?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Crop+and+Couple%3A+Cardiac+Image+Segmentation+Using+Interlinked+Specialist+Networks&rft.creator=Khan%2C+A&rft.creator=Asad%2C+M&rft.creator=Benning%2C+M&rft.creator=Roney%2C+C&rft.creator=Slabaugh%2C+G&rft.description=Diagnosis+of+cardiovascular+disease+using+automated+methods+often+relies+on+the+critical+task+of+cardiac+image+segmentation.+We+propose+a+novel+strategy+that+performs+segmentation+using+specialist+networks+that+focus+on+a+single+anatomy+(left+ventricle%2C+right+ventricle%2C+or+myocardium).+Given+an+input+long-axis+cardiac+MR+image%2C+our+method+performs+a+ternary+segmentation+in+the+first+stage+to+identify+these+anatomical+regions%2C+followed+by+cropping+the+original+image+to+focus+subsequent+processing+on+the+anatomical+regions.+The+specialist+networks+are+coupled+through+an+attention+mechanism+that+performs+cross-attention+to+interlink+features+from+different+anatomies%2C+serving+as+a+soft+relative+shape+prior.+Central+to+our+approach+is+an+additive+attention+block+(E-2A+block)%2C+which+is+used+throughout+our+architecture+thanks+to+its+efficiency.+The+source+code+is+available+at1.&rft.publisher=Institute+of+Electrical+and+Electronics+Engineers+(IEEE)&rft.date=2024&rft.type=Proceedings+paper&rft.language=eng&rft.source=+++++In%3A++Proceedings+of+the+IEEE+International+Symposium+on+Biomedical+Imaging+(ISBI)+2024.++(pp.+pp.+1-5).++Institute+of+Electrical+and+Electronics+Engineers+(IEEE)+(2024)+++++&rft.format=text&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10197895%2F1%2F2402.09156v1.pdf&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10197895%2F&rft.rights=open