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

An Experience-driven Interpretable Multi-task Model for Segmentation and Classification of Small Cell Lung Cancer and Non-small Cell Lung Cancer from CT Images.

IEEE journal of biomedical and health informatics·2026
Same author

PCSK9 inhibitor failure in a statin-intolerant FH patient with a novel LDLR variant: a case report.

Frontiers in cardiovascular medicine·2025
Same author

Recent Advancements in Hyperspectral Image Reconstruction from a Compressive Measurement.

Sensors (Basel, Switzerland)·2025
Same author

EISegNet: Enhancing Instrument Segmentation Network via Dual-View Disparity Estimation.

IEEE journal of biomedical and health informatics·2025
Same author

Multi-Task Collaborative Assisted Training Method for Grouping Fuzzy Categories Classification of Cervical Cancer Cells.

IEEE journal of biomedical and health informatics·2025
Same author

NpCIPK6-NpSnRK1 module facilitates intersubgeneric hybridization barriers in water lily (<i>Nymphaea</i>) by reducing abscisic acid content.

Horticulture research·2025

Related Experiment Video

Updated: Jun 28, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K

A multi-instance tumor subtype classification method for small PET datasets using RA-DL attention module guided deep

Zhaoshuo Diao1, Huiyan Jiang2

  • 1Software College, Northeastern University, Shenyang 110819, China.

Computers in Biology and Medicine
|April 16, 2024
PubMed
Summary

This study introduces a novel Radiomics-DeepLearning (RA-DL) attention method for accurate tumor subtype classification in small Positron Emission Tomography (PET) datasets. The approach enhances diagnostic capabilities for liver cancer, lung cancer, and lymphoma, even with limited patient data.

Keywords:
Biomedical classificationDeep learning featuresMulti-instance learningPositron emission tomographyRadiomics

More Related Videos

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

7.2K
PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator
10:48

PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator

Published on: December 28, 2017

9.5K

Related Experiment Videos

Last Updated: Jun 28, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K
Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

7.2K
PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator
10:48

PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator

Published on: December 28, 2017

9.5K

Area of Science:

  • Medical Imaging and Diagnostics
  • Artificial Intelligence in Healthcare
  • Oncology and Cancer Research

Background:

  • Positron Emission Tomography (PET) is vital for cancer diagnosis and staging, but accurate tumor subtype classification is challenging due to limited and imbalanced datasets.
  • Effective treatment planning relies on precise tumor subtype identification, with examples including diffuse large B-cell lymphoma, Hodgkin's lymphoma, adenocarcinoma, small cell carcinoma, squamous cell carcinoma, cholangiocarcinoma, and hepatocellular carcinoma.

Purpose of the Study:

  • To develop a novel Radiomics-DeepLearning (RA-DL) attention approach for precise tumor subtype classification in small, imbalanced PET datasets.
  • To overcome the limitations of small sample sizes in achieving accurate cancer subtype identification.

Main Methods:

  • Utilized Support Vector Machines (SVM) as a classifier for tumor subtypes, combined with radiomics and deep features extracted from PET images.
  • Employed an autoencoder for radiomics feature compression and an RA-DL-Attention mechanism to extract complementary deep features, minimizing redundancy.
  • Incorporated 2D Region of Interest (ROI) segmentation and image reconstruction as auxiliary tasks to address data limitations, aggregating lesion features using multi-instance learning.

Main Results:

  • Achieved high performance in lung cancer subtype classification with Area Under Curve (AUC) values of 0.82, 0.84, and 0.83.
  • Demonstrated notable results in lymphoma binary classification with AUC values of 0.95 and 0.75.
  • Showcased promising performance in liver tumor binary classification with AUC values of 0.84 and 0.86.

Conclusions:

  • The proposed RA-DL attention method significantly outperforms alternative approaches for tumor subtype classification on small PET datasets.
  • The integration of complementary radiomics and deep features enhances classification accuracy, offering a robust solution for challenging clinical scenarios.