Boosting EfficientNets Ensemble Performance via Pseudo-Labels and Synthetic Images by pix2pixHD for Infection and Ischaemia Classification in Diabetic Foot Ulcers

• URL: http://arxiv.org/abs/2112.00065v1
• Date: Tue, 30 Nov 2021 19:42:06 GMT
• Title: Boosting EfficientNets Ensemble Performance via Pseudo-Labels and Synthetic Images by pix2pixHD for Infection and Ischaemia Classification in Diabetic Foot Ulcers
• Authors: Louise Bloch, Raphael Br\"ungel, Christoph M. Friedrich
• Abstract summary: This research investigates an approach on classification of infection and ischaemia conducted as part of the Diabetic Foot Ulcer Challenge (DFUC) 2021. The resulting extended training dataset features $8.68$ times the size of the baseline. Performances of models and ensembles trained on the baseline and extended training dataset are compared.
• Score: 2.191505742658975
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diabetic foot ulcers are a common manifestation of lesions on the diabetic foot, a syndrome acquired as a long-term complication of diabetes mellitus. Accompanying neuropathy and vascular damage promote acquisition of pressure injuries and tissue death due to ischaemia. Affected areas are prone to infections, hindering the healing progress. The research at hand investigates an approach on classification of infection and ischaemia, conducted as part of the Diabetic Foot Ulcer Challenge (DFUC) 2021. Different models of the EfficientNet family are utilized in ensembles. An extension strategy for the training data is applied, involving pseudo-labeling for unlabeled images, and extensive generation of synthetic images via pix2pixHD to cope with severe class imbalances. The resulting extended training dataset features $8.68$ times the size of the baseline and shows a real to synthetic image ratio of $1:3$. Performances of models and ensembles trained on the baseline and extended training dataset are compared. Synthetic images featured a broad qualitative variety. Results show that models trained on the extended training dataset as well as their ensemble benefit from the large extension. F1-Scores for rare classes receive outstanding boosts, while those for common classes are either not harmed or boosted moderately. A critical discussion concretizes benefits and identifies limitations, suggesting improvements. The work concludes that classification performance of individual models as well as that of ensembles can be boosted utilizing synthetic images. Especially performance for rare classes benefits notably.

Related papers

• Training Class-Imbalanced Diffusion Model Via Overlap Optimization [55.96820607533968]
  Diffusion models trained on real-world datasets often yield inferior fidelity for tail classes. Deep generative models, including diffusion models, are biased towards classes with abundant training images. We propose a method based on contrastive learning to minimize the overlap between distributions of synthetic images for different classes.
  arXiv  Detail & Related papers  (2024-02-16T16:47:21Z)
• What limits performance of weakly supervised deep learning for chest CT classification? [0.44241702149260353]
  Weakly supervised learning with noisy data has drawn attention in the medical imaging community due to the sparsity of high-quality disease labels. In this paper, we test the effects of such weak supervision by examining model tolerance for noisy data. Results demonstrated that the model could endure up to 10% added label error before experiencing a decline in disease classification performance.
  arXiv  Detail & Related papers  (2024-02-06T21:38:29Z)
• Transfer-Ensemble Learning based Deep Convolutional Neural Networks for Diabetic Retinopathy Classification [0.7614628596146599]
  This article aims to classify diabetic retinopathy (DR) disease into five different classes using an ensemble approach based on two popular pre-trained convolutional neural networks: VGG16 and Inception V3. Experimental results on the test set demonstrate the efficacy of the proposed ensemble model for DR classification achieving an accuracy of 96.4%.
  arXiv  Detail & Related papers  (2023-08-01T13:07:39Z)
• Quantifying the Effect of Image Similarity on Diabetic Foot Ulcer Classification [4.318783737552881]
  This research conducts an investigation on the effect of visually similar images within a publicly available diabetic foot ulcer dataset when training deep learning classification networks. The presence of binary-identical duplicate images in datasets used to train deep learning algorithms can introduce unwanted bias which can degrade network performance. We use an open-source fuzzy algorithm to identify groups of increasingly similar images in the Diabetic Foot Ulcers Challenge 2021 training dataset.
  arXiv  Detail & Related papers  (2023-04-25T16:54:27Z)
• Mine yOur owN Anatomy: Revisiting Medical Image Segmentation with Extremely Limited Labels [54.58539616385138]
  We introduce a novel semi-supervised 2D medical image segmentation framework termed Mine yOur owN Anatomy (MONA) First, prior work argues that every pixel equally matters to the model training; we observe empirically that this alone is unlikely to define meaningful anatomical features. Second, we construct a set of objectives that encourage the model to be capable of decomposing medical images into a collection of anatomical features.
  arXiv  Detail & Related papers  (2022-09-27T15:50:31Z)
• Categorical Relation-Preserving Contrastive Knowledge Distillation for Medical Image Classification [75.27973258196934]
  We propose a novel Categorical Relation-preserving Contrastive Knowledge Distillation (CRCKD) algorithm, which takes the commonly used mean-teacher model as the supervisor. With this regularization, the feature distribution of the student model shows higher intra-class similarity and inter-class variance. With the contribution of the CCD and CRP, our CRCKD algorithm can distill the relational knowledge more comprehensively.
  arXiv  Detail & Related papers  (2021-07-07T13:56:38Z)
• On the Robustness of Pretraining and Self-Supervision for a Deep Learning-based Analysis of Diabetic Retinopathy [70.71457102672545]
  We compare the impact of different training procedures for diabetic retinopathy grading. We investigate different aspects such as quantitative performance, statistics of the learned feature representations, interpretability and robustness to image distortions. Our results indicate that models from ImageNet pretraining report a significant increase in performance, generalization and robustness to image distortions.
  arXiv  Detail & Related papers  (2021-06-25T08:32:45Z)
• Cost-Sensitive Regularization for Diabetic Retinopathy Grading from Eye Fundus Images [20.480034690570196]
  We propose a straightforward approach to enforce the constraint for the task of predicting Diabetic Retinopathy (DR) severity from eye fundus images. We expand standard classification losses with an extra term that acts as a regularizer. We show how to adapt our method to the modelling of label noise in each of the sub-problems associated to DR grading.
  arXiv  Detail & Related papers  (2020-10-01T10:42:06Z)
• A Benchmark for Studying Diabetic Retinopathy: Segmentation, Grading, and Transferability [76.64661091980531]
  People with diabetes are at risk of developing diabetic retinopathy (DR) Computer-aided DR diagnosis is a promising tool for early detection of DR and severity grading. This dataset has 1,842 images with pixel-level DR-related lesion annotations, and 1,000 images with image-level labels graded by six board-certified ophthalmologists.
  arXiv  Detail & Related papers  (2020-08-22T07:48:04Z)
• Multi-label Thoracic Disease Image Classification with Cross-Attention Networks [65.37531731899837]
  We propose a novel scheme of Cross-Attention Networks (CAN) for automated thoracic disease classification from chest x-ray images. We also design a new loss function that beyond cross-entropy loss to help cross-attention process and is able to overcome the imbalance between classes and easy-dominated samples within each class.
  arXiv  Detail & Related papers  (2020-07-21T14:37:00Z)

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.