Domain shifts in dermoscopic skin cancer datasets: Evaluation of essential limitations for clinical translation

• URL: http://arxiv.org/abs/2304.06968v3
• Date: Mon, 3 Jul 2023 08:40:03 GMT
• Title: Domain shifts in dermoscopic skin cancer datasets: Evaluation of essential limitations for clinical translation
• Authors: Katharina Fogelberg, Sireesha Chamarthi, Roman C. Maron, Julia Niebling, Titus J. Brinker
• Abstract summary: We grouped publicly available images from ISIC archive based on their metadata to generate meaningful domains. We used multiple quantification measures to estimate the presence and intensity of domain shifts. We observed that in most of our grouped domains, domain shifts in fact exist.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The limited ability of Convolutional Neural Networks to generalize to images from previously unseen domains is a major limitation, in particular, for safety-critical clinical tasks such as dermoscopic skin cancer classification. In order to translate CNN-based applications into the clinic, it is essential that they are able to adapt to domain shifts. Such new conditions can arise through the use of different image acquisition systems or varying lighting conditions. In dermoscopy, shifts can also occur as a change in patient age or occurence of rare lesion localizations (e.g. palms). These are not prominently represented in most training datasets and can therefore lead to a decrease in performance. In order to verify the generalizability of classification models in real world clinical settings it is crucial to have access to data which mimics such domain shifts. To our knowledge no dermoscopic image dataset exists where such domain shifts are properly described and quantified. We therefore grouped publicly available images from ISIC archive based on their metadata (e.g. acquisition location, lesion localization, patient age) to generate meaningful domains. To verify that these domains are in fact distinct, we used multiple quantification measures to estimate the presence and intensity of domain shifts. Additionally, we analyzed the performance on these domains with and without an unsupervised domain adaptation technique. We observed that in most of our grouped domains, domain shifts in fact exist. Based on our results, we believe these datasets to be helpful for testing the generalization capabilities of dermoscopic skin cancer classifiers.

Related papers

• Generalizing to Unseen Domains in Diabetic Retinopathy with Disentangled Representations [32.7667209371645]
  Existing models experience notable performance degradation on unseen domains due to domain shifts. We propose a novel framework where representations of paired data from different domains are decoupled into semantic features and domain noise. The resulting augmented representation comprises original retinal semantics and domain noise from other domains, aiming to generate enhanced representations aligned with real-world clinical needs.
  arXiv  Detail & Related papers  (2024-06-10T15:43:56Z)
• Mitigating the Influence of Domain Shift in Skin Lesion Classification: A Benchmark Study of Unsupervised Domain Adaptation Methods on Dermoscopic Images [3.2186308082558632]
  The potential of deep neural networks in skin lesion classification has already been demonstrated to be on-par if not superior to the dermatologists diagnosis. The performance of these models usually deteriorates when the test data differs significantly from the training data (i.e. domain shift) In this study, we carry out an in-depth analysis of eight different unsupervised domain adaptation methods to analyze their effectiveness in improving generalization for dermoscopic datasets.
  arXiv  Detail & Related papers  (2023-10-05T10:17:47Z)
• Generalizing Across Domains in Diabetic Retinopathy via Variational Autoencoders [0.0]
  Domain generalization for Diabetic Retinopathy classification allows a model to adeptly classify retinal images. In this study, we explore the inherent capacity of variational autoencoders to disentangle the latent space of fundus images.
  arXiv  Detail & Related papers  (2023-09-20T13:29:22Z)
• Dis-AE: Multi-domain & Multi-task Generalisation on Real-World Clinical Data [0.0]
  We propose a novel disentangled autoencoder (Dis-AE) neural network architecture. Dis-AE learns domain-invariant data representations for multi-label classification of medical measurements. We evaluate the model's domain generalisation capabilities on synthetic datasets and full blood count (FBC) data from blood donors.
  arXiv  Detail & Related papers  (2023-06-15T14:56:37Z)
• Unsupervised Domain Transfer with Conditional Invertible Neural Networks [83.90291882730925]
  We propose a domain transfer approach based on conditional invertible neural networks (cINNs) Our method inherently guarantees cycle consistency through its invertible architecture, and network training can efficiently be conducted with maximum likelihood. Our method enables the generation of realistic spectral data and outperforms the state of the art on two downstream classification tasks.
  arXiv  Detail & Related papers  (2023-03-17T18:00:27Z)
• Multi-Scale Multi-Target Domain Adaptation for Angle Closure Classification [50.658613573816254]
  We propose a novel Multi-scale Multi-target Domain Adversarial Network (M2DAN) for angle closure classification. Based on these domain-invariant features at different scales, the deep model trained on the source domain is able to classify angle closure on multiple target domains.
  arXiv  Detail & Related papers  (2022-08-25T15:27:55Z)
• Hospital-Agnostic Image Representation Learning in Digital Pathology [0.7412445894287709]
  Whole Slide Images (WSIs) in digital pathology are used to diagnose cancer subtypes. The difference in procedures to acquire WSIs at various trial sites gives rise to variability in the histopathology images. A domain generalization technique is leveraged in this study to improve the generalization capability of a Deep Neural Network (DNN)
  arXiv  Detail & Related papers  (2022-04-05T11:45:46Z)
• Self-Supervised Domain Adaptation for Diabetic Retinopathy Grading using Vessel Image Reconstruction [61.58601145792065]
  We learn invariant target-domain features by defining a novel self-supervised task based on retinal vessel image reconstructions. It can be shown that our approach outperforms existing domain strategies.
  arXiv  Detail & Related papers  (2021-07-20T09:44:07Z)
• DoFE: Domain-oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets [96.92018649136217]
  We present a novel Domain-oriented Feature Embedding (DoFE) framework to improve the generalization ability of CNNs on unseen target domains. Our DoFE framework dynamically enriches the image features with additional domain prior knowledge learned from multi-source domains. Our framework generates satisfying segmentation results on unseen datasets and surpasses other domain generalization and network regularization methods.
  arXiv  Detail & Related papers  (2020-10-13T07:28:39Z)
• Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization [59.5104563755095]
  We introduce a simple but effective approach to improve the generalization capability of deep neural networks in the field of medical imaging classification. Motivated by the observation that the domain variability of the medical images is to some extent compact, we propose to learn a representative feature space through variational encoding.
  arXiv  Detail & Related papers  (2020-09-27T12:30:30Z)
• Phase Consistent Ecological Domain Adaptation [76.75730500201536]
  We focus on the task of semantic segmentation, where annotated synthetic data are aplenty, but annotating real data is laborious. The first criterion, inspired by visual psychophysics, is that the map between the two image domains be phase-preserving. The second criterion aims to leverage ecological statistics, or regularities in the scene which are manifest in any image of it, regardless of the characteristics of the illuminant or the imaging sensor.
  arXiv  Detail & Related papers  (2020-04-10T06:58:03Z)

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.