Semi-supervised tissue segmentation from histopathological images with consistency regularization and uncertainty estimation

Abstract Pathologists have depended on their visual experience to assess tissue structures in smear images, which was time-consuming, error-prone, and inconsistent. Deep learning, particularly Convolutional Neural Networks (CNNs), offers the ability to automate this procedure by recognizing patterns...

Full description

Saved in:
Bibliographic Details
Main Authors: G. V. S. Sudhamsh, S. Girisha, R. Rashmi
Format: Article
Language:English
Published: Nature Portfolio 2025-02-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-90221-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849724225632337920
author G. V. S. Sudhamsh
S. Girisha
R. Rashmi
author_facet G. V. S. Sudhamsh
S. Girisha
R. Rashmi
author_sort G. V. S. Sudhamsh
collection DOAJ
description Abstract Pathologists have depended on their visual experience to assess tissue structures in smear images, which was time-consuming, error-prone, and inconsistent. Deep learning, particularly Convolutional Neural Networks (CNNs), offers the ability to automate this procedure by recognizing patterns in tissue images. However, training these models necessitates huge amounts of labeled data, which can be difficult to come by due to the skill required for annotation and the unavailability of data, particularly for rare diseases. This work introduces a new semi-supervised method for tissue structure semantic segmentation in histopathological images. The study presents a CNN based teacher model that generates pseudo-labels to train a student model, aiming to overcome the drawbacks of conventional supervised learning approaches. Self-supervised training is used to improve the teacher model’s performance on smaller datasets. Consistency regularization is integrated to efficiently train the student model on labeled data. Further, the study uses Monte Carlo dropout to estimate the uncertainty of proposed model. The proposed model demonstrated promising results by achieving an mIoU score of 0.64 on a public dataset, highlighting its potential to improve segmentation accuracy in histopathological image analysis.
format Article
id doaj-art-55b89f126d854871b78dcb01d20f4fab
institution DOAJ
issn 2045-2322
language English
publishDate 2025-02-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-55b89f126d854871b78dcb01d20f4fab2025-08-20T03:10:49ZengNature PortfolioScientific Reports2045-23222025-02-0115111610.1038/s41598-025-90221-xSemi-supervised tissue segmentation from histopathological images with consistency regularization and uncertainty estimationG. V. S. Sudhamsh0S. Girisha1R. Rashmi2Department of Computer Science and Engineering, Manipal Institute of Technology Bengaluru, Manipal Academy of Higher EducationDepartment of Data Science and Computer Applications, Manipal Institute of Technology, Manipal Academy of Higher EducationDepartment of Computer Science and Engineering, Manipal Institute of Technology Bengaluru, Manipal Academy of Higher EducationAbstract Pathologists have depended on their visual experience to assess tissue structures in smear images, which was time-consuming, error-prone, and inconsistent. Deep learning, particularly Convolutional Neural Networks (CNNs), offers the ability to automate this procedure by recognizing patterns in tissue images. However, training these models necessitates huge amounts of labeled data, which can be difficult to come by due to the skill required for annotation and the unavailability of data, particularly for rare diseases. This work introduces a new semi-supervised method for tissue structure semantic segmentation in histopathological images. The study presents a CNN based teacher model that generates pseudo-labels to train a student model, aiming to overcome the drawbacks of conventional supervised learning approaches. Self-supervised training is used to improve the teacher model’s performance on smaller datasets. Consistency regularization is integrated to efficiently train the student model on labeled data. Further, the study uses Monte Carlo dropout to estimate the uncertainty of proposed model. The proposed model demonstrated promising results by achieving an mIoU score of 0.64 on a public dataset, highlighting its potential to improve segmentation accuracy in histopathological image analysis.https://doi.org/10.1038/s41598-025-90221-xComputer Aided Diagnostic SystemsDeep LearningHistopathological Image AnalysisSemantic SegmentationSemi-Supervised Learning
spellingShingle G. V. S. Sudhamsh
S. Girisha
R. Rashmi
Semi-supervised tissue segmentation from histopathological images with consistency regularization and uncertainty estimation
Scientific Reports
Computer Aided Diagnostic Systems
Deep Learning
Histopathological Image Analysis
Semantic Segmentation
Semi-Supervised Learning
title Semi-supervised tissue segmentation from histopathological images with consistency regularization and uncertainty estimation
title_full Semi-supervised tissue segmentation from histopathological images with consistency regularization and uncertainty estimation
title_fullStr Semi-supervised tissue segmentation from histopathological images with consistency regularization and uncertainty estimation
title_full_unstemmed Semi-supervised tissue segmentation from histopathological images with consistency regularization and uncertainty estimation
title_short Semi-supervised tissue segmentation from histopathological images with consistency regularization and uncertainty estimation
title_sort semi supervised tissue segmentation from histopathological images with consistency regularization and uncertainty estimation
topic Computer Aided Diagnostic Systems
Deep Learning
Histopathological Image Analysis
Semantic Segmentation
Semi-Supervised Learning
url https://doi.org/10.1038/s41598-025-90221-x
work_keys_str_mv AT gvssudhamsh semisupervisedtissuesegmentationfromhistopathologicalimageswithconsistencyregularizationanduncertaintyestimation
AT sgirisha semisupervisedtissuesegmentationfromhistopathologicalimageswithconsistencyregularizationanduncertaintyestimation
AT rrashmi semisupervisedtissuesegmentationfromhistopathologicalimageswithconsistencyregularizationanduncertaintyestimation