Spatially aware deep learning reveals tumor heterogeneity patterns that encode distinct kidney cancer states

Jackson Nyman; Thomas Denize; Ziad Bakouny; Chris Labaki; Breanna M Titchen; Kevin Bi; Surya Narayanan Hari; Jacob Rosenthal; Nicita Mehta; Bowen Jiang; Bijaya Sharma; Kristen Felt; Renato Umeton; David A Braun; Scott Rodig; Toni K Choueiri; Sabina Signoretti; Eliezer M Van Allen

doi:10.1016/j.xcrm.2023.101189

Spatially aware deep learning reveals tumor heterogeneity patterns that encode distinct kidney cancer states

Cell Rep Med. 2023 Sep 19;4(9):101189. doi: 10.1016/j.xcrm.2023.101189.

Authors

Jackson Nyman¹, Thomas Denize², Ziad Bakouny³, Chris Labaki⁴, Breanna M Titchen⁵, Kevin Bi⁶, Surya Narayanan Hari⁶, Jacob Rosenthal⁷, Nicita Mehta⁸, Bowen Jiang⁹, Bijaya Sharma¹⁰, Kristen Felt¹⁰, Renato Umeton¹¹, David A Braun¹², Scott Rodig², Toni K Choueiri¹³, Sabina Signoretti¹⁴, Eliezer M Van Allen¹⁵

Affiliations

¹ Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, USA; Harvard Graduate Program in Systems Biology, Cambridge, MA, USA; Broad Institute, Cambridge, MA, USA.
² Department of Pathology, Brigham and Women's Hospital, Boston, MA, USA.
³ Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, USA; Broad Institute, Cambridge, MA, USA; Department of Medicine, Brigham and Women's Hospital, Boston, MA, USA; Harvard Medical School, Boston, MA, USA; Department of Medicine, Memorial Sloan Kettering Cancer Center, New York, NY, USA.
⁴ Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, USA; Broad Institute, Cambridge, MA, USA; Harvard Medical School, Boston, MA, USA; Department of Medicine, Beth Israel Deaconess Medical Center, Boston, MA, USA.
⁵ Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, USA; Broad Institute, Cambridge, MA, USA; Harvard Graduate Program in Biological and Biomedical Sciences, Boston, MA, USA.
⁶ Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, USA; Broad Institute, Cambridge, MA, USA.
⁷ Department of Informatics & Analytics, Dana-Farber Cancer Institute, Boston, MA, USA; Department of Pathology and Laboratory Medicine, Weill Cornell Medicine, New York, NY, USA.
⁸ Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, USA; Broad Institute, Cambridge, MA, USA; Harvard Medical School, Boston, MA, USA.
⁹ Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, USA; Broad Institute, Cambridge, MA, USA; Stanford University, Stanford, CA, USA.
¹⁰ ImmunoProfile, Department of Pathology, Brigham & Women's Hospital and Dana-Farber Cancer Institute, Boston, MA, USA.
¹¹ Department of Informatics & Analytics, Dana-Farber Cancer Institute, Boston, MA, USA; Department of Pathology and Laboratory Medicine, Weill Cornell Medicine, New York, NY, USA; Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA; Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA.
¹² Center of Molecular and Cellular Oncology, Yale Cancer Center, Yale School of Medicine, New Haven, CT, USA.
¹³ Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, USA; Harvard Medical School, Boston, MA, USA; Brigham and Women's Hospital, Boston, MA, USA.
¹⁴ Broad Institute, Cambridge, MA, USA; Department of Pathology, Brigham and Women's Hospital, Boston, MA, USA; Harvard Medical School, Boston, MA, USA; Department of Oncologic Pathology, Dana-Farber Cancer Institute, Boston, MA, USA.
¹⁵ Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, USA; Broad Institute, Cambridge, MA, USA; Harvard Medical School, Boston, MA, USA; Department of Population Sciences, Dana-Farber Cancer Institute, Boston, MA, USA. Electronic address: [email protected].

Abstract

Clear cell renal cell carcinoma (ccRCC) is molecularly heterogeneous, immune infiltrated, and selectively sensitive to immune checkpoint inhibition (ICI). However, the joint tumor-immune states that mediate ICI response remain elusive. We develop spatially aware deep-learning models of tumor and immune features to learn representations of ccRCC tumors using diagnostic whole-slide images (WSIs) in untreated and treated contexts (n = 1,102 patients). We identify patterns of grade heterogeneity in WSIs not achievable through human pathologist analysis, and these graph-based "microheterogeneity" structures associate with PBRM1 loss of function and with patient outcomes. Joint analysis of tumor phenotypes and immune infiltration identifies a subpopulation of highly infiltrated, microheterogeneous tumors responsive to ICI. In paired multiplex immunofluorescence images of ccRCC, microheterogeneity associates with greater PD1 activation in CD8⁺ lymphocytes and increased tumor-immune interactions. Our work reveals spatially interacting tumor-immune structures underlying ccRCC biology that may also inform selective response to ICI.

Keywords: AI; artificial intelligence; computational histopathology; computer vision; deep learning; immunotherapy; kidney cancer; precision medicine; tumor heterogeneity.

Publication types

Research Support, U.S. Gov't, Non-P.H.S.
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't

MeSH terms

Carcinoma*
Carcinoma, Renal Cell* / genetics
Deep Learning*
Humans
Kidney Neoplasms*
Phenotype

Abstract

Publication types

MeSH terms

Grants and funding