Adenocarcinoma Segmentation Using Pre-trained Swin-UNet with Parallel Cross-Attention for Multi-Domain Imaging

• URL: http://arxiv.org/abs/2409.15501v1
• Date: Mon, 23 Sep 2024 19:38:43 GMT
• Title: Adenocarcinoma Segmentation Using Pre-trained Swin-UNet with Parallel Cross-Attention for Multi-Domain Imaging
• Authors: Abdul Qayyum, Moona Mazher Imran Razzak, Steven A Niederer,
• Abstract summary: We present a framework consist of pre-trained encoder with a Swin-UNet architecture enhanced by a parallel cross-attention module to tackle the problem of adenocarcinoma segmentation across different organs and scanners. Experiment showed that our framework achieved segmentation scores of 0.7469 for the cross-organ track and 0.7597 for the cross-scanner track.
• Score: 0.2878844332549157
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Computer aided pathological analysis has been the gold standard for tumor diagnosis, however domain shift is a significant problem in histopathology. It may be caused by variability in anatomical structures, tissue preparation, and imaging processes challenges the robustness of segmentation models. In this work, we present a framework consist of pre-trained encoder with a Swin-UNet architecture enhanced by a parallel cross-attention module to tackle the problem of adenocarcinoma segmentation across different organs and scanners, considering both morphological changes and scanner-induced domain variations. Experiment conducted on Cross-Organ and Cross-Scanner Adenocarcinoma Segmentation challenge dataset showed that our framework achieved segmentation scores of 0.7469 for the cross-organ track and 0.7597 for the cross-scanner track on the final challenge test sets, and effectively navigates diverse imaging conditions and improves segmentation accuracy across varying domains.

Related papers

• Understanding Stain Separation Improves Cross-Scanner Adenocarcinoma Segmentation with Joint Multi-Task Learning [2.3470559413988936]
  Digital pathology has made significant advances in tumor diagnosis and segmentation, but image variability limits the effectiveness of current algorithms. The COSAS (Cross-Organ and Cross-Scanner Adenocarcinoma) challenge addresses this issue by improving the resilience of segmentation algorithms to domain shift. Our approach employs unsupervised learning through stain separation within a multi-task learning framework using a multi-decoder autoencoder.
  arXiv  Detail & Related papers  (2024-09-20T06:12:52Z)
• Domain-stratified Training for Cross-organ and Cross-scanner Adenocarcinoma Segmentation in the COSAS 2024 Challenge [0.0]
  This manuscript presents an image segmentation algorithm developed for the Cross-Organ and Cross-Scanner Adenocarcinoma (COSAS 2024) challenge. We adopted an organ-stratified and scanner-stratified approach to train multiple Upernet-based segmentation models and ensembled the results.
  arXiv  Detail & Related papers  (2024-09-19T02:36:34Z)
• Domain and Content Adaptive Convolutions for Cross-Domain Adenocarcinoma Segmentation [0.44569778071604066]
  We present a U-Net-based segmentation framework to tackle the Cross-Organ and Cross-Scanner Adenocarcinoma (COSAS) challenge. Our approach achieved segmentation scores of 0.8020 for the cross-organ track and 0.8527 for the cross-scanner track on the final challenge test sets, ranking it the best-performing submission.
  arXiv  Detail & Related papers  (2024-09-15T17:08:34Z)
• Anatomy-guided Pathology Segmentation [56.883822515800205]
  We develop a generalist segmentation model that combines anatomical and pathological information, aiming to enhance the segmentation accuracy of pathological features. Our Anatomy-Pathology Exchange (APEx) training utilizes a query-based segmentation transformer which decodes a joint feature space into query-representations for human anatomy. In doing so, we are able to report the best results across the board on FDG-PET-CT and Chest X-Ray pathology segmentation tasks with a margin of up to 3.3% as compared to strong baseline methods.
  arXiv  Detail & Related papers  (2024-07-08T11:44:15Z)
• QUBIQ: Uncertainty Quantification for Biomedical Image Segmentation Challenge [93.61262892578067]
  Uncertainty in medical image segmentation tasks, especially inter-rater variability, presents a significant challenge. This variability directly impacts the development and evaluation of automated segmentation algorithms. We report the set-up and summarize the benchmark results of the Quantification of Uncertainties in Biomedical Image Quantification Challenge (QUBIQ)
  arXiv  Detail & Related papers  (2024-03-19T17:57:24Z)
• Reliable Joint Segmentation of Retinal Edema Lesions in OCT Images [55.83984261827332]
  In this paper, we propose a novel reliable multi-scale wavelet-enhanced transformer network. We develop a novel segmentation backbone that integrates a wavelet-enhanced feature extractor network and a multi-scale transformer module. Our proposed method achieves better segmentation accuracy with a high degree of reliability as compared to other state-of-the-art segmentation approaches.
  arXiv  Detail & Related papers  (2022-12-01T07:32:56Z)
• Mitosis domain generalization in histopathology images -- The MIDOG challenge [12.69088811541426]
  Recognition of mitotic figures by pathologists is subject to a strong inter-rater bias, which limits the prognostic value. State-of-the-art deep learning methods can support the expert in this assessment but are known to strongly deteriorate when applied in a different clinical environment than was used for training. The MICCAI MIDOG 2021 challenge has been to propose and evaluate methods that derive scanner-agnostic mitosis detection algorithms.
  arXiv  Detail & Related papers  (2022-04-06T11:43:10Z)
• Redesigning Fully Convolutional DenseUNets for Large Histopathology Images [0.0]
  We propose a Fully Convolutional DenseUNet to solve histopathology problems. We evaluated our network in two public pathology datasets published as challenges.
  arXiv  Detail & Related papers  (2021-08-05T15:14:20Z)
• Co-Heterogeneous and Adaptive Segmentation from Multi-Source and Multi-Phase CT Imaging Data: A Study on Pathological Liver and Lesion Segmentation [48.504790189796836]
  We present a novel segmentation strategy, co-heterogenous and adaptive segmentation (CHASe) We propose a versatile framework that fuses appearance based semi-supervision, mask based adversarial domain adaptation, and pseudo-labeling. CHASe can further improve pathological liver mask Dice-Sorensen coefficients by ranges of $4.2% sim 9.4%$.
  arXiv  Detail & Related papers  (2020-05-27T06:58:39Z)
• Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentation [73.84166499988443]
  We present a novel unsupervised domain adaptation framework, named as Synergistic Image and Feature Alignment (SIFA) Our proposed SIFA conducts synergistic alignment of domains from both image and feature perspectives. Experimental results on two different tasks demonstrate that our SIFA method is effective in improving segmentation performance on unlabeled target images.
  arXiv  Detail & Related papers  (2020-02-06T13:49:47Z)
• VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images [121.31355003451152]
  Large Scale Vertebrae Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2019 and 2020. We present the the results of this evaluation and further investigate the performance-variation at vertebra-level, scan-level, and at different fields-of-view.
  arXiv  Detail & Related papers  (2020-01-24T21:09:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.