加賀谷 丈紘

BACKGROUND: Detecting pathological complete response (pCR) preoperatively facilitated a non-surgical approach after neoadjuvant chemotherapy (NAC). We previously developed a deep neural network-based endoscopic evaluation to determine pCR preoperatively. Its quality warrants improvement with a larger data series for clinical application. METHODS: This study retrospectively reviewed patients with esophageal squamous cell carcinoma (ESCC) receiving NAC at 46 Japanese esophageal centers certified by the Japan Esophageal Society. Endoscopic images after NAC were collected with clinicopathological factors and long-term outcomes. We randomly selected the same number of patients with Grades 0-1a and Grades 1b-2 based on those with pCR (Grade 3). A deep neural network was used for endoscopic image analyses. A test data set, consisting of 100 photos, was utilized for validation. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of the deep neural network-based model and experienced physicians were calculated. RESULTS: The study enrolled 1041 patients, including 354 (33%) patients with pCR, the same number of histological non-responders (Grade 0-1a/1b-2, 352 [33%]/368 [34%]). The median values of sensitivity, specificity, PPV, NPV, and accuracy for pCR detection were 80%, 90%, 89%, 82%, and 85%, respectively. The patients with pCR preoperatively demonstrated significantly better overall survival and recurrence-free survival. CONCLUSIONS: This large-scale study revealed that the deep neural network-based endoscopic evaluation after NAC identified pCR with feasible accuracy. The current artificial intelligence technology may guide an individualized treatment strategy, including a non-surgical approach, in patients with ESCC through prospective studies with careful external validation.

BACKGROUND: This study aimed to elucidate the clinical impact of osteopenia on the recurrence of colon cancer liver metastases. METHODS: Patients with colon cancer liver metastases (N = 186) undergoing hepatectomy at Jichi Medical University Hospital between March 2006 and March 2020 were examined retrospectively. Computed tomography (CT) scans on the 11th vertebra within 3 months of surgery assessed bone mineral density (BMD). Age-adjusted BMD determined osteopenia presence. Kaplan-Meier method with a log-rank test estimated survival. Factors associated with survival were assessed using Cox's proportional hazards model after adjustment for confounders. RESULTS: Patients with osteopenia had shorter overall (p = 0.0001; 5-year overall survival, 51.8% vs 81.8%) and recurrence-free survival (p = 0.0008, 5-year recurrence-free survival: 26.3% vs 51.5%) than BMD-normal patients. In multivariable analysis, the risk factor for overall survival was osteopenia (Hazard ratio (HR) 3.79, 95% confidence interval (CI) 2.09-6.87, p = 0.001). Risk factors for recurrence were chemotherapy (HR 1.92, 95%CI 1.12-3.30, p = 0.002), tumor number (HR 1.51, 95%CI 1.02-2.27, p = 0.04), and osteopenia (HR 2.18, 95%CI 1.46-3.24 p = 0.001). Patients with osteopenia are more likely to develop lung metastases, and BMD-value reduction associated with KRAS mutation. CONCLUSION: Osteopenia may have prognostic significance in patients with liver metastases colorectal cancer.

BACKGROUND: Osteopenia reflects frailty and has been shown to be associated with outcomes in cancer patients. This study was undertaken to examine whether osteopenia is an independent prognostic factor in patients with esophageal cancer after resection. METHODS: A total of 214 patients who underwent surgery for esophageal cancer were analyzed retrospectively. Bone mineral density (BMD) of the 11th thoracic vertebra was measured by computed tomography scan, and patients classified into osteopenia and normal BMD groups with BMD <160 Hounsfield units as the cutoff. Clinicopathological data and prognosis were analyzed. RESULTS: The 5-year survival rate was 55.4% for the osteopenia group and 74.7% for the normal BMD group with a significantly worse prognosis in the osteopenia group (p = 0.0080). In multivariable analysis, osteopenia was a significant independent risk factor associated with overall survival (hazard ratio [HR] 1.90, 95% confidence interval [CI] 1.27-3.34, and p = 0.0151) along with R1/2 resection (HR 3.02, 95% CI 1.71-5.18, and p = 0.0002). CONCLUSION: In patients with esophageal cancer undergoing resection, osteopenia may be a surrogate marker for frailty and an independent predictor of prognosis.