Revisiting the Shape-Bias of Deep Learning for Dermoscopic Skin Lesion Classification

• URL: http://arxiv.org/abs/2206.06466v1
• Date: Mon, 13 Jun 2022 20:59:06 GMT
• Title: Revisiting the Shape-Bias of Deep Learning for Dermoscopic Skin Lesion Classification
• Authors: Adriano Lucieri and Fabian Schmeisser and Christoph Peter Balada and Shoaib Ahmed Siddiqui and Andreas Dengel and Sheraz Ahmed
• Abstract summary: It is generally believed that the human visual system is biased towards the recognition of shapes rather than textures. In this paper, we revisit the significance of shape-biases for the classification of skin lesion images.
• Score: 4.414962444402826
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: It is generally believed that the human visual system is biased towards the recognition of shapes rather than textures. This assumption has led to a growing body of work aiming to align deep models' decision-making processes with the fundamental properties of human vision. The reliance on shape features is primarily expected to improve the robustness of these models under covariate shift. In this paper, we revisit the significance of shape-biases for the classification of skin lesion images. Our analysis shows that different skin lesion datasets exhibit varying biases towards individual image features. Interestingly, despite deep feature extractors being inclined towards learning entangled features for skin lesion classification, individual features can still be decoded from this entangled representation. This indicates that these features are still represented in the learnt embedding spaces of the models, but not used for classification. In addition, the spectral analysis of different datasets shows that in contrast to common visual recognition, dermoscopic skin lesion classification, by nature, is reliant on complex feature combinations beyond shape-bias. As a natural consequence, shifting away from the prevalent desire of shape-biasing models can even improve skin lesion classifiers in some cases.

Related papers

• DDI-CoCo: A Dataset For Understanding The Effect Of Color Contrast In Machine-Assisted Skin Disease Detection [51.92255321684027]
  We study the interaction between skin tone and color difference effects and suggest that color difference can be an additional reason behind model performance bias between skin tones. Our work provides a complementary angle to dermatology AI for improving skin disease detection.
  arXiv  Detail & Related papers  (2024-01-24T07:45:24Z)
• Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models [49.95603725998561]
  We propose a new paradigm to build robust and interpretable medical image classifiers with natural language concepts. Specifically, we first query clinical concepts from GPT-4, then transform latent image features into explicit concepts with a vision-language model.
  arXiv  Detail & Related papers  (2023-10-04T21:57:09Z)
• Few-Shot Meta Learning for Recognizing Facial Phenotypes of Genetic Disorders [55.41644538483948]
  Automated classification and similarity retrieval aid physicians in decision-making to diagnose possible genetic conditions as early as possible. Previous work has addressed the problem as a classification problem and used deep learning methods. In this study, we used a facial recognition model trained on a large corpus of healthy individuals as a pre-task and transferred it to facial phenotype recognition.
  arXiv  Detail & Related papers  (2022-10-23T11:52:57Z)
• A Survey on Deep Learning for Skin Lesion Segmentation [32.523358996420846]
  Skin cancer is a major public health problem that could benefit from computer-aided diagnosis to reduce the burden of this common disease. Skin lesion segmentation from images is an important step toward achieving this goal. The presence of natural and artificial artifacts (e.g., hair and air bubbles), intrinsic factors (e.g., lesion shape and contrast), and variations in image acquisition conditions make skin lesion segmentation a challenging task.
  arXiv  Detail & Related papers  (2022-06-01T09:43:10Z)
• Salient Skin Lesion Segmentation via Dilated Scale-Wise Feature Fusion Network [28.709314434820953]
  Current skin lesion segmentation approaches show poor performance in challenging circumstances. We propose a dilated scale-wise feature fusion network based on convolution factorization. Our proposed model consistently showcases state-of-the-art results.
  arXiv  Detail & Related papers  (2022-05-20T16:08:37Z)
• Analyzing the Effects of Handling Data Imbalance on Learned Features from Medical Images by Looking Into the Models [50.537859423741644]
  Training a model on an imbalanced dataset can introduce unique challenges to the learning problem. We look deeper into the internal units of neural networks to observe how handling data imbalance affects the learned features.
  arXiv  Detail & Related papers  (2022-04-04T09:38:38Z)
• What Do You See in this Patient? Behavioral Testing of Clinical NLP Models [69.09570726777817]
  We introduce an extendable testing framework that evaluates the behavior of clinical outcome models regarding changes of the input. We show that model behavior varies drastically even when fine-tuned on the same data and that allegedly best-performing models have not always learned the most medically plausible patterns.
  arXiv  Detail & Related papers  (2021-11-30T15:52:04Z)
• Unravelling the Effect of Image Distortions for Biased Prediction of Pre-trained Face Recognition Models [86.79402670904338]
  We evaluate the performance of four state-of-the-art deep face recognition models in the presence of image distortions. We have observed that image distortions have a relationship with the performance gap of the model across different subgroups.
  arXiv  Detail & Related papers  (2021-08-14T16:49:05Z)
• Dermoscopic Image Classification with Neural Style Transfer [5.314466196448187]
  We propose an adaptation of the Neural Style Transfer (NST) as a novel image pre-processing step for skin lesion classification problems. We represent each dermoscopic image as the style image and transfer the style of the lesion onto a homogeneous content image. This transfers the main variability of each lesion onto the same localized region, which allows us to integrate the generated images together and extract latent, low-rank style features.
  arXiv  Detail & Related papers  (2021-05-17T03:50:51Z)
• Improving Lesion Detection by exploring bias on Skin Lesion dataset [0.0]
  The ISIC Archive is one of the most used skin lesion sources to benchmark deep learning-based tools. Deep learning models could classify skin lesion images without clinically meaningful information in the input data. We performed experiments that generate shape-preserving masks instead of rectangular bounding-box based masks.
  arXiv  Detail & Related papers  (2020-10-04T05:04:58Z)
• Bi-directional Dermoscopic Feature Learning and Multi-scale Consistent Decision Fusion for Skin Lesion Segmentation [28.300486641368234]
  We propose a novel bi-directional dermoscopic feature learning (biDFL) framework to model the complex correlation between skin lesions and their informative context. We also propose a multi-scale consistent decision fusion (mCDF) that is capable of selectively focusing on the informative decisions generated from multiple classification layers.
  arXiv  Detail & Related papers  (2020-02-20T12:00:24Z)

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.