Use of Deep Learning to Evaluate Tumor Microenvironmental Features for Prediction of Colon Cancer Recurrence.

Journal: Cancer research communications
PMID:

Abstract

UNLABELLED: Deep learning may detect biologically important signals embedded in tumor morphologic features that confer distinct prognoses. Tumor morphologic features were quantified to enhance patient risk stratification within DNA mismatch repair (MMR) groups using deep learning. Using a quantitative segmentation algorithm (QuantCRC) that identifies 15 distinct morphologic features, we analyzed 402 resected stage III colon carcinomas [191 deficient (d)-MMR; 189 proficient (p)-MMR] from participants in a phase III trial of FOLFOX-based adjuvant chemotherapy. Results were validated in an independent cohort (176 d-MMR; 1,094 p-MMR). Association of morphologic features with clinicopathologic variables, MMR, KRAS, BRAFV600E, and time-to-recurrence (TTR) was determined. Multivariable Cox proportional hazards models were developed to predict TTR. Tumor morphologic features differed significantly by MMR status. Cancers with p-MMR had more immature desmoplastic stroma. Tumors with d-MMR had increased inflammatory stroma, epithelial tumor-infiltrating lymphocytes (TIL), high-grade histology, mucin, and signet ring cells. Stromal subtype did not differ by BRAFV600E or KRAS status. In p-MMR tumors, multivariable analysis identified tumor-stroma ratio (TSR) as the strongest feature associated with TTR [HRadj 2.02; 95% confidence interval (CI), 1.14-3.57; P = 0.018; 3-year recurrence: 40.2% vs. 20.4%; Q1 vs. Q2-4]. Among d-MMR tumors, extent of inflammatory stroma (continuous HRadj 0.98; 95% CI, 0.96-0.99; P = 0.028; 3-year recurrence: 13.3% vs. 33.4%, Q4 vs. Q1) and N stage were the most robust prognostically. Association of TSR with TTR was independently validated. In conclusion, QuantCRC can quantify morphologic differences within MMR groups in routine tumor sections to determine their relative contributions to patient prognosis, and may elucidate relevant pathophysiologic mechanisms driving prognosis.

Authors

  • Frank A Sinicrope
    Departments of Medicine and Oncology, Rochester, Minnesota.
  • Garth D Nelson
    Division of Clinical Trials and Biostatistics, Mayo Clinic, Rochester, Minnesota.
  • Bahar Saberzadeh-Ardestani
    Gastrointestinal Research Unit, Mayo Clinic, Rochester, Minnesota.
  • Diana I Segovia
    Division of Clinical Trials and Biostatistics, Mayo Clinic, Rochester, Minnesota.
  • Rondell P Graham
    Mayo Clinic, Rochester, MN, USA.
  • Christina Wu
    Division of Medical Oncology, Mayo Clinic, Phoenix, Arizona.
  • Catherine E Hagen
    Department of Pathology and Laboratory Medicine, Mayo Clinic Rochester, Rochester, Minnesota, USA.
  • Sameer Shivji
    Department of Pathology, Mount Sinai Hospital, Toronto, Ontario, Canada.
  • Paul Savage
    Mount Sinai Hospital, Toronto, Ontario, Canada.
  • Dan D Buchanan
    Colorectal Oncogenomics Group, Department of Clinical Pathology, The University of Melbourne, Parkville, Victoria, Australia.
  • Mark A Jenkins
    Centre for Epidemiology and Biostatistics, Melbourne School of Population and Global Health, The University of Melbourne, Melbourne, Victoria, Australia.
  • Amanda I Phipps
    Department of Epidemiology, University of Washington, Seattle.
  • Carol Swallow
    Lunenfeld-Tanenbaum Research Institute, Toronto, Ontario, Canada.
  • Loic LeMarchand
    Department of Epidemiology, University of Hawaii, Honolulu, Hawaii.
  • Steven Gallinger
    Lunenfeld-Tanenbaum Research Institute, Sinai Health System, Toronto, ON, Canada.
  • Robert C Grant
    Princess Margaret Cancer Centre, University Health Network, Toronto, ON, Canada.
  • Reetesh K Pai
    Department of Pathology, University of Pittsburgh Medical Center, Pittsburgh, PA, USA.
  • Stephen N Sinicrope
    University of Chicago Medical Center, Chicago, Illinois.
  • Dongyao Yan
    Roche Tissue Diagnostics, Medical and Scientific Affairs, Tucson, Arizona.
  • Kandavel Shanmugam
    Roche Tissue Diagnostics, Medical and Scientific Affairs, Tucson, Arizona. kandavel.shanmugam@roche.com.
  • James Conner
    Department of Pathology, Mount Sinai Hospital, Toronto, Ontario, Canada.
  • David P Cyr
    Lunenfeld-Tanenbaum Research Institute, Toronto, Ontario, Canada.
  • Richard Kirsch
    Department of Pathology, Mount Sinai Hospital, Toronto, Ontario, Canada.
  • Imon Banerjee
    Mayo Clinic, Department of Radiology, Scottsdale, AZ, USA.
  • Steve R Alberts
    Department of Oncology, Mayo Clinic, Rochester, Minnesota.
  • Qian Shi
    School of Electrical Information Engineering, Jiangsu University, Zhenjiang, Jiangsu 212013, China.
  • Rish K Pai
    Department of Pathology and Laboratory Medicine, Mayo Clinic Arizona, Scottsdale, AZ, USA.