Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Detection of Gross Error: The Q Test

Detection of Gross Error: The Q Test

When one or more data points appear far from the rest of the data, there is a need to determine whether they are outliers and whether they should be eliminated from the data set to ensure an accurate representation of the measured value. In many cases, outliers arise from gross errors (or human errors) and do not accurately reflect the underlying phenomenon. In some cases, however, these apparent outliers reflect true phenomenological differences. In these cases, we can use statistical methods...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Pulmonary tularemia leading to a relapse of tularemia orchitis in a patient on TNF-alpha inhibitor.

Wiener klinische Wochenschrift·2026

Same author

Proteomic characterization of SMARCA-deficient esophageal adenocarcinoma reveals complement evasion and DNA repair-associated prognostic subgroups.

British journal of cancer·2026

Same author

MET Expression in Upper Gastrointestinal Adenocarcinoma: Prevalence, Prognostic Impact, and Implications for Anti-MET Antibody-Drug Conjugate Therapy.

International journal of cancer·2026

Same author

Oncogenic KRAS-driven type I interferon signalling primes pancreatic cancer for necroptosis.

Nature communications·2026

Same author

Molecular and clinical characteristics of patients with non-small cell lung cancer (NSCLC) harboring KRAS Q61 mutations to assess therapeutic responses.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026

Same author

Health-related quality of life comparing standard and prolonged time-to-surgery after neoadjuvant chemoradiotherapy for esophageal cancer: results from the multicenter, randomized, controlled NeoRes II trial.

Diseases of the esophagus : official journal of the International Society for Diseases of the Esophagus·2026

Search research articles

Related Experiment Video

Updated: Nov 1, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

Quality control stress test for deep learning-based diagnostic model in digital pathology.

Birgid Schömig-Markiefka¹, Alexey Pryalukhin², Wolfgang Hulla²

¹Institute of Pathology, University Hospital Cologne, Cologne, Germany.

Modern Pathology : an Official Journal of the United States and Canadian Academy of Pathology, Inc

|June 25, 2021

Summary

Histological artifacts significantly degrade the accuracy of deep learning models for prostate cancer detection in digital pathology. Robust validation strategies, including synthetic artifact testing, are crucial for clinical deployment.

More Related Videos

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Related Experiment Videos

Last Updated: Nov 1, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Area of Science:

Computational pathology
Artificial intelligence in medicine
Histopathology

Background:

Digital pathology enables computational analysis of histological slides, automating routine tasks.
Histological slides exhibit heterogeneity due to variations in staining, thickness, and processing artifacts.
Deep learning models are increasingly used for disease detection in digital pathology.

Purpose of the Study:

To investigate the impact of major histological artifacts on the accuracy of a deep learning-based prostate cancer detection model.
To evaluate model performance across diverse datasets from multiple institutions and scanner systems.
To identify the need for strategies mitigating artifact-induced accuracy loss.

Main Methods:

Digitally reproduced major types of histological artifacts.
Systematically explored artifact influence using six datasets from four institutions.
Utilized a pre-trained, validated deep learning model for prostate cancer detection.

Main Results:

Histological artifacts, dependent on severity, caused a substantial loss in model performance.
Model accuracy was significantly affected by variations in staining, thickness, and processing artifacts.
Performance degradation was observed across different scanner systems and institutions.

Conclusions:

Histological artifacts pose a significant challenge to the accuracy of deep learning models in digital pathology.
Strategies to prevent diagnostic accuracy loss due to artifacts are necessary.
Stress-testing models with synthetically generated artifacts is essential for clinical validation.