Search

Purpose: Lymphovascular invasion (LVI) and perineural invasion (PNI) are associated with poor prognosis in gastric cancers. In this work, we aimed to investigate the potential role of computed tomography (CT) texture analysis in predicting LVI and PNI in patients with tubular gastric adenocarcinoma (GAC) using a machine learning (ML) approach., Methods: Sixty-eight patients who underwent total gastrectomy with curative (R0) resection and D2-lymphadenectomy were included in this retrospective study. Texture features were extracted from the portal venous phase CT images. Dimension reduction was first done with a reproducibility analysis by two radiologists. Then, a feature selection algorithm was used to further reduce the high-dimensionality of the radiomic data. Training and test splits were created with 100 random samplings. ML-based classifications were done using adaptive boosting, k-nearest neighbors, Naive Bayes, neural network, random forest, stochastic gradient descent, support vector machine, and decision tree. Predictive performance of the ML algorithms was mainly evaluated using the mean area under the curve (AUC) metric., Results: Among 271 texture features, 150 features had excellent reproducibility, which were included in the further feature selection process. Dimension reduction steps yielded five texture features for LVI and five for PNI. Considering all eight ML algorithms, mean AUC and accuracy ranges for predicting LVI were 0.777-0.894 and 76%-81.5%, respectively. For predicting PNI, mean AUC and accuracy ranges were 0.482-0.754 and 54%-68.2%, respectively. The best performances for predicting LVI and PNI were achieved with the random forest and Naive Bayes algorithms, respectively., Conclusion: ML-based CT texture analysis has a potential for predicting LVI and PNI of the tubular GACs. Overall, the method was more successful in predicting LVI than PNI.

Background: Appendiceal diverticular disease (ADD) is a rare pathology which is associated with an increased mortality risk due to rapid perforation and high rates of neoplasm. In our study, we aimed to evaluate the clinical and histopathological characteristics of ADD with differences from acute appendicitis (AA) diagnosis and to determine the association with neoformative processes., Methods: The 4279 patients who underwent appendectomy were evaluated retrospectively. ADD patients histopathologically classified into four groups. Patients' demographic characteristics, imaging and preoperative laboratory findings, additionally postoperative histopathology results were compared between groups., Results: The prevalence of ADD was 2.29% (n = 98). In addition, the male/female ratio was 2.37 in ADD patients who were found to be significantly older than those with AA patients. Type III was the most frequently (62.2%) identified sub-group of ADD. The incidence of neoplasms, plastrone, and Littre's hernia was found statistically higher in ADD group than AA group. Mucinous adenomas (10.2%) was the most common neoplasm while the carcinoid tumor (1%) and precancerous serrated adenomas (4.1%) were also reported., Conclusions: As a result, high neoplasm in ADD patients can be shown with incidence of perforation and plastron, and in order to avoid possible neoplasm or major complications, it is necessary to carry out new studies for the right diagnosis of ADD whether the diagnosis is done preoperatively or ıntraoperatively. We recommend surgical resection of the ADD, which may even be incidentally detected during any surgical procedure, due to its high risk of neoplasm and rapid perforation.