Artificial Intelligence-Based Prediction of Recurrence after Curative Resection for Colorectal Cancer from Digital Pathological Images.

BACKGROUND: To develop an artificial intelligence-based model to predict recurrence after curative resection for stage I-III colorectal cancer from digitized pathological slides. PATIENTS AND METHODS: In this retrospective study, 471 consecutive patients who underwent curative resection for stage I-III colorectal cancer at our institution from 2004 to 2015 were enrolled, and 512 randomly selected tiles from digitally scanned images of hematoxylin and eosin-stained tumor tissue sections were used to train a convolutional neural network. Five-fold cross-validation was used to validate the model. The association between recurrence and the model's output scores were analyzed in the test cohorts. RESULTS: The area under the receiver operating characteristic curve of the cross-validation was 0.7245 [95% confidence interval (CI) 0.6707-0.7783; P < 0.0001]. The score successfully classified patients into those with better and worse recurrence free survival (P < 0.0001). Multivariate analysis revealed that a high score was significantly associated with worse recurrence free survival [odds ratio (OR) 1.857; 95% CI 1.248-2.805; P = 0.0021], which was independent from other predictive factors: male sex (P = 0.0238), rectal cancer (P = 0.0396), preoperative abnormal carcinoembryonic antigen (CEA) level (P = 0.0216), pathological T3/T4 stage (P = 0.0162), and pathological positive lymph node metastasis (P < 0.0001). CONCLUSIONS: The artificial intelligence-based prediction model discriminated patients with a high risk of recurrence. This approach could help decision-makers consider the benefits of adjuvant chemotherapy.

Clinical significance of signal regulatory protein alpha (SIRPα) expression in esophageal squamous cell carcinoma.

Signal regulatory protein alpha (SIRPα) is a type I transmembrane protein that inhibits macrophage phagocytosis of tumor cells upon interaction with CD47, and the CD47-SIRPα pathway acts as an immune checkpoint factor in cancers. This study aims to clarify the clinical significance of SIRPα expression in esophageal squamous cell carcinoma (ESCC). First, we assessed SIRPα expression using RNA sequencing data of 95 ESCC tissues from The Cancer Genome Atlas (TCGA) and immunohistochemical analytic data from our cohort of 131 patients with ESCC. Next, we investigated the correlation of SIRPα expression with clinicopathological factors, patient survival, infiltration of tumor immune cells, and expression of programmed cell death-ligand 1 (PD-L1). Overall survival was significantly poorer with high SIRPα expression than with low expression in both TCGA and our patient cohort (P < .001 and P = .027, respectively). High SIRPα expression was associated with greater depth of tumor invasion (P = .0017). Expression of SIRPα was also significantly correlated with the tumor infiltration of M1 macrophages, M2 macrophages, CD8+ T cells, and PD-L1 expression (P < .001, P < .001, P = .03, and P < .001, respectively). Moreover, patients with SIRPα/PD-L1 coexpression tended to have a worse prognosis than patients with expression of either protein alone or neither. Taken together, SIRPα indicates poor prognosis in ESCC, possibly through inhibiting macrophage phagocytosis of tumor cells and inducing suppression of antitumor immunity. Signal regulatory protein alpha should be considered as a potential therapeutic target in ESCC, especially if combined with PD-1-PD-L1 blockade.

Radiomics Texture Analysis for the Identification of Colorectal Liver Metastases Sensitive to First-Line Oxaliplatin-Based Chemotherapy.

OBJECTIVE: The aim of this study was to develop a radiomics-based prediction model for the response of colorectal liver metastases to oxaliplatin-based chemotherapy. METHODS: Forty-two consecutive patients treated with oxaliplatin-based first-line chemotherapy for colorectal liver metastasis at our institution from August 2013 to October 2019 were enrolled in this retrospective study. Overall, 126 liver metastases were chronologically divided into the training (n = 94) and validation (n = 32) cohorts. Regions of interest were manually segmented, and the best response to chemotherapy was decided based on Response Evaluation Criteria in Solid Tumors (RECIST). Patients who achieved clinical complete and partial response according to RECIST were defined as good responders. Radiomics features were extracted from the pretreatment enhanced computed tomography scans, and a radiomics score was calculated using the least absolute shrinkage and selection operator regression model in a trial cohort. RESULTS: The radiomics score significantly discriminated good responders in both the trial (area under the curve [AUC] 0.8512, 95% confidence interval [CI] 0.7719-0.9305; p < 0.0001) and validation (AUC 0.7792, 95% CI 0.6176-0.9407; p < 0.0001) cohorts. Multivariate analysis revealed that high radiomics scores greater than - 0.06 (odds ratio [OR] 23.803, 95% CI 8.432-80.432; p < 0.0001), clinical non-T4 (OR 6.054, 95% CI 2.164-18.394; p = 0.0005), and metachronous disease (OR 11.787, 95% CI 2.333-70.833; p = 0.0025) were independently associated with good response. CONCLUSIONS: Radiomics signatures may be a potential biomarker for the early prediction of chemosensitivity in colorectal liver metastases. This approach may support the treatment strategy for colorectal liver metastasis.

Primary amelanotic malignant melanoma of the esophagus: a case report.

BACKGROUND: Primary amelanotic malignant melanoma of esophagus, which is a subtype of primary malignant melanoma of the esophagus (PMME), is a very rare disease with a poor prognosis. We herein report a case of the amelanotic type of PMME. CASE PRESENTATION: An 86-year-old woman was admitted to our hospital with symptoms of dysphagia. An endoscopic examination and constructed radiography revealed an elevated and semipedunculated lesion with an ulcer in the lower thoracic esophagus accompanied by another submucosal lesion of the esophagus. She was diagnosed with esophageal squamous cell carcinoma by a preoperative endoscopic biopsy. We performed thoracoscopy- and laparoscopy-assisted subtotal esophagectomy with lymphadenectomy. Based on the surgical specimens, although there were no melanocytes, we made a diagnosis of a malignant melanoma immunohistochemically; the tumor cells were positive for S-100 protein and HMB45 focally and partially for Melan-A. CONCLUSION: We experienced a case of primary amelanotic malignant melanoma, and the patient has remained disease-free for 1 year since the surgery. Since the diagnosis of amelanotic type of PMME is difficult, it should be made by the combination of a morphological examination, pathological examination, and immunohistochemistry.