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

Computed Tomography01:10

Computed Tomography

Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Invariant Content Representation for Generalizable Medical Image Segmentation.

Journal of imaging informatics in medicine·2024
Same author

iERM: An Interpretable Deep Learning System to Classify Epiretinal Membrane for Different Optical Coherence Tomography Devices: A Multi-Center Analysis.

Journal of clinical medicine·2023
See all related articles

Related Experiment Video

Updated: Jun 26, 2026

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

41.0K

ITSRS: An Inverse Taylor Series Adaptive Loss Based on Synergized Regional-Structural Information for Medical Image

Rui Han1, Zhiming Cheng2, Jianxiang Zhao1

  • 1School of Cyberspace Security, Hangzhou Dianzi University, Hangzhou, 310018, China.

Journal of Imaging Informatics in Medicine
|February 26, 2026
PubMed
Summary

A novel Inverse Taylor Synergized Regional-Structural (ITSRS) loss function improves medical image segmentation by balancing regional details and global structure. This method enhances accuracy and robustness across diverse datasets, outperforming existing loss functions.

Keywords:
Computing gradientsInverse taylor adaptive mechanismLoss functionSynergized regional-structural

More Related Videos

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.5K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

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

Published on: September 25, 2019

49.5K

Related Experiment Videos

Last Updated: Jun 26, 2026

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

41.0K
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.5K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

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

Published on: September 25, 2019

49.5K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Machine Learning

Background:

  • Accurate medical image segmentation is crucial for diagnosis and treatment.
  • Global loss functions struggle with irrelevant regions, while region-specific losses may lose structural context.
  • Existing methods face challenges in balancing regional specificity and global continuity.

Purpose of the Study:

  • To introduce a novel loss function, Inverse Taylor Synergized Regional-Structural (ITSRS) Loss, for enhanced medical image segmentation.
  • To address the trade-off between regional specificity and global structural relationships in segmentation.
  • To adaptively optimize hyperparameters for improved segmentation accuracy.

Main Methods:

  • Designed a Synergized Regional-Structural (SRS) loss function using overlapping local regions to maintain regional and global continuity.
  • Developed an Inverse Taylor-based (IT) adaptive mechanism to refine SRS, forming ITSRS.
  • Utilized inverse Taylor expansion for adaptive balancing of false positives and false negatives, enhancing stability and structural awareness.

Main Results:

  • ITSRS demonstrated improved performance across six medical image segmentation datasets.
  • On Kvasir-SEG, mean Dice increased from 83.03% to 87.15%, and HD95 decreased from 6.826 to 6.464.
  • ITSRS consistently outperformed existing loss functions in accuracy and robustness.

Conclusions:

  • The proposed ITSRS loss function effectively balances regional and structural information for superior medical image segmentation.
  • ITSRS offers improved stability, responsiveness to data imbalance, and fine-grained structural awareness.
  • ITSRS represents a significant advancement in medical image segmentation loss functions, applicable across various modalities and tasks.