Development and interpretation of a pathomics-based model for the prediction of microsatellite instability in Colorectal Cancer.

Microsatellite instability (MSI) has been approved as a pan-cancer biomarker for immune checkpoint blockade (ICB) therapy. However, current MSI identification methods are not available for all patients. We proposed an ensemble multiple instance deep learning model to predict microsatellite status based on histopathology images, and interpreted the pathomics-based model with multi-omics correlation. Methods: Two cohorts of patients were collected, including 429 from The Cancer Genome Atlas (TCGA-COAD) and 785 from an Asian colorectal cancer (CRC) cohort (Asian-CRC). We established the pathomics model, named Ensembled Patch Likelihood Aggregation (EPLA), based on two consecutive stages: patch-level prediction and WSI-level prediction. The initial model was developed and validated in TCGA-COAD, and then generalized in Asian-CRC through transfer learning. The pathological signatures extracted from the model were analyzed with genomic and transcriptomic profiles for model interpretation. Results: The EPLA model achieved an area-under-the-curve (AUC) of 0.8848 (95% CI: 0.8185-0.9512) in the TCGA-COAD test set and an AUC of 0.8504 (95% CI: 0.7591-0.9323) in the external validation set Asian-CRC after transfer learning. Notably, EPLA captured the relationship between pathological phenotype of poor differentiation and MSI (P < 0.001). Furthermore, the five pathological imaging signatures identified from the EPLA model were associated with mutation burden and DNA damage repair related genotype in the genomic profiles, and antitumor immunity activated pathway in the transcriptomic profiles. Conclusions: Our pathomics-based deep learning model can effectively predict MSI from histopathology images and is transferable to a new patient cohort. The interpretability of our model by association with pathological, genomic and transcriptomic phenotypes lays the foundation for prospective clinical trials of the application of this artificial intelligence (AI) platform in ICB therapy.

Radiomics-based nomogram using CT imaging for noninvasive preoperative prediction of early recurrence in patients with hepatocellular carcinoma.

PURPOSE: The aim of this study was to develop and validate a radiomics nomogram based on radiomics features and clinical data for the non-invasive preoperative prediction of early recurrence (≤2 years) in patients with hepatocellular carcinoma (HCC). METHODS: We enrolled 262 HCC patients who underwent preoperative contrast-enhanced computed tomography and curative resection (training cohort, n=214; validation cohort, n=48). We applied propensity score matching (PSM) to eliminate redundancy between clinical characteristics and image features, and the least absolute shrinkage and selection operator (LASSO) was used to prevent overfitting. Next, a radiomics signature, clinical nomogram, and combined clinical-radiomics nomogram were built to predict early recurrence, and we compared the performance and generalization of these models. RESULTS: The radiomics signature stratified patients into low-risk and high-risk, which show significantly difference in recurrence free survival and overall survival (P ≤ 0.01). Multivariable analysis identified dichotomised radiomics signature, alpha fetoprotein, and tumour number and size as key early recurrence indicators, which were incorporated into clinical and radiomics nomograms. The radiomics nomogram showed the highest area under the receiver operating characteristic curve (AUC), with significantly superior predictive performance over the clinical nomogram in the training cohort (0.800 vs 0.716, respectively; P = 0.001) and the validation cohort (0.785 vs 0.654, respectively; P = 0.039). CONCLUSION: The radiomics nomogram is a non-invasive preoperative biomarker for predicting early recurrence in patients with HCC. This model may be of clinical utility for guiding surveillance follow-ups and identifying optimal interventional strategies.

Smoking Exposure and Survival of Patients with Esophagus Cancer: A Systematic Review and Meta-Analysis.

Smoking is a well-known major risk factor in development of esophageal cancer, but few studies have reported the association between smoking status and prognosis of these patients. We conduct the present study to summarize current evidence. A computerized search of the PubMed and EMBASE was performed up to April 30, 2015. Eight studies, containing 4,286 patients, were analyzed. In the grouping analysis, among esophageal squamous-cell carcinoma patients, current and former smokers, compared to those who have never smoked, seemed to have a poorer prognosis (HR = 1.41, 95% CI 1.22-1.64, and HR = 1.35, 95% CI 0.92-1.97, resp.). In the subgroup analysis, adverse effects on current smoker compared with never smoker were also observed in China and the other countries (HR = 1.5, 95% CI 1.18-1.92, and HR = 1.36, 95% CI 1.12-1.65, resp.). In the group that ever smoked, we could not get a similar result. No significantly increased risk was found in esophageal adenocarcinoma patients compared to the squamous-cell histology ones. In the smoking intensity analysis, heavy smoking was associated with poor survival in esophageal squamous-cell carcinoma. Our pooled results supported the existence of harmful effects of smoking on survival after esophagus cancer diagnosis.

Efficacy of adding bevacizumab in the first-line chemotherapy of metastatic colorectal cancer: evidence from seven randomized clinical trials.

Background. Efficacy of adding bevacizumab in first-line chemotherapy of metastatic colorectal cancer (mCRC) has been controversial. The aim of this study is to gather current data to analyze efficacy of adding bevacizumab to the most used combination first-line chemotherapy in mCRC, based on the 2012 meta-analysis reported by Macedo et al. Methods. Medline, EMBASE and Cochrane library, meeting presentations and abstracts were searched. Eligible studies were randomized controlled trials (RCTs) which evaluated first-line chemotherapy with or without bevacizumab in mCRC. The extracting data were included and examined in the meta-analysis according to the type of chemotherapy regimen. Results. Seven trials, totaling 3436 patients, were analyzed. Compared with first-line chemothery alone, the adding of bevacizumab did not show clinical benefit for OS both in first-line therapy and the most used combination chemotherapy (HR = 0.89; 95% CI = 0.78-1.02; P = 0.08; HR = 0.93; 95% CI = 0.83-1.05; P = 0.24). In contrast with OS, the addition of bevacizumab resulted in significant improvement for PFS (HR = 0.68; 95% CI = 0.59-0.78; P < 0.00001). Moreover, it also demonstrated statistical benefit for PFS in the most used combination first-line chemotherapy (HR = 0.84; 95% CI = 0.75-0.94; P = 0.002). And the subgroup analysis indicated only capacitabine-based regimens were beneficial. Conclusions. This meta-analysis shows that the addition of bevacizumab to FOLFOX/FOLFIRI/XELOX regimens might not be beneficial in terms of OS. Benefit has been seen when PFS has been taken into account. In subgroup analysis, benefit adding bevacizumab has been seen when capecitabine-based regimens are used. Further studies are warranted to explore the combination with bevacizumab.