Label uncertainty-guided multi-stream model for disease screening

• URL: http://arxiv.org/abs/2201.12089v1
• Date: Fri, 28 Jan 2022 12:53:18 GMT
• Title: Label uncertainty-guided multi-stream model for disease screening
• Authors: Chi Liu, Zongyuan Ge, Mingguang He, Xiaotong Han
• Abstract summary: In this paper, we cast the intra-observer variability as an uncertainty problem and incorporate the label uncertainty information as guidance to improve the final decision. The main idea is dividing the images into simple and hard cases by uncertainty information, and then developing a multi-stream network to deal with different cases separately. Experiments on a fundus image-based glaucoma screening case study show that the proposed model outperforms several baselines, especially in screening hard cases.
• Score: 17.633322372675572
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The annotation of disease severity for medical image datasets often relies on collaborative decisions from multiple human graders. The intra-observer variability derived from individual differences always persists in this process, yet the influence is often underestimated. In this paper, we cast the intra-observer variability as an uncertainty problem and incorporate the label uncertainty information as guidance into the disease screening model to improve the final decision. The main idea is dividing the images into simple and hard cases by uncertainty information, and then developing a multi-stream network to deal with different cases separately. Particularly, for hard cases, we strengthen the network's capacity in capturing the correct disease features and resisting the interference of uncertainty. Experiments on a fundus image-based glaucoma screening case study show that the proposed model outperforms several baselines, especially in screening hard cases.

Related papers

• FairSkin: Fair Diffusion for Skin Disease Image Generation [54.29840149709033]
  Diffusion Model (DM) has become a leading method in generating synthetic medical images, but it suffers from a critical twofold bias. We propose FairSkin, a novel DM framework that mitigates these biases through a three-level resampling mechanism. Our approach significantly improves the diversity and quality of generated images, contributing to more equitable skin disease detection in clinical settings.
  arXiv  Detail & Related papers  (2024-10-29T21:37:03Z)
• Confidence-aware multi-modality learning for eye disease screening [58.861421804458395]
  We propose a novel multi-modality evidential fusion pipeline for eye disease screening. It provides a measure of confidence for each modality and elegantly integrates the multi-modality information. Experimental results on both public and internal datasets demonstrate that our model excels in robustness.
  arXiv  Detail & Related papers  (2024-05-28T13:27:30Z)
• Rescuing referral failures during automated diagnosis of domain-shifted medical images [17.349847762608086]
  We show that even state-of-the-art domain generalization approaches fail severely during referral when tested on medical images acquired from a different demographic or using a different technology. We evaluate novel combinations of robust generalization and post hoc referral approaches, that rescue these failures and achieve significant performance improvements.
  arXiv  Detail & Related papers  (2023-11-28T13:14:55Z)
• Reliable Multimodality Eye Disease Screening via Mixture of Student's t Distributions [49.4545260500952]
  We introduce a novel multimodality evidential fusion pipeline for eye disease screening, EyeMoSt. Our model estimates both local uncertainty for unimodality and global uncertainty for the fusion modality to produce reliable classification results. Our experimental findings on both public and in-house datasets show that our model is more reliable than current methods.
  arXiv  Detail & Related papers  (2023-03-17T06:18:16Z)
• Improving Uncertainty-based Out-of-Distribution Detection for Medical Image Segmentation [1.1199585259018459]
  Out-of-Distribution (OOD) images represent a significant challenge in the context of medical image analysis. We show that methods relying on the predictive uncertainty of binary segmentation models often fails in detecting outlying inputs.
  arXiv  Detail & Related papers  (2022-11-10T08:54:40Z)
• Out-of-Distribution Detection for Dermoscopic Image Classification [0.0]
  We develop a novel yet simple method to train neural networks, which enables them to classify in-distribution dermoscopic skin disease images. We show that our BinaryHeads model not only does not hurt classification balanced accuracy when the data is imbalanced, but also consistently improves the balanced accuracy.
  arXiv  Detail & Related papers  (2021-04-15T23:34:53Z)
• Uncertainty aware and explainable diagnosis of retinal disease [0.0]
  We perform uncertainty analysis of a deep learning model for diagnosis of four retinal diseases. We show the features that a system used to make prediction while uncertainty awareness is the ability of a system to highlight when it is not sure about the decision.
  arXiv  Detail & Related papers  (2021-01-26T23:37:30Z)
• Weakly-Supervised Cross-Domain Adaptation for Endoscopic Lesions Segmentation [79.58311369297635]
  We propose a new weakly-supervised lesions transfer framework, which can explore transferable domain-invariant knowledge across different datasets. A Wasserstein quantified transferability framework is developed to highlight widerange transferable contextual dependencies. A novel self-supervised pseudo label generator is designed to equally provide confident pseudo pixel labels for both hard-to-transfer and easy-to-transfer target samples.
  arXiv  Detail & Related papers  (2020-12-08T02:26:03Z)
• Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models [103.64435911083432]
  We present a novel contrastive learning strategy called it Proactive Pseudo-Intervention (PPI) PPI leverages proactive interventions to guard against image features with no causal relevance. We also devise a novel causally informed salience mapping module to identify key image pixels to intervene, and show it greatly facilitates model interpretability.
  arXiv  Detail & Related papers  (2020-12-06T20:30:26Z)
• Semi-supervised Medical Image Classification with Relation-driven Self-ensembling Model [71.80319052891817]
  We present a relation-driven semi-supervised framework for medical image classification. It exploits the unlabeled data by encouraging the prediction consistency of given input under perturbations. Our method outperforms many state-of-the-art semi-supervised learning methods on both single-label and multi-label image classification scenarios.
  arXiv  Detail & Related papers  (2020-05-15T06:57:54Z)
• Finding novelty with uncertainty [7.565565370757736]
  We propose a Bayesian deep learning method that learns to translate healthy computed tomography images to magnetic resonance images and simultaneously calculates voxel-wise uncertainty. We show encouraging experimental results on an unsupervised anomaly segmentation task by combining two types of uncertainty into a novel quantity we call scibilic uncertainty.
  arXiv  Detail & Related papers  (2020-02-11T19:00:22Z)

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.