Prognostic and predictive value of a pathomics signature in gastric cancer

Abstract

The current tumour-node-metastasis (TNM) staging system alone cannot provide adequate information for prognosis and adjuvant chemotherapy benefits in patients with gastric cancer (GC). Pathomics, which is based on the development of digital pathology, is an emerging field that might improve clinical management. Herein, we propose a pathomics signature (PSGC) that is derived from multiple pathomics features of haematoxylin and eosin-stained slides. We find that the PSGC is an independent predictor of prognosis. A nomogram incorporating the PSGC and TNM staging system shows significantly improved accuracy in predicting the prognosis compared to the TNM staging system alone. Moreover, in stage II and III GC patients with a low PSGC (but not in those with a high PSGC), satisfactory chemotherapy benefits are observed. Therefore, the PSGC could serve as a prognostic predictor in patients with GC and might be a potential predictive indicator for decision-making regarding adjuvant chemotherapy.

Predicting peritoneal recurrence in gastric cancer with serosal invasion using a pathomics nomogram

“…Pathomics embodies a wide variety of data that are captured from digital pathology image analyses to generate quantitative features for characterizing diverse phenotypes of tissue samples, and these data are subsequently analyzed to determine a diagnosis or predict survival outcomes. 17 , 18 , 19 Herein, we hypothesized that the pathomics analysis of digital H&E-stained images could aid in predicting the peritoneal recurrence of GC with serosal invasion.…”

Subjective and objective quality assessment of gastrointestinal endoscopy images: From manual operation to artificial intelligence

“…Gastric cancer (GC) is the major cause of cancer death worldwide (Chen et al, 2022 ). Recently, gastrointestinal endoscopy has been identified as an important tool for cancer diagnosis and therapy, particularly for treating patients with early gastric cancer (EGC) (Li Y.-D. et al, 2021 ).…”

Editorial: The use of data mining in radiological-pathological images for personal medicine

“…

Editorial on the Research TopicThe use of data mining in radiological-pathological images for personal medicineThe use of data mining in radiological-pathological images for personalized medicine is a promising and rapidly developing field. This innovative approach involves the integration of large amounts of data from medical images, pathology reports, and clinical records to improve patient care and treatment outcomes.Currently, there are mainly two methods for data mining on medical images: image findings (subjectively summarized factors) (Renzulli et al, 2016;Yue et al, 2022) and high-order features (objectively calculated features, such as radiomics and pathomics) (Lambin et al, 2017;Chen et al, 2022). Image findings can be easily obtained and explained by pathophysiological mechanisms (Segal et al, 2007).

…”

“…Currently, there are mainly two methods for data mining on medical images: image findings (subjectively summarized factors) ( Renzulli et al, 2016 ; Yue et al, 2022 ) and high-order features (objectively calculated features, such as radiomics and pathomics) ( Lambin et al, 2017 ; Chen et al, 2022 ). Image findings can be easily obtained and explained by pathophysiological mechanisms ( Segal et al, 2007 ).…”