Nuclei Segmentation in Histopathological Images with Enhanced U-Net3+

Bishal Ranjan Swain, Kyung Joo Cheoi, Jaepil Ko
Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, PMLR 250:1513-1530, 2024.

Abstract

In the rapidly evolving field of nuclei segmentation, there is an increasing trend towards developing a universal segmentation model capable of delivering top-tier results across diverse datasets. While achieving this is the ultimate goal, we argue that such a model should also outperform dataset-specific specialized models. To this end, we propose a task-specific feature sensitive U-Net model, that sets a baseline standard in segmentation of nuclei in histopathological images. We meticulously select and optimize the underlying U-Net3+ model, using adaptive feature selection to capture both short- and long-range dependencies. Max blur pooling is included to achieve scale and position invariance, while DropBlock is utilized to mitigate overfitting by selectively obscuring feature map regions. Additionally, a Guided Filter Block is employed to delineate fine-grained details in nuclei structures. Furthermore, we apply various data augmentation techniques, along with stain normalization, to reduce inconsistencies and thus resulting in significantly outperforming the state-of-the-art performance and paving the way for precise nuclear segmentation essential for cancer diagnosis and possible treatment strategies.

Cite this Paper

BibTeX
@InProceedings{pmlr-v250-swain24a, title = {Nuclei Segmentation in Histopathological Images with Enhanced U-Net3+}, author = {Swain, Bishal Ranjan and Cheoi, Kyung Joo and Ko, Jaepil}, booktitle = {Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning}, pages = {1513--1530}, year = {2024}, editor = {Burgos, Ninon and Petitjean, Caroline and Vakalopoulou, Maria and Christodoulidis, Stergios and Coupe, Pierrick and Delingette, Hervé and Lartizien, Carole and Mateus, Diana}, volume = {250}, series = {Proceedings of Machine Learning Research}, month = {03--05 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v250/main/assets/swain24a/swain24a.pdf}, url = {https://proceedings.mlr.press/v250/swain24a.html}, abstract = {In the rapidly evolving field of nuclei segmentation, there is an increasing trend towards developing a universal segmentation model capable of delivering top-tier results across diverse datasets. While achieving this is the ultimate goal, we argue that such a model should also outperform dataset-specific specialized models. To this end, we propose a task-specific feature sensitive U-Net model, that sets a baseline standard in segmentation of nuclei in histopathological images. We meticulously select and optimize the underlying U-Net3+ model, using adaptive feature selection to capture both short- and long-range dependencies. Max blur pooling is included to achieve scale and position invariance, while DropBlock is utilized to mitigate overfitting by selectively obscuring feature map regions. Additionally, a Guided Filter Block is employed to delineate fine-grained details in nuclei structures. Furthermore, we apply various data augmentation techniques, along with stain normalization, to reduce inconsistencies and thus resulting in significantly outperforming the state-of-the-art performance and paving the way for precise nuclear segmentation essential for cancer diagnosis and possible treatment strategies.} }
Endnote
%0 Conference Paper %T Nuclei Segmentation in Histopathological Images with Enhanced U-Net3+ %A Bishal Ranjan Swain %A Kyung Joo Cheoi %A Jaepil Ko %B Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ninon Burgos %E Caroline Petitjean %E Maria Vakalopoulou %E Stergios Christodoulidis %E Pierrick Coupe %E Hervé Delingette %E Carole Lartizien %E Diana Mateus %F pmlr-v250-swain24a %I PMLR %P 1513--1530 %U https://proceedings.mlr.press/v250/swain24a.html %V 250 %X In the rapidly evolving field of nuclei segmentation, there is an increasing trend towards developing a universal segmentation model capable of delivering top-tier results across diverse datasets. While achieving this is the ultimate goal, we argue that such a model should also outperform dataset-specific specialized models. To this end, we propose a task-specific feature sensitive U-Net model, that sets a baseline standard in segmentation of nuclei in histopathological images. We meticulously select and optimize the underlying U-Net3+ model, using adaptive feature selection to capture both short- and long-range dependencies. Max blur pooling is included to achieve scale and position invariance, while DropBlock is utilized to mitigate overfitting by selectively obscuring feature map regions. Additionally, a Guided Filter Block is employed to delineate fine-grained details in nuclei structures. Furthermore, we apply various data augmentation techniques, along with stain normalization, to reduce inconsistencies and thus resulting in significantly outperforming the state-of-the-art performance and paving the way for precise nuclear segmentation essential for cancer diagnosis and possible treatment strategies.
APA
Swain, B.R., Cheoi, K.J. & Ko, J.. (2024). Nuclei Segmentation in Histopathological Images with Enhanced U-Net3+. Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 250:1513-1530 Available from https://proceedings.mlr.press/v250/swain24a.html.

Related Material