The DOI matches its Crossref record; 37 of the 39 references it cites were found in a registry or an index; 16 of the 36 sources its claims cite were checked for support.
A multimodal and fully automated system for prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer
Open accessAbstract
Accurately predicting pathological complete response (pCR) before neoadjuvant chemotherapy (NAC) is crucial for patients with breast cancer. In this study, we developed a multimodal integrated fully automated pipeline system (MIFAPS) in forecasting pCR to NAC, using a multicenter and prospective dataset of 1004 patients with locally advanced breast cancer, incorporating pretreatment magnetic resonance imaging, whole slide image, and clinical risk factors. The results demonstrated that MIFAPS offered a favorable predictive performance in both the pooled external test set [area under the curve (AUC) = 0.882] and the prospective test set (AUC = 0.909). In addition, MIFAPS significantly outperformed single-modality models ( P < 0.05). Furthermore, the high deep learning scores were associated with immune-related pathways and the promotion of antitumor cells in the microenvironment during biological basis exploration. Overall, our study demonstrates a promising approach for improving the prediction of pCR to NAC in patients with breast cancer through the integration of multimodal data.
Overview
CoChat Summary
## TL;DR
The paper develops MIFAPS, a fully automated multimodal deep learning pipeline that predicts pathological complete response (pCR) to neoadjuvant chemotherapy in locally advanced breast cancer from pretreatment MRI, biopsy whole-slide images (WSI), and clinical factors. It reports strong discrimination in external and prospective testing and links higher model scores to immune-response-related biology in the tumor microenvironment.
## Key findings
- In 1004 enrolled patients, MIFAPS achieved AUCs of 0.932 in the internal test set, 0.882 in the pooled external test set, and 0.909 in the prospective test set.
- In the pooled external and prospective test sets, MIFAPS outperformed the MRI-only model (0.813 vs 0.882; 0.822 vs 0.909), the WSI-only model (0.797–0.816 vs 0.882–0.932 reported across tests), and the clinical model (0.653–0.689 for clinical only in internal/external sets; 0.745 in the prospective set).
- The model’s sensitivity and specificity across the three test sets ranged from 0.815 to 0.947 and 0.766 to 0.854, respectively; AUPRC was 0.781 in the pooled external test set and 0.833 in the prospective test set.
- Biological exploration in 67 patients found that high MIFAPS scores were associated with immune response pathways, including positive regulation of interferon-γ production and T cell proliferation, with higher CD4 memory T cells (P = 0.010) and more M1 macrophages in the high-score group.
## Methods
- Multicenter study with 1004 patients with locally advanced breast cancer: 478 retrospective development/internal validation cases from one hospital, 417 pooled external test cases from multiple centers, and 109 prospectively enrolled cases from one hospital.
- The model integrated three pretreatment inputs: MRI (T2WI, DWI, CE-T1WI) with automated segmentation and classification, WSI with attention-based multi-instance learning, and clinical risk factors selected by logistic regression.
- Main analysis was logistic-regression-based multimodal fusion; performance was evaluated with AUC, AUPRC, sensitivity, specificity, accuracy, and DeLong tests, with subgroup analyses and visualization using Grad-CAM and WSI attention heatmaps.
## Limitations
- The paper states that, despite multicenter validation, the model “did not achieve satisfactory sensitivity in the prospective and external test sets,” suggesting limited generalization across institutions.
- The authors note several model constraints: the MRI model used only a specific MRI phase, the WSI model used single-scale images, and the biological analysis relied on bulk RNA sequencing, which may lose gene-expression heterogeneity.
- Evident from the text: the deep learning and biological-basis analyses were performed on a limited subset for transcriptomics (67 patients), which may constrain biological inference.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures







Verification
Claims the paper makes
14 Valid · 1 Not valid · 6 Not checked · 66 Own results and interpretations
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“the model was developed based on single-center data.”
§ A multimodal and fully automated system for prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer > DISCUSSION
What the sources say
- Supportedcites [13] Y. Huang, T. Zhu, X. Zhang, W. Li, X. Zheng, M. Cheng, F. Ji, L. Zhang, C. Yang, Z. Wu, G. Ye, Y. Lin, K. Wang, Longitudinal MRI-based fusion novel model predicts pathological complete response in breast cancer treated with neoadjuvant chemotherapy: A multicenter, retrospective study. EClinicalMedicine 58, 101899 (2023). 37007742 PMC10050775 source
Methods > Study participants (page unavailable) says patients from Guangdong Provincial People's Hospital formed the primary cohort used to develop the models. Methods > Development and assessment of models says model construction used that primary cohort; patients from three other hospitals were used for external validation. (LLM, conf=0.94)
- Not checked — no full text of the sourcecites [16] P. Courtiol, C. Maussion, M. Moarii, E. Pronier, S. Pilcer, M. Sefta, P. Manceron, S. Toldo, M. Zaslavskiy, N. Le Stang, N. Girard, O. Elemento, A. G. Nicholson, J.-Y. Blay, F. Galateau-Sallé, G. Wainrib, T. Clozel, Deep learning-based classification of mesothelioma improves prediction of patient outcome. Nat. Med. 25, 1519– 1525 (2019). 31591589 source
- Not checked — no full text of the sourcecites [18] L. Feng, Z. Liu, C. Li, Z. Li, X. Lou, L. Shao, Y. Wang, Y. Huang, H. Chen, X. Pang, S. Liu, F. He, J. Zheng, X. Meng, P. Xie, G. Yang, Y. Ding, M. Wei, J. Yun, M.-C. Hung, W. Zhou, D. R. Wahl, P. Lan, J. Tian, X. Wan, Development and validation of a radiopathomics model to predict pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer: A multicentre observational study. Lancet Digit. Health 4, e8– e17 (2022). 34952679 source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“MRI is superior to mammography and US in determining tumor extent and morphology before and after NAC because it provides comprehensive imaging information about tumors (6).”
§ A multimodal and fully automated system for prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer > INTRODUCTION
What the sources say
- Partly supportedcites [6] M. B. Lobbes, R. Prevos, M. Smidt, V. C. Tjan-Heijnen, M. van Goethem, R. Schipper, R. G. Beets-Tan, J. E. Wildberger, The role of magnetic resonance imaging in assessing residual disease and pathologic complete response in breast cancer patients receiving neoadjuvant chemotherapy: A systematic review. Insights Imaging 4, 163– 175 (2013). 23359240 PMC3609956 sourceExperimental — accuracy not yet measured
The Introduction says MRI is superior to mammography and ultrasound for assessing tumour extent and additional foci; the Results and Discussion report better assessment of residual disease after NAC. The cited passages do not establish superiority for assessing tumour morphology before and after NAC, or give “comprehensive imaging information” as the reason for it. Page numbers are unavailable in our copy. (LLM, conf=0.84)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Many researchers found that deep learning can improve the prediction ability of NAC response prediction in breast cancer (13, 22).”
§ A multimodal and fully automated system for prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer > DISCUSSION
What the sources say
- Supportedcites [13] Y. Huang, T. Zhu, X. Zhang, W. Li, X. Zheng, M. Cheng, F. Ji, L. Zhang, C. Yang, Z. Wu, G. Ye, Y. Lin, K. Wang, Longitudinal MRI-based fusion novel model predicts pathological complete response in breast cancer treated with neoadjuvant chemotherapy: A multicenter, retrospective study. EClinicalMedicine 58, 101899 (2023). 37007742 PMC10050775 source
The Methods describe extracting deep-learning features from breast MRI to predict pathological complete response to NAC. The Discussion reports improved predictive performance for the ensemble model that incorporated those features across three validation cohorts; the finding concerns deep learning used alongside radiomics, not deep learning alone. Page numbers are unavailable in our copy. (LLM, conf=0.88)
- Not checked — no full text of the sourcecites [22] M. Jiang, C. L. Li, X. M. Luo, Z. R. Chuan, W. Z. Lv, X. Li, X. W. Cui, C. F. Dietrich, Ultrasound-based deep learning radiomics in the assessment of pathological complete response to neoadjuvant chemotherapy in locally advanced breast cancer. Eur. J. Cancer 147, 95– 105 (2021). 33639324 source
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Most of the previous studies trained the data using a single network; thus, the complementary advantages of multiple networks were overlooked (27, 28).”
§ A multimodal and fully automated system for prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer > DISCUSSION
What the sources say
- Could not verifycites [27] I. Skarping, M. Larsson, D. Fornvik, Analysis of mammograms using artificial intelligence to predict response to neoadjuvant chemotherapy in breast cancer patients: Proof of concept. Eur. Radiol. 32, 3131– 3141 (2022). 34652522 PMC9038782 sourceExperimental — accuracy not yet measured
The Materials and methods section (Neural networks; page unavailable) describes this paper’s detection and classification networks, but does not assess how many networks most previous studies used. The Discussion (AI and treatment response evaluation; page unavailable) compares prior studies’ results without saying they overlooked complementary advantages of multiple networks. Searches for single-network training and combinations of networks found no passage addressing that claim. (LLM, conf=0.73)
- Not checked — no full text of the sourcecites [28] J. Gu, T. Tong, C. He, M. Xu, X. Yang, J. Tian, T. Jiang, K. Wang, Deep learning radiomics of ultrasonography can predict response to neoadjuvant chemotherapy in breast cancer at an early stage of treatment: A prospective study. Eur. Radiol. 32, 2099– 2109 (2022). 34654965 source
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Emerging evidence has shown that histopathology whole slide image (WSI) provides information that reflects molecular characteristics or genetic patterns.”
§ A multimodal and fully automated system for prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer > INTRODUCTION
What the sources say
- Not checked — no full text of the sourcecites [14] O.-J. Skrede, S. De Raedt, A. Kleppe, T. S. Hveem, K. Liestøl, J. Maddison, H. A. Askautrud, M. Pradhan, J. A. Nesheim, F. Albregtsen, I. N. Farstad, E. Domingo, D. N. Church, A. Nesbakken, N. A. Shepherd, I. Tomlinson, R. Kerr, M. Novelli, D. J. Kerr, H. E. Danielsen, Deep learning for prediction of colorectal cancer outcome: A discovery and validation study. Lancet 395, 350– 360 (2020). 32007170 source
- Supportedcites [15] F. Li, Y. Yang, Y. Wei, P. He, J. Chen, Z. Zheng, H. Bu, Deep learning-based predictive biomarker of pathological complete response to neoadjuvant chemotherapy from histological images in breast cancer. J. Transl. Med. 19, 348 (2021). 34399795 PMC8365907 source
The Background says histological images provide information about tumor characteristics that reflects underlying molecular processes. It also describes work using such images to predict gene mutations and classify molecular profiles, supporting the claim about genetic patterns. (LLM, conf=0.92)
- Not checked — no full text of the sourcecites [16] P. Courtiol, C. Maussion, M. Moarii, E. Pronier, S. Pilcer, M. Sefta, P. Manceron, S. Toldo, M. Zaslavskiy, N. Le Stang, N. Girard, O. Elemento, A. G. Nicholson, J.-Y. Blay, F. Galateau-Sallé, G. Wainrib, T. Clozel, Deep learning-based classification of mesothelioma improves prediction of patient outcome. Nat. Med. 25, 1519– 1525 (2019). 31591589 source
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
39 more claims
Create a free account to see all 87 claims and every source verdict.
- Probably not a substantial claim. 23
- It may state two separate claims as one. 24
Citations
Cites
Sung, H., Ferlay, J., Siegel, R. L., Laversanne, M., Soerjomataram, I., Jemal, A., & Bray, F. (2021) · CA: A Cancer Journal for Clinicians · doi:10.3322/caac.21660 · Cited by 108,699
Radiomics: extracting more information from medical images using advanced feature analysis
Lambin, P., Rios-Velazquez, E., Leijenaar, R., Carvalho, S., van Stiphout, R. G. P. M., Granton, P., Zegers, C. M. L., Gillies, R., Boellard, R., Dekker, A., et al. (2012) · European Journal of Cancer · doi:10.1016/j.ejca.2011.11.036 · Cited by 6,084 · cited 1×
“In recent years, machine learning, particularly radiomics, has emerged as a research hotspot ( 9 ).”
Radiomics: the bridge between medical imaging and personalized medicine
Lambin, P., Leijenaar, R. T. H., Deist, T. M., Peerlings, J., de Jong, E. E. C., van Timmeren, J., Sanduleanu, S., Larue, R. T. H. M., Even, A. J. G., Jochems, A., et al. (2017) · Nature Reviews Clinical Oncology · doi:10.1038/nrclinonc.2017.141 · Cited by 5,688 · cited 1×
“Recent research has indicated that multimodal integration can yield good predictive performance ( 23 ).”
Data-efficient and weakly supervised computational pathology on whole-slide images
Lu, M. Y., Williamson, D. F. K., Chen, T. Y., Chen, R. J., Barbieri, M., & Mahmood, F. (2021) · Nature Biomedical Engineering · doi:10.1038/s41551-020-00682-w · Cited by 2,282 · cited 1×
“2B, was trained based on the CLAM library ( 36 ).”
RECIST 1.1—Update and clarification: From the RECIST committee
Schwartz, L. H., Litière, S., de Vries, E., Ford, R., Gwyther, S., Mandrekar, S., Shankar, L., Bogaerts, J., Chen, A., Dancey, J., et al. (2016) · European Journal of Cancer · doi:10.1016/j.ejca.2016.03.081 · Cited by 1,906
Macrophage Polarization States in the Tumor Microenvironment
Boutilier, A. J., & Elsawa, S. F. (2021) · International Journal of Molecular Sciences · doi:10.3390/ijms22136995 · Cited by 1,631 · cited 1×
“In addition, CD4 + T cells impact cancer immunology ( 30 ), M1 macrophages suppress tumors, and M2 macrophages aid tumor growth ( 31 ).”
Breast Cancer, Version 4.2017, NCCN Clinical Practice Guidelines in Oncology
Gradishar, W. J., Anderson, B. O., Balassanian, R., Blair, S. L., Burstein, H. J., Cyr, A., Elias, A. D., Farrar, W. B., Forero, A., Giordano, S. H., et al. (2018) · Journal of the National Comprehensive Cancer Network · doi:10.6004/jnccn.2018.0012 · Cited by 1,609
CD4+ T cell help in cancer immunology and immunotherapy
Borst, J., Ahrends, T., Bąbała, N., Melief, C. J. M., & Kastenmüller, W. (2018) · Nature Reviews Immunology · doi:10.1038/s41577-018-0044-0 · Cited by 1,585 · cited 1×
“In addition, CD4 + T cells impact cancer immunology ( 30 ), M1 macrophages suppress tumors, and M2 macrophages aid tumor growth ( 31 ).”
Estrogen and progesterone receptor testing in breast cancer: ASCO/CAP Guideline update
Allison, K. H., Hammond, M. E. H., Dowsett, M., McKernin, S. E., Carey, L. A., Fitzgibbons, P. L., Hayes, D. F., Lakhani, S. R., Chavez-MacGregor, M., Perlmutter, J., et al. (2020) · Journal of Clinical Oncology · doi:10.1200/jco.19.02309 · Cited by 1,574
Hover-Net: Simultaneous segmentation and classification of nuclei in multi-tissue histology images
Graham, S., Vu, Q. D., Raza, S. E. A., Azam, A., Tsang, Y. W., Kwak, J. T., & Rajpoot, N. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.101563 · Cited by 1,423
Cited by
Zhang, X.-M., Gao, T.-H., Cai, Q.-Y., Xia, J.-B., Sun, Y., Yang, J. M., Li, W., Zhang, S.-X.-M., Lou, H.-R., Yu, X., et al. (2026) · Military Medical Research · doi:10.1186/s40779-025-00680-6 · Cited by 50
“They employ models such as CNNs and Transformers [142–148] to automatically extract prognostic features from pathological data and to integrate multi-omics information [143, 144, 148] for response prediction.”
Ran, D., Li, J., Zhao, M., Du, L., Zhang, Y., & Zhu, J. (2025) · Frontiers in Oncology · doi:10.3389/fonc.2025.1612474 · Cited by 23
Krasniqi, E., Filomeno, L., Arcuri, T., Ferretti, G., Gasparro, S., Fulvi, A., Roselli, A., D’Onofrio, L., Pizzuti, L., Barba, M., et al. (2025) · Biology Direct · doi:10.1186/s13062-025-00661-8 · Cited by 25
“…of 1004 patients, the DL model fused pretreatment MRI, WSI pathology images and structured clinical variables inside one unified CNN-based pipeline, and achieved an external-test AUC of 0.88 and a prospective-test AUC of 0.91, significantly higher than any of its single-modality counterparts [70].”
InfluentialJiang, B., Wu, Y., Chen, X., Jian, C., & Wang, W. (2026) · Critical Reviews in Oncology/Hematology · doi:10.1016/j.critrevonc.2026.105160 · Cited by 18
Self-citationJi, J., Duan, F., Liao, Q., Wang, H., Liu, S., Liu, Y., & Huang, Z. (2025) · Cancer Medicine · doi:10.1002/cam4.71132 · Cited by 15
“This model exhibited excellent predictive performance in an independent prospective test set (AUC = 0.909), confirming the clinical value of multi-modal data fusion strategies in improving prediction accuracy [71].”
Influential
Metadata
- Authors
- Mao, N., Dai, Y., Zhou, H., Lin, F., Zheng, T., Li, Z., Yang, P., Zhao, F., Li, Q., Wang, W., Liang, Y., Xie, H., Ma, H., Zhang, L., Guo, Y., Song, X., Zhang, H., & Lu, J.
- Affiliations
- Qingdao University (CN)
- Peking University Shenzhen Hospital (CN)
- Shandong Institute of Business and Technology (CN)
- Fudan University Shanghai Cancer Center (CN)
- Affiliated Hospital of Jining Medical University (CN)
- Department of Medical Imaging, Guilin Municipal Hospital of Traditional Chinese Medicine, Guilin, Guangxi 541002, P. R. China.
- Department of Radiology, The First Hospital of China Medical University, Shenyang, Liaoning 110001, P. R. China.
- Guangzhou First People's Hospital (CN)
- Yuhuangding Hospital (CN)
- Capital Medical University (CN)
- Corresponding author
- Mao, Ning
- Dai, Yi
- Zhou, Heng
- Song, Xicheng
- Zhang, Haicheng
- Lu, Jie
- ORCID
- Venue
- Science Advances
- Published
- 2025-05-02
- Volume
- 11
- Issue
- 18
- Pages
- eadr1576-eadr1576
- ISSN
- 2375-2548 (ISSN-L)
- PMC
- PMC12042891
- OpenAlex
- W4409982803
- Cited by
- 51
- References
- 39
- Citations by year
- 2026: 35 · 2025: 15
- FWCI
- 19.90
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by-nc
- Locations
- Science Advances (publishedVersion, cc-by-nc)
- PubMed Central (publishedVersion, cc-by-nc)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Cancer Research › Breast Cancer Treatment Studies
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › MRI in cancer diagnosis
- Keywords
- pathological complete response, neoadjuvant chemotherapy, breast cancer, locally advanced breast cancer, multimodal prediction, pre-treatment MRI, whole slide images, clinical risk factors, deep learning, tumor immune microenvironment, immune pathways
- MeSH terms
- Deep Learning, Adult, Aged, Breast Neoplasms, Female, Humans, Magnetic Resonance Imaging, Middle Aged, Prognosis, Prospective Studies, Treatment Outcome, Neoadjuvant Therapy
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: A multimodal and fully automated system for prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer. https://app.cochat.ai/papers/10.1126/sciadv.adr1576
- The paper
- Mao, N., Dai, Y., Zhou, H., Lin, F., Zheng, T., Li, Z., Yang, P., Zhao, F., Li, Q., Wang, W., Liang, Y., Xie, H., Ma, H., Zhang, L., Guo, Y., Song, X., Zhang, H., & Lu, J. (2025). A multimodal and fully automated system for prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer. Science Advances. https://doi.org/10.1126/sciadv.adr1576
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.