intelligence"],"prefix":"10.3390","volume":"15","author":[{"given":"Wadi\u2019","family":"Othmani","sequence":"first","affiliation":[{"name":"M\u00e9decine Nucl\u00e9aire, Institut Godinot, 51100 Reims, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arthur","family":"Coste","sequence":"additional","affiliation":[{"name":"M\u00e9decine Nucl\u00e9aire, Institut Godinot, 51100 Reims, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitri","family":"Papathanassiou","sequence":"additional","affiliation":[{"name":"M\u00e9decine Nucl\u00e9aire, Institut Godinot, 51100 Reims, France"},{"name":"CReSTIC, UR 3804, Universit\u00e9 de Reims Champagne-Ardenne, 51100 Reims, France"},{"name":"Laboratoire de Biophysique, UFR de M\u00e9decine, Universit\u00e9 de Reims Champagne-Ardenne, 51100 Reims, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8738-4841","authenticated-orcid":false,"given":"David","family":"Morland","sequence":"additional","affiliation":[{"name":"M\u00e9decine Nucl\u00e9aire, Institut Godinot, 51100 Reims, France"},{"name":"CReSTIC, UR 3804, Universit\u00e9 de Reims Champagne-Ardenne, 51100 Reims, France"},{"name":"Laboratoire de Biophysique, UFR de M\u00e9decine, Universit\u00e9 de Reims Champagne-Ardenne, 51100 Reims, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,5,31]]},"reference":[{"key":"ref_1","first-page":"747","article-title":"Nuclear Imaging in the Diagnosis of Clinically Uncertain Parkinsonian Syndromes","volume":"116","author":"Buchert","year":"2019","journal-title":"Dtsch \u00c4rztebl Int."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1288","DOI":"10.2967\/jnumed.114.140228","article-title":"Individual-Reader Diagnostic Performance and Between-Reader Agreement in Assessment of Subjects with Parkinsonian Syndrome or Dementia Using 123 I-Ioflupane Injection (DaTscan) Imaging","volume":"55","author":"Seibyl","year":"2014","journal-title":"J. Nucl. Med."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1367","DOI":"10.1007\/s00259-008-0777-2","article-title":"The cost effectiveness of 123I-FP-CIT SPECT imaging in patients with an uncertain clinical diagnosis of parkinsonism","volume":"35","author":"Everaert","year":"2008","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1885","DOI":"10.1007\/s00259-020-04817-8","article-title":"EANM practice guideline\/SNMMI procedure standard for dopaminergic imaging in Parkinsonian syndromes 1","volume":"47","author":"Morbelli","year":"2020","journal-title":"0. Eur. J. Nucl. Med. Mol. Imaging"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e005122","DOI":"10.1136\/bmjopen-2014-005122","article-title":"Is ioflupane I123 injection diagnostically effective in patients with movement disorders and dementia? Pooled analysis of four clinical trials","volume":"4","author":"Oertel","year":"2014","journal-title":"BMJ Open"},{"key":"ref_6","first-page":"885","article-title":"Impact of DaTscan Imaging on Clinical Decision Making in Clinically Uncertain Parkinson\u2019s Disease","volume":"11","author":"Isaacson","year":"2021","journal-title":"J. Park. Dis."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"4452","DOI":"10.1007\/s00259-022-05891-w","article-title":"Application of artificial intelligence in nuclear medicine and molecular imaging: A review of current status and future perspectives for clinical translation","volume":"49","author":"Visvikis","year":"2022","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.ijmedinf.2016.03.001","article-title":"High-Accuracy Detection of Early Parkinson\u2019s Disease through Multimodal Features and Machine Learning","volume":"90","author":"Prashanth","year":"2016","journal-title":"Int. J. Med. Inform."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Ortiz, A., Munilla, J., Mart\u00ednez-Iba\u00f1ez, M., G\u00f3rriz, J.M., Ram\u00edrez, J., and Salas-Gonzalez, D. (2019). Parkinson\u2019s Disease Detection Using Isosurfaces-Based Features and Convolutional Neural Networks. Front. Neuroinform., 13.","DOI":"10.3389\/fninf.2019.00048"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Chien, C.Y., Hsu, S.W., Lee, T.L., Sung, P.S., and Lin, C.C. (2021). Using Artificial Neural Network to Discriminate Parkinson\u2019s Disease from Other Parkinsonisms by Focusing on Putamen of Dopamine Transporter SPECT Images. Biomedicines, 9.","DOI":"10.3390\/biomedicines9010012"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Magesh, P.R., Myloth, R.D., and Tom, R.J. (2020). An Explainable Machine Learning Model for Early Detection of Parkinson\u2019s Disease using LIME on DaTSCAN Imagery. Comput. Biol. Med., 126.","DOI":"10.1016\/j.compbiomed.2020.104041"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Hathaliya, J., Parekh, R., Patel, N., Gupta, R., Tanwar, S., Alqahtani, F., Elghatwary, M., Ivanov, O., Raboaca, M.S., and Neagu, B.-C. (2022). Convolutional Neural Network-Based Parkinson Disease Classification Using SPECT Imaging Data. Mathematics, 10.","DOI":"10.3390\/math10152566"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Thakur, M., Kuresan, H., Dhanalakshmi, S., Lai, K.W., and Wu, X. (2022). Soft Attention Based DenseNet Model for Parkinson\u2019s Disease Classification Using SPECT Images. Front. Aging Neurosci., 14.","DOI":"10.3389\/fnagi.2022.908143"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1173","DOI":"10.3390\/diagnostics12051173","article-title":"An Ensemble of CNN Models for Parkinson\u2019s Disease Detection Using DaTscan Images","volume":"12","author":"Kurmi","year":"2022","journal-title":"Diagnostics"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1333","DOI":"10.1007\/s00259-023-06566-w","article-title":"Automated Identification of Uncertain Cases in Deep Learning-Based Classification of Dopamine Transporter SPECT to Improve Clinical Utility and Acceptance","volume":"51","author":"Budenkotte","year":"2024","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yoon, H., Kang, D.-Y., and Kim, S. (2024). Enhancement and Evaluation for Deep Learning-Based Classification of Volumetric Neuroimaging with 3D-to-2D Knowledge Distillation. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-80938-6"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1176","DOI":"10.1007\/s00259-021-05569-9","article-title":"Explainable AI to improve acceptance of convolutional neural networks for automatic classification of dopamine transporter SPECT in the diagnosis of clinically uncertain parkinsonian syndromes","volume":"49","author":"Nazari","year":"2022","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"ref_18","first-page":"2831","article-title":"Comparison of spatial resolution and sensitivity of fan beam and parallel hole collimators in brain imaging","volume":"57","author":"Olsen","year":"2016","journal-title":"J. Nucl. Med."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1097\/00019442-200201000-00005","article-title":"Age-related decline in dopamine transporters: Analysis of striatal subregions, nonlinear effects, and hemispheric asymmetries","volume":"10","author":"Seibyl","year":"2002","journal-title":"Am. J. Geriatr. Psychiatry"},{"key":"ref_20","unstructured":"Simonyan, K., and Zisserman, A. (2015). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_21","unstructured":"(2024, October 10). BCEWithLogitsLoss\u2014PyTorch 2.3 Documentation. Available online: https:\/\/pytorch.org\/docs\/stable\/generated\/torch.nn.BCEWithLogitsLoss.html."},{"key":"ref_22","first-page":"485","article-title":"Significance of Epochs on Training a Neural Network","volume":"9","author":"Saahil","year":"2020","journal-title":"Int. J. Sci. Technol. Res."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1136\/eb-2012-100645","article-title":"Principles for high-quality, high-value testing","volume":"18","author":"Power","year":"2013","journal-title":"BMJ Evid-Based Med."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","volume":"128","author":"Selvaraju","year":"2020","journal-title":"Int. J. Comput. Vis."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Dobbin, K.K., and Simon, R.M. (2011). Optimally splitting cases for training and testing high dimensional classifiers. BMC Med. Genom., 4.","DOI":"10.1186\/1755-8794-4-31"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"45","DOI":"10.4103\/0301-4738.37595","article-title":"Understanding and using sensitivity, specificity and predictive values","volume":"56","author":"Parikh","year":"2008","journal-title":"Indian J. Ophthalmol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1463","DOI":"10.2967\/jnumed.124.267570","article-title":"Unrealistic Data Augmentation Improves the Robustness of Deep Learning-Based Classification of Dopamine Transporter SPECT Against Variability Between Sites and Between Cameras","volume":"65","author":"Buddenkotte","year":"2024","journal-title":"J. Nucl. Med."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"100258","DOI":"10.1016\/j.array.2022.100258","article-title":"Data augmentation: A comprehensive survey of modern approaches","volume":"16","author":"Mumuni","year":"2022","journal-title":"Array"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"188","DOI":"10.2967\/jnumed.121.263703","article-title":"Artificial Intelligence in Nuclear Medicine: Opportunities, Challenges, and Responsbilities Toward a Trustworthy Ecosystem","volume":"64","author":"Saboury","year":"2023","journal-title":"J. Nucl. Med."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1002\/1531-8257(200005)15:3<503::AID-MDS1013>3.0.CO;2-V","article-title":"Accurate differentiation of parkinsonism and essential tremor using visual assessment of [123I]-FP-CIT SPECT imaging: The [123I]-FP-CIT study group","volume":"15","author":"Benamer","year":"2000","journal-title":"Mov. Disord."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1821","DOI":"10.2967\/jnumed.116.189266","article-title":"Diagnostic Performance of the Visual Reading of 123I-Ioflupane SPECT Images With or Without Quantification in Patients with Movement Disorders or Dementia","volume":"58","author":"Booij","year":"2017","journal-title":"J. Nucl. Med. Novemb."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.54569\/aair.1016544","article-title":"Importance of Preprocessing in Histopathology Image Classification Using Deep Convolutional Neural Network","volume":"2","year":"2022","journal-title":"Adv. Artif. Intell. Res."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"843","DOI":"10.1097\/MNM.0000000000001729","article-title":"Quantitative [123]I-Ioflupane DaTSCAN single-photon computed tomography-computed tomography in Parkinsonism","volume":"44","author":"Missir","year":"2023","journal-title":"Nucl. Med. Commun."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Chen, Y., Goorden, M., and Beekman, F.J. (2021). Convolutional neural network basedattenuation correction for 123I-FP-CIT SPECT with focusedstriatum imaging. Phys. Med. Biol., 66.","DOI":"10.1088\/1361-6560\/ac2470"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Massari, R., and Mok, G.S.P. (2023). New trends in single photon emission computed tomography (SPECT). Front. Med., 10.","DOI":"10.3389\/fmed.2023.1349877"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Adams, M.P., Rahmim, A., and Tang, J. (2021). Improved motor outcome prediction in Parkinson\u2019s disease applying deep learning to DaTscan SPECT images. Comput. Biol. Med., 132.","DOI":"10.1016\/j.compbiomed.2021.104312"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/11\/1407\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:45:00Z","timestamp":1760031900000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/11\/1407"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,31]]},"references-count":36,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["diagnostics15111407"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics15111407","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,31]]}}}