Harald Kittler

Harald Kittler
Medical University of Vienna | MedUni Vienna · Department of Dermatology

MD

About

303
Publications
126,920
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
13,636
Citations
Additional affiliations
January 1996 - present
Medical University of Vienna
Position
  • Ao Univ. Prof

Publications

Publications (303)
Article
Full-text available
Background: Evolving dermoscopic terminology motivated us to initiate a new consensus. Objective: We sought to establish a dictionary of standardized terms. Methods: We reviewed the medical literature, conducted a survey, and convened a discussion among experts. Results: Two competitive terminologies exist, a more metaphoric terminology that...
Article
Full-text available
Background: Whether machine-learning algorithms can diagnose all pigmented skin lesions as accurately as human experts is unclear. The aim of this study was to compare the diagnostic accuracy of state-of-the-art machine-learning algorithms with human readers for all clinically relevant types of benign and malignant pigmented skin lesions. Methods...
Article
Full-text available
The rapid increase in telemedicine coupled with recent advances in diagnostic artificial intelligence (AI) create the imperative to consider the opportunities and risks of inserting AI-based support into new paradigms of care. Here we build on recent achievements in the accuracy of image-based AI for skin cancer diagnosis to address the effects of...
Article
Full-text available
Background: Diagnostic algorithms may reduce noise and bias and improve interrater agreement of clinical decisions. In a practical sense, algorithms may serve as alternatives to specialist consultations or decision support in store-and-forward teledermatology. It is, however, unknown how dermatologists interact with algorithms based on questionnair...
Article
Background: Preoperative assessment of whether a melanoma is invasive or in situ (MIS) is a common task that might have important implications for triage, prognosis, and the selection of surgical margins. Several dermoscopic features suggestive of melanoma have been described, but only a few of these are useful in differentiating MIS from invasive...
Article
Full-text available
Background Previous studies of artificial intelligence (AI) applied to dermatology have shown AI to have higher diagnostic classification accuracy than expert dermatologists; however, these studies did not adequately assess clinically realistic scenarios, such as how AI systems behave when presented with images of disease categories that are not in...
Article
Background Histopathological classification of basal cell carcinoma (BCC) has important prognostic and therapeutic implications, but reproducibility of BCC subtyping among dermatopathologists is poor. Objectives To obtain a consensus paper on BCC classification and subtype definitions. Methods A panel of 12 recognized dermatopathologists (G12) fr...
Article
Importance The use of artificial intelligence (AI) is accelerating in all aspects of medicine and has the potential to transform clinical care and dermatology workflows. However, to develop image-based algorithms for dermatology applications, comprehensive criteria establishing development and performance evaluation standards are required to ensure...
Article
Background Sequential digital dermoscopy (SDD) is applied for early melanoma detection by uncovering dynamic changes of monitored lesions. Convolutional neural networks (CNN) are capable of high diagnostic accuracies similar to trained dermatologists. Objectives To investigate the capability of CNN to correctly classify melanomas originally diagno...
Article
Full-text available
Background Multiple studies have compared the performance of artificial intelligence (AI)–based models for automated skin cancer classification to human experts, thus setting the cornerstone for a successful translation of AI-based tools into clinicopathological practice. Objective The objective of the study was to systematically analyse the curre...
Article
Background and Objective Most melanomas (including melanomas in situ), in Australasia, are treated by general practitioners (GPs). Previously undescribed, the characteristics of a series of melanomas treated by multiple GPs are examined. Patients and Methods Six hundred and thirty-seven melanomas treated by 27 Australasian GPs during 2013 and docu...
Article
Full-text available
The conventional narrative states that the steadily rising incidence of melanoma among fair-skinned Caucasian populations during the last decades is caused by excessive UV-exposure. There is, however, no doubt that other factors had a significant impact on the rising incidence of melanoma. Pre-1980s the clinical diagnosis of melanoma was based on g...
Article
Full-text available
Background Chronic sun damage in the background is common in pigmented actinic keratoses and Bowen’s disease (pAK/BD). While explainable artificial intelligence (AI) demonstrated increased background attention for pAK/BD, humans frequently miss this clue in dermatoscopic images because they tend to focus on the lesion. Aim To analyze whether peril...
Article
Nodular melanoma (ΝΜ) is the most aggressive melanoma subtype and is considered as responsible for more than 40% of melanoma deaths. Early detection of NM is a major challenge, as most NMs lack the ABCD diagnostic criteria and display a nonspecific clinical pattern that may mimic other benign lesions.
Article
Because of the tendency of lentigo maligna (LM) for subclinical extension, staged excisions with margin control achieve lower recurrence rates than conventional wide local excision (0‐9.5% vs 8‐20%). However, these surgical techniques are limited by their requirement in time, costs and training.
Article
Full-text available
Spatio-temporal patterns of melanocytic proliferations observed in vivo are important for diagnosis but the mechanisms that produce them are poorly understood. Here we present an agent-based model for simulating the emergence of the main biologic patterns found in melanocytic proliferations. Our model portrays the extracellular matrix of the dermo-...
Article
Background The clinical differentiation of face and scalp lesions (FSLs) is challenging even for trained dermatologists. Studies comparing the diagnostic performance of a convolutional neural network (CNN) with dermatologists in FSL are lacking. Methods A market-approved CNN (Moleanalyzer-Pro, FotoFinder Systems) was used for binary classification...
Article
Full-text available
Introduction: The International Dermoscopy Society (IDS) conducted an online survey to investigate the impact of coronavirus disease 2019 (COVID-19) outbreak on the daily practice of dermatologists working with skin cancer patients, to collect data regarding the frequency of skin manifestations noticed by the members, and to obtain information abo...
Article
Full-text available
Prior skin image datasets have not addressed patient-level information obtained from multiple skin lesions from the same patient. Though artificial intelligence classification algorithms have achieved expert-level performance in controlled studies examining single images, in practice dermatologists base their judgment holistically from multiple les...
Article
Background Combined blue nevi may mimic melanoma and are relatively often biopsied for diagnostic reasons. Objective To better characterize combined blue nevi and to compare it with melanoma. Methods We collected clinical and dermatoscopic images of 111 histologically confirmed combined blue nevi and contrasted their dermatoscopic characteristics...
Article
Full-text available
Epidemiological and experimental data implicate cutaneous human papillomavirus infection as co‐factor in the development of cutaneous squamous cell carcinomas (cSCCs), particularly in immunocompromised organ transplant recipients (OTRs). Herein, we established and characterized a skin cancer model, in which Mus musculus papillomavirus 1 (MmuPV1) in...
Article
Zusammenfassung Hintergrund und Ziel Pigmentierte intraepidermale Karzinome sind dermatoskopisch durch Punkte und strukturlose Bereiche sowie durch linear angeordnete Punkte und Knäuelgefäße gekennzeichnet. Es gibt keine Studien zu den dermatoskopischen Merkmalen pigmentierter intraepidermaler Karzinome an Kopf und Hals. Unser Ziel ist die Beschre...
Article
Summary Background and Objective Pigmented intraepidermal carcinoma is characterized by dermatoscopic dots and structureless areas, including dots in linear arrangement and by coiled vessels. There are no studies describing the dermatoscopic features of pigmented intraepidermal carcinoma on the head and neck. We aim to characterize the clinical and...
Article
Background There is no internationally vetted set of anatomic terms to describe human surface anatomy. Objective To establish expert consensus on a standardized set of terms that describe clinically‐relevant human surface anatomy. Methods We conducted a Delphi consensus on surface anatomy terminology between July 2017 and July 2019. The initial s...
Preprint
Full-text available
Prior skin image datasets have not addressed patient-level information obtained from multiple skin lesions from the same patient. Though artificial intelligence classification algorithms have achieved expert-level performance in controlled studies examining single images, in practice dermatologists base their judgment holistically from multiple les...
Article
Background Artificial intelligence (AI) is increasingly being used in medical practice. Especially in the image-based diagnosis of skin cancer, AI shows great potential. However, there is a significant discrepancy between expectations and true relevance of AI in current dermatological practice.Objectives This article summarizes promising study resu...
Article
Full-text available
Many systemic viral infections are accompanied by skin rashes of variable morphology, some of them pathognomonic for the respective disease. Limited information is available about cutaneous signs in the course of SARS CoV‐2 infection. Anecdotal observations and small case series collected from all over the globe have described a plethora of skin si...
Article
Advantages of artificial intelligence (ai): With responsible, safe and successful use of artificial intelligence (AI), possible advantages in the field of dermato-oncology include the following: (1) medical work can focus on skin cancer patients, (2) patients can be more quickly and effectively treated despite the increasing incidence of skin canc...
Article
Background Digital dermoscopy monitoring (DDM) helps to recognize melanomas lacking specific dermoscopic features at baseline, but the number of melanomas eventually developing specific features is still unknown. Objective To assess how many melanomas are identified because they develop melanoma-specific criteria over time as compared to melanomas...
Article
Background Thin nodular melanoma (NM) often lacks conspicuous melanoma‐specific dermatoscopic criteria, and escapes clinical detection until it progresses to a thicker and more advanced tumor. Objective To investigate the dermatoscopic morphology of thin (≤2mm Breslow thickness) versus thick (>2mm) NM and to identify dermatoscopic predictors of it...
Article
Full-text available
Recurrent pigmentations on scars after melanocytic tumor excision can be confusing due to its similarities to melanoma. Meanwhile, these conditions which can be mixed with malignant conditions also cause difficulties in diagnosis. Herein, we present a melanoma case developed on a scar region after a while later compound nevus excision.
Article
Background A recently introduced dermatoscopic method for diagnosis of early lentigo maligna (LM) is based on the absence of prevalent patterns of pigmented actinic keratosis (PAK) and solar lentigo/flat seborrheic keratosis (SL/SK). We term this the “inverse approach” Objective To determine whether training on the inverse approach increases the d...
Article
Dermatoscopy as a noninvasive diagnostic tool is not only useful in the differentiation of malignant and benign skin tumors, but is also effective in the diagnosis of inflammatory, infiltrative and infectious dermatoses. As a result, the need for diagnostic punch biopsies in dermatoses could be reduced. Hereby the selection of affected skin areas i...
Article
Background The number needed to biopsy (NNB) ratio for melanoma diagnosis is calculated by dividing the total number of biopsies by the number of biopsied melanomas. It is the inverse of positive predictive value (PPV), which is calculated by dividing the number of biopsied melanomas by the total number of biopsies. NNB is increasingly used as a me...
Article
Background No specific features of nevus-associated melanoma (NAM) are currently defined. Objective To identify clinical/dermoscopic features of NAM. Methods Retrospective evaluation of histopathologically diagnosed NAM. Results 80/165 NAMs had a clinically recognizable nevus component, often raised or nodular, most frequently characterized by d...
Article
皮肤镜检查是使用一种名为皮肤镜的手持放大设备进行检查的技术,可让医生看到裸眼不可见的皮肤内部结构。这有助于诊断皮肤疾病,并减少了对活检的需要(取下一小块皮肤在显微镜下检查)。 它主要用于皮肤肿瘤(例如皮肤癌)的诊断,但它也越来越多地用于其他皮肤疾病,尤其是炎症性和感染性皮肤疾病。在过去几年,发表了若干有关非肿瘤性(即非癌症)皮肤疾病的皮肤镜检查的文章,但不同研究中所用的术语(语言)极不一致。 本研究以国际皮肤镜学会的名义,邀请遍布世界各地的 37 位国际专家参加,旨在确定统一的术语和基本参数(医生应查看的内容),以在非肿瘤性皮肤疾病的皮肤镜检查中使用/评估。 通过使用标准化的一致程序(称为“改进的 DELPHI 方法”)实现了这一目标。作者确定了五个标准化的基本参数。对于每个参数,都选择了可...
Article
Dermoscopy is a technique using a handheld magnifying device called a dermatoscope that allows doctors to see structures in the skin that are not visible to the naked eye. This helps with the diagnosis of skin diseases and reduces the need for biopsies (removal of a small sample of skin to be examined under a microscope). Its main use is for skin t...
Article
Full-text available
Background The diagnosis of pigmented skin lesion is error prone and requires domain-specific expertise, which is not readily available in many parts of the world. Collective intelligence could potentially decrease the error rates of nonexperts. Objective The aim of this study was to evaluate the feasibility and impact of collective intelligence fo...
Article
Full-text available
Artificial intelligence (AI) has emerged as a hot topic within dermatology and during the last years several studies have demonstrated its benefits in a research setting. While this development is unravelling rapidly and has also been made available to consumers, little is known about the attitudes towards AI among dermatologists. To increase our u...
Preprint
Full-text available
Diagnosing basal cell carcinomas (BCC), one of the most common cutaneous malignancies in humans, is a task regularly performed by pathologists and dermato-pathologists. Improving histological diagnosis by providing diagnosis suggestions, i.e. computer-assisted diagnoses is actively researched to improve safety, quality and efficiency. Increasingly,...
Preprint
Dermtrainer is a medical decision support system that assists general practitioners in diagnosing skin diseases and serves as a training platform for dermatologists. Its key components are a comprehensive dermatological knowledge base, a clinical algorithm for diagnosing skin diseases, a reasoning component for deducing the most likely differential...
Article
Importance The recent advances in the field of machine learning have raised expectations that computer-aided diagnosis will become the standard for the diagnosis of melanoma. Objective To critically review the current literature and compare the diagnostic accuracy of computer-aided diagnosis with that of human experts. Data Sources The MEDLINE, a...
Article
Background: Mammary Paget's disease (MPD) is a rare intraepidermal adenocarcinoma of the nipple-areola complex, associated with an underlying breast cancer in approximately 90% of cases. Delayed diagnosis of MPD is common. Its dermoscopic features have been ill defined in the literature. Objectives: To determine the clinical and dermoscopic feat...
Article
Full-text available
Cutaneous blood flow plays a key role in numerous physiological and pathological processes and has significant potential to be used as a biomarker to diagnose skin diseases such as basal cell carcinoma (BCC). The determination of the lesion area and vascular parameters within it, such as vessel density, is essential for diagnosis, surgical treatmen...
Article
Background Over the last few years, several articles on dermoscopy of non‐neoplastic dermatoses have been published, yet there is poor consistency in the terminology among different studies. Objective We aimed to standardize the dermoscopic terminology and identify basic parameters to evaluate in non‐neoplastic dermatoses through an expert consens...
Article
Background: A hallmark of Euphorbia myrsinites (EM), a member of the widespread perennial Euphorbia species, is the extrusion of a poisonous, latex-like sap irritant to the skin and eye after contact. The exact mechanisms underlying these effects have not been unraveled so far. Objectives: The aims of the study were to allocate EM sap-induced ph...
Preprint
Full-text available
The International Skin Imaging Collaboration (ISIC) is a global partnership that has organized the world's largest public repository of dermoscopic images of skin lesions. This archive has been used for 3 consecutive years to host challenges on skin lesion analysis toward melanoma detection, covering 3 analysis tasks of lesion segmentation, lesion...
Article
Computeralgorithmen sind heute in der Lage, klinische und dermatoskopische Bilder zu analysieren und stehen in ihren Erfolgsquoten Dermatologen nicht nach. Bis sich die neuen künstlichen Intelligenzen für einen Praxiseinsatz anbieten, muss jedoch erst die Kommunikation zwischen Maschine und Mensch verfeinert werden.
Chapter
Background: Process mining is a relatively new discipline that helps to discover and analyze actual process executions based on log data. In this paper we apply conformance checking techniques to the process of surveillance of melanoma patients. This process consists of recurring events with time constraints between the events. Objectives: The goal...
Article
Full-text available
Background: Process mining is a relatively new discipline that helps to discover and analyze actual process executions based on log data. In this paper we apply conformance checking techniques to the process of surveillance of melanoma patients. This process consists of recurring events with time constraints between the events. Objectives: The goal...
Article
Importance Convolutional neural networks (CNNs) achieve expert-level accuracy in the diagnosis of pigmented melanocytic lesions. However, the most common types of skin cancer are nonpigmented and nonmelanocytic, and are more difficult to diagnose. Objective To compare the accuracy of a CNN-based classifier with that of physicians with different le...
Article
Background and objective: Fully convolutional neural networks have been shown to perform well for automated skin lesion segmentation on digital dermatoscopic images. Our concept is that transferring encoder weights from a network trained on a classification task on images of the same domain may contain useful information for segmentation. Methods...
Article
Full-text available
Opinion statement: Dermatoscopy (dermoscopy) improves the diagnosis of benign and malignant cutaneous neoplasms in comparison with examination with the unaided eye and should be used routinely for all pigmented and non-pigmented cutaneous neoplasms. It is especially useful for the early stage of melanoma when melanoma-specific criteria are invisib...
Article
Full-text available
Background: Multiple BAP-1 inactivated melanocytic tumors (BIMTs) have been associated with a familial cancer-syndrome involving germline mutations in BAP1. Objectives: We sought to describe the clinical and dermoscopic features of BIMTs. Methods: Retrospective, multicenter, case-control study. Participating centers clinical data, dermoscopic...
Article
Full-text available
A correction to this article has been published and is linked from the HTML and PDF versions of this paper. The error has not been fixed in the paper.
Article
Full-text available
Training of neural networks for automated diagnosis of pigmented skin lesions is hampered by the small size and lack of diversity of available datasets of dermatoscopic images. We tackle this problem by releasing the HAM10000 ("Human Against Machine with 10000 training images") dataset. We collected dermatoscopic images from different populations a...
Article
Background and objectives While dermatoscopy improves diagnostic accuracy for raised nonpigmented lesions, those with white surface keratin can be problematical. We investigated whether retention of povidone–iodine by surface keratin provides a clue to benignity. Methods We performed a retrospective pilot study (n = 57) followed by a prospective s...