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

Search research articles

Related Experiment Video

Updated: Apr 10, 2026

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models

Published on: June 20, 2025

MesoRet: a reticulin stain-based deep learning algorithm to assist diffuse mesothelioma subtyping.

Giulia Orlando¹, Anna Paola Ferrero², Giorgia Andrea Impalà²

¹Department of Oncology, University of Turin, Turin, Italy.

|April 9, 2026

Summary

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Targeted therapies in thoracic neuroendocrine tumors: challenges and failures of tyrosine kinase inhibition in lung and thymic carcinoids.

Expert opinion on pharmacotherapy·2026

Same author

IASLC Update on Classification of Pulmonary Neuroendocrine Neoplasms.

Journal of thoracic oncology : official publication of the International Association for the Study of Lung Cancer·2026

Same author

Three-Tier Prognostic Stratification of Lung Carcinoids (NET G1-G2-G3) by Multivariable, Data-Driven Integration of Ki-67 and Mitotic Count.

Endocrine pathology·2026

Same author

Stromal-only endometriosis catamenial pneumothorax: A diagnostic algorithm with potential pitfalls.

Virchows Archiv : an international journal of pathology·2026

Same author

The antimetastatic effects of calorie restriction are negated by voluntary exercise in an aggressive breast cancer mouse model.

Proceedings of the National Academy of Sciences of the United States of America·2026

Same author

Reply to the Letter to the Editor: CT-guided lung biopsy in patients with interstitial lung abnormalities.

European radiology·2026

This summary is machine-generated.

A new deep learning model, MesoRet, accurately identifies mesothelioma patterns using reticulin stains. This AI tool aids in histologic subtyping, improving diagnostic accuracy and consistency for diffuse mesothelioma.

Area of Science:

Oncology
Pathology
Artificial Intelligence in Medicine

Background:

Diffuse mesothelioma diagnosis relies on accurate histologic subtyping, which can be challenging.
Reticulin staining is crucial for identifying architectural patterns in mesothelioma.
Distinguishing between epithelioid, sarcomatoid, and transitional patterns is key for prognosis and treatment.

Purpose of the Study:

To develop and validate a deep learning model (MesoRet) for analyzing reticulin-stained whole slide images of diffuse mesothelioma.
To accurately identify transitional features and assist in the histologic subtyping of diffuse mesothelioma.
To compare the model's performance against expert pathologists.

Main Methods:

A dataset of 115 diffuse mesothelioma cases from two institutions was curated.

Keywords:

computational pathology.deep learning diffuse mesothelioma reticulin stain transitional mesothelioma

More Related Videos

Generation and Expansion of Primary, Malignant Pleural Mesothelioma Tumor Lines

Generation and Expansion of Primary, Malignant Pleural Mesothelioma Tumor Lines

Published on: April 21, 2022

Elastic Staining on Paraffin-embedded Slides of pT3N0M0 Gastric Cancer Tissue

Elastic Staining on Paraffin-embedded Slides of pT3N0M0 Gastric Cancer Tissue

Published on: May 1, 2019

Related Experiment Videos

Last Updated: Apr 10, 2026

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models

Published on: June 20, 2025

Generation and Expansion of Primary, Malignant Pleural Mesothelioma Tumor Lines

Generation and Expansion of Primary, Malignant Pleural Mesothelioma Tumor Lines

Published on: April 21, 2022

Elastic Staining on Paraffin-embedded Slides of pT3N0M0 Gastric Cancer Tissue

Elastic Staining on Paraffin-embedded Slides of pT3N0M0 Gastric Cancer Tissue

Published on: May 1, 2019

Reticulin-stained whole-slide images were used to train a supervised deep learning model (MesoRet) on the Aiforia Create platform.

The model was trained to distinguish epithelioid, sarcomatoid, and transitional patterns and validated on independent slides.

Main Results:

MesoRet achieved high accuracy in identifying reticulin patterns across mesothelioma histotypes, with 96.32% precision and 99.06% sensitivity.
The model successfully excluded artifacts and non-tumour tissue.
MesoRet outperformed expert pathologists in identifying transitional patterns, reducing diagnostic time and errors.

Conclusions:

MesoRet offers an accurate and objective method for detecting reticulin patterns in mesothelioma, aiding histological subtyping.
The model contributes to more consistent diagnoses and shows promise for improving diagnostic precision.
Further validation is needed, but MesoRet has the potential to guide therapeutic decision-making in mesothelioma.