Purpose To test whether histology-derived gene-expression signatures from routine hematoxylin and eosin slides are prognostic for recurrence and predictive of chemotherapy benefit in early breast cancer.

Methods We conducted a multi-cohort study including CALGB 9344 (anthracycline ± paclitaxel), CALGB 9741 (standard vs dose-dense chemotherapy), a pooled Chicago real-world cohort, and the American Cancer Society (ACS) Cancer Prevention Studies-II and -3. Whole-slide images were processed with a previously described pipeline to generate 61 histology-derived signatures per patient. The primary endpoint was distant recurrence-free interval (DRFI), except in ACS, where breast cancer-specific survival was used. Secondary endpoints include distant recurrence-free survival (DRFS) and overall survival. The most prognostic signature in CALGB 9344, selected by Harrell’s C-index, was evaluated in additional cohorts. Signature-treatment interaction was assessed by likelihood-ratio tests. Multivariable Cox models incorporating age, tumor size, nodal status, estrogen/progesterone receptor status, and signature were fit in CALGB 9344 to improve risk stratification.

Results A total of 7,170 patients were included across four cohorts. The top histology-derived signature in CALGB 9344 showed strong prognostic performance for 5-year DRFI (C-index 0.63) and performed well across validation cohorts (C-index 0.60, 0.70, and 0.62 in CALGB 9741, Chicago, and ACS, respectively). The strongest predictive signal for treatment benefit was observed for DRFS. High-risk cases identified by the signature demonstrated greater benefit from taxane in CALGB 9344 (adjusted hazard ratio [aHR] 0.76 for DRFS, 95% CI 0.66-0.88; interaction p=0.028), from dose-dense chemotherapy in CALGB 9741 (aHR 0.69, 95% CI 0.56-0.85; interaction p=0.039), and differential chemotherapy benefit in the Chicago cohort (aHR 0.84, 95% CI 0.59-1.21; interaction p=0.009). Combined clinical-histology models improved risk stratification and identified low-risk groups with a 2%-10% risk of distant recurrence or breast cancer death.

Conclusion Histology-derived signatures from H&E images are broadly prognostic and, unlike clinical factors, may predict chemotherapy benefit.

Highlights

Histology-derived H&E signatures consistently predicted recurrence risk across randomized trials and real-world cohorts.

A single cutoff of a low-risk histology signature predicted taxane benefit and dose-dense chemotherapy benefit.

Combined clinical-histology models identified low-risk groups with 2%-10% risk of distant recurrence.

FMH reports consulting fees from Novartis and Leica Biosystems, advisory board participation with Exact Sciences, and stock ownership from Celcuity. ATP reports consulting fees from Prelude Biotherapeutics, LLC, Ayala Pharmaceuticals, Elvar Therapeutics, Abbvie, and Privo, and contracted research with Kura Oncology, Abbvie, and EMD Serono. CMP is an equity stockholder and consultant of BioClassifier LLC; CMP is also listed as an inventor on patent applications for the Breast PAM50 Subtyping assay. WFS reports stock / ownership interests in ISIS Pharmaceuticals, Delphi Diagnostics, and Eiger BioPharmaceuticals, consulting / advisory role for AstraZeneca, SAGA Diagnostics, and other uncompensated relationships with Delphi Diagnostics. DS reports consulting / advisory role for Guardant Health and Natera, research funding from NeoGenomics Laboratories and Foundation Medicine. LC reports research funding from NanoString Technologies, Seagen, Veracyte, Gilead Sciences, Novartis, and other uncompensated relationships with Lilly, SeaGen, Gilead Sciences, Reveal Genomics, Novartis. OIO reports support from Healthy Life for All Foundation, other support from CancerIQ, grants and other support from Tempus, and grants from Color Genomics outside the submitted work. RN reports consulting funding from Astrazeneca, Daiichi Sankyo, Exact Sciences, GE, Gilead, Guardant Health, Merck, Moderna, Novartis, OBI, Pfizer, Sanofi, Seagen, Stemline, Summit Therapeutics and research funding from Arvinas, AstraZeneca, BMS, Corcept Therapeutics, Genentech/Roche, Gilead, GSK, Merck, Novartis, OBI Pharma, OncoSec, Pfizer, Relay, Seagen, Sun Pharma, Taiho. All other authors declare no competing interests.

NCT00003088

Cancer and Leukemia Group B (CALGB) is now part of the Alliance for Clinical Trials in Oncology, a National Clinical Trials Network cooperative group. Data and slides from studies CALGB 9344 and CALGB 9741 were obtained from the Alliance for Clinical Trials in Oncology, under Alliance data sharing agreement A152324. The authors express sincere appreciation to all Cancer Prevention Study-II and Cancer Prevention Study-3 participants, and to each member of the study and biospecimen management group. The authors would like to acknowledge the contribution to this study from central cancer registries supported through the Centers for Disease Control and Prevention's National Program of Cancer Registries and cancer registries supported by the National Cancer Institute's Surveillance Epidemiology and End Results Program. Through acceptance of this federal funding, NIH has been given a right to make the Author Accepted Manuscript publicly available in PubMed Central upon the Official Date of Publication, as defined by NIH. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health or the American Cancer Society or American Cancer Society -- Cancer Action Network. This manuscript is the result of funding in whole or in part by the National Cancer Institute of the National Institutes of Health (NIH) under Award Numbers U10CA180821, and U24CA196171 (to the Alliance for Clinical Trials in Oncology), UG1CA233327, UG1CA189847, UG1CA233329, UG1CA233373, UG1CA233180, UG1CA233290, UG1CA233331, and UG1CA233339. Also supported in part by Bristol Myers Squibb (CALGB 9344). This work was also supported by the following research grants: National Cancer Institutes grant K08CA283261 (FMH) Cancer Research Foundation grant (FMH) Lynn Sage Breast Cancer Foundation (FMH) Alliance Foundation Trials Special Projects Award (FMH) Breast Cancer Research Foundation Next Generation Award (FMH) National Institute of Dental and Craniofacial Research grant R56DE030958, (ATP) National Cancer Institutes grant R01CA276652 (ATP) European Commission Horizon grant 2021-SC1-BHC, (ATP) Adenoid Cystic Carcinoma Research Foundation grant (ATP) Cancer Research Foundation grant (ATP) American Cancer Society grant (ATP) Department of Defense grant BC211095P1 (FMH, ATP) National Cancer Institutes grant P50CA058223 (CMP) Breast Cancer Research Foundation BCRF-23-127, (CMP) Stand Up To Cancer grant (ATP)

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

IRB of University of Chicago gave ethical approval for this work (IRB 22-0707).

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

De-identified patient data from the CALGB 9344 and 9741 trials may be requested from Alliance for Clinical Trials in Oncology via Datasharingalliancenctn.org if data are not publicly available. A formal review process includes verifying the availability of data, conducting a review of any existing agreements that may have implications for the project, and ensuring that any transfer is in compliance with the IRB. The investigator will be required to sign a data release form prior to transfer. Data from the Cancer Prevention Studies are available from the American Cancer Society by following the ACS Data Access Procedures (https://www.cancer.org/research/population-science/research-collaboration.html) for researchers who meet the criteria for access to confidential data. Please email cohort.datacancer.org to inquire about access. Data from the Chicago cohort can be obtained via reasonable request to study authors. All code and trained models used for this analysis are available at https://github.com/fmhoward/TIGER.