Purpose: The goal of this study is to create a novel framework for identifying MSI status in colorectal cancer using advanced radiomics and deep learning strategies, aiming to enhance clinical decision-making and improve patient outcomes in oncology.

Procedures: The study utilizes histopathological slide images from the NCT-CRC-HE-100 K and PAIP 2020 databases. Key procedures include self-attentive adversarial stain normalization for data standardization, tumor delineation via a Slimmable Transformer, and radiomics feature extraction using a hybrid quantum-classical neural network.

Results: The proposed system reaches 99% accuracy when identifying colorectal cancer MSI status. It shows the model is good at telling the difference between MSI and MSS tumors and can be used in real medical care for cancer.

Conclusions: Our research shows that the new system improves colorectal cancer MSI status determination better than previous methods. Our optimized processing technology works better than other methods to divide and analyze tissue features making the system good for improving patient care decisions.

Download full-text PDF

Source
http://dx.doi.org/10.1007/s11307-025-01990-wDOI Listing

Publication Analysis

Top Keywords

colorectal cancer
16
msi status
12
hybrid quantum-classical
8
cancer msi
8
leveraging radiomics
4
radiomics hybrid
4
quantum-classical convolutional
4
convolutional networks
4
networks non-invasive
4
non-invasive detection
4

Similar Publications

Background: Prior studies of participants with breast and other obesity-associated cancers in the Women's Health Initiative (WHI) showed worse mortality and cardiovascular disease (CVD) outcomes for individuals with a higher number of cardiometabolic risk factors at study entry. The purpose of this analysis is to compare the relationship between cardiometabolic abnormalities and mortality among women with and without cancer in the WHI.

Methods: Women with one of five early-stage obesity-associated cancers (breast, colorectal, endometrial, ovarian, and non-Hodgkin lymphoma) and controls without any new or prior history of cancer were selected from the WHI-Life and Longevity after Cancer ancillary study.

View Article and Find Full Text PDF

Objective: To compare early recurrence patterns, safety, survival and investigate the clinical risk factors of early recurrence (ER) after liver resection or thermal ablation (TA) for patients with colorectal liver metastases (CRLM) with number ≤ 5 and largest diameter ≤ 3 cm.

Materials And Methods: This retrospective study included patients with CRLM who underwent liver resection or TA between January 2016 and December 2021 at two hospitals in China. The Kaplan-Meier method and log-rank test were used to assess recurrence-free survival (RFS) and overall survival (OS).

View Article and Find Full Text PDF

In recent years, assessing dihydropyrimidine dehydrogenase (DPD) activity has become crucial for cancer patients undergoing 5-fluorouracil (5FU)-based chemotherapy due to the life-threatening toxicity associated with reduced DPD function. The methods for evaluating DPD activity have evolved, with the analysis of DPYD polymorphisms in blood samples becoming the preferred approach. As the indications for liver transplantation are increasing-particularly due to a rise in cases of cholangiocarcinoma (CCA) and non-resectable colorectal liver metastasis-more cancer patients with a history of liver transplantation may experience disease relapse.

View Article and Find Full Text PDF

Colorectal cancer is the fourth leading cause of cancer-related deaths worldwide. Capecitabine is a chemotherapeutic agent commonly used for the treatment of colon cancer. To realize local sustained release, promote efficient local intracellular transport, and mitigate the systemic toxic effects of capecitabine, a capecitabine prodrug, capecitabine-poly (p-dioxanone) (Cap-PPDO), was successfully synthesized.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!