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

Microwave-assisted thermal profiling of blood: a potential biomarker for differentiating cancer and non-cancer states.

Journal of medical engineering & technology·2026
Same author

Whole-body MRI versus fluorodeoxyglucose PET/CT for extra-nodal metastatic staging in lung adenocarcinoma.

European journal of radiology·2026
Same author

Artificial intelligence for detecting fetal orofacial clefts and advancing medical education.

Nature communications·2026
Same author

Multi-omic analysis of deep learning-derived phenotypes links ophthalmic imaging to cardiovascular and neurological traits.

Nature cardiovascular research·2026
Same author

From pixels to polygons: A survey of deep learning approaches for medical image-to-mesh reconstruction.

Medical image analysis·2026
Same author

Fourier-Net+: Band-Limited Spatial Representation for Efficient Medical Image Registration.

IEEE transactions on neural networks and learning systems·2026

Related Experiment Video

Updated: Oct 11, 2025

Automated Measurement of Cryptococcal Species Polysaccharide Capsule and Cell Body
08:08

Automated Measurement of Cryptococcal Species Polysaccharide Capsule and Cell Body

Published on: January 11, 2018

7.5K

MICaps: Multi-instance capsule network for machine inspection of Munro's microabscess.

Anabik Pal1, Akshay Chaturvedi2, Aditi Chandra3

  • 1National Library of Medicine, National Institutes of Health, Bethesda, MD, USA.

Computers in Biology and Medicine
|December 5, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces MICaps, an AI framework for detecting neutrophils in skin biopsies, crucial for diagnosing psoriasis. MICaps improves diagnostic accuracy and reduces model parameters, aiding dermatologists.

Keywords:
Capsule networkConvolutional neural networkDatasetHistopathology imageMunro's microabscessPsoriasis skin biopsySegmentationSuper-pixel

More Related Videos

Utilization of Capsules for Negative Staining of Viral Samples within Biocontainment
08:22

Utilization of Capsules for Negative Staining of Viral Samples within Biocontainment

Published on: July 19, 2017

10.4K
A Unique Mouse Model for Quantitative Assessment of Biofilm Formation on Surgical Implants in Subcutaneous Abscess
03:44

A Unique Mouse Model for Quantitative Assessment of Biofilm Formation on Surgical Implants in Subcutaneous Abscess

Published on: June 6, 2025

215

Related Experiment Videos

Last Updated: Oct 11, 2025

Automated Measurement of Cryptococcal Species Polysaccharide Capsule and Cell Body
08:08

Automated Measurement of Cryptococcal Species Polysaccharide Capsule and Cell Body

Published on: January 11, 2018

7.5K
Utilization of Capsules for Negative Staining of Viral Samples within Biocontainment
08:22

Utilization of Capsules for Negative Staining of Viral Samples within Biocontainment

Published on: July 19, 2017

10.4K
A Unique Mouse Model for Quantitative Assessment of Biofilm Formation on Surgical Implants in Subcutaneous Abscess
03:44

A Unique Mouse Model for Quantitative Assessment of Biofilm Formation on Surgical Implants in Subcutaneous Abscess

Published on: June 6, 2025

215

Area of Science:

  • Dermatopathology
  • Computational Pathology
  • Artificial Intelligence in Medicine

Background:

  • Munro's Microabscess (MM) is a key indicator for psoriasis diagnosis.
  • Identifying neutrophils in the Stratum Corneum (SC) is vital for MM detection in skin biopsies.
  • Manual microscopic inspection is time-consuming and prone to errors due to staining variations.

Purpose of the Study:

  • To develop an automated computational framework to assist dermatologists in diagnosing psoriasis.
  • To improve the accuracy and efficiency of neutrophil detection in skin biopsies.
  • To reduce diagnostic errors associated with manual microscopic examination.

Main Methods:

  • A computational framework, MICaps, was developed using UNet and CapsNet for SC segmentation and neutrophil classification.
  • CapsNet was chosen for its superior hierarchical object representation and localization capabilities.
  • The framework was trained using Dice Loss and Focal Loss, and validated on 290 skin biopsy images.

Main Results:

  • MICaps demonstrated improved state-of-the-art diagnosis performance by up to 3.27%.
  • The framework significantly reduced the number of model parameters by 50%.
  • Comparative studies evaluated the effectiveness of Dice Loss and Focal Loss during training.

Conclusions:

  • The proposed MICaps framework enhances the accuracy of psoriasis diagnosis through automated neutrophil detection.
  • CapsNet-based approach offers a robust solution for segmentation and classification in histopathology.
  • MICaps represents a significant advancement in computational pathology for dermatological applications.