Malignant melanoma (MM) is one of the deadliest types of skin cancer. Analysing dermatoscopic images plays an important role in the early detection of MM and other pigmented skin lesions. Among different computer-based methods, deep learning-based approaches and in particular convolutional neural networks have shown excellent classification and segmentation performances for dermatoscopic skin lesion images. These models can be trained end-to-end without requiring any hand-crafted features. However, the effect of using lesion segmentation information on classification performance has remained an open question. In this study, we explicitly investigated the impact of using skin lesion segmentation masks on the performance of dermatoscopic image classification. To do this, first, we developed a baseline classifier as the reference model without using any segmentation masks. Then, we used either manually or automatically created segmentation masks in both training and test phases in different scenarios and investigated the classification performances. Evaluated on the ISIC 2017 challenge dataset which contained two binary classification tasks (i.e. MM vs. all and seborrheic keratosis (SK) vs. all) and based on the derived area under the receiver operating characteristic curve scores, we observed four main outcomes. Our results show that 1) using segmentation masks did not significantly improve the MM classification performance in any scenario, 2) in one of the scenarios (using segmentation masks for dilated cropping), SK classification performance was significantly improved, 3) removing all background information by the segmentation masks significantly degraded the overall classification performance, and 4) in case of using the appropriate scenario (using segmentation for dilated cropping), there is no significant difference of using manually or automatically created segmentation masks.
Fusion of Foundation and Vision Transformer Model Features for Dermatoscopic Image Classification
Research Center for Medical Image Analysis and Artificial Intelligence, Department of Medicine, Faculty of Medicine and Dentistry, Danube Private University（医学影像分析与人工智能研究中心、医学部、医学与牙科学院、多瑙私人大学）；Department of Research and Development, TissueGnostics GmbH（研发部、TissueGnostics GmbH）
Colorimeter-Supervised Skin Tone Estimation from Dermatoscopic Images for Fairness Auditing
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Josip Juraj Strossmayer University of Osijek（奥西杰克大学电子工程、计算机科学与信息科技学院）
Diagnostic Accuracy of Content Based Dermatoscopic Image Retrieval with Deep Classification Features
背景：通过神经网络对医学图像进行自动分类可以达到很高的准确率，但缺乏可解释性。目的：比较使用基于内容的图像检索（CBIR）检索视觉上相似的皮肤镜图像（带有相应的疾病标签）与神经网络预测的诊断准确性。研究方法：一个神经网络进行训练，预测疾病类别的皮肤镜图像从三个回顾性收集的图像数据集，分别包含888，2750和16691图像。诊断预测是基于视觉相似图像中最常见的诊断，或者基于网络输出的softmax的前1类预测。结果测量是预测恶性病变的ROC曲线下面积（AUC），多类准确度和平均精度（mAP），在相应数据集的未见过的测试图像上测量。结果如下：在所有三个数据集中，来自CBIR的皮肤癌预测（评估16个最相似的图像）显示出与softmax预测相似的AUC值（分别为0.842，0.806和0.852与0.830，0.810和0.847;所有p值>0.99）。同样，CBIR的多类准确性与softmax预测相当。当使用CBIR时，与softmax预测相比，训练用于检测仅3个类的网络在具有8个类的数据集上表现更好（mAP分别为0.184 vs. 0.368和0.198 vs. 0.403）。结论：基于神经网络的特征呈现视觉上相似的图像显示出与卷积神经网络的softmax基于概率的诊断相当的准确性。CBIR可能比softmax分类器更有助于提高临床医生在常规临床环境中的诊断准确性。
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）
Boosting Dermatoscopic Lesion Segmentation via Diffusion Models with Visual and Textual Prompts
Shanghai Artificial Intelligence Lab（上海人工智能实验室）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of California Santa Cruz（加利福尼亚大学圣克鲁兹分校）；West China Biomedical Big Data Center, Sichuan University West China Hospital（四川大学华西医院华西生物医学大数据中心）
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）
A Multi-Level Deep Ensemble Model for Skin Lesion Classification in Dermoscopy Images
National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology（空天地海一体化大数据应用技术国家工程实验室）；School of Computer Science and Engineering, Northwestern Polytechnical University（西北工业大学计算机学院）
Skin Lesion Classification Using Hybrid Deep Neural Networks
Medical University of Vienna（维也纳医科大学）；TissueGnostics GmbH（TissueGnostics有限公司）；Loughborough University（拉夫堡大学）；KTH Royal Institute of Technology（KTH皇家理工学院）
Comparative Analysis of Automatic Skin Lesion Segmentation with Two Different Implementations
从周围皮肤中分割病变是开发皮肤癌自动计算机辅助诊断的首要任务。病变的不同特征，如颜色分布不均匀，形状不规则，边界和纹理使这项任务具有挑战性。本文的贡献是提出和比较两种不同的方法来分割皮肤病变。第一种方法使用分水岭，而第二种方法使用均值漂移。在两种方法中进行预处理步骤以去除显微图像的毛发和暗边界。使用Jaccard指数（Intersection over Union或IoU）对所提出的方法进行评估。本文的一个额外的贡献是目前的管道进行预处理和分割应用现有的分割和形态学算法，导致有前途的结果。平均而言，第一种方法表现出比第二种方法更好的性能，200张ISIC-2017挑战图像的平均Jaccard指数分别为89.16%和76.94%。
