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

Search research articles

Related Experiment Video

Updated: Oct 25, 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

HMIC: Hierarchical Medical Image Classification, A Deep Learning Approach.

Kamran Kowsari^1,2,3, Rasoul Sali¹, Lubaina Ehsan⁴

¹Department of Systems and Information Engineering, University of Virginia, Charlottesville, VA 22904, USA.

Information (Basel)

|August 9, 2021

Summary

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

Explainable Machine Learning for Predicting Dengue Recovery Duration: Insights from Multi-Center Clinical Data.

Healthcare (Basel, Switzerland)·2026

Same author

Gestational weight gain and maternal immediate perinatal and postpartum outcomes in low and middle income countries: individual participant data meta-analyses.

BMJ medicine·2026

Same author

Structural and Hormonal Changes Associated With Starvation in Zambian Adult Patients With Esophageal Strictures: A Cross-Sectional Study.

Health science reports·2026

Same author

Highly stable photothermal CO<sub>2</sub> conversion to C<sub>2</sub>H<sub>6</sub> with 87% selectivity: cooperative charge redistribution in a heteronuclear catalyst stabilizes the reaction intermediates and enhances C-C coupling.

Materials horizons·2026

Same author

Atomically dispersed cobalt on niobium oxide enables photothermal nitrogen fixation via nitrogen-hydrogen coupling.

Journal of colloid and interface science·2026

Same author

Letter to the Editor on "Clinical profile and optical coherence tomography based morphological characteristics of coronary in-stent restenosis: A cross-sectional study".

Indian heart journal·2026

This study introduces Hierarchical Medical Image classification (HMIC), a novel deep learning approach for medical image analysis. HMIC improves diagnostic accuracy by classifying images hierarchically, outperforming traditional methods.

Area of Science:

Medical Imaging
Artificial Intelligence
Pathology

Background:

Deep learning significantly advances medical image analysis for diagnosis.
Traditional supervised classifiers face limitations in complex medical image classification tasks.
Current methods often treat medical image classification as a multi-class problem.

Purpose of the Study:

To introduce a novel Hierarchical Medical Image classification (HMIC) approach.
To address the limitations of traditional multi-class classification in medical imaging.
To improve diagnostic accuracy through a hierarchical deep learning framework.

Main Methods:

Implemented a hierarchical classification strategy using stacked deep learning models.
Developed the Hierarchical Medical Image classification (HMIC) approach.

Keywords:

deep Learning hierarchical classification hierarchical medical image classification medical imaging

Related Experiment Videos

Last Updated: Oct 25, 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

Utilized small bowel biopsy images for performance evaluation.

Main Results:

The HMIC approach demonstrated effective hierarchical classification capabilities.
Successfully classified parent-level categories: Celiac Disease, Environmental Enteropathy, and normal controls.
Classified child-level Celiac Disease Severity into four distinct grades (I, IIIa, IIIb, IIIC).

Conclusions:

Hierarchical Medical Image classification (HMIC) offers a promising alternative to traditional multi-class approaches.
The HMIC framework provides enhanced comprehension at different levels of the clinical hierarchy.
This method shows potential for improved diagnostic accuracy in medical image analysis.