{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T04:46:34Z","timestamp":1782535594934,"version":"3.54.5"},"reference-count":21,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"abstract":"<jats:p>Background\/Objectives: The \u201csmall-n-large-p\u201d dilemma in mammography artificial intelligence (AI)\u2014where the number of candidate imaging features far exceeds the number of labeled cases\u2014commonly results in model overfitting, unstable feature selection, and poor generalization across clinical settings. This study aims to reassess the internal performance of the HiTopology-GOA-CSA (Grasshopper Optimization Algorithm\u2013Crow Search Algorithm) feature-selection framework for mammography using a larger real Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM) cohort and a stricter leakage-aware evaluation strategy. Methods: In this retrospective computational study using public anonymized datasets, an expanded internal cohort of 98 CBIS-DDSM mass cases (49 benign, 49 malignant) was assembled from digital imaging and communications in medicine (DICOM) region of interest (ROI) series. A total of 1074 features were extracted per case, including 88 handcrafted radiomic descriptors and 986 EfficientNet-B5 deep features. HiTopology-GOA-CSA selected 102 features, corresponding to 91% feature reduction. Two internal evaluation modes were compared: Mode A, which matched the original pilot methodology by performing feature selection once on the full cohort before cross-validation, and Mode B, which used strict nested feature selection within training folds. Performance was assessed with 5-fold stratified cross-validation using a multilayer perceptron (MLP) classifier. Results: On the expanded cohort, Mode A achieved an area under the receiver operating characteristic curve (AUC) of 0.726 (95% CI: 0.594\u20130.858), sensitivity of 0.658, specificity of 0.651, and F1-score of 0.644. Under the stricter nested evaluation, Mode B achieved AUC of 0.683 (95% CI: 0.549\u20130.817), sensitivity of 0.598, specificity of 0.631, and F1-score of 0.595. Mean pairwise Jaccard similarity across nested folds was 0.604, indicating moderate feature stability. Benchmark comparisons showed that the proposed method was competitive but did not outperform standard baselines; LASSO logistic regression achieved the highest AUC of 0.739, while the proposed HiTopology-GOA-CSA + MLP achieved an AUC of 0.683. Real external validation on the locked VinDr-Mammo subset (n = 25) remained near-random (AUC of 0.500 [95% CI: 0.304\u20130.696]), with complete prediction collapse (sensitivity of 1.000, specificity of 0.000). Conclusions: The framework demonstrated feasibility for structured feature selection and stress testing in a small-cohort mammography AI setting; however, external validation revealed near-random discrimination and prediction collapse, indicating limited generalizability. These findings emphasize the need for benchmark comparisons, transparent uncertainty reporting, patient-level validation, and larger multicenter datasets before clinical translation.<\/jats:p>","DOI":"10.3390\/jcm15124846","type":"journal-article","created":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T03:09:17Z","timestamp":1782270557000},"page":"4846","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid Metaheuristic Feature Selection for Breast Cancer Detection in Digital Mammography: A Feasibility Study with Nested Validation, Benchmarking, and External Stress Testing"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9284-4262","authenticated-orcid":false,"given":"Bandar S.","family":"Alshreef","sequence":"first","affiliation":[{"name":"Department of Clinical Laboratory Sciences, College of Applied Medical Sciences, Shaqra University, Shaqra 11961, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2507-2292","authenticated-orcid":false,"given":"Yousif A.","family":"Kariri","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory Sciences, College of Applied Medical Sciences, Shaqra University, Shaqra 11961, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,22]]},"reference":[{"key":"ref_1","first-page":"209","article-title":"Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA Cancer J. Clin."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1038\/s41586-019-1799-6","article-title":"International evaluation of an AI system for breast cancer screening","volume":"577","author":"McKinney","year":"2020","journal-title":"Nature"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1581","DOI":"10.1001\/jamaoncol.2020.3321","article-title":"External Evaluation of 3 Commercial Artificial Intelligence Algorithms for Independent Assessment of Screening Mammograms","volume":"6","author":"Salim","year":"2020","journal-title":"JAMA Oncol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1148\/radiol.210948","article-title":"An Artificial Intelligence-based Mammography Screening Protocol for Breast Cancer: Outcome and Radiologist Workload","volume":"304","author":"Lauritzen","year":"2022","journal-title":"Radiology"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e232479","DOI":"10.1148\/radiol.232479","article-title":"Early Indicators of the Impact of Using AI in Mammography Screening for Breast Cancer","volume":"311","author":"Lauritzen","year":"2024","journal-title":"Radiology"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Stefano, A., Bini, F., Giovagnoli, E., Dimarco, M., Lauciello, N., Narbonese, D., Pasini, G., Marinozzi, F., Russo, G., and D\u2019Angelo, I. (2025). Comparative Evaluation of Machine Learning-Based Radiomics and Deep Learning for Breast Lesion Classification in Mammography. Diagnostics, 15.","DOI":"10.20944\/preprints202503.0184.v1"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"106003","DOI":"10.1016\/j.compbiomed.2022.106003","article-title":"Multilevel segmentation of 2D and volumetric medical images using hybrid Coronavirus Optimization Algorithm","volume":"150","author":"Hosny","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref_8","first-page":"100108","article-title":"An hybrid particle swarm optimization with crow search algorithm for feature selection","volume":"6","author":"Adamu","year":"2021","journal-title":"Mach. Learn. Appl."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1007\/s10462-025-11232-8","article-title":"Recent trends on mammogram breast density analysis using deep learning models: Neoteric review","volume":"58","author":"Hemalatha","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"170177","DOI":"10.1038\/sdata.2017.177","article-title":"A curated mammography data set for use in computer-aided detection and diagnosis research","volume":"4","author":"Lee","year":"2017","journal-title":"Sci. Data"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1038\/s41597-023-02100-7","article-title":"VinDr-Mammo: A large-scale benchmark dataset for computer-aided diagnosis in full-field digital mammography","volume":"10","author":"Nguyen","year":"2023","journal-title":"Sci. Data"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1093\/jbi\/wbae058","article-title":"External Validation of a Commercial Artificial Intelligence Algorithm on a Diverse Population for Detection of False Negative Breast Cancers","volume":"7","author":"Plimpton","year":"2025","journal-title":"J. Breast Imaging"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e-rbgo71","DOI":"10.61622\/rbgo\/2024rbgo71","article-title":"Artificial intelligence in mammography: A systematic review of the external validation","volume":"46","author":"Branco","year":"2024","journal-title":"Rev. Bras. Ginecol. Obstet."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"e104","DOI":"10.1158\/0008-5472.CAN-17-0339","article-title":"Computational Radiomics System to Decode the Radiographic Phenotype","volume":"77","author":"Fedorov","year":"2017","journal-title":"Cancer Res."},{"key":"ref_15","unstructured":"Tan, M., and Le, Q. (2019, January 9\u201315). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multilayer feedforward networks are universal approximators","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural Netw."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/j.neunet.2020.07.021","article-title":"Two-hidden-layer feed-forward networks are universal approximators: A constructive approach","volume":"131","year":"2020","journal-title":"Neural Netw."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"e082505","DOI":"10.1136\/bmj-2024-082505","article-title":"PROBAST+AI: An updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods","volume":"388","author":"Moons","year":"2025","journal-title":"BMJ"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e081554","DOI":"10.1136\/bmj-2024-081554","article-title":"FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare","volume":"388","author":"Lekadir","year":"2025","journal-title":"BMJ"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2923","DOI":"10.1038\/s41598-024-53141-w","article-title":"Feature importance feedback with Deep Q process in ensemble-based metaheuristic feature selection algorithms","volume":"14","author":"Potharlanka","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Tran, A.T., Wen, J., Abou Karam, G., Zeevi, D., Qureshi, A.I., Malhotra, A., Majidi, S., Valizadeh, N., Murthy, S.B., and Sabuncu, M.R. (2025). Comparing Handcrafted Radiomics Versus Latent Deep Learning Features of Admission Head CT for Hemorrhagic Stroke Outcome Prediction. BioTech, 14.","DOI":"10.3390\/biotech14040087"}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/12\/4846\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T04:16:41Z","timestamp":1782533801000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/12\/4846"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":21,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["jcm15124846"],"URL":"https:\/\/doi.org\/10.3390\/jcm15124846","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,22]]}}}