Tubular gastric adenocarcinoma: machine learning-based CT texture analysis for predicting lymphovascular and perineural invasion

• Published in: Diagnostic and interventional radiology (Ankara, Turkey) Vol. 26; no. 6; pp. 515 - 522
• Main Authors: Yardimci, Aytul Hande, Kocak, Burak, Bektas, Ceyda Turan, Sel, Ipek, Yarikkaya, Enver, Dursun, Nevra, Bektas, Hasan, Afsarriz, Cigdem Usul, Gursu, Riza Umar, Kilickesmez, Ozgur
• Format: Journal Article
• Language: English
• Published: Ankara Galenos Yayinevi Tic. Ltd 01.11.2020; Galenos Publishing House; Turkish Society of Radiology
• Subjects: Abdominal Imaging; Adenocarcinoma; Algorithms; Computed tomography; Computer-aided medical diagnosis; CT imaging; Decision trees; Diagnosis; Feature extraction; Feature selection; Gastric cancer; Machine learning; Metastasis; Methods; Neural networks; Performance prediction; Prognosis; Reduction; Reproducibility; Risk factors; Stomach cancer; Support vector machines; Texture; Turkey
• ISSN: 1305-3612; 1305-3825; 1305-3612
• DOI: 10.5152/dir.2020.19507

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.