An interpretable machine learning model based on computed tomography radiomics for predicting programmed death ligand 1 expression status in gastric cancer.

Background: Programmed death ligand 1 (PD-L1) expression status, closely related to immunotherapy outcomes, is a reliable biomarker for screening patients who may benefit from immunotherapy. Here, we developed and validated an interpretable machine learning (ML) model based on contrast-enhanced computed tomography (CECT) radiomics for preoperatively predicting PD-L1 expression status in patients with gastric cancer (GC).

Methods: We retrospectively recruited 285 GC patients who underwent CECT and PD-L1 detection from two medical centers.

The contents and forms of solid-phase species of radioactive strontium and cesium in Taiwan soils.

This study was to investigate the activities and contents of (137)Cs in the profiles of selected arable and forest soils in Taiwan and various solid-phase species of (85)Sr and (137)Cs in selected arable soils in Taiwan. The gamma (gamma) ray spectra of the collected soil samples and some of the soils amended with (85)Sr and (137)Cs were measured. The data indicate that the arable soils from Sanhsing series, Sanhsing Township and Chuangwei series, Chuangwei Township, Ilan County, and from Tunglochuan series, Pinglin Township, Taipei County shows significantly higher radioactivity of (137)Cs (ND - 11.