Data-driven models are now deployed in a plethora of real-world applications - including automated diagnosis - but models learned from data risk learning biases from that same data. When models learn spurious correlations not found in real-world situations, their deployment for critical tasks, such as medical decisions, can be catastrophic. In this work we address this issue for skin-lesion classification models, with two objectives: finding out what are the spurious correlations exploited by biased networks, and debiasing the models by removing such spurious correlations from them. We perform a systematic integrated analysis of 7 visual artifacts (which are possible sources of biases exploitable by networks), employ a state-of-the-art technique to prevent the models from learning spurious correlations, and propose datasets to test models for the presence of bias. We find out that, despite interesting results that point to promising future research, current debiasing methods are not ready to solve the bias issue for skin-lesion models.
Federal University of Espirito Santo, UFES（圣埃斯皮里图联邦大学（UFES））
Skin cancer is one of the most common types of cancer in the world. Different computer-aided diagnosis systems have been proposed to tackle skin lesion diagnosis, most of them based in deep convolutional neural networks. However, recent advances in computer vision achieved state-of-art results in many tasks, notably Transformer-based networks. We explore and evaluate advances in computer vision architectures, training methods and multimodal feature fusion for skin lesion diagnosis task. Experiments show that PiT ($0.800 \pm 0.006$), CoaT ($0.780 \pm 0.024$) and ViT ($0.771 \pm 0.018$) backbone…
Institute of Computing (IC)（计算学院）；School of Electrical and Computing Engineering (FEEC)（电气与计算工程学院）；RECOD Lab.（RECOD实验室）；University of Campinas (UNICAMP)（坎皮纳斯大学）
Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC)
Louisiana State University in Shreveport（路易斯安那州立大学什里夫波特分校）；Kitware（Kitware公司）；Memorial Sloan-Kettering Cancer Center（纪念斯隆-凯特琳癌症中心）；Missouri University of Science and Technology（密苏里科技大学）；Emory University（埃默里大学）；IBM T. J. Watson Research Center（IBM托马斯·J·沃森研究中心）
Privileged Lesion-Context Relational Distillation for Mask-Free Skin Lesion Classification
Victoria University（维多利亚大学）；Bangaldesh University of Business and Technology（孟加拉国商业与技术大学）；Daffodil Institute of Information Technology（达芙妮信息技术学院）；American International University-Bangladesh (AIUB)（孟加拉国美国国际大学）；Multimedia University（多媒体大学）
University of British Columbia（不列颠哥伦比亚大学）；Simon Fraser University（西蒙弗雷泽大学）
Deep learning models have achieved great success in automating skin lesion diagnosis. However, the ethnic disparity in these models' predictions, where lesions on darker skin types are usually underrepresented and have lower diagnosis accuracy, receives little attention. In this paper, we propose FairDisCo, a disentanglement deep learning framework with contrastive learning that utilizes an additional network branch to remove sensitive attributes, i.e. skin-type information from representations for fairness and another contrastive branch to enhance feature extraction. We compare FairDisCo to t…
Skin Lesion Classification Using Ensembles of Multi-Resolution EfficientNets with Meta Data
Hamburg University of Technology（汉堡工业大学）；Forschungszentrum Medizintechnik Hamburg（汉堡医疗技术研究中心）；University Medical Center Hamburg-Eppendorf（汉堡-埃彭多夫大学医学中心）
Automatic Lesion Detection System (ALDS) for Skin Cancer Classification Using SVM and Neural Classifiers
Pakistan Navy Engineering College (PNEC)（巴基斯坦海军工程学院）；National University of Sciences & Technology (NUST)（国家科技大学）；Electronics and Power Engineering (EPE)（电子与动力工程系）
Nanyang Technological University（南洋理工大学）；Central South University（中南大学）；Singapore University of Technology and Design（新加坡科技设计大学）
Deep learning techniques have shown their superior performance in dermatologist clinical inspection. Nevertheless, melanoma diagnosis is still a challenging task due to the difficulty of incorporating the useful dermatologist clinical knowledge into the learning process. In this paper, we propose a novel knowledge-aware deep framework that incorporates some clinical knowledge into collaborative learning of two important melanoma diagnosis tasks, i.e., skin lesion segmentation and melanoma recognition. Specifically, to exploit the knowledge of morphological expressions of the lesion region and …
DERM12345: A Large, Multisource Dermatoscopic Skin Lesion Dataset with 38 Subclasses
Imperial College London（帝国理工学院）；The University of Health Sciences（健康科学大学）；Haydarpasa Numune Research and Training Hospital（海达尔帕夏努穆内研究与培训医院）；Istinye University（伊斯坦布尔伊斯坦尼耶大学）；Liv Hospital Vadistanbul（瓦迪斯坦布尔丽芙医院）
Microsoft（微软）；Cupertino High School（库比蒂诺高中）；Inglemoor High School（英格尔穆尔高中）
All datasets contain some biases, often unintentional, due to how they were acquired and annotated. These biases distort machine-learning models' performance, creating spurious correlations that the models can unfairly exploit, or, contrarily destroying clear correlations that the models could learn. With the popularity of deep learning models, automated skin lesion analysis is starting to play an essential role in the early detection of Melanoma. The ISIC Archive is one of the most used skin lesion sources to benchmark deep learning-based tools. Bissoto et al. experimented with different boun…
The segmentation of skin lesions is a crucial task in clinical decision support systems for the computer aided diagnosis of skin lesions. Although deep learning-based approaches have improved segmentation performance, these models are often susceptible to class imbalance in the data, particularly, the fraction of the image occupied by the background healthy skin. Despite variations of the popular Dice loss function being proposed to tackle the class imbalance problem, the Dice loss formulation does not penalize misclassifications of the background pixels. We propose a novel metric-based loss f…
The iToBoS dataset: skin region images extracted from 3D total body photographs for lesion detection
Computer Vision and Robotics Research Institute, University of Girona（赫罗纳大学计算机视觉与机器人研究所）；Hospital Clínic Barcelona, Universitat de Barcelona（巴塞罗那大学巴塞罗那临床医院）；Frazer Institute, The University of Queensland（昆士兰大学弗雷泽研究所）；University of Trieste（的里雅斯特大学）；ISAHIT；Canfield Scientific, Inc.（坎菲尔德科学公司）；HUN-REN Institute for Computer Science and Control（HUN-REN计算机科学与控制研究所）
University of Science and Technology of China（中国科学技术大学）；The Ohio State University Medical Center（俄亥俄州立大学医学中心）
Deep convolutional neural network (DCNN) models have been widely explored for skin disease diagnosis and some of them have achieved the diagnostic outcomes comparable or even superior to those of dermatologists. However, broad implementation of DCNN in skin disease detection is hindered by small size and data imbalance of the publically accessible skin lesion datasets. This paper proposes a novel single-model based strategy for classification of skin lesions on small and imbalanced datasets. First, various DCNNs are trained on different small and imbalanced datasets to verify that the models w…
Effective Attention-Guided Multi-Scale Medical Network for Skin Lesion Segmentation
Business University Yantai, China（烟台 business 大学）；Artificial Intelligence Ludong University Yantai, China（人工智能 岭东大学）；Engineering Shandong University of Finance（工程 山东财经大学）
Skin lesion identification is a key step toward dermatological diagnosis. When describing a skin lesion, it is very important to note its body site distribution as many skin diseases commonly affect particular parts of the body. To exploit the correlation between skin lesions and their body site distributions, in this study, we investigate the possibility of improving skin lesion classification using the additional context information provided by body location. Specifically, we build a deep multi-task learning (MTL) framework to jointly optimize skin lesion classification and body location cla…
Shanghai Jiao Tong University（上海交通大学）；École de technologie supérieure, Université du Québec（魁北克大学高等技术学院）；University of Leicester（莱斯特大学）
Skin lesion detection in dermoscopic images is essential in the accurate and early diagnosis of skin cancer by a computerized apparatus. Current skin lesion segmentation approaches show poor performance in challenging circumstances such as indistinct lesion boundaries, low contrast between the lesion and the surrounding area, or heterogeneous background that causes over/under segmentation of the skin lesion. To accurately recognize the lesion from the neighboring regions, we propose a dilated scale-wise feature fusion network based on convolution factorization. Our network is designed to simul…
In this study, we investigate what a practically useful approach is in order to achieve robust skin disease diagnosis. A direct approach is to target the ground truth diagnosis labels, while an alternative approach instead focuses on determining skin lesion characteristics that are more visually consistent and discernible. We argue that, for computer-aided skin disease diagnosis, it is both more realistic and more useful that lesion type tags should be considered as the target of an automated diagnosis system such that the system can first achieve a high accuracy in describing skin lesions, an…
A Novel Multi-task Deep Learning Model for Skin Lesion Segmentation and Classification
Institute of High Performance Computing, A*STAR（新加坡科技研究局高性能计算研究所）；Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）；National Skin Center, National Healthcare Group（国立皮肤中心，国立保健集团）
Unsupervised Skin Lesion Segmentation via Structural Entropy Minimization on Multi-Scale Superpixel Graphs
Beihang University（北京航空航天大学）；Zhongguancun Laboratory（中关村实验室）；Salesforce AI Research（赛富时人工智能研究院）；Didi Chuxing（滴滴出行）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）；Lehigh University（理海大学）
