To pretrain or not to pretrain? A case study of domain-specific pretraining for semantic segmentation in histopathology

• URL: http://arxiv.org/abs/2307.03275v2
• Date: Mon, 21 Aug 2023 23:56:44 GMT
• Title: To pretrain or not to pretrain? A case study of domain-specific pretraining for semantic segmentation in histopathology
• Authors: Tushar Kataria, Beatrice Knudsen and Shireen Elhabian
• Abstract summary: Fine-tuning (or transfer learning) is the most effective method for digital pathology vision applications such as disease classification and semantic segmentation. Here, we compare the performance of gland and cell segmentation tasks with histopathology domain-specific and non-domain-specific (real-world images) pretrained weights. The results indicate that performance gain using domain-specific pretrained weights depends on both the task and the size of the training dataset.
• Score: 0.9208007322096533
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Annotating medical imaging datasets is costly, so fine-tuning (or transfer learning) is the most effective method for digital pathology vision applications such as disease classification and semantic segmentation. However, due to texture bias in models trained on real-world images, transfer learning for histopathology applications might result in underperforming models, which necessitates the need for using unlabeled histopathology data and self-supervised methods to discover domain-specific characteristics. Here, we tested the premise that histopathology-specific pretrained models provide better initializations for pathology vision tasks, i.e., gland and cell segmentation. In this study, we compare the performance of gland and cell segmentation tasks with histopathology domain-specific and non-domain-specific (real-world images) pretrained weights. Moreover, we investigate the dataset size at which domain-specific pretraining produces significant gains in performance. In addition, we investigated whether domain-specific initialization improves the effectiveness of out-of-distribution testing on distinct datasets but the same task. The results indicate that performance gain using domain-specific pretrained weights depends on both the task and the size of the training dataset. In instances with limited dataset sizes, a significant improvement in gland segmentation performance was also observed, whereas models trained on cell segmentation datasets exhibit no improvement.

Related papers

• LoRKD: Low-Rank Knowledge Decomposition for Medical Foundation Models [59.961172635689664]
  "Knowledge Decomposition" aims to improve the performance on specific medical tasks. We propose a novel framework named Low-Rank Knowledge Decomposition (LoRKD) LoRKD explicitly separates gradients from different tasks by incorporating low-rank expert modules and efficient knowledge separation convolution.
  arXiv  Detail & Related papers  (2024-09-29T03:56:21Z)
• Benchmarking Retinal Blood Vessel Segmentation Models for Cross-Dataset and Cross-Disease Generalization [5.237321836999284]
  We train and evaluate five published models on the publicly available FIVES fundus image dataset. We find that image quality is a key factor determining segmentation outcomes.
  arXiv  Detail & Related papers  (2024-06-21T09:12:34Z)
• Efficient Transferability Assessment for Selection of Pre-trained Detectors [63.21514888618542]
  This paper studies the efficient transferability assessment of pre-trained object detectors. We build up a detector transferability benchmark which contains a large and diverse zoo of pre-trained detectors. Experimental results demonstrate that our method outperforms other state-of-the-art approaches in assessing transferability.
  arXiv  Detail & Related papers  (2024-03-14T14:23:23Z)
• Explanations of Classifiers Enhance Medical Image Segmentation via End-to-end Pre-training [37.11542605885003]
  Medical image segmentation aims to identify and locate abnormal structures in medical images, such as chest radiographs, using deep neural networks. Our work collects explanations from well-trained classifiers to generate pseudo labels of segmentation tasks. We then use Integrated Gradients (IG) method to distill and boost the explanations obtained from the classifiers, generating massive diagnosis-oriented localization labels (DoLL) These DoLL-annotated images are used for pre-training the model before fine-tuning it for downstream segmentation tasks, including COVID-19 infectious areas, lungs, heart, and clavicles.
  arXiv  Detail & Related papers  (2024-01-16T16:18:42Z)
• ArSDM: Colonoscopy Images Synthesis with Adaptive Refinement Semantic Diffusion Models [69.9178140563928]
  Colonoscopy analysis is essential for assisting clinical diagnosis and treatment. The scarcity of annotated data limits the effectiveness and generalization of existing methods. We propose an Adaptive Refinement Semantic Diffusion Model (ArSDM) to generate colonoscopy images that benefit the downstream tasks.
  arXiv  Detail & Related papers  (2023-09-03T07:55:46Z)
• Active Learning Based Domain Adaptation for Tissue Segmentation of Histopathological Images [1.4724454726700604]
  We propose a pre-trained deep neural network that uses a small set of labeled data from the target domain to select the most informative samples to label next. We demonstrate that our approach performs with significantly fewer labeled samples compared to traditional supervised learning approaches for similar F1-scores.
  arXiv  Detail & Related papers  (2023-03-09T13:03:01Z)
• Stacking Ensemble Learning in Deep Domain Adaptation for Ophthalmic Image Classification [61.656149405657246]
  Domain adaptation is effective in image classification tasks where obtaining sufficient label data is challenging. We propose a novel method, named SELDA, for stacking ensemble learning via extending three domain adaptation methods. The experimental results using Age-Related Eye Disease Study (AREDS) benchmark ophthalmic dataset demonstrate the effectiveness of the proposed model.
  arXiv  Detail & Related papers  (2022-09-27T14:19:00Z)
• CHALLENGER: Training with Attribution Maps [63.736435657236505]
  We show that utilizing attribution maps for training neural networks can improve regularization of models and thus increase performance. In particular, we show that our generic domain-independent approach yields state-of-the-art results in vision, natural language processing and on time series tasks.
  arXiv  Detail & Related papers  (2022-05-30T13:34:46Z)
• Deep learning based domain adaptation for mitochondria segmentation on EM volumes [5.682594415267948]
  We present three unsupervised domain adaptation strategies to improve mitochondria segmentation in the target domain. We propose a new training stopping criterion based on morphological priors obtained exclusively in the source domain. In the absence of validation labels, monitoring our proposed morphology-based metric is an intuitive and effective way to stop the training process and select in average optimal models.
  arXiv  Detail & Related papers  (2022-02-22T09:49:25Z)
• TraND: Transferable Neighborhood Discovery for Unsupervised Cross-domain Gait Recognition [77.77786072373942]
  This paper proposes a Transferable Neighborhood Discovery (TraND) framework to bridge the domain gap for unsupervised cross-domain gait recognition. We design an end-to-end trainable approach to automatically discover the confident neighborhoods of unlabeled samples in the latent space. Our method achieves state-of-the-art results on two public datasets, i.e., CASIA-B and OU-LP.
  arXiv  Detail & Related papers  (2021-02-09T03:07:07Z)
• Cross-Domain Segmentation with Adversarial Loss and Covariate Shift for Biomedical Imaging [2.1204495827342438]
  This manuscript aims to implement a novel model that can learn robust representations from cross-domain data by encapsulating distinct and shared patterns from different modalities. The tests on CT and MRI liver data acquired in routine clinical trials show that the proposed model outperforms all other baseline with a large margin.
  arXiv  Detail & Related papers  (2020-06-08T07:35:55Z)

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.