A radiomics-boosted deep-learning for risk assessment of synchronous peritoneal metastasis in colorectal cancer.

OBJECTIVES: Synchronous colorectal cancer peritoneal metastasis (CRPM) has a poor prognosis. This study aimed to create a radiomics-boosted deep learning model by PET/CT image for risk assessment of synchronous CRPM. METHODS: A total of 220 colorectal cancer (CRC) cases were enrolled in this study. We mapped the feature maps (Radiomic feature maps (RFMs)) of radiomic features across CT and PET image patches by a 2D sliding kernel. Based on ResNet50, a radiomics-boosted deep learning model was trained using PET/CT image patches and RFMs. Besides that, we explored whether the peritumoral region contributes to the assessment of CRPM. In this study, the performance of each model was evaluated by the area under the curves (AUC). RESULTS: The AUCs of the radiomics-boosted deep learning model in the training, internal, external, and all validation datasets were 0.926 (95% confidence interval (CI): 0.874-0.978), 0.897 (95% CI: 0.801-0.994), 0.885 (95% CI: 0.795-0.975), and 0.889 (95% CI: 0.823-0.954), respectively. This model exhibited consistency in the calibration curve, the Delong test and IDI identified it as the most predictive model. CONCLUSIONS: The radiomics-boosted deep learning model showed superior estimated performance in preoperative prediction of synchronous CRPM from pre-treatment PET/CT, offering potential assistance in the development of more personalized treatment methods and follow-up plans. CRITICAL RELEVANCE STATEMENT: The onset of synchronous colorectal CRPM is insidious, and using a radiomics-boosted deep learning model to assess the risk of CRPM before treatment can help make personalized clinical treatment decisions or choose more sensitive follow-up plans. KEY POINTS: Prognosis for patients with CRPM is bleak, and early detection poses challenges. The synergy between radiomics and deep learning proves advantageous in evaluating CRPM. The radiomics-boosted deep-learning model proves valuable in tailoring treatment approaches for CRC patients.

The strategy for estrogen receptor mediated-risk assessment in environmental water: A combination of species sensitivity distributions and in silico approaches.

Risk assessment for molecular toxicity endpoints of environmental matrices may be a pressing issue. Here, we combined chemical analysis with species sensitivity distributions (SSD) and in silico docking for multi-species estrogen receptor mediated-risk assessment in water from Dongjiang River, China. The water contains high levels of phenolic endocrine-disrupting chemicals (PEDCs) and phthalic acid esters (PAEs). The concentration of ∑4PEDCs and ∑6PAEs ranged from 2202 to 3404 ng/L and 834-4368 ng/L, with an average of 3241 and 2215 ng/L, respectively. The SSD approach showed that 4-NP, BPA, E2 of PEDCs, and DBP, DOP, and DEHP could severely threaten the aquatic ecosystems, while most other target compounds posed low-to-medium risks. Moreover, binding affinities from molecular docking among PEDCs, PAEs, and estrogen receptors (ERα, Erß, and GPER) were applied as toxic equivalency factors. Estrogen receptor-mediated risk suggested that PEDCs were the main contributors, containing 53.37-69.79% of total risk. They potentially pose more severe estrogen-receptor toxicity to zebrafish, turtles, and frogs. ERß was the major contributor, followed by ERα and GPER. This study is the first attempt to assess the estrogen receptor-mediated risk of river water in multiple aquatic organisms. The in silico simulation approach could complement toxic effect evaluations in molecular endpoints.

Ecological and AhR-mediated risk assessment of polycyclic aromatic hydrocarbons and polybrominated diphenyl ethers on multiple aquatic species in river water: A combined chemical analysis and in silico approach.

Assessing the adverse health risks at molecular endpoints to various aquatic organisms could be an urgent issue. In this manuscript, the ecological and AhR-mediated risk of sixteen polycyclic aromatic hydrocarbons (PAHs) and six polybrominated diphenyl ethers (PBDEs) in surface water of Dongjiang River, Southern China was evaluated using chemical analysis and in silico approaches. Average concentrations of ∑16PAHs and ∑6PBDEs were 586.3 ng/L and 2.672 ng/L in the dry season (DS), and 366.8 ng/L and 2.554 ng/L in the wet season (WS). Concentrations of PAHs during the DS were significantly higher than that in the WS, while no obvious seasonal distribution was observed for PBDEs. Only Ant and BaP in all congers of PAHs posed low to medium ecological risks, and PBDEs posed a low ecological risk. Moreover, AhR-mediated risk from PAHs was two orders of magnitude higher that from PBDEs, and the AhR-mediated toxicity on frog and eel were higher than those on other aquatic organisms in Dongjiang River. Phe and BDE209 were the significant contributor to the AhR-mediated risk induced by PAHs and PBDEs, respectively. This study is the first attempt to assess AhR-mediated risk of river water in multiple aquatic organisms.