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

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

A coach-supported, digital parenting programme for parents of adolescents at risk of suicide: pilot trial of acceptability, feasibility, validity and short-term effects.

BJPsych open·2026

Same author

A Dosimetric Comparison of the Accumulated Dose in Prostate SBRT for Non-Adaptive and Adaptive External Beam Radiotherapy.

Cancers·2026

Same author

Identifying Clinical Characteristics of Young People with Treatment-Resistant Schizophrenia Undergoing Community Initiation of Clozapine.

Schizophrenia bulletin·2026

Same author

Structured Illumination Microscopy.

Methods in molecular biology (Clifton, N.J.)·2026

Same author

Initial physical health assessment for psychosis in Australia and New Zealand: 2026 recommendations.

The Australian and New Zealand journal of psychiatry·2026

Same author

Impact of Early Intervention Services on Substance Use Outcomes Among Young People at Risk for Psychosis.

Psychiatric services (Washington, D.C.)·2026

Same journal

Correction to "On the shape of the radiation survival curve in tumor spheroids: The role of oxygen heterogeneity".

Medical physics·2026

Same journal

Multi-view constrained semi-supervised vertebra detection for 3D ultrasound spine volume.

Medical physics·2026

Same journal

Accuracy of quantitative <sup>177</sup>Lu SPECT/CT imaging: A systematic review.

Medical physics·2026

Same journal

Physics-constrained dual-domain network for CBCT reconstruction from orthogonal X-rays in gynecologic radiotherapy.

Medical physics·2026

Same journal

Decomposition-based harmonization for quantitative PET imaging across scanners and radiotracers.

Medical physics·2026

Same journal

Development and evaluation of an in vivo dose-based monitoring system for electron FLASH radiation therapy.

Medical physics·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Dec 28, 2025

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging

Published on: November 10, 2015

Hippocampus segmentation on noncontrast CT using deep learning.

Evan Porter^1,2,3, Patricia Fuentes^2,4, Zaid Siddiqui^2,3

¹Department of Medical Physics, Wayne State University, Detroit, MI, USA.

Medical Physics

|February 18, 2020

Summary

This summary is machine-generated.

Automated deep learning models can now segment the hippocampus using CT scans alone, matching expert accuracy for radiotherapy planning. This AI approach simplifies treatment and reduces costs by eliminating the need for MRI scans.

Keywords:

CT ResNet U-Net attention gating deep learning hippocampus segmentation whole-brain radiotherapy

More Related Videos

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

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

Published on: November 30, 2022

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Related Experiment Videos

Last Updated: Dec 28, 2025

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging

Published on: November 10, 2015

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

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

Published on: November 30, 2022

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Area of Science:

Radiotherapy and Medical Imaging
Artificial Intelligence in Medicine
Neuroimaging and Radiation Oncology

Background:

Accurate hippocampal segmentation is crucial for hippocampal avoidance whole-brain radiotherapy.
Current methods rely on high-resolution MRI and expert manual segmentation, increasing complexity and cost.
Automating segmentation using deep learning can streamline the process and reduce potential image registration uncertainties.

Purpose of the Study:

To investigate the accuracy and reliability of automated hippocampal segmentation using deep learning models solely from CT images.
To compare the performance of these AI models against expert manual segmentation using MRI-CT fusion.
To assess the potential of AI to reduce complexity and cost in radiotherapy planning.

Main Methods:

Retrospective analysis of 390 Gamma Knife patients with both CT and MR images.
Development and training of four 3D deep convolutional network models, including an Attention-Gated 3D ResNet (AG-3D ResNet).
Evaluation using nested tenfold validation, calculating the 100% Hausdorff distance (HD), and assessing against RTOG 0933 criteria (HD ≤ 7 mm).

Main Results:

The AG-3D ResNet achieved a bilateral hippocampus passing rate of 80.2% across 90 trained models.
This performance was comparable to the pass rate of physicians during centralized review for the RTOG 0933 Phase II clinical trial (P = 0.3345).
The study demonstrates the feasibility of accurate hippocampal segmentation from CT images alone.

Conclusions:

The proposed AG-3D ResNet model demonstrates comparable accuracy to expert physicians for hippocampal segmentation using noncontrast CT images.
AI-driven segmentation from CT alone offers a viable alternative to MRI-based methods, simplifying radiotherapy planning.
This approach has the potential to significantly reduce treatment planning complexity, imaging requirements, and associated costs.