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

The Neuroproteomic Basis of Enhanced Perception and Processing of Brood Signals That Trigger Increased Reproductive Investment in Honeybee (<i>Apis mellifera</i>) Workers.

Molecular & cellular proteomics : MCP·2020

Same author

TIM-3 blockade combined with bispecific antibody MT110 enhances the anti-tumor effect of γδ T cells.

Cancer immunology, immunotherapy : CII·2020

Same author

Correction for Han et al., "<i>In Vitro</i> Susceptibility of Hepatitis C Virus Genotype 1 through 6 Clinical Isolates to the Pangenotypic NS3/4A Inhibitor Voxilaprevir".

Journal of clinical microbiology·2020

Same author

Effect of Nutritional Restriction on the Hair Follicles Development and Skin Transcriptome of Chinese Merino Sheep.

Animals : an open access journal from MDPI·2020

Same author

Pan-Genome of Wild and Cultivated Soybeans.

Cell·2020

Same author

Colchicine prevents atrial fibrillation promotion by inhibiting IL-1β-induced IL-6 release and atrial fibrosis in the rat sterile pericarditis model.

Biomedicine & pharmacotherapy = Biomedecine & pharmacotherapie·2020

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: May 14, 2025

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

Inference-specific learning for improved medical image segmentation.

Yizheng Chen¹, Sheng Liu^1,2, Mingjie Li¹

¹Department of Radiation Oncology, Stanford University, Stanford, California, USA.

Medical Physics

|May 12, 2025

Summary

This summary is machine-generated.

This study introduces an inference-specific learning strategy to improve deep learning model accuracy. By aligning training data with inference data, the method enhances predictions for tasks like medical image segmentation.

Keywords:

deep learning medical image registration segmentation training data

More Related Videos

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Related Experiment Videos

Last Updated: May 14, 2025

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

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Area of Science:

Artificial Intelligence
Machine Learning
Medical Imaging

Background:

Deep learning networks rely on training data for parameter fitting.
Inaccurate predictions arise when inference data distribution differs from training data.

Purpose of the Study:

To enhance deep learning prediction accuracy on unseen inference data.
To bridge the distribution gap between training and inference datasets.

Main Methods:

Developed an inference-specific learning strategy without altering network architecture.
Created inference-specific training datasets by aligning training data to inference data.
Applied the strategy to medical image auto-segmentation using CT datasets.

Main Results:

Achieved significant improvements in organ-averaged mean Dice scores across multiple datasets.
Demonstrated notable accuracy increases for challenging organs, like the gallbladder.
Showcased enhanced accuracy and robustness through organ mask-based weak supervision and moving-averaged calculations.

Conclusions:

The inference-specific learning strategy consistently improves auto-segmentation accuracy.
This approach shows potential for broad application in enhancing deep learning decision-making.