Features Partner Sites Information LinkXpress hp
Sign In
Advertise with Us
LGC Clinical Diagnostics

Download Mobile App




Acute Myeloid Leukemia Diagnosed by Convolutional Neural Networks

By LabMedica International staff writers
Posted on 27 Nov 2019
Every day, millions of single blood cells are evaluated for disease diagnostics in medical laboratories and clinics. Most of this repetitive task is still done manually by trained cytologists who inspect cells in stained blood smears and classify them into roughly 15 different categories.

Scientists have now shown that deep learning algorithms perform similar to human experts when classifying blood samples from patients suffering from acute myeloid leukemia (AML). Their proof of concept study paves the way for an automated, standardized and on-hand sample analysis in the near future.

Scientists from the Helmholtz Zentrum München (Neuherberg, Germany) and their colleagues compiled an annotated image dataset of over 18,000 white blood cells, use it to train a convolutional neural network for leukocyte classification and evaluate the network’s performance by comparing to inter- and intra-expert variability. They used images which were extracted from blood smears of 100 patients suffering from the aggressive blood disease AML and 100 controls. The new AI-driven approach was then evaluated by comparing its performance with the accuracy of human experts.

The network classifies the most important cell types with high accuracy. It also allowed the investigators to decide two clinically relevant questions with human-level performance: (1) if a given cell has blast character and (2) if it belongs to the cell types normally present in non-pathological blood smears. The result showed that the AI-driven solution is able to identify diagnostic blast cells at least as good as a trained cytologist expert.

Carsten Marr, PhD, a computational stem cell biologists and the senior author of the study, said, “To bring our approach to clinics, digitization of patients' blood samples has to become routine. Algorithms have to be trained with samples from different sources to cope with the inherent heterogeneity in sample preparation and staining. Together with our partners we could prove that deep learning algorithms show a similar performance as human cytologists. In a next step, we will evaluate how well other disease characteristics, such as genetic mutations or translocations, can be predicted with this new AI-driven method.”

The authors concluded that their approach holds the potential to be used as a classification aid for examining much larger numbers of cells in a smear than can usually is done by a human expert. This will allow clinicians to recognize malignant cell populations with lower prevalence at an earlier stage of the disease. The study was published on November 12, 2019 in the journal Nature Machine Intelligence.

Related Links:
Helmholtz Zentrum München


Gold Member
Fully Automated Cell Density/Viability Analyzer
BioProfile FAST CDV
Verification Panels for Assay Development & QC
Seroconversion Panels
New
Immunoassays and Calibrators
QMS Tacrolimus Immunoassays
New
Troponin I Test
Quidel Triage Troponin I Test
Read the full article by registering today, it's FREE! It's Free!
Register now for FREE to LabMedica.com and get access to news and events that shape the world of Clinical Laboratory Medicine.
  • Free digital version edition of LabMedica International sent by email on regular basis
  • Free print version of LabMedica International magazine (available only outside USA and Canada).
  • Free and unlimited access to back issues of LabMedica International in digital format
  • Free LabMedica International Newsletter sent every week containing the latest news
  • Free breaking news sent via email
  • Free access to Events Calendar
  • Free access to LinkXpress new product services
  • REGISTRATION IS FREE AND EASY!
Click here to Register








Channels

Clinical Chemistry

view channel
Image: The tiny clay-based materials can be customized for a range of medical applications (Photo courtesy of Angira Roy and Sam O’Keefe)

‘Brilliantly Luminous’ Nanoscale Chemical Tool to Improve Disease Detection

Thousands of commercially available glowing molecules known as fluorophores are commonly used in medical imaging, disease detection, biomarker tagging, and chemical analysis. They are also integral in... Read more

Immunology

view channel
Image: The cancer stem cell test can accurately choose more effective treatments (Photo courtesy of University of Cincinnati)

Stem Cell Test Predicts Treatment Outcome for Patients with Platinum-Resistant Ovarian Cancer

Epithelial ovarian cancer frequently responds to chemotherapy initially, but eventually, the tumor develops resistance to the therapy, leading to regrowth. This resistance is partially due to the activation... Read more

Microbiology

view channel
Image: The lab-in-tube assay could improve TB diagnoses in rural or resource-limited areas (Photo courtesy of Kenny Lass/Tulane University)

Handheld Device Delivers Low-Cost TB Results in Less Than One Hour

Tuberculosis (TB) remains the deadliest infectious disease globally, affecting an estimated 10 million people annually. In 2021, about 4.2 million TB cases went undiagnosed or unreported, mainly due to... Read more

Pathology

view channel
Image: The ready-to-use DUB enzyme assay kits accelerate routine DUB activity assays without compromising data quality (Photo courtesy of Adobe Stock)

Sensitive and Specific DUB Enzyme Assay Kits Require Minimal Setup Without Substrate Preparation

Ubiquitination and deubiquitination are two important physiological processes in the ubiquitin-proteasome system, responsible for protein degradation in cells. Deubiquitinating (DUB) enzymes contain around... Read more

Technology

view channel
Image: The HIV-1 self-testing chip will be capable of selectively detecting HIV in whole blood samples (Photo courtesy of Shutterstock)

Disposable Microchip Technology Could Selectively Detect HIV in Whole Blood Samples

As of the end of 2023, approximately 40 million people globally were living with HIV, and around 630,000 individuals died from AIDS-related illnesses that same year. Despite a substantial decline in deaths... Read more

Industry

view channel
Image: The collaboration aims to leverage Oxford Nanopore\'s sequencing platform and Cepheid\'s GeneXpert system to advance the field of sequencing for infectious diseases (Photo courtesy of Cepheid)

Cepheid and Oxford Nanopore Technologies Partner on Advancing Automated Sequencing-Based Solutions

Cepheid (Sunnyvale, CA, USA), a leading molecular diagnostics company, and Oxford Nanopore Technologies (Oxford, UK), the company behind a new generation of sequencing-based molecular analysis technologies,... Read more
Copyright © 2000-2025 Globetech Media. All rights reserved.