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

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. SIGNIFICANCE: A deep learning algorithm can quantify tumor morphologic features that may reflect underlying mechanisms driving prognosis within MMR groups. TSR was the most robust morphologic feature associated with TTR in p-MMR colon cancers. Extent of inflammatory stroma and N stage were the strongest prognostic features in d-MMR tumors. TIL density was not independently prognostic in either MMR group.

Immediate versus delayed zoledronic acid for prevention of bone loss in postmenopausal women with breast cancer starting letrozole after tamoxifen-N03CC.

Postmenopausal women with breast cancer (BC) are at increased risk for bone loss. Bisphosphonates improve bone mineral density (BMD) in normal postmenopausal women. The purpose of this study was to determine if immediate treatment with zoledronic acid preserves BMD in postmenopausal women with BC starting letrozole after tamoxifen. Postmenopausal women with BC completing tamoxifen were treated with daily letrozole 2.5 mg/vitamin D 400 I.U., calcium 500 mg twice daily and were randomized to upfront or delayed zoledronic acid 4 mg every 6 months. Patients in the delayed arm were only given zoledronic acid if they developed a post-baseline BMD T score <-2.0 or had a fracture. The primary endpoint was the mean percent change in lumbar spine (LS) BMD at 1 year. About 558 women enrolled; 395 provided 1 year BMD data. The upfront arm experienced a mean change of +3.66% in LS BMD versus -1.66% for the delayed group (P < 0.001). Changes at the femoral neck/total hip were also greater for the upfront versus delayed arms (P < 0.001; P < 0.001) with differences persisting at 2 years. Patients in the delayed arm were more likely to experience a clinically meaningful 5% loss of BMD at all sites versus the upfront zoledronate group. Patients in the upfront arm were slightly more likely to report limb edema, fatigue, fever, nausea and jaw osteonecrosis(1%). Upfront zoledronic acid prevents bone loss in postmenopausal women with BC starting letrozole after tamoxifen.

North Central Cancer Treatment Group--achievements and perspectives.

The North Central Cancer Treatment Group (NCCTG) was founded in 1977 as a regional cooperative group to allow cancer patients in the upper Midwest of the United States to gain access to clinical trials in oncology by establishing a network of community oncology practices with one academic research base, the Mayo Clinic. Since then, the NCCTG has grown into an international cooperative group with 43 members in 33 US states and Canada. This article details 30 years of achievements of the NCCTG, including important scientific contributions from disease-specific and treatment modality committees, the cancer control program, patient-reported outcomes and quality-of-life research, and biostatisticians that support the NCCTG's specific aims: to improve the duration and quality of life of cancer patients, to enhance our understanding of the biological consequences of cancer and its treatment, and to improve methods for clinical trial conduct.