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

Machine Learning-Based Prediction of Drug-Induced QTc Changes in a Large Finnish Biobank Cohort.

Clinical and translational science·2026

Same author

Malignant vs. Non-malignant Annotations on TCGA Breast Cancer Whole Slide Images for AI Analysis.

Scientific data·2026

Same author

Clinicopathological characteristics of patients with inoperable non-small cell lung cancer harboring circulating NRF2 pathway mutations.

The Journal of pathology·2026

Same author

The role of digital twins in P4 medicine: A paradigm for modern healthcare.

NPJ digital medicine·2025

Same author

Threshold-Based Overlap of Breast Cancer High-Risk Classification Using Family History, Polygenic Risk Scores, and Traditional Risk Models in 180,398 Women.

Cancers·2025

Same author

GenoGraph: An Interpretable Graph Contrastive Learning Approach for Identifying Breast Cancer Risk Variants.

IEEE transactions on computational biology and bioinformatics·2025

Search research articles

Related Experiment Video

Updated: Jul 12, 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

Nuclei instance segmentation from histopathology images using Bayesian dropout based deep learning.

Naga Raju Gudhe¹, Veli-Matti Kosma^2,3, Hamid Behravan²

¹Institute of Clinical Medicine, Pathology and Forensic Medicine, Multidisciplinary Cancer research community RC Cancer, University of Eastern Finland, P.O. Box 1627, Kuopio, 70211, Finland. raju.gudhe@uef.fi.

BMC Medical Imaging

|October 19, 2023

Summary

This study introduces a Bayesian deep learning model for nuclei segmentation in histopathology images, outperforming existing methods by quantifying prediction uncertainty for more reliable results in medical image analysis.

Keywords:

Bayesian deep learning Digital pathology Medical image analysis Nuclei segmentation Semantic segmentation Uncertainty estimation

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy

Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy

Published on: August 1, 2022

Related Experiment Videos

Last Updated: Jul 12, 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

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy

Whole-Brain Single-Cell Imaging and Analysis of Intact Neonatal Mouse Brains Using MRI, Tissue Clearing, and Light-Sheet Microscopy

Published on: August 1, 2022

Area of Science:

Medical Image Analysis
Computational Pathology
Deep Learning

Background:

Deterministic deep learning models excel in medical image analysis, including nuclei segmentation, but lack confidence assessment in predictions.
Current models prioritize accuracy over quantifying prediction reliability for critical diagnostic tasks.

Purpose of the Study:

To develop a semantic segmentation model using Bayesian representation for nuclei segmentation in histopathology images.
To quantify epistemic uncertainty in model predictions for improved reliability.
To enhance diagnostic accuracy in medical image analysis through uncertainty estimation.

Main Methods:

Proposed a Bayesian deep learning model for semantic segmentation of nuclei.
Employed Monte Carlo (MC) dropout during inference for estimating prediction uncertainty.
Evaluated performance on the PanNuke dataset, comparing against U-Net, SegNet, and Hover-net.

Main Results:

Achieved a mean F1-score of 0.893 ± 0.008 and IoU of 0.868 ± 0.003 on the PanNuke dataset.
Outperformed the state-of-the-art Hover-net (F1: 0.871 ± 0.010, IoU: 0.840 ± 0.032).
Demonstrated superior nuclei segmentation accuracy and reliable uncertainty quantification.

Conclusions:

The Bayesian deep learning approach with MC dropout offers superior nuclei segmentation performance in histopathology.
Incorporating epistemic uncertainty estimation leads to more reliable predictions for medical image analysis.
This work contributes to developing more accurate and dependable computer-aided diagnostic systems.