Deep Learning Predicts Underlying Features on Pathology Images with Therapeutic Relevance for Breast and Gastric Cancer

Valieris, Renan; Amaro, Lucas; Osório, Cynthia Aparecida Bueno de Toledo; Bueno, Adriana Passos; Rosales Mitrowsky, Rafael Andres; Carraro, Dirce Maria; Nunes, Diana Noronha; Dias-Neto, Emmanuel; Silva, Israel Tojal da

doi:10.3390/cancers12123687

Submit to this Journal Review for this Journal Edit a Special Issue

Article Menu

...

Open AccessArticle

Deep Learning Predicts Underlying Features on Pathology Images with Therapeutic Relevance for Breast and Gastric Cancer

Renan Valieris

^1,†

Lucas Amaro

^1,†,

Cynthia Aparecida Bueno de Toledo Osório

²,

Adriana Passos Bueno

^1,2,

Rafael Andres Rosales Mitrowsky

³,

Dirce Maria Carraro

⁴,

Diana Noronha Nunes

⁵,

Emmanuel Dias-Neto

⁵

and

Israel Tojal da Silva

^1,*

Laboratory of Computational Biology Bioinformatics, CIPE/A.C. Camargo Cancer Center, São Paulo 01508-010, Brazil

Department of Pathology, CIPE/A.C. Camargo Cancer Center, São Paulo 01525-001, Brazil

Department of Computation and Mathematics, University of São Paulo, Ribeirão Preto 14040-901, Brazil

⁴

Laboratory of Genomics and Molecular Biology, CIPE/A.C. Camargo Cancer Center, São Paulo 01508-010, Brazil

⁵

Medical Genomics Laboratory, CIPE/A.C. Camargo Cancer Center, São Paulo 01525-001, Brazil

Author to whom correspondence should be addressed.

^†

These authors contributed equally to this work.

Cancers 2020, 12(12), 3687; https://doi.org/10.3390/cancers12123687

Received: 13 October 2020 / Revised: 4 November 2020 / Accepted: 6 November 2020 / Published: 9 December 2020

(This article belongs to the Special Issue Surgical Pathology in the Digital Era)

View Full-Text Download PDF

Browse Figures

Citation Export

Simple Summary

DNA repair deficiency (DRD) is common in many cancers. This deficiency contributes to pathogenesis of the disease, but it also presents an opportunity for therapeutic targeting. However, current DRD identification assays are not available for all patients. We propose an efficient machine learning algorithm which can predict DRD from histopathological images. The utility of our method was shown by considering the detection of homologous recombination deficiency (HRD) and mismatch repair deficiency (MMRD) in breast and gastric cancer respectively. Our findings demonstrate that machine-learning approaches can be used in advanced applications to assist therapy decisions.

Abstract

DNA repair deficiency (DRD) is an important driver of carcinogenesis and an efficient target for anti-tumor therapies to improve patient survival. Thus, detection of DRD in tumors is paramount. Currently, determination of DRD in tumors is dependent on wet-lab assays. Here we describe an efficient machine learning algorithm which can predict DRD from histopathological images. The utility of this algorithm is demonstrated with data obtained from 1445 cancer patients. Our method performs rather well when trained on breast cancer specimens with homologous recombination deficiency (HRD), AUC (area under curve) = 0.80. Results for an independent breast cancer cohort achieved an AUC = 0.70. The utility of our method was further shown by considering the detection of mismatch repair deficiency (MMRD) in gastric cancer, yielding an AUC = 0.81. Our results demonstrate the capacity of our learning-base system as a low-cost tool for DRD detection. View Full-Text

Keywords: digital pathology; deep learning; mutational signature; biomarker; DNA repair deficiency

▼ Show Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited

Supplementary Material

Supplementary File 1:
ZIP-Document (ZIP, 1462 KiB)

Share and Cite

MDPI and ACS Style

Valieris, R.; Amaro, L.; Osório, C.A.B.d.T.; Bueno, A.P.; Rosales Mitrowsky, R.A.; Carraro, D.M.; Nunes, D.N.; Dias-Neto, E.; Silva, I.T.d. Deep Learning Predicts Underlying Features on Pathology Images with Therapeutic Relevance for Breast and Gastric Cancer. Cancers 2020, 12, 3687. https://doi.org/10.3390/cancers12123687

AMA Style

Valieris R, Amaro L, Osório CABdT, Bueno AP, Rosales Mitrowsky RA, Carraro DM, Nunes DN, Dias-Neto E, Silva ITd. Deep Learning Predicts Underlying Features on Pathology Images with Therapeutic Relevance for Breast and Gastric Cancer. Cancers. 2020; 12(12):3687. https://doi.org/10.3390/cancers12123687

Chicago/Turabian Style

Valieris, Renan, Lucas Amaro, Cynthia A.B.d.T. Osório, Adriana P. Bueno, Rafael A. Rosales Mitrowsky, Dirce M. Carraro, Diana N. Nunes, Emmanuel Dias-Neto, and Israel T.d. Silva. 2020. "Deep Learning Predicts Underlying Features on Pathology Images with Therapeutic Relevance for Breast and Gastric Cancer" Cancers 12, no. 12: 3687. https://doi.org/10.3390/cancers12123687

Find Other Styles

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Metrics

Abstract views Pdf views Html views

Article Menu

Deep Learning Predicts Underlying Features on Pathology Images with Therapeutic Relevance for Breast and Gastric Cancer

Simple Summary

Abstract

Supplementary Material

Share and Cite

Article Metrics

Article Access Statistics

Article Access Map by Country/Region

Further Information

Guidelines

MDPI Initiatives

Follow MDPI