The prediction of tumor in the TNM staging (tumor, node, and metastasis) stage of colon cancer using the most influential histopathology parameters and to predict the five years disease-free survival (DFS) period using machine learning (ML) in clinical research have been studied here. From the colorectal cancer (CRC) registry of Chang Gung Memorial Hospital, Linkou, Taiwan, 4021 patients were selected for the analysis. Various ML algorithms were applied for the tumor stage prediction of the colon cancer by considering the Tumor Aggression Score (TAS) as a prognostic factor. Performances of different ML algorithms were evaluated using five-fold cross-validation, which is an effective way of the model validation. The accuracy achieved by the algorithms taking both cases of standard TNM staging and TNM staging with the Tumor Aggression Score was determined. It was observed that the Random Forest model achieved an F-measure of 0.89, when the Tumor Aggression Score was considered as an attribute along with the standard attributes normally used for the TNM stage prediction. We also found that the Random Forest algorithm outperformed all other algorithms, with an accuracy of approximately 84% and an area under the curve (AUC) of 0.82 ± 0.10 for predicting the five years DFS.

Colorectal cancer is one of the leading causes of cancer-related death worldwide. The early diagnosis of colon cancer not only reduces mortality but also reduces the burden related to the treatment strategies such as chemotherapy and/or radiotherapy. However, when the microscopic examination of the suspected colon tissue sample is carried out, it becomes a tedious and time-consuming job for the pathologists to find the abnormality in the tissue. In addition, there may be interobserver variability that might lead to conflict in the final diagnosis. As a result, there is a crucial need of developing an intelligent automated method that can learn from the patterns themselves and assist the pathologist in making a faster, accurate, and consistent decision for determining the normal and abnormal region in the colorectal tissues. Moreover, the intelligent method should be able to localize the abnormal region in the whole slide image (WSI), which will make it easier for the pathologists to focus on only the region of interest making the task of tissue examination faster and lesser time-consuming. As a result, artificial intelligence (AI)-based classification and localization models are proposed for determining and localizing the abnormal regions in WSI. The proposed models achieved F-score of 0.97, area under curve (AUC) 0.97 with pretrained Inception-v3 model, and F-score of 0.99 and AUC 0.99 with customized Inception-ResNet-v2 Type 5 (IR-v2 Type 5) model.

Background: Bevacizumab-based regimens are used as standard treatments for colorectal cancer. Unfortunately, there are no established predictive markers for bevacizumab response. Methods: Tumor samples from 36 metastatic colorectal cancer patients treated with bevacizumab plus chemotherapy were analyzed by next-generation sequencing of all coding exons of more than 400 genes. Single gene and signaling pathway analyses were performed to correlate genomic data with response. Results: Among the genes most frequently mutated in our cohort, only mutations in PTPRT, a phosphatase involved in JAK/STAT signaling, were associated with response status, with deleterious mutations being enriched in non-responders. Pathway analysis revealed that deleterious mutations in genes of the JAK/STAT pathway, namely in PTPRT and the related gene PTPRD, correlated with resistance. Mutations in RTK/PI3K/RAS, Wnt and TGFβ pathways did not associate with response. Lack of response was observed in all patients with deleterious mutations or copy number loss of PTPRT/PTPRD (n = 10), compared to only 30.8% (n = 8) of patients without such alterations (relative risk, 3.25; 95% CI, 1.83–5.79, p = 0.0003). Similarly, PTPRT/PTPRD deleterious alterations were associated with shorter progression-free survival, an association that was retained in multivariate analysis (HR, 3.33; 95% CI, 1.47–7.54; p = 0.0038). Conclusion: Deleterious alterations in PTPRT/PTPRD are potential biomarkers for bevacizumab resistance.

Background: Laparoscopic surgery has achieved significant results in elderly patients with colorectal cancer (CRC). In this study, we compared the short-term and long-term outcomes of open surgery and laparoscopic surgery in patients with CRC aged above 75 years at a single tertiary medical center. Methods: We analyzed 967 patients who underwent curative resection for primary colorectal adenocarcinoma without distant metastasis between January 2009 and December 2015, in a single institution. Of the enrolled patients, 305 underwent laparoscopic surgery, and 662 received open laparotomy surgery. Results: Compared to the patients who underwent open surgery, those who received laparoscopic surgery had significantly shorter postoperative stay (10.3 vs. 13.5 days p < 0.001) and similar postoperative morbidity (p = 0.354) and mortality (p = 0.082). In the laparoscopy cohort, six of 305 patients were converted to open surgery and one died. The long-term overall survival, cancer-specific survival, and recurrence rate were similar between both cohorts in each stage. Conclusions: Laparoscopic surgery is suitable for elderly patients owing to shorter postoperative stay, similar long-term outcomes with open surgery, and acceptable low conversion rates. For long-term overall and oncological outcomes, the results of laparoscopic surgery were similar to that of open surgery in each TNM stage.

Background: Approximately 20% of patients with colorectal cancer are initially diagnosed with stage IV disease. This study aims to examine the role of regional lymph node (LN) status in metastatic colorectal cancer (mCRC) with respect to clinicopathologic features and survival outcomes. Methods: We investigated 1147 patients diagnosed with mCRC and had undergone surgical resection of the primary CRC. A total of 167 patients were placed in the LN-negative (LN−) group and another 980 in the LN-positive (LN+) group. Results: LN+ patients exhibited a significantly higher rate of T4 tumors (p = 0.008), poorly differentiated adenocarcinoma (p < 0.001), lymphovascular invasion (p < 0.001), and perineural invasion (p < 0.001) than those in the LN− group. LN− patients had a significantly higher rate of lung metastasis (p < 0.001), whereas the rate of peritoneal seeding (p < 0.001) and systemic node metastasis (p < 0.001) was both significantly higher in the LN+ group. The 5-year overall survival (OS) in the LN+ group was significantly poorer than that in the LN− group (LN− vs. LN+ 23.2% vs. 18.1%; p = 0.040). In patients with curative resection, the 5-year OS rate has no significant difference between the two groups (LN− vs. LN+ 19.5% vs. 24.3%; p = 0.890). Conclusions: Metastatic CRC patients with LN+ who underwent primary tumor resection may present with more high-risk pathological features, more peritoneal seeding, and systemic node metastasis, but less lung metastasis than LN− patients. LN+ patients had poorer long-term outcomes compared with that in LN− patients. Nevertheless, with curative resection, LN+ patients could have similar survival outcomes as LN− patients.