Artificial Intelligence in the Imaging of Gastric Cancer: Current Applications and Future Direction

Abstract

Gastric cancer (GC) is one of the most common cancers and one of the leading causes of cancer-related death worldwide. Precise diagnosis and evaluation of GC, especially using noninvasive methods, are fundamental to optimal therapeutic decision-making. Despite the recent rapid advancements in technology, pretreatment diagnostic accuracy varies between modalities, and correlations between imaging and histological features are far from perfect. Artificial intelligence (AI) techniques, particularly hand-crafted radiomics and deep learning, have offered hope in addressing these issues. AI has been used widely in GC research, because of its ability to convert medical images into minable data and to detect invisible textures. In this article, we systematically reviewed the methodological processes (data acquisition, lesion segmentation, feature extraction, feature selection, and model construction) involved in AI. We also summarized the current clinical applications of AI in GC research, which include characterization, differential diagnosis, treatment response monitoring, and prognosis prediction. Challenges and opportunities in AI-based GC research are highlighted for consideration in future studies.

Enhanced CT-based radiomics predicts pathological complete response after neoadjuvant chemotherapy for advanced adenocarcinoma of the esophagogastric junction: a two-center study

“…Therefore, it is clinically relevant to monitor the efficacy of NAC during treatment and to identify patients who respond to NAC in a timely and accurate manner. Radiomics integrates meaningful quantitative imaging features for modeling, which is a major difference from methods utilizing the traditional visual interpretation of images [35][36][37][38][39]. Chen et al [40] used the features of the CT venous phase and established a predictive model to distinguish between advanced gastric cancer patients with potentially pathologically significant reactions and those with mild reactions and were able to effectively stratify patients according to their response to NAC.…”

Deciphering gastric inflammation-induced tumorigenesis through multi-omics data and AI methods

“…In early GC, endoscopy shows a mild mucosal uplift or depression, accompanied by mild redness; because the images lack typical features, early cancer interpretation is highly dependent on the endoscopists’ experience. Simultaneously, predicting progression risk according to pathological information regarding GPLs is difficult 27 . With the gathering of extensive gastroscopy image data, AI methods have emerged as a promising avenue in GC research, owing to their efficient computational and learning capabilities 28 .…”

Establishing a cancer driver gene signature-based risk model for predicting the prognoses of gastric cancer patients

“…Over the past few decades, several studies that focused on developing molecular targeted therapies for GC and understanding their underlying molecular mechanisms have shed light on GC pathogenesis [ 4 ]. However, despite the importance of accurate classification and risk stratification of GC patients in improving management decisions and prognosis predictions, reliable biomarkers to predict GC prognosis are lacking [ 5 , 6 ].…”