Using an anomaly detection approach for the segmentation of colorectal cancer tumors in whole slide images.

J Pathol Inform

Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN 55901, United States.

Published: September 2023

AI Article Synopsis

  • Colorectal cancer (CRC) is the second most common cancer in the U.S., and genetic testing is important for early detection and tailored treatment, improving patient survival rates.
  • The tissue slide review (TSR), essential for genetic testing, presents challenges due to pathologist discrepancies and a lack of quality metrics.
  • An advanced method called progressive context encoder anomaly detection (P-CEAD) offers an automated and more reliable approach for segmenting CRC tumors from whole slide images, outperforming traditional manual methods in terms of reproducible quality.

Article Abstract

Colorectal cancer (CRC) is the second most commonly diagnosed cancer in the United States. Genetic testing is critical in assisting in the early detection of CRC and selection of individualized treatment plans, which have shown to improve the survival rate of CRC patients. The tissue slide review (TSR), a tumor tissue macro-dissection procedure, is a required pre-analytical step to perform genetic testing. Due to the subjective nature of the process, major discrepancies in CRC diagnostics by pathologists are reported, and metrics for quality are often only qualitative. Progressive context encoder anomaly detection (P-CEAD) is an anomaly detection approach to detect tumor tissue from whole slide images (WSIs), since tumor tissue is by its nature, an anomaly. P-CEAD-based CRC tumor segmentation achieves a 71% 26% sensitivity, 92% 7% specificity, and 63% 23% F1 score. The proposed approach provides an automated CRC tumor segmentation pipeline with a quantitatively reproducible quality compared with the conventional manual tumor segmentation procedure.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10550750PMC
http://dx.doi.org/10.1016/j.jpi.2023.100336DOI Listing

Publication Analysis

Top Keywords

anomaly detection
12
tumor tissue
12
tumor segmentation
12
detection approach
8
colorectal cancer
8
slide images
8
genetic testing
8
tissue slide
8
crc tumor
8
crc
6

Similar Publications

Ischemic stroke, accounting for approximately 80% of all stroke cases, remains a leading cause of death and disability worldwide. Effective management of ischemic stroke is heavily influenced by its etiology, which can range from large-artery atherosclerosis and cardiac embolism to cerebral small-vessel occlusions and cryptogenic strokes. Cardioembolic stroke, which makes up about 30% of ischemic strokes, often leads to more severe symptoms and worse outcomes, necessitating anticoagulation therapy for prevention.

View Article and Find Full Text PDF

Aim: This study investigates the impact of sub-toxic cisplatin levels on nuclear and nucleolar abnormalities and chromosome instability in HeLa cells since our current knowledge of cisplatin effects on these parameters is based on studies with high concentrations of cisplatin.

Materials And Methods: HeLa cells were exposed to gradually increasing sub-toxic doses of cisplatin (0.01 to 0.

View Article and Find Full Text PDF

Comparison of retinal vascular abnormalities in the fellow eyes of children with Coats' disease and normal subjects using ultra-widefield fundus fluorescein angiography.

Photodiagnosis Photodyn Ther

December 2024

Beijing Tongren Eye Center, Beijing Tongren Hospital, Capital Medical University, Beijing 100730, China; Beijing Ophthalmology and Visual Science Key Laboratory, Beijing 100730, China. Electronic address:

Purpose: To investigate retinal vascular abnormalities in the affected and fellow eyes of children with Coats' disease using Optos® ultra-widefield fundus fluorescein angiography (UWFFA) and compare the peripheral vascular abnormalities between fellow eyes and normal control eyes.

Methods: Children diagnosed with Coats' disease who underwent UWFFA were retrospectively reviewed. Healthy eyes with complete UWFFA data were selected as controls.

View Article and Find Full Text PDF

A prospectively deployed deep learning-enabled automated quality assurance tool for oncological palliative spine radiation therapy.

Lancet Digit Health

January 2025

Department of Radiation Oncology, Brigham and Women's Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA, USA; Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA, USA. Electronic address:

Background: Palliative spine radiation therapy is prone to treatment at the wrong anatomic level. We developed a fully automated deep learning-based spine-targeting quality assurance system (DL-SpiQA) for detecting treatment at the wrong anatomic level. DL-SpiQA was evaluated based on retrospective testing of spine radiation therapy treatments and prospective clinical deployment.

View Article and Find Full Text PDF

Prevalence and outcomes of nonmass lesions detected on screening breast ultrasound based on ultrasound features.

J Ultrasound

December 2024

Department of Radiology, Research Institute of Radiology, Asan Medical Center, College of Medicine, University of Ulsan, Olympic-ro 43-gil, Songpa-gu, 05505, Seoul, Republic of Korea.

Purpose: To determine how often non-mass lesions are seen in screening breast ultrasounds, and analyze their ultrasound features according to the ultrasound lexicon to find features suggestive of malignant non-mass lesions.

Methods: This study is a single center retrospective study for nonmass lesions on screening breast ultrasound. Among 21,604 patients who underwent screening breast US, there were 279 patients with nonmass lesions.

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!