皮肤科医师与深度卷积神经网络诊断色素痣和脂溢性角化病皮肤镜图像比较

【摘要】 目的 比较深度卷积神经网络（CNN）与皮肤科医师对色素痣和脂溢性角化病的诊断准确率。方法 使用5 094幅色素痣和脂溢性角化病（SK）的皮肤镜图像对CNN网络ResNet?50通过迁移学习进行训练,建立CNN二分类模型,并应用该模型对30幅色素痣和30幅SK的皮肤镜图像进行自动分类。同时,95位经过皮肤镜培训的有经验的皮肤科医师结合临床皮损图片对上述CNN自动分类的60幅皮肤镜图像进行判读。比较二者的诊断准确率,并对错误分类的图像做进一步统计分析。结果 CNN自动分类模型对色素痣和SK的皮肤镜图像的分类准确率分别为100%（30/30）和76.67%（23/30）,总准确率为88.33%（53/60）;95位皮肤科医师的诊断准确率平均值分别为82.98%（25.8/30）和85.96%（24.9/30）,总准确率为84.47%（50.7/60）。CNN自动分类模型与95位皮肤科医师对色素痣和SK的诊断准确率差异无统计学意义（χ2 = 0.38,P > 0.05）。CNN错误分类的皮肤镜图像被分为3类,即特殊类型（如皮损色素含量多、角化明显）,具有典型特征但存在干扰因素,具有典型特征尚找不到错误分类的原因。结论 CNN自动分类模型在色素痣和SK皮肤镜图像的二分类任务中的表现与有经验的皮肤科医师水平相当。CNN错误分类的原因仍需皮肤科医师与人工智能专业人员共同探索。     

皮肤肿瘤的研究现状及存在问题

相对于炎性皮肤病来说，皮肤肿瘤尤其是皮肤恶性肿瘤在所有皮肤病中所占的比例不高，但其预后则更为严重，引起了皮肤科同行的重视。近10年来对皮肤肿瘤，主要是针对皮肤恶性黑素瘤、皮肤淋巴瘤、皮肤鳞状细胞癌、基底细胞癌及蕈样肉芽肿等进行了深入的研究，取得了可喜的进步。     

人工智能在皮肤科领域的应用与发展

【摘要】 人工智能被称为制造智能机器的科学和工程,为影响当今社会发展的前沿科学技术之一。随着计算机科学、互联网技术等的进步,人工智能逐渐形成认知计算、机器学习及深度学习三个主要分支。近年来,人工智能在影像识别、辅助诊断、医学机器人、药物研发等诸多方面得到应用。皮肤病学自身的学科特点及人工智能在图像识别方面的优势,使得人工智能在皮肤科领域的应用成为当今热点之一。本文阐述了人工智能在皮肤科领域的适用范围,如皮肤影像、皮肤病理及医学机器人等,分析了人工智能在皮肤科应用的现状,并对其未来发展趋势进行了展望。     

皮肤镜情景教学法在临床教学设计中的应用与反思

皮肤影像检查是基于皮肤影像技术发展起来的一系列无创性辅助诊断方法。目前,皮肤镜是我国皮肤科临床最常用的皮肤影像技术。结合皮肤外科和皮肤肿瘤的专业特色,该教研室以基底细胞癌(basal cell carcinoma,BCC)为例,依托皮肤镜影像为教学创新点,构思临床实践的教学设计,并进行反思。     

提高皮肤美容的理论水平及实践技能，引领规范的美容市场

皮肤美容学是一门以皮肤科学为基础，以美学为指导的学科。它是皮肤科学、美学、美容学三者有机结合的产物，是皮肤科学一个新的分支。近年来，我国美容行业快速发展，在一定程度上满足了广大人民群众美容日益增长的需求。但是，随着服务领域和服务数量的不断扩大，有的皮肤科医师缺乏皮肤医学美容专业知识，在治疗皮肤疾病的同时往往不能指导患者进行正确的皮肤美容，达不到疾病治愈与皮肤美容相结合的效果。因此，提高皮肤专科医师皮肤美容的理论水平及实践技能，引领我国规范的美容市场迫在眉睫。     

端粒酶在皮肤科领域的研究进展

端粒一端粒酶在细胞永生化及肿瘤发生中的作用已逐渐被人们所揭示。对近年来端粒酶在皮肤科领域的研究进展，包括皮肤恶性肿瘤、良性肿瘤、癌前病变、某些炎性皮肤病及正常皮肤、皮肤附属器中的表达进行了综述，并对以端粒酶为靶点的治疗在皮肤科领域的应用前景进行了展望。     

全国皮肤外科及美容治疗学习班通知北大核心CSCD

为推动我国皮肤外科及美容治疗学的发展,中国医学科学院皮肤病医院定于2012年11月3-7日在苏州市举办全国皮肤外科及美容治疗学习班通知,届时将邀请皮肤美容外科领域知名专家就皮肤美容外科的基础及临床进行系统的讲座。学习内容涉及皮肤肿瘤、瘢痕与瘢痕疙瘩、皮肤老化、形体雕塑（吸脂及脂肪移植、色紊性皮肤病、皮肤附属器疾病、注射微美容、激光、光动力技术的应用。学习结束、经考核合格后,颁发中国医学科学院皮肤病医院皮肤外科学习班结业证书及中国医师协会皮肤科医师分会皮肤美容培训基地培训证书,并授予国家级一类继续医学教育10学分。     

咪喹莫特治疗皮肤肿瘤的研究进展

咪喹莫特作为一种新的免疫调节药物，由于其具有良好的抗肿瘤和抗病毒活性，自上市以来就被应用于多种皮肤科疾病，包括皮肤肿瘤、病毒和增生类疾病等。除了介绍目前最新研究的咪喹莫特治疗机制外还综述了近年来局部外用5％咪喹莫特软膏在若干皮肤原位癌和皮肤肿瘤类疾病中的成功应用经验及临床研究资料，包括给药方法、不良反应及联合治疗等。探讨咪喹莫特对皮肤肿瘤治疗的新方法及其可能的治疗机制，提示咪喹莫特在皮肤科领域有着广阔的应用前景。     

皮肤恶性肿瘤及癌前病变707例统计分析

对北京大学第一医院皮肤科20年病理检出的恶性肿瘤及癌前病变进行统计分析,了解皮肤恶性肿瘤及癌前病变在皮肤科门诊就诊人群中的患病情况和各种肿瘤出现的频率。     

肝炎病毒与皮肤疾病

肝炎病毒感染无症状者或在出现黄疸等典型肝炎临床症状前后，会有各种各样的皮肤表现，文介绍了与肝炎毒感染相关的多种皮肤疾患及各型肝炎病毒的传播途径，提示皮肤科医师在寻找皮肤病的病因时，应常规进行肝炎病毒的系列血清学检查。     

Skin tear classification using machine learning from digital RGB image

AimSkin tears are traumatic wounds characterised by separation of the skin layers. Severity evaluation is important in the management of skin tears. To support the assessment and management of skin tears, this study aimed to develop an algorithm to estimate a category of the Skin Tear Audit Research classification system (STAR classification) using digital images via machine learning. This was achieved by introducing shape features representing complicated shape of the skin tears.MethodsA skin tear image was separated into small segments, and features of each segment were estimated. The segments were then classified into different classes by machine learning algorithms, namely support vector machine and random forest. Their performance in classifying wound segments and STAR categories was evaluated with 31 images using the leave-one-out cross validation.ResultsSupport vector machine showed an accuracy of 74% and 69% in classifying wound segments and STAR categories, respectively. The corresponding accuracy using random forest were 71% and 63%.ConclusionMachine learning algorithms revealed capable of classifying categories of skin tears. This could offer the potential to aid nurses in their management of skin tears, even if they are not specialised in wound care.     

Deep-learning-based,computer-aided classifier developed with a small dataset of clinical images surpasses board-certified dermatologists in skin tumour diagnosis

Skin cancer is increasing worldwide. However, it is not always practical to send all patients with skin symptoms to dermatology clinics. Artificial intelligence holds great promise in helping the screening for and diagnosis of skin cancer. Although several computer-aided classification systems have been introduced that achieve high sensitivity of melanoma detection, low specificity was a trade-off for high sensitivity. Sensitivity measures the proportion of ‘actual positives’ that are correctly identified (e.g. the percentage of sick people who are correctly identified as having the condition). Specificity measures the proportion of ‘actual negatives’ that are correctly identified as such (e.g. the percentage of healthy people who are correctly identified as not having the condition). The application of a new machine learning method, called deep convolutional neural network (DCNN), to a skin cancer classifier can potentially improve skin cancer screening sensitivity and specificity. However, the number of training images required for such a system is thought to be extremely large and compiling a large data set for rare skin conditions is difficult. In this study, we trained DCNN using fewer than 5000 images, and developed a DCNN classifier that can classify 14 different skin tumors and related conditions. Its performance was tested against 13 board-certified dermatologists. As a result, our system requires only a single image and comes with 96.3% sensitivity and 89.5% specificity in the detection of skin cancer. The accuracy of malignant or benign classification by the DCNN achieved statistically greater accuracy compared with board-certified dermatologists, 85.3% and 92.4%, respectively. In conclusion, we used DCNN trained with a relatively small number of images to develop an efficient skin tumor classifier. The current system could be used in screening purposes in general medical practice but it needs to be thoroughly tested in clinical trials first.     

Uso del aprendizaje automático en el diagnóstico del melanoma. Limitaciones por superar

BackgroundAutomated image classification is a promising branch of machine learning (ML) useful for skin cancer diagnosis, but little has been determined about its limitations for general usability in current clinical practice.ObjectiveTo determine limitations in the selection of skin cancer images for ML analysis, particularly in melanoma.MethodsRetrospective cohort study design, including 2,849 consecutive high-quality dermoscopy images of skin tumors from 2010 to 2014, for evaluation by a ML system. Each dermoscopy image was assorted according to its eligibility for ML analysis.ResultsOf the 2,849 images chosen from our database, 968 (34%) met the inclusion criteria for analysis by the ML system. Only 64.7% of nevi and 36.6% of melanoma met the inclusion criteria. Of the 528 melanomas, 335 (63.4%) were excluded. An absence of normal surrounding skin (40.5% of all melanomas from our database) and absence of pigmentation (14.2%) were the most common reasons for exclusion from ML analysis.DiscussionOnly 36.6% of our melanomas were admissible for analysis by state-of-the-art ML systems. We conclude that future ML systems should be trained on larger datasets which include relevant non-ideal images from lesions evaluated in real clinical practice. Fortunately, many of these limitations are being overcome by the scientific community as recent works show.     

In vivo reflectance confocal microscopy: automated diagnostic image analysis of melanocytic skin tumours

Background In vivo reflectance confocal microscopy (RCM) has been shown to be a valuable imaging tool in the diagnosis of melanocytic skin tumours. However, diagnostic image analysis performed by automated systems is to date quite rare. Objectives In this study, we investigated the applicability of an automated image analysis system using a machine learning algorithm on diagnostic discrimination of benign and malignant melanocytic skin tumours in RCM. Methods Overall, 16 269 RCM tumour images were evaluated. Image analysis was based on features of the wavelet transform. A learning set of 6147 images was used to establish a classification tree algorithm and an independent test set of 10 122 images was applied to validate the tree model (grouping method 1). Additionally, randomly generated ‘new’ learning and test sets, tumour images only and different skin layers were evaluated (grouping method 2, 3 and 4). Results The classification tree analysis correctly classified 93.60% of the melanoma and 90.40% of the nevi images of the learning set. When the classification tree was applied to the independent test set 46.71 ± 19.97% (range 7.81–83.87%) of the tumour images in benign melanocytic skin lesions were classified as ‘malignant’, in contrast to 55.68 ± 14.58% (range 30.65–83.59%; t‐test: P < 0.036) in malignant melanocytic skin lesions (grouping method 1). Further investigations could not improve the results significantly (grouping method 2, 3 and 4). Conclusions The automated RCM image analysis procedure holds promise for further investigations. However, to date our system cannot be applied to routine skin tumour screening.     

Diagnostic image analysis of malignant melanoma in in vivo confocal laser-scanning microscopy: a preliminary study

Background/purpose: In this study we assessed the applicability of image analysis and a machine learning algorithm on diagnostic discrimination of benign and malignant melanocytic skin tumours in in vivo confocal laser-scanning microscopy (CLSM).
Methods: A total of 857 CLSM tumour images including 408 benign nevi and 449 melanoma images was evaluated. Image analysis was based on features of the wavelet transform. For classification purposes we used a classification tree software (CART). Moreover, automated image analysis results were compared with the prediction success of an independent human observer.
Results: CART analysis of the whole set of CLSM tumour images correctly classified 97.55% and 96.32% of melanoma and nevi images. In contrast, sensitivity and specificity of 85.52% and 80.15% could be reached by the human observer. When the image set was randomly divided into a learning (67% of the images) and a test set (33% of the images), overall 97.31% and 81.03% of the tumour images in the learning and test set could be classified correctly by the CART procedure.
Conclusion: Provided automated decisions can be used as a second opinion. This can be valuable in assisting diagnostic decisions in this new and exciting imaging technique.     

Are computers better diagnosticians than dermatologists? A discussion of how artificial intelligence can help in diagnosing skin lesions

Skin cancers are the most common cancers in the UK. Malignant Melanoma (MM) is the most dangerous type of skin cancer. Primary Care Physicians (GPs) often have difficulty in distinguishing harmless skin blemishes from MM, leading to many patients being referred to dermatology departments. There have been enormous advances recently in the application of computer-based Artificial Intelligence (AI) to the field of image analysis. This paper from four authors in London (UK) explores the current position of AI systems in analysing skin lesions (affected patches of skin). Important AI concepts such as convolutional neural networks (CNN) and “deep learning” are explained. By exposing AI systems to hundreds of thousands of pictures of skin lesions, it is possible to “train” them to recognise lesions with a high degree of accuracy. Skin cancer detection, particularly melanoma detection, has now been tested by numerous different groups with multiple AI systems; the most successful ones are generally “convolutional neural networks”. When comparing their performance to dermatologists who are presented with photographs of skin lesions, these AI systems perform similarly, if not better, at identifying whether something is a melanoma or a benign (non-cancerous) mole. However, these programmes are limited by the data sets on which they have been “trained”; for example, a lot of the datasets are trained on Caucasian skin, and will perform less well when detecting melanoma in skin of colour, as they may not have been exposed to enough of this type of image to perform well. They have also not been shown to be particularly useful for diagnosing other types of skin conditions yet and they are not able to provide any kind of explanation for their classification. Because of these limitations, it is unlikely that they will replace dermatologists. The legal framework for AI systems also doesn't allow them to take responsibility for decisions, so responsibility for diagnosis still falls to a responsible clinician. However, in the near future they may well prove to be extremely useful in aiding GPs in making clinical decisions about skin lesions, particularly with regards to urgent referrals to dermatology. Linked Article:   Du-Harpur et al. Br J Dermatol 2020; 183 :423–430 .     

利用影像比色计对肤色进行定量分析

目的　探索用影像比色计对肤色进行定量测定的临床意义。方法　用摄像机和图像分析装置组合成非接触性肤色测量装置———影像比色计 ,对肤色进行定量测定和分析。结果　影像比色计较反射式分光光度仪对肤色测量的精确度明显提高 ,并能对所获取的图像进行长期保存和比较分析。色彩指数a 或b 增大表示大红色或大黄色增强。日本人正常肤色的色度角在 50°～ 70°范围之内。结论　该方法科学、易行 ,适用于有关肤色疾病的诊断和治疗效果的评价。影像CIE L表色系各参数对黄色人种肤色的测量和评价具有重要的临床意义     

The skin through reflectance confocal microscopy — Historical background,technical principles,and its correlation with histopathology

Since its first introduction into medical practice, reflectance confocal microscopy (RCM) has been a valuable non-invasive diagnostic tool for the assessment of benign and malignant neoplasms of the skin. It has also been used as an adjunct for diagnosing equivocal cutaneous neoplasms that lack characteristic clinical or dermoscopic features. The use of RCM has led to a decreased number of biopsies of benign lesions. Multiple published studies show a strong correlation between RCM and histopathology thereby creating a bridge between clinical aspects, dermoscopy, and histopathology. Dermatopathologists may potentially play an important role in the interpretation of confocal images, by their ability to correlate histopathologic findings. RCM has also been shown to be an important adjunct to delineating tumoral margins during surgery, as well as for monitoring the non-surgical treatment of skin cancers. Advanced technology with smaller probes, such as the VivaScope 3000, has allowed access to lesions in previously inaccessible anatomic locations. This review explains the technical principles of RCM and describes the most common RCM features of normal skin with their corresponding histological correlation.     

汉族和藏族人群肤色的测定

目的 测量并比较汉族和藏族人群皮肤反射系数。方法 用新的便携式装置测量３７２名汉族人和２７４名藏族人上臂内侧非暴露部位皮肤的光反射系数,分析有关因素,如年龄、性别、纬度和种族对皮肤反射系数的影响。并确定皮肤反射系数的正常值分布范围,结果 中国汉族和藏族人群之间皮肤反谢系数差异有显著性,同时发现藏族人的肤色深于汉族人;结果还表明肤色与个体年龄的关系不明显,结论 皮肤反射光谱测定是反映肤色深浅的一个客