{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Kita A"],"funding":["Japan Society for the Promotion of Science"],"pagination":["1371"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC10137239"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["13(8)"],"pubmed_abstract":["This study aimed to develop a new convolutional neural network (CNN) method for estimating the specific binding ratio (SBR) from only frontal projection images in single-photon emission-computed tomography using [<sup>123</sup>I]ioflupane. We created five datasets to train two CNNs, LeNet and AlexNet: (1) 128FOV used a 0° projection image without preprocessing, (2) 40FOV used 0° projection images cropped to 40 × 40 pixels centered on the striatum, (3) 40FOV training data doubled by data augmentation (40FOV_DA, left-right reversal only), (4) 40FOVhalf, and (5) 40FOV_DAhalf, split into left and right (20 × 40) images of 40FOV and 40FOV_DA to separately evaluate the left and right SBR. The accuracy of the SBR estimation was assessed using the mean absolute error, root mean squared error, corr"],"journal":["Diagnostics (Basel, Switzerland)"],"pubmed_title":["Specific Binding Ratio Estimation of [<sup>123</sup>I]-FP-CIT SPECT Using Frontal Projection Image and Machine Learning."],"pmcid":["PMC10137239"],"funding_grant_id":["JP2K15842"],"pubmed_authors":["Kosaka N","Kita A","Tsujikawa T","Okazawa H","Kidoya E","Sugimoto K"],"additional_accession":[]},"is_claimable":false,"name":"Specific Binding Ratio Estimation of [<sup>123</sup>I]-FP-CIT SPECT Using Frontal Projection Image and Machine Learning.","description":"This study aimed to develop a new convolutional neural network (CNN) method for estimating the specific binding ratio (SBR) from only frontal projection images in single-photon emission-computed tomography using [<sup>123</sup>I]ioflupane. We created five datasets to train two CNNs, LeNet and AlexNet: (1) 128FOV used a 0° projection image without preprocessing, (2) 40FOV used 0° projection images cropped to 40 × 40 pixels centered on the striatum, (3) 40FOV training data doubled by data augmentation (40FOV_DA, left-right reversal only), (4) 40FOVhalf, and (5) 40FOV_DAhalf, split into left and right (20 × 40) images of 40FOV and 40FOV_DA to separately evaluate the left and right SBR. The accuracy of the SBR estimation was assessed using the mean absolute error, root mean squared error, corr","dates":{"release":"2023-01-01T00:00:00Z","publication":"2023 Apr","modification":"2025-04-22T05:17:44.326Z","creation":"2025-04-05T21:16:59.619Z"},"accession":"S-EPMC10137239","cross_references":{"pubmed":["37189472"],"doi":["10.3390/diagnostics13081371"]}}