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

Diabetes mellitus affects long-term survival in hepatitis B virus-related hepatocellular carcinoma patients: A propensity score-matched analysis.

Medicine·2021
Same author

Intermedin facilitates hepatocellular carcinoma cell survival and invasion via ERK1/2-EGR1/DDIT3 signaling cascade.

Scientific reports·2021
Same author

Effect of the Affordances of the FM New Media Communication Interface Design for Smartphones.

Sensors (Basel, Switzerland)·2021
Same author

Circular RNA circGSE1 Promotes Cervical Cancer Progression Through miR-138-5p/Vimentin.

OncoTargets and therapy·2021
Same author

Factors Correlated with the Accuracy of Colposcopy-Directed Biopsy: A Systematic Review and Meta-Analysis.

Journal of investigative surgery : the official journal of the Academy of Surgical Research·2020
Same author

Post-transplant Lymphoproliferative Disorder in Recipient's Reconstructed Middle Hepatic Vein After Pediatric Living Donor Liver Transplant: A Case Report.

Transplantation proceedings·2020

Related Experiment Video

Updated: Nov 2, 2025

Endoscopic Endonasal Trans-sphenoidal Approach: Minimally Invasive Surgery for Pituitary Adenomas
07:43

Endoscopic Endonasal Trans-sphenoidal Approach: Minimally Invasive Surgery for Pituitary Adenomas

Published on: January 17, 2018

19.1K

Image-driven classification of functioning and nonfunctioning pituitary adenoma by deep convolutional neural

Hongyu Li1,2, Qi Zhao1, Yihua Zhang3

  • 1State Key Laboratory of Oncology in South China, Cancer Center, Collaborative Innovation Center for Cancer Medicine, School of Life Science, Sun Yat-sen University, Guangzhou, Guangdong 510060, China.

Computational and Structural Biotechnology Journal
|June 17, 2021
PubMed
Summary

This study introduces a deep learning model using MRI scans to accurately segment and classify pituitary adenomas (PAs), aiding in early diagnosis and treatment planning.

Keywords:
Deep learningMRIPituitary adenomas

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.1K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

3.2K

Related Experiment Videos

Last Updated: Nov 2, 2025

Endoscopic Endonasal Trans-sphenoidal Approach: Minimally Invasive Surgery for Pituitary Adenomas
07:43

Endoscopic Endonasal Trans-sphenoidal Approach: Minimally Invasive Surgery for Pituitary Adenomas

Published on: January 17, 2018

19.1K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.1K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

3.2K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Oncology

Background:

  • Pituitary adenoma (PA) function is crucial for treatment, but MRI analysis is time-consuming and subjective.
  • Accurate segmentation and classification of PAs are essential for effective patient management.

Purpose of the Study:

  • To develop and validate a deep learning model for automated segmentation and classification of pituitary adenomas using 3D MRI.
  • To distinguish functioning PAs from non-functioning subtypes to aid in treatment strategy development.

Main Methods:

  • A convolutional neural network (CNN) model was developed for segmentation and classification of PAs from 185 patient MRI scans.
  • Transfer learning and an attention mechanism were incorporated into the classification model for enhanced feature extraction and interpretability.

Main Results:

  • The segmentation model achieved high performance with Dice scores ranging from 0.8091 to 0.8188 across datasets.
  • The classification model demonstrated strong performance with AUROC values between 0.7881 and 0.8478.
  • The model showed consistent results in internal validation and external testing datasets.

Conclusions:

  • This work presents the first deep learning-based models for PA segmentation and classification from MRI.
  • The developed models offer a promising tool for automated, accurate, and efficient early diagnosis and subtyping of pituitary adenomas.