We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

Features Partner Sites Information LinkXpress
Sign In
Advertise with Us
Abbott Diagnostics- Hematology Division

Download Mobile App




Events

ATTENTION: Due to the COVID-19 PANDEMIC, many events are being rescheduled for a later date, converted into virtual venues, or altogether cancelled. Please check with the event organizer or website prior to planning for any forthcoming event.

AI Accurately Detects and Diagnoses Colorectal Cancer from Tissue Scans As Well or Better Than Pathologists

By LabMedica International staff writers
Posted on 05 Nov 2021
Print article
Illustration
Illustration

Artificial intelligence (A) can accurately detect and diagnose colorectal cancer from tissue scans as well or better than pathologists, according to a new study.

The study, which was conducted by researchers from Tulane University (New Orleans, LA, USA), was designed to test whether AI could be a tool to help pathologists keep pace with the rising demand for their services. Pathologists evaluate and label thousands of histopathology images on a regular basis to tell whether someone has cancer. But their average workload has increased significantly and can sometimes cause unintended misdiagnoses due to fatigue. To conduct the study, the team collected over 13,000 images of colorectal cancer from 8,803 subjects and 13 independent cancer centers in China, Germany and the US. Using the images, which were randomly selected by technicians, they built a machine assisted pathological recognition program that allows a computer to recognize images that show colorectal cancer, one of the most common causes of cancer related deaths in Europe and the US.

The area under the receiver operating characteristic (ROC) curve or AUC is the performance measurement tool that the team used to determine the success of the study. After comparing the computer’s results with the work of highly experienced pathologists who interpreted data manually, the study found that the average pathologist scored at .969 for accurately identifying colorectal cancer manually. The average score for the machine-assisted AI computer program was .98, which is comparable if not more accurate. Using AI to identify cancer is an emerging technology and hasn’t yet been widely accepted. The researchers hope that the study will lead to more pathologists using prescreening technology in the future to make quicker diagnoses.

“Even though a lot of their work is repetitive, most pathologists are extremely busy because there’s a huge demand for what they do but there’s a global shortage of qualified pathologists, especially in many developing countries” said Dr. Hong-Wen Deng, professor and director of the Tulane Center of Biomedical Informatics and Genomics at Tulane University School of Medicine. “This study is revolutionary because we successfully leveraged artificial intelligence to identify and diagnose colorectal cancer in a cost-effective way, which could ultimately reduce the workload of pathologists.”

“The challenges of this study stemmed from complex large image sizes, complex shapes, textures, and histological changes in nuclear staining,” Deng said. “But ultimately the study revealed that when we used AI to diagnose colorectal cancer, the performance is shown comparable to and even better in many cases than real pathologists.”

Related Links:
Tulane University

Gold Supplier
Molecular Diagnostic System
iPonatic
New
Clinical Chemistry Reagents
SEKURE Clinical Chemistry Reagents
New
Silver Supplier
Bacteriuria Test Strips
MAST Bacteruritest Strips
New
Molecular Diagnostic Platform
VERIGENE II System

Print article

Channels

Molecular Diagnostics

view channel
Image: Absence of nuclear immunohistochemical staining of MSH2 protein (A) and presence of MLH1 protein (B) in urothelial cell carcinoma of the urinary bladder of a patient carrying a germline MSH2 mutation. Observe the nuclear staining in stromal cells as an internal control (Photo courtesy of Radboud University Nijmegen Medical Centre)

Simple Urine Test Detects Urothelial Cancers in Lynch Syndrome Patients

Lynch Syndrome (LS) is an inherited genetic disorder that carries a high risk of cancer. LS is caused by mutations affecting MLH1, MSH2, MSH6 or PMS2 genes. More than one in 300 people have LS but most... Read more

Hematology

view channel
Image: The Gazelle Hb Variant Test for screening, diagnosis and management of sickle cell disease and related hemoglobinopathies at the point of care (Photo courtesy of Hemex Health)

Point-of-Care Device Accurately Rapidly Diagnoses Sickle Cell Disease

Hemoglobinopathies are the most common autosomal hereditary disorders. Approximately 7% of the global population carries hemoglobin gene mutation including structural hemoglobin variants like sickle hemoglobin... Read more

Immunology

view channel
Image: The IMMULITE 2000 XPi Immunoassay System provides multiple tests on a single, easy-to-use analyzer, including the thyroid-stimulating immunoglobulin assay (Photo courtesy of Siemens Healthcare)

Immunoassays Evaluated for Thyroid-Stimulating Receptor Antibody in Graves’ Disease

Graves' disease (GD), also known as toxic diffuse goiter, is an autoimmune disease that affects the thyroid. It frequently results in and is the most common cause of hyperthyroidism and it also often results... Read more

Microbiology

view channel
Image: The sciREADER CL2 enables high quality digital colorimetric imaging of various support formats (Photo courtesy of SCIENION)

Multiplex Immunoassay Developed for Confirmation and Typing of HTLV Infections

Human T-Cell Lymphotropic Viruses (HTLV) type 1 and type 2 account for an estimated five to 10 million infections worldwide and are transmitted through breast feeding, sexual contacts and contaminated... Read more

Technology

view channel
Image: PKeye Workflow Monitor System (Photo courtesy of PerkinElmer, Inc.)

PerkinElmer’s New Cloud-Based Platform Enables Laboratory Personnel to Remotely Manage Its Instruments in Real-Time

PerkinElmer, Inc. (Waltham, MA; USA) has launched its PKeye Workflow Monitor, a cloud-based platform enabling laboratory personnel to remotely manage and monitor their PerkinElmer instruments and workflows... Read more

Industry

view channel
Illustration

Global Point of Care Diagnostics Market to Top USD 35 Billion by 2027 Due to Rising Diabetic Cases

The global point of care diagnostics market is projected to grow at a CAGR of close to 6% from more than USD 23 billion in 2020 to over USD 35 billion by 2027, driven by an increase in the number of diabetic... Read more
Copyright © 2000-2021 Globetech Media. All rights reserved.