23 May 2024 in Cancer Research Communications
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.
3 September 2026 in JNCI Cancer Spectrum
Background: Improving patient-centered care and communication in breast cancer remains challenging in the complex and evolving landscape of breast cancer care delivery. Methods: The SharES (Alliance A231901CD) trial (ClinicalTrials.gov NCT04549571) was carried out in collaboration with the Alliance National Cancer Institute Community Oncology Research Program Research Base to evaluate a multilevel intervention in a crossed design: (1) a patient-level randomized intervention of the evidence-based iCanDecide online tool with added emotional support enhancements, intended to promote better information uptake by supporting management of distress associated with a new diagnosis vs the standard version, and (2) a clinic-level stepped-wedge randomized clinician dashboard intervention. Patient-reported outcomes assessed 5 weeks after registration were knowledge about breast cancer locoregional treatment (primary outcome), with cancer worry and breast cancer self-efficacy as key secondary outcomes. We evaluated outcomes using linear mixed models, considering the nesting of individuals within the clinic across time periods. Results: We enrolled 542 (403 evaluable) patients and 54 clinicians across 25 surgical clinics. The CIs for all outcomes included zero but excluded prespecified clinically important differences in the knowledge score. We found good fidelity to the intervention components and considerable variation in the primary outcome across sites. Conclusions: The addition of emotional support components to a patient support tool previously found effective is unlikely to result in clinically important improvements in knowledge, cancer worry, or breast cancer self-efficacy. The strong engagement of National Cancer Institute Community Oncology Research Program sites, clinicians, and patients with the study and intervention components suggests future cancer care delivery studies could use implementation strategies to promote multilevel patient-centered communication interventions. Trial Registration: ClinicalTrials.gov NCT04549571.