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

Nano-enabled spatially selective protein degradation modulates lactate metabolism to potentiate antitumor immunity in liver cancer.

Nature nanotechnology·2026
Same author

ICAM-1 promotes T cell glycolytic reprogramming and tumor infiltration to drive 18F-FDG PET flares following radiotherapy.

Protein & cell·2025
Same author

A Nanoradiosensitizer Potentiates Tumor Radiotherapy through JFK Inhibition and Hypoxia Alleviation.

Nano letters·2025
Same author

Noncanonical UPR factor CREB3L2 drives immune evasion of triple-negative breast cancer through Hedgehog pathway modulation in T cells.

Science advances·2025
Same author

<sup>68</sup>Ga-grazytracer PET for noninvasive assessment of response to immunotherapy in solid tumors and lymphomas: a phase 1/2 clinical trial.

Nature communications·2024
Same author

Targeted protein degradation combined with PET imaging reveals the role of host PD-L1 in determining anti-PD-1 therapy efficacy.

European journal of nuclear medicine and molecular imaging·2024

Related Experiment Video

Updated: Aug 9, 2025

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

168

Colorectal cancer lymph node metastasis prediction with weakly supervised transformer-based multi-instance learning.

Luxin Tan1, Huan Li1, Jinze Yu2,3,4

  • 1Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education), Department of Pathology, Peking University Cancer Hospital & Institute, Beijing, 100142, China.

Medical & Biological Engineering & Computing
|February 22, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces a deep learning system for colorectal cancer (CRC) lymph node classification, improving diagnostic accuracy and efficiency. The DT-DSMIL model aids pathologists by accurately identifying metastatic lymph nodes in whole slide images (WSIs).

Keywords:
Colorectal cancerComputer-aided diagnosingDeep learningLymph node metastasisMulti-instance learningVision transformerWhole slide image

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K

Related Experiment Videos

Last Updated: Aug 9, 2025

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

168
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K

Area of Science:

  • Oncology
  • Pathology
  • Computer Science

Background:

  • Lymph node metastasis is a critical prognostic factor in colorectal cancer (CRC).
  • Accurate pathological examination of lymph nodes is labor-intensive and time-consuming.
  • Expert pathologists face a significant burden in inspecting whole slide images (WSIs) for metastasis.

Purpose of the Study:

  • To develop a deep learning system for automated colorectal cancer lymph node classification.
  • To reduce the workload of pathologists and accelerate the diagnostic process.
  • To improve the accuracy and efficiency of detecting lymph node metastasis in CRC.

Main Methods:

  • A transformer-based multi-instance learning (MIL) model, DT-DSMIL, was developed using a deformable transformer and a dual-stream MIL framework.
  • The system integrates local and global image feature extraction for classification.
  • A diagnostic system combining DT-DSMIL with Faster R-CNN was created to detect, crop, and classify lymph nodes within WSIs.

Main Results:

  • The DT-DSMIL model achieved 95.3% accuracy and an AUC of 0.9762 for single lymph node classification on a dataset of 843 CRC slides.
  • The system demonstrated high AUC values for micro-metastasis (0.9816) and macro-metastasis (0.9902).
  • The diagnostic system reliably localized metastatic regions, showing potential to minimize false negatives and identify mislabeled slides.

Conclusions:

  • The developed deep learning system, DT-DSMIL, effectively classifies lymph node metastasis in colorectal cancer.
  • The system enhances diagnostic efficiency and accuracy, supporting pathologists in clinical practice.
  • This AI-driven approach shows significant promise for improving the management of colorectal cancer patients.