<HashMap><database>biostudies-literature</database><scores/><additional><omics_type>Unknown</omics_type><volume>13(8)</volume><submitter>Chou HH</submitter><pubmed_abstract>Cardiomegaly is associated with poor clinical outcomes and is assessed by routine monitoring of the cardiothoracic ratio (CTR) from chest X-rays (CXRs). Judgment of the margins of the heart and lungs is subjective and may vary between different operators.&lt;h4>Methods&lt;/h4>Patients aged > 19 years in our hemodialysis unit from March 2021 to October 2021 were enrolled. The borders of the lungs and heart on CXRs were labeled by two nephrologists as the ground truth (nephrologist-defined mask). We implemented AlbuNet-34, a U-Net variant, to predict the heart and lung margins from CXR images and to automatically calculate the CTRs.&lt;h4>Results&lt;/h4>The coefficient of determination (R&lt;sup>2&lt;/sup>) obtained using the neural network model was 0.96, compared with an R&lt;sup>2&lt;/sup> of 0.90 obtained by nu</pubmed_abstract><journal>Diagnostics (Basel, Switzerland)</journal><pagination>1376</pagination><full_dataset_link>https://www.ebi.ac.uk/biostudies/studies/S-EPMC10137564</full_dataset_link><repository>biostudies-literature</repository><pubmed_title>Validation of an Automated Cardiothoracic Ratio Calculation for Hemodialysis Patients.</pubmed_title><pmcid>PMC10137564</pmcid><pubmed_authors>Shen GT</pubmed_authors><pubmed_authors>Lin JY</pubmed_authors><pubmed_authors>Huang CY</pubmed_authors><pubmed_authors>Chou HH</pubmed_authors></additional><is_claimable>false</is_claimable><name>Validation of an Automated Cardiothoracic Ratio Calculation for Hemodialysis Patients.</name><description>Cardiomegaly is associated with poor clinical outcomes and is assessed by routine monitoring of the cardiothoracic ratio (CTR) from chest X-rays (CXRs). Judgment of the margins of the heart and lungs is subjective and may vary between different operators.&lt;h4>Methods&lt;/h4>Patients aged > 19 years in our hemodialysis unit from March 2021 to October 2021 were enrolled. The borders of the lungs and heart on CXRs were labeled by two nephrologists as the ground truth (nephrologist-defined mask). We implemented AlbuNet-34, a U-Net variant, to predict the heart and lung margins from CXR images and to automatically calculate the CTRs.&lt;h4>Results&lt;/h4>The coefficient of determination (R&lt;sup>2&lt;/sup>) obtained using the neural network model was 0.96, compared with an R&lt;sup>2&lt;/sup> of 0.90 obtained by nu</description><dates><release>2023-01-01T00:00:00Z</release><publication>2023 Apr</publication><modification>2025-04-22T05:12:25.908Z</modification><creation>2025-04-05T21:17:09.574Z</creation></dates><accession>S-EPMC10137564</accession><cross_references><pubmed>37189477</pubmed><doi>10.3390/diagnostics13081376</doi></cross_references></HashMap>