{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T09:07:20Z","timestamp":1785143240049,"version":"3.55.0"},"reference-count":37,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T00:00:00Z","timestamp":1785110400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Early prediction of pathologic complete response (pCR) during neoadjuvant therapy could improve diagnostic assessment of treatment response, adaptive treatment monitoring, and early prognostic stratification in breast cancer, but longitudinal public MRI archives are not immediately ready for reproducible paired-image modeling. The aim of this study was to develop a reproducible longitudinal breast MRI workflow from the public ACRIN 6698\/BMMR2 archive and to compare handcrafted radiomics with frozen deep image embeddings for early treatment-response modeling and imaging-based pCR prediction. Methods: The raw archive was reduced to a validated 183-patient cohort with matched T0 and T1 cropped DCE image\u2013mask pairs, preserved predefined train\/test assignment, and binary pCR labels. Handcrafted radiomic features were extracted at T0 and T1 using a MIRP-based workflow, longitudinal delta descriptors were constructed, and train-only cleaning, filtering, and feature selection were applied before predictive modeling. In parallel, lesion-centered paired 2.5D tensors were generated for image-based deep analysis. Exploratory end-to-end paired deep-learning models were evaluated but showed substantial overfitting. Therefore, a frozen pretrained ResNet18 feature-extraction strategy was used to derive T0, T1, DELTA, and AVG image embeddings, which were then modeled using train-only selection and classical classifiers. Results: In the handcrafted radiomics branch, the strongest refined model was the T1-only random forest model with 10 selected features, achieving an AUROC of 0.670 and an AUPRC of 0.405 on the independent test subset. In the frozen deep-embedding branch, the best configuration by AUROC was the DELTA-only random forest model with 30 selected features (AUROC 0.672, AUPRC 0.408), whereas the strongest configuration by AUPRC was the AVG-only logistic regression model with 100 selected features (AUROC 0.666, AUPRC 0.472). End-to-end paired deep-learning models were technically feasible but were not retained because of marked overfitting. Conclusions: A complex public longitudinal breast MRI archive can be converted into a reproducible modeling cohort for early response assessment. Within this framework, handcrafted radiomics and frozen deep image embeddings yielded comparable exploratory discrimination but emphasized different representation spaces: the strongest handcrafted signal was concentrated in the early-treatment T1 phenotype, whereas the strongest deep signal was concentrated in latent longitudinal change and integrated paired-image state. These findings indicate that longitudinal breast MRI-derived biomarkers warrant further investigation for early treatment-response assessment; however, the present models remain exploratory and require independent external validation before any clinical application.<\/jats:p>","DOI":"10.3390\/diagnostics16152349","type":"journal-article","created":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T08:15:56Z","timestamp":1785140156000},"page":"2349","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Longitudinal Breast MRI for Early Treatment-Response Modeling: A Comparative Study of Handcrafted Radiomics and Frozen Deep Image Embeddings for pCR Prediction"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7650-7798","authenticated-orcid":false,"given":"Diana Ioana","family":"Panaite","sequence":"first","affiliation":[{"name":"Department of Medical Oncology-Radiotherapy, University of Medicine and Pharmacy \u201cGrigore T. Popa\u201d Ia\u0219i, 700115 Ia\u0219i, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2791-3400","authenticated-orcid":false,"given":"C\u0103lin Gheorghe","family":"Buzea","sequence":"additional","affiliation":[{"name":"National Institute of Research and Development for Technical Physics, IFT Ia\u0219i, 700050 Ia\u0219i, Romania"},{"name":"Clinical Emergency Hospital \u201cProf. Dr. Nicolae Oblu\u201d Ia\u0219i, 700309 Ia\u0219i, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3863-6904","authenticated-orcid":false,"given":"Florin","family":"Nedeff","sequence":"additional","affiliation":[{"name":"Department of Environmental Engineering, Mechanical Engineering and Agritourism, Faculty of Engineering, \u201cVasile Alecsandri\u201d University of Bac\u0103u, 600115 Bac\u0103u, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valentin","family":"Nedeff","sequence":"additional","affiliation":[{"name":"Department of Environmental Engineering, Mechanical Engineering and Agritourism, Faculty of Engineering, \u201cVasile Alecsandri\u201d University of Bac\u0103u, 600115 Bac\u0103u, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0922-740X","authenticated-orcid":false,"given":"Diana","family":"Miril\u0103","sequence":"additional","affiliation":[{"name":"Department of Environmental Engineering, Mechanical Engineering and Agritourism, Faculty of Engineering, \u201cVasile Alecsandri\u201d University of Bac\u0103u, 600115 Bac\u0103u, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8582-1988","authenticated-orcid":false,"given":"Mirela","family":"Panainte-Leh\u0103du\u0219","sequence":"additional","affiliation":[{"name":"Department of Environmental Engineering, Mechanical Engineering and Agritourism, Faculty of Engineering, \u201cVasile Alecsandri\u201d University of Bac\u0103u, 600115 Bac\u0103u, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0507-002X","authenticated-orcid":false,"given":"Claudia","family":"Tomozei","sequence":"additional","affiliation":[{"name":"Department of Environmental Engineering, Mechanical Engineering and Agritourism, Faculty of Engineering, \u201cVasile Alecsandri\u201d University of Bac\u0103u, 600115 Bac\u0103u, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lucian","family":"Dobreci","sequence":"additional","affiliation":[{"name":"Department of Environmental Engineering, Mechanical Engineering and Agritourism, Faculty of Engineering, \u201cVasile Alecsandri\u201d University of Bac\u0103u, 600115 Bac\u0103u, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Constantin","family":"Volov\u0103\u021b","sequence":"additional","affiliation":[{"name":"Department of Medical Oncology-Radiotherapy, University of Medicine and Pharmacy \u201cGrigore T. Popa\u201d Ia\u0219i, 700115 Ia\u0219i, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cristian Constantin","family":"Volov\u0103\u021b","sequence":"additional","affiliation":[{"name":"Department of Radiology, University of Medicine and Pharmacy \u201cGrigore T. Popa\u201d Ia\u0219i, 700115 Ia\u0219i, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roxana Irina","family":"Iancu","sequence":"additional","affiliation":[{"name":"Oral Pathology Department, Faculty of Dental Medicine, University of Medicine and Pharmacy \u201cGrigore T. Popa\u201d Ia\u0219i, 700115 Ia\u015fi, Romania"},{"name":"\u201cSt. Spiridon\u201d Emergency Hospital, 700111 Ia\u015fi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maricel","family":"Agop","sequence":"additional","affiliation":[{"name":"Department of Environmental Engineering, Mechanical Engineering and Agritourism, Faculty of Engineering, \u201cVasile Alecsandri\u201d University of Bac\u0103u, 600115 Bac\u0103u, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6447-0958","authenticated-orcid":false,"given":"L\u0103cr\u0103mioara","family":"Ochiuz","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, University of Medicine and Pharmacy \u201cGrigore T. Popa\u201d Ia\u0219i, 700115 Ia\u0219i, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simona Ruxandra","family":"Volov\u0103\u021b","sequence":"additional","affiliation":[{"name":"Department of Medical Oncology-Radiotherapy, University of Medicine and Pharmacy \u201cGrigore T. Popa\u201d Ia\u0219i, 700115 Ia\u0219i, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,27]]},"reference":[{"key":"ref_1","unstructured":"U.S. Food and Drug Administration (2020). Pathological Complete Response in Neoadjuvant Treatment of High-Risk Early-Stage Breast Cancer: Use as an Endpoint to Support Accelerated Approval; Guidance for Industry."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2438","DOI":"10.1056\/NEJMp1205737","article-title":"Pathological complete response and accelerated drug approval in early breast cancer","volume":"366","author":"Prowell","year":"2012","journal-title":"N. Engl. J. Med."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1016\/S0140-6736(13)62422-8","article-title":"Pathological complete response and long-term clinical benefit in breast cancer: The CTNeoBC pooled analysis","volume":"384","author":"Cortazar","year":"2014","journal-title":"Lancet"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Cheng, Q., Huang, J., Liang, J., Ma, M., Ye, K., Shi, C., and Luo, L. (2020). The diagnostic performance of DCE-MRI in evaluating the pathological response to neoadjuvant chemotherapy in breast cancer: A meta-analysis. Front. Oncol., 10.","DOI":"10.3389\/fonc.2020.00093"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"110247","DOI":"10.1016\/j.ejrad.2022.110247","article-title":"Machine learning with magnetic resonance imaging for prediction of response to neoadjuvant chemotherapy in breast cancer: A systematic review and meta-analysis","volume":"150","author":"Liang","year":"2022","journal-title":"Eur. J. Radiol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"100883","DOI":"10.1016\/j.currproblcancer.2022.100883","article-title":"Prediction of the pathological response to neoadjuvant chemotherapy in breast cancer patients with MRI-radiomics: A systematic review and meta-analysis","volume":"46","author":"Pesapane","year":"2022","journal-title":"Curr. Probl. Cancer"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1148\/radiol.12110748","article-title":"Locally advanced breast cancer: MR imaging for prediction of response to neoadjuvant chemotherapy\u2014Results from ACRIN 6657\/I-SPY TRIAL","volume":"263","author":"Hylton","year":"2012","journal-title":"Radiology"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1148\/rg.2021200134","article-title":"Breast MRI for evaluation of response to neoadjuvant therapy","volume":"41","author":"Reig","year":"2021","journal-title":"Radiographics"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1587","DOI":"10.1002\/jmri.27145","article-title":"Role of MRI to assess response to neoadjuvant therapy for breast cancer","volume":"52","author":"Reig","year":"2020","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_10","unstructured":"The Cancer Imaging Archive (2026, June 15). ACRIN 6698\/I-SPY2 Breast DWI. Available online: https:\/\/www.cancerimagingarchive.net\/collection\/acrin-6698\/."},{"key":"ref_11","first-page":"e230033","article-title":"Breast multiparametric MRI for prediction of neoadjuvant therapy response: The BMMR2 challenge","volume":"6","author":"Li","year":"2024","journal-title":"Radiol. Artif. Intell."},{"key":"ref_12","unstructured":"ClinicalTrials.gov (2026, June 15). DWI in Assessing Treatment Response in Patients with Breast Cancer Undergoing Neoadjuvant Chemotherapy (ACRIN 6698\/I-SPY2), Identifier NCT01564368, Available online: https:\/\/clinicaltrials.gov\/study\/NCT01564368."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1148\/radiol.2020191145","article-title":"The Image Biomarker Standardization Initiative: Standardized quantitative radiomics for high-throughput image-based phenotyping","volume":"295","author":"Zwanenburg","year":"2020","journal-title":"Radiology"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"106510","DOI":"10.1016\/j.cmpb.2021.106510","article-title":"MRI radiogenomics for intelligent diagnosis of breast tumors and accurate prediction of neoadjuvant chemotherapy responses\u2014A review","volume":"214","author":"Yin","year":"2022","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Pesapane, F., Botta, F., Rotili, A., Agazzi, G.M., Nicosia, L., Cassano, E., Penco, S., Dominelli, V., Di Micco, R., and Esposito, A. (2021). Radiomics of MRI for the prediction of the pathological response to neoadjuvant chemotherapy in breast cancer patients: A single referral centre analysis. Cancers, 13.","DOI":"10.3390\/cancers13174271"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1148\/radiol.2021203645","article-title":"Breast MRI during neoadjuvant chemotherapy: Lack of background parenchymal enhancement suppression and inferior treatment response","volume":"301","author":"Onishi","year":"2021","journal-title":"Radiology"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1111\/1759-7714.13309","article-title":"Prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer using a deep learning method","volume":"11","author":"Qu","year":"2020","journal-title":"Thorac. Cancer"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Umutlu, L., Kirchner, J., Bruckmann, N.-M., Morawitz, J., Antoch, G., Ting, S., Bittner, A.-K., Hoffmann, O., H\u00e4berle, L., and Ruckh\u00e4berle, E. (2022). Multiparametric ^18F-FDG PET\/MRI-based radiomics for prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer. Cancers, 14.","DOI":"10.3390\/cancers14071727"},{"key":"ref_19","first-page":"3818","article-title":"Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: A study using I-SPY trial data","volume":"81","author":"Cain","year":"2019","journal-title":"Magn. Reson. Med."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1097\/RLI.0000000000000518","article-title":"Impact of machine learning with multiparametric magnetic resonance imaging of the breast for early prediction of response to neoadjuvant chemotherapy and survival outcomes in breast cancer patients","volume":"54","author":"Tahmassebi","year":"2019","journal-title":"Investig. Radiol."},{"key":"ref_21","first-page":"330","article-title":"MRI-based machine learning in breast cancer response prediction during neoadjuvant therapy","volume":"52","author":"Gullo","year":"2020","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2784","DOI":"10.3390\/tomography8060232","article-title":"Deep learning prediction of pathologic complete response from breast MRI in the neoadjuvant setting: A systematic review","volume":"8","author":"Khan","year":"2022","journal-title":"Tomography"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"110561","DOI":"10.1016\/j.ejrad.2022.110561","article-title":"The accuracy of breast MRI radiomic methodologies in predicting pathological complete response to neoadjuvant chemotherapy: A systematic review and network meta-analysis","volume":"157","author":"Pinker","year":"2022","journal-title":"Eur. J. Radiol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1148\/radiol.2021203871","article-title":"Development and validation of a predictive nomogram incorporating MRI and clinicopathologic factors for pathologic complete response after neoadjuvant chemotherapy in breast cancer","volume":"299","author":"Kim","year":"2021","journal-title":"Radiology"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1057841","DOI":"10.3389\/fonc.2023.1057841","article-title":"Multiparametric MRI radiomics fusion for predicting the pathological complete response to neoadjuvant chemotherapy in breast cancer","volume":"13","author":"Fan","year":"2023","journal-title":"Front Oncol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1007\/s00432-024-05680-y","article-title":"Predicting pathological complete response to neoadjuvant chemotherapy in breast cancer patients: Use of MRI radiomics data from three regions with multiple machine learning algorithms","volume":"150","author":"Zheng","year":"2024","journal-title":"J. Cancer Res. Clin. Oncol."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zheng, G., Hou, J., Shu, Z., Peng, J., Han, L., Yuan, Z., He, X., and Gong, X. (2024). Prediction of neoadjuvant chemotherapy pathological complete response for breast cancer based on radiomics nomogram of intratumoral and derived tissue. BMC Med. Imaging, 24.","DOI":"10.1186\/s12880-024-01198-4"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Yu, Y., Wang, Z., Wang, Q., Su, X., Li, Z., Wang, R., Guo, T., Gao, W., Wang, H., and Zhang, B. (2024). Radiomic model based on magnetic resonance imaging for predicting pathological complete response after neoadjuvant chemotherapy in breast cancer patients. Front. Oncol., 13.","DOI":"10.3389\/fonc.2023.1249339"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Li, Y., Fan, Y., Xu, D., Li, Y., Zhong, Z., Pan, H., Huang, B., Xie, X., Yang, Y., and Liu, B. (2023). Deep learning radiomic analysis of DCE-MRI combined with clinical characteristics for predicting pathological complete response after neoadjuvant chemotherapy in breast cancer. Front. Oncol., 12.","DOI":"10.3389\/fonc.2022.1041142"},{"key":"ref_30","first-page":"7","article-title":"Prediction of pathologic complete response to neoadjuvant systemic therapy for triple-negative breast cancers using deep learning on multiparametric MRIs","volume":"23","author":"Zhou","year":"2023","journal-title":"Cancer Imaging"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Lowekamp, B.C., Chen, D.T., Ib\u00e1\u00f1ez, L., and Blezek, D. (2013). The Design of SimpleITK. Front. Neuroinform., 7.","DOI":"10.3389\/fninf.2013.00045"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"6413","DOI":"10.21105\/joss.06413","article-title":"MIRP: A Python package for standardised radiomics","volume":"9","author":"Zwanenburg","year":"2024","journal-title":"J. Open Source Softw."},{"key":"ref_33","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_35","first-page":"8024","article-title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","volume":"Volume 32","author":"Wallach","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref_36","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). ImageNet: A Large-Scale Hierarchical Image Database. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/15\/2349\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T08:25:50Z","timestamp":1785140750000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/15\/2349"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,27]]},"references-count":37,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["diagnostics16152349"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16152349","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,27]]}}}