DEPICTER: Deep representation clustering for histology annotation
- PMID: 38308865
- DOI: 10.1016/j.compbiomed.2024.108026
DEPICTER: Deep representation clustering for histology annotation
Abstract
Automatic segmentation of histopathology whole-slide images (WSI) usually involves supervised training of deep learning models with pixel-level labels to classify each pixel of the WSI into tissue regions such as benign or cancerous. However, fully supervised segmentation requires large-scale data manually annotated by experts, which can be expensive and time-consuming to obtain. Non-fully supervised methods, ranging from semi-supervised to unsupervised, have been proposed to address this issue and have been successful in WSI segmentation tasks. But these methods have mainly been focused on technical advancements in algorithmic performance rather than on the development of practical tools that could be used by pathologists or researchers in real-world scenarios. In contrast, we present DEPICTER (Deep rEPresentatIon ClusTERing), an interactive segmentation tool for histopathology annotation that produces a patch-wise dense segmentation map at WSI level. The interactive nature of DEPICTER leverages self- and semi-supervised learning approaches to allow the user to participate in the segmentation producing reliable results while reducing the workload. DEPICTER consists of three steps: first, a pretrained model is used to compute embeddings from image patches. Next, the user selects a number of benign and cancerous patches from the multi-resolution image. Finally, guided by the deep representations, label propagation is achieved using our novel seeded iterative clustering method or by directly interacting with the embedding space via feature space gating. We report both real-time interaction results with three pathologists and evaluate the performance on three public cancer classification dataset benchmarks through simulations. The code and demos of DEPICTER are publicly available at https://github.com/eduardchelebian/depicter.
Keywords: Clustering; Histology; Interactive annotation; Self-supervised learning.
Copyright © 2024 The Author(s). Published by Elsevier Ltd.. All rights reserved.
Conflict of interest statement
Declaration of competing interest C.W. is on the advisory board of Navinci Diagnostics, Sweden. F.C. was Chair of the Scientific and Medical Advisory Board of TRIBVN Healthcare, France, and received advisory board fees from TRIBVN Healthcare, France in the last five years. F.C is shareholder of Aiosyn BV, the Netherlands.
Similar articles
-
Learning with limited annotations: A survey on deep semi-supervised learning for medical image segmentation.Comput Biol Med. 2024 Feb;169:107840. doi: 10.1016/j.compbiomed.2023.107840. Epub 2023 Dec 16. Comput Biol Med. 2024. PMID: 38157773 Review.
-
Local contrastive loss with pseudo-label based self-training for semi-supervised medical image segmentation.Med Image Anal. 2023 Jul;87:102792. doi: 10.1016/j.media.2023.102792. Epub 2023 Mar 11. Med Image Anal. 2023. PMID: 37054649
-
PyMIC: A deep learning toolkit for annotation-efficient medical image segmentation.Comput Methods Programs Biomed. 2023 Apr;231:107398. doi: 10.1016/j.cmpb.2023.107398. Epub 2023 Feb 7. Comput Methods Programs Biomed. 2023. PMID: 36773591
-
Weakly Supervised Learning using Attention gates for colon cancer histopathological image segmentation.Artif Intell Med. 2022 Nov;133:102407. doi: 10.1016/j.artmed.2022.102407. Epub 2022 Sep 24. Artif Intell Med. 2022. PMID: 36328667 Review.
-
Self-supervised driven consistency training for annotation efficient histopathology image analysis.Med Image Anal. 2022 Jan;75:102256. doi: 10.1016/j.media.2021.102256. Epub 2021 Oct 13. Med Image Anal. 2022. PMID: 34717189
MeSH terms
LinkOut - more resources
Full Text Sources