Nuclei segmentation and classification from histopathology images using federated learning for end-edge platform.
Accurate nuclei segmentation and classification in histology images are critical for cancer detection but remain challenging due to color inconsistency, blurry boundaries, and overlapping nuclei. Manual segmentation is time-consuming and labor-intensive, highlighting the need for efficient and scala...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0322749 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849318363607597056 |
|---|---|
| author | Anjir Ahmed Chowdhury S M Hasan Mahmud Md Palash Uddin Seifedine Kadry Jung-Yeon Kim Yunyoung Nam |
| author_facet | Anjir Ahmed Chowdhury S M Hasan Mahmud Md Palash Uddin Seifedine Kadry Jung-Yeon Kim Yunyoung Nam |
| author_sort | Anjir Ahmed Chowdhury |
| collection | DOAJ |
| description | Accurate nuclei segmentation and classification in histology images are critical for cancer detection but remain challenging due to color inconsistency, blurry boundaries, and overlapping nuclei. Manual segmentation is time-consuming and labor-intensive, highlighting the need for efficient and scalable automated solutions. This study proposes a deep learning framework that combines segmentation and classification to enhance nuclei evaluation in histopathology images. The framework follows a two-stage approach: first, a SegNet model segments the nuclei regions, and then a DenseNet121 model classifies the segmented instances. Hyperparameter optimization using the Hyperband method enhances the performance of both models. To protect data privacy, the framework employs a FedAvg-based federated learning scheme, enabling decentralized training without exposing sensitive data. For efficient deployment on edge devices, full integer quantization is applied to reduce computational overhead while maintaining accuracy. Experimental results show that the SegNet model achieves 91.4% Mean Pixel Accuracy (MPA), 63% Mean Intersection over Union (MIoU), and 90.6% Frequency-Weighted IoU (FWIoU). The DenseNet121 classifier achieves 83% accuracy and a 67% Matthews Correlation Coefficient (MCC), surpassing state-of-the-art models. Post-quantization, both models exhibit performance gains of 1.3% and 1.0%, respectively. The proposed framework demonstrates high accuracy and efficiency, highlighting its potential for real-world clinical deployment in cancer diagnosis. |
| format | Article |
| id | doaj-art-e98f3f7ac65b4e4882e26288936c88fc |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-e98f3f7ac65b4e4882e26288936c88fc2025-08-20T03:50:52ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01207e032274910.1371/journal.pone.0322749Nuclei segmentation and classification from histopathology images using federated learning for end-edge platform.Anjir Ahmed ChowdhuryS M Hasan MahmudMd Palash UddinSeifedine KadryJung-Yeon KimYunyoung NamAccurate nuclei segmentation and classification in histology images are critical for cancer detection but remain challenging due to color inconsistency, blurry boundaries, and overlapping nuclei. Manual segmentation is time-consuming and labor-intensive, highlighting the need for efficient and scalable automated solutions. This study proposes a deep learning framework that combines segmentation and classification to enhance nuclei evaluation in histopathology images. The framework follows a two-stage approach: first, a SegNet model segments the nuclei regions, and then a DenseNet121 model classifies the segmented instances. Hyperparameter optimization using the Hyperband method enhances the performance of both models. To protect data privacy, the framework employs a FedAvg-based federated learning scheme, enabling decentralized training without exposing sensitive data. For efficient deployment on edge devices, full integer quantization is applied to reduce computational overhead while maintaining accuracy. Experimental results show that the SegNet model achieves 91.4% Mean Pixel Accuracy (MPA), 63% Mean Intersection over Union (MIoU), and 90.6% Frequency-Weighted IoU (FWIoU). The DenseNet121 classifier achieves 83% accuracy and a 67% Matthews Correlation Coefficient (MCC), surpassing state-of-the-art models. Post-quantization, both models exhibit performance gains of 1.3% and 1.0%, respectively. The proposed framework demonstrates high accuracy and efficiency, highlighting its potential for real-world clinical deployment in cancer diagnosis.https://doi.org/10.1371/journal.pone.0322749 |
| spellingShingle | Anjir Ahmed Chowdhury S M Hasan Mahmud Md Palash Uddin Seifedine Kadry Jung-Yeon Kim Yunyoung Nam Nuclei segmentation and classification from histopathology images using federated learning for end-edge platform. PLoS ONE |
| title | Nuclei segmentation and classification from histopathology images using federated learning for end-edge platform. |
| title_full | Nuclei segmentation and classification from histopathology images using federated learning for end-edge platform. |
| title_fullStr | Nuclei segmentation and classification from histopathology images using federated learning for end-edge platform. |
| title_full_unstemmed | Nuclei segmentation and classification from histopathology images using federated learning for end-edge platform. |
| title_short | Nuclei segmentation and classification from histopathology images using federated learning for end-edge platform. |
| title_sort | nuclei segmentation and classification from histopathology images using federated learning for end edge platform |
| url | https://doi.org/10.1371/journal.pone.0322749 |
| work_keys_str_mv | AT anjirahmedchowdhury nucleisegmentationandclassificationfromhistopathologyimagesusingfederatedlearningforendedgeplatform AT smhasanmahmud nucleisegmentationandclassificationfromhistopathologyimagesusingfederatedlearningforendedgeplatform AT mdpalashuddin nucleisegmentationandclassificationfromhistopathologyimagesusingfederatedlearningforendedgeplatform AT seifedinekadry nucleisegmentationandclassificationfromhistopathologyimagesusingfederatedlearningforendedgeplatform AT jungyeonkim nucleisegmentationandclassificationfromhistopathologyimagesusingfederatedlearningforendedgeplatform AT yunyoungnam nucleisegmentationandclassificationfromhistopathologyimagesusingfederatedlearningforendedgeplatform |