{"doi":"10.1371/journal.pone.0261307","title":"Novel loss functions for ensemble-based medical image classification","abstract":"Medical images commonly exhibit multiple abnormalities. Predicting them requires multi-class classifiers whose training and desired reliable performance can be affected by a combination of factors, such as, dataset size, data source, distribution, and the loss function used to train deep neural networks. Currently, the cross-entropy loss remains the de-facto loss function for training deep learning classifiers. This loss function, however, asserts equal learning from all classes, leading to a bias toward the majority class. Although the choice of the loss function impacts model performance, to the best of our knowledge, we observed that no literature exists that performs a comprehensive analysis and selection of an appropriate loss function toward the classification task under study. In this work, we benchmark various state-of-the-art loss functions, critically analyze model performance, and propose improved loss functions for a multi-class classification task. We select a pediatric chest X-ray (CXR) dataset that includes images with no abnormality (normal), and those exhibiting manifestations consistent with bacterial and viral pneumonia. We construct prediction-level and model-level ensembles to improve classification performance. Our results show that compared to the individual models and the state-of-the-art literature, the weighted averaging of the predictions for top-3 and top-5 model-level ensembles delivered significantly superior classification performance (p < 0.05) in terms of MCC (0.9068, 95% confidence interval (0.8839, 0.9297)) metric. Finally, we performed localization studies to interpret model behavior and confirm that the individual models and ensembles learned task-specific features and highlighted disease-specific regions of interest. The code is available at https://github.com/sivaramakrishnan-rajaraman/multiloss_ensemble_models.","journal":"PLoS ONE","year":2021,"id":158256,"datarank":1.4471142333439704,"base_score":3.8712010109078907,"endowment":3.8712010109078907,"self_citation_contribution":0.5806801516361837,"citation_network_contribution":0.8664340817077868,"self_endowment_contribution":0.5806801516361837,"citer_contribution":0.8664340817077868,"corpus_percentile":null,"corpus_rank":null,"citation_count":47,"citer_count":45,"citers_with_citation_signal":29,"citers_with_endowment":29,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9524,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2021-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":294654,"name":"Ghada Zamzmi","orcid":"0000-0003-4723-5539","position":1,"is_corresponding":false},{"id":75954,"name":"Sameer Antani","orcid":"0000-0002-0040-1387","position":2,"is_corresponding":false},{"id":259902,"name":"Sivaramakrishnan Rajaraman","orcid":"0000-0003-0871-8634","position":0,"is_corresponding":true}],"reference_count":42,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-07-18T23:44:26.210708Z","pmid":"34968393","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":[]}