首页|University of Sao Paulo (USP) Reports Findings in Rectal Cancer (Machine Learnin g-Based Prediction of Responsiveness to Neoadjuvant Chemoradiotheapy in Locally Advanced Rectal Cancer Patients from Endomicroscopy)
University of Sao Paulo (USP) Reports Findings in Rectal Cancer (Machine Learnin g-Based Prediction of Responsiveness to Neoadjuvant Chemoradiotheapy in Locally Advanced Rectal Cancer Patients from Endomicroscopy)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Oncology - Rectal Canc er is the subject of a report. According to news reporting originating in Sao Pa ulo, Brazil, by NewsRx journalists, research stated, "The protocol for treating locally advanced rectal cancer consists of the application of chemoradiotherapy (neoCRT) followed by surgical intervention. One issue for clinical oncologists i s predicting the efficacy of neoCRT in order to adjust the dosage and avoid trea tment toxicity in cases when surgery should be conducted promptly." The news reporters obtained a quote from the research from the University of Sao Paulo (USP), "Biomarkers may be used for this purpose along with in vivo cell-l evel images of the colorectal mucosa obtained by probe-based confocal laser endo microscopy (pCLE) during colonoscopy. The aim of this article is to report our e xperience with Motiro, a computational framework that we developed for machine l earning (ML) based analysis of pCLE videos for predicting neoCRT response in loc ally advanced rectal cancer patients. pCLE videos were collected from 47 patient s who were diagnosed with locally advanced rectal cancer (T3/T4, or N+). The pat ients received neoCRT. Response to treatment by all patients was assessed by end oscopy along with biopsy and magnetic resonance imaging (MRI). Thirty-seven pati ents were classified as non-responsive to neoCRT because they presented a visibl e macroscopic neoplastic lesion, as confirmed by pCLE examination. Ten remaining patients were considered responsive to neoCRT because they presented lesions as a scar or small ulcer with negative biopsy, at post-treatment follow-up. Motiro was used for batch mode analysis of pCLE videos. It automatically characterized the tumoral region and its surroundings. That enabled classifying a patient as responsive or non-responsive to neoCRT based on pre-neoCRT pCLE videos. Motiro c lassified patients as responsive or non-responsive to neoCRT with an accuracy of 0.62 when using images of the tumor. When using images of regions surrounding the tumor, it reached an accuracy of 0.70. Feature analysis showed that spati al heterogeneity in fluorescence distribution within regions surrounding the tum or was the main contributor to predicting response to neoCRT. We developed a com putational framework to predict response to neoCRT by locally advanced rectal ca ncer patients based on pCLE images acquired pre-neoCRT."
Sao PauloBrazilSouth AmericaCancerCyborgsEmerging TechnologiesGastroenterologyHealth and MedicineMachine LearningOncologyRectal Cancer
NETL
NSTL
