Pattern Classification for Gastrointestinal Stromal Tumors by Integration of Radiomics and Deep Convolutional Features

Predicting malignant potential is one of the most critical components of a computer-aided diagnosis system for gastrointestinal stromal tumors (GISTs). These tumors have been studied only on the basis of subjective computed tomography findings. Among various methodologies, radiomics, and deep learning algorithms, specifically convolutional neural networks (CNNs), have recently been confirmed to achieve significant success by outperforming the state-of-the-art performance in medical image pattern classification and have rapidly become leading methodologies in this field. However, the existing methods generally use radiomics or deep convolutional features independently for pattern classification, which tend to take into account only global or local features, respectively. In this paper, we introduce and evaluate a hybrid structure that includes different features selected with radiomics model and CNNs and integrates these features to deal with GISTs classification. The Radiomics model and CNNs are constructed for global radiomics and local convolutional feature selection, respectively. Subsequently, we utilize distinct radiomics and deep convolutional features to perform pattern classification for GISTs. Specifically, we propose a new pooling strategy to assemble the deep convolutional features of 54 three-dimensional patches from the same case and integrate these features with the radiomics features for independent case, followed by random forest classifier. Our method can be extensively evaluated using multiple clinical datasets. The classification performance (area under the curve (AUC): 0.882; 95% confidence interval (CI): 0.816-0.947) consistently outperforms those of independent radiomics (AUC: 0.807; 95% CI: 0.724-0.892) and CNNs (AUC: 0.826; 95% CI: 0.795-0.856) approaches.

I. Introduction

Gastrointestinal stromal tumors (GISTs) are the most common mesenchymal neoplasms in the gastrointestinal tract and considered potentially malignant tumors [1], [2]. These tumors are most commonly found in the stomach (50%–60%), small intestines (20%–30%), colon and rectum (10%), and esophagus (5%) [3]. Immunohistochemistry demonstrated that the majority of GISTs expresses c-kit protein; some GISTs also express CD34. C-kit is recognized as a highly sensitive and specific marker for GISTs [4], [5]. The clinical features of GISTs cannot be predicted by age because they occur over a wide age distribution, but most of them are found in patients older than 50 years. Similarly, no significant difference is observed between GISTs and sex [6]. Molecularly targeted therapies have changed the management of GISTs, but surgical resection is still regarded as the main treatment for GISTs. Assessing the preoperative malignancy risk of patients is crucial because it significantly influences treatment and prognosis [7].