Gene expression profiling (GEP) provides valuable information for the care of breast cancer patients. However, the test itself is expensive and can take a long time to process. In contrast, microscopic examination of hematoxylin and eosin (H&E) stained tissue is inexpensive, fast, and integrated into the standard of care. This work explores the possibility of predicting ESR1 gene expression from H&E images, and its use in predicting clinical variables and patient outcomes. We utilized a weakly supervised method to train a deep learning model to predictESR1expression from whole slide images, and achieved 0.57 [95% CI: 0.46, 0.67] Pearson's correlation with the ground truth value. Our ESR1 expression prediction achieved an AUROC of 0.81 [0.74, 0.87] in predicting clinical ER status obtained using an immunohistochemistry staining technique, and a c-index of 0.59 [0.52,0.65] in predicting progression-free interval for the patients in our cohort. This work further demonstrates the potential to infer gene expression from H&E stained images in a manner that shows meaningful associations with clinical variables. Because obtaining H&E stained images is substantially easier and faster than genetic testing, the capability to derive molecular genetic information from these images may increase access to this type of information for patient risk stratification and provide research insights into molecular-morphological associations.

The authors have declared no competing interest.

The study was funded by Google LLC.

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:

Advarra institutional review board waived ethical approval for this work.

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the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