{"doi":"10.3389/fradi.2023.1223294","title":"AI in the Loop: functionalizing fold performance disagreement to monitor automated medical image segmentation workflows","abstract":"Introduction: Methods that automatically flag poor performing predictions are drastically needed to safely implement machine learning workflows into clinical practice as well as to identify difficult cases during model training. Methods: Disagreement between the fivefold cross-validation sub-models was quantified using dice scores between folds and summarized as a surrogate for model confidence. The summarized Interfold Dices were compared with thresholds informed by human interobserver values to determine whether final ensemble model performance should be manually reviewed. Results: The method on all tasks efficiently flagged poor segmented images without consulting a reference standard. Using the median Interfold Dice for comparison, substantial dice score improvements after excluding flagged images was noted for the in-domain CT (0.85 ± 0.20 to 0.91 ± 0.08, 8/50 images flagged) and MR (0.76 ± 0.27 to 0.85 ± 0.09, 8/50 images flagged). Most impressively, there were dramatic dice score improvements in the simulated out-of-distribution task where the model was trained on a radical nephrectomy dataset with different contrast phases predicting a partial nephrectomy all cortico-medullary phase dataset (0.67 ± 0.36 to 0.89 ± 0.10, 122/300 images flagged). Discussion: Comparing interfold sub-model disagreement against human interobserver values is an effective and efficient way to assess automated predictions when a reference standard is not available. This functionality provides a necessary safeguard to patient care important to safely implement automated medical image segmentation workflows.","journal":"Frontiers in Radiology","year":2023,"id":388821,"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":1,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.955,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2023-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":689465,"name":"Panagiotis Korfiatis","orcid":"0000-0003-2516-1751","position":1,"is_corresponding":false},{"id":286368,"name":"Adriana Gregory","orcid":"0000-0001-9760-5302","position":2,"is_corresponding":false},{"id":328678,"name":"Timothy L. Kline","orcid":"0000-0002-7917-9853","position":3,"is_corresponding":false},{"id":75920,"name":"Harrison C. Gottlich","orcid":"0000-0001-7357-5540","position":0,"is_corresponding":true}],"reference_count":31,"raw_metadata":null,"created_at":"2026-07-19T01:18:18.214733Z","pmid":"37780641","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":[]}