<HashMap><database>biostudies-literature</database><scores/><additional><submitter>Kita A</submitter><funding>Japan Society for the Promotion of Science</funding><pagination>1371</pagination><full_dataset_link>https://www.ebi.ac.uk/biostudies/studies/S-EPMC10137239</full_dataset_link><repository>biostudies-literature</repository><omics_type>Unknown</omics_type><volume>13(8)</volume><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 [&lt;sup>123&lt;/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</pubmed_abstract><journal>Diagnostics (Basel, Switzerland)</journal><pubmed_title>Specific Binding Ratio Estimation of [&lt;sup>123&lt;/sup>I]-FP-CIT SPECT Using Frontal Projection Image and Machine Learning.</pubmed_title><pmcid>PMC10137239</pmcid><funding_grant_id>JP2K15842</funding_grant_id><pubmed_authors>Kosaka N</pubmed_authors><pubmed_authors>Kita A</pubmed_authors><pubmed_authors>Tsujikawa T</pubmed_authors><pubmed_authors>Okazawa H</pubmed_authors><pubmed_authors>Kidoya E</pubmed_authors><pubmed_authors>Sugimoto K</pubmed_authors></additional><is_claimable>false</is_claimable><name>Specific Binding Ratio Estimation of [&lt;sup>123&lt;/sup>I]-FP-CIT SPECT Using Frontal Projection Image and Machine Learning.</name><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 [&lt;sup>123&lt;/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</description><dates><release>2023-01-01T00:00:00Z</release><publication>2023 Apr</publication><modification>2025-04-22T05:17:44.326Z</modification><creation>2025-04-05T21:16:59.619Z</creation></dates><accession>S-EPMC10137239</accession><cross_references><pubmed>37189472</pubmed><doi>10.3390/diagnostics13081371</doi></cross_references></HashMap>