Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

High-dose furmonertinib as first-line treatment for untreated EGFR-mutated advanced NSCLC with central nervous system metastases: A phase 2 trial.

Cell reports. Medicine·2026
Same author

Retraction Note: Time-of-day immunochemotherapy in non-small cell lung cancer: a randomized phase 3 trial.

Nature medicine·2026
Same author

Organoid modeling of lung branching morphogenesis and epithelial lineage specification.

Developmental cell·2026
Same author

Effectiveness and safety of vedolizumab in real-world studies in Asian patients with inflammatory bowel disease: a systematic review and meta-analysis.

BMC gastroenterology·2026
Same author

Single-cell RNA sequencing reveals pancreatic cancer microenvironment heterogeneity for precision therapy.

Journal of translational internal medicine·2026
Same author

IL11⁺ fibroblasts are implicated in non-response to anti-TNFα via fibrosis in inflammatory bowel disease.

JCI insight·2026
Same journal

Facial iPPG heatmap patterns based on period-aware autoencoder show association with carotid atherosclerosis towards non-contact hemodynamic assessment.

Computer methods and programs in biomedicine·2026
Same journal

Explainable machine learning models predict liver fibrosis risk and outcome in the general population: Development and multi-cohort external validation.

Computer methods and programs in biomedicine·2026
Same journal

Evaluation of surrogate endpoints for survival outcomes using the surrogate package in R.

Computer methods and programs in biomedicine·2026
Same journal

Relative spectral and frication-based descriptors as numerical indicators of place of articulation shifts in fricatives produced by Polish children.

Computer methods and programs in biomedicine·2026
Same journal

Leaflet resection improves valve expansion and hemodynamic performance in redo TAVI with balloon- and self-expanding transcatheter heart valve configurations.

Computer methods and programs in biomedicine·2026
Same journal

Spectral super-resolution for Parkinson's voice via representation-level methods under mixed-reality acquisition.

Computer methods and programs in biomedicine·2026
See all related articles

Related Experiment Video

Updated: Jan 15, 2026

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

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

Published on: July 11, 2025

800

Detection-driven two-stage framework for intraoperative ROSE WSI classification.

Yingjiao Deng1, Qing Zhang1, Chunhua Zhou2

  • 1Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai, 200241, China.

Computer Methods and Programs in Biomedicine
|October 8, 2025
PubMed
Summary
This summary is machine-generated.

A new two-stage framework enhances rapid on-site evaluation (ROSE) of pancreatic cancer slides. This AI approach improves diagnostic accuracy and significantly reduces computational time for intraoperative decision-making.

Keywords:
Multiple instance learningObject detectionPancreatic solid lesionsWhole slide image analysis

More Related Videos

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.6K
Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment
13:01

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

4.5K

Related Experiment Videos

Last Updated: Jan 15, 2026

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

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

Published on: July 11, 2025

800
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.6K
Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment
13:01

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

4.5K

Area of Science:

  • Artificial Intelligence in Pathology
  • Digital Pathology
  • Computational Cytology

Background:

  • Solid pancreatic lesions (SPLs) are highly lethal gastrointestinal malignancies.
  • Rapid on-site evaluation (ROSE) is crucial for intraoperative diagnosis but faces interpretation challenges with gigapixel whole-slide images (WSIs).
  • Current ROSE interpretation is hindered by large image scale, sparse diagnostic regions, and the need for real-time feedback.

Purpose of the Study:

  • To develop a novel, efficient, and precise two-stage framework for ROSE whole-slide image (WSI) classification.
  • To emulate the clinical diagnostic workflow of cytopathologists for ROSE slide interpretation.
  • To accelerate real-time intraoperative decision-making in pancreatic cancer diagnosis.

Main Methods:

  • A two-stage framework combining object detection and multiple instance learning.
  • Stage 1: RoF DETR, a Transformer-based network for detecting cell clusters at 5x magnification, incorporating foundation model features and multi-scale fusion.
  • Stage 2: Prototype-guided multiple instance learning (PG-MIL) with pseudo-bag augmentation for 20x magnification patch extraction, enhancing discrimination and robustness.

Main Results:

  • Achieved 0.482 AP@0.5 in cell cluster detection and 92.36% AUC in WSI-level classification on a dedicated ROSE WSI dataset.
  • The proposed framework reduces computational overhead by approximately 100× compared to conventional WSI pipelines.
  • Inference time is halved, demonstrating significant efficiency gains.

Conclusions:

  • The developed framework offers a scalable and efficient solution for rapid cytological assessment of ROSE slides.
  • This approach has the potential to significantly support real-time intraoperative decision-making in clinical settings.
  • The AI-driven method addresses key challenges in ROSE interpretation, paving the way for improved pancreatic cancer diagnosis.