{"doi":"10.1117/1.jmi.12.2.024002","title":"Evaluation of state-of-the-art deep learning models in the segmentation of the left and right ventricles in parasternal short-axis echocardiograms","abstract":"PurposePrevious studies on echocardiogram segmentation are focused on the left ventricle in parasternal long-axis views. Deep-learning models were evaluated on the segmentation of the ventricles in parasternal short-axis echocardiograms (PSAX-echo). Segmentation of the ventricles in complementary echocardiogram views will allow the computation of important metrics with the potential to aid in diagnosing cardio-pulmonary diseases and other cardiomyopathies. Evaluating state-of-the-art models with small datasets can reveal if they improve performance on limited data.ApproachPSAX-echo was performed on 33 volunteer women. An experienced cardiologist identified end-diastole and end-systole frames from 387 scans, and expert observers manually traced the contours of the cardiac structures. Traced frames were pre-processed and used to create labels to train two domain-specific (Unet-Resnet101 and Unet-ResNet50), and four general-domain [three segment anything (SAM) variants, and the Detectron2] deep-learning models. The performance of the models was evaluated using the Dice similarity coefficient (DSC), Hausdorff distance (HD), and difference in cross-sectional area (DCSA).ResultsThe Unet-Resnet101 model provided superior performance in the segmentation of the ventricles with 0.83, 4.93 pixels, and 106 pixel2 on average for DSC, HD, and DCSA, respectively. A fine-tuned MedSAM model provided a performance of 0.82, 6.66 pixels, and 1252 pixel2, whereas the Detectron2 model provided 0.78, 2.12 pixels, and 116 pixel2 for the same metrics, respectively.ConclusionsDeep-learning models are suitable for the segmentation of the left and right ventricles in PSAX-echo. We demonstrated that domain-specific trained models such as Unet-ResNet provide higher accuracy for echo segmentation than general-domain segmentation models when working with small and locally acquired datasets.","journal":"Journal of Medical Imaging","year":2025,"id":519275,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":6,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9612,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":945473,"name":"Vu Dinh","orcid":null,"position":1,"is_corresponding":false},{"id":1388191,"name":"Manjula V. Burri","orcid":null,"position":2,"is_corresponding":false},{"id":1388192,"name":"Julie Roelandts","orcid":null,"position":3,"is_corresponding":false},{"id":1388193,"name":"Jutta Wendling","orcid":null,"position":4,"is_corresponding":false},{"id":1143184,"name":"Jon D. Klingensmith","orcid":null,"position":5,"is_corresponding":false},{"id":1387613,"name":"Juan Rodríguez Cuéllar","orcid":"0000-0002-8925-6373","position":0,"is_corresponding":true}],"reference_count":48,"raw_metadata":null,"created_at":"2026-07-19T02:49:18.751199Z","pmid":"40151505","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}