Harald Kittler

Bio: Harald Kittler is an academic researcher from Medical University of Vienna. The author has contributed to research in topics: Dermatoscopy & Nevus. The author has an hindex of 55, co-authored 252 publications receiving 12811 citations. Previous affiliations of Harald Kittler include Brigham and Women's Hospital & Aristotle University of Thessaloniki.

The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions

Abstract: 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 acquired and stored by different modalities. Given this diversity we had to apply different acquisition and cleaning methods and developed semi-automatic workflows utilizing specifically trained neural networks. The final dataset consists of 10015 dermatoscopic images which are released as a training set for academic machine learning purposes and are publicly available through the ISIC archive. This benchmark dataset can be used for machine learning and for comparisons with human experts. Cases include a representative collection of all important diagnostic categories in the realm of pigmented lesions. More than 50% of lesions have been confirmed by pathology, while the ground truth for the rest of the cases was either follow-up, expert consensus, or confirmation by in-vivo confocal microscopy.

Skin lesion analysis toward melanoma detection: A challenge at the 2017 International symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC)

Abstract: This article describes the design, implementation, and results of the latest installment of the dermoscopic image analysis benchmark challenge. The goal is to support research and development of algorithms for automated diagnosis of melanoma, the most lethal skin cancer. The challenge was divided into 3 tasks: lesion segmentation, feature detection, and disease classification. Participation involved 593 registrations, 81 pre-submissions, 46 finalized submissions (including a 4-page manuscript), and approximately 50 attendees, making this the largest standardized and comparative study in this field to date. While the official challenge duration and ranking of participants has concluded, the dataset snapshots remain available for further research and development.

Diagnostic accuracy of dermoscopy

Abstract: Summary The accuracy of the clinical diagnosis of cutaneous melanoma with the unaided eye is only about 60%. Dermoscopy, a non-invasive, in vivo technique for the microscopic examination of pigmented skin lesions, has the potential to improve the diagnostic accuracy. Our objectives were to review previous publications, to compare the accuracy of melanoma diagnosis with and without dermoscopy, and to assess the influence of study characteristics on the diagnostic accuracy. We searched for publications between 1987 and 2000 and identified 27 studies eligible for meta-analysis. The diagnostic accuracy for melanoma was significantly higher with dermoscopy than without this technique (log odds ratio 4·0 [95% CI 3·0 to 5·1] versus 2·7 [1·9 to 3·4]; an improvement of 49%, p=0·001). The diagnostic accuracy of dermoscopy significantly depended on the degree of experience of the examiners. Dermoscopy by untrained or less experienced examiners was no better than clinical inspection without dermoscopy. The diagnostic performance of dermoscopy improved when the diagnosis was made by a group of examiners in consensus and diminished as the prevalence of melanoma increased. A comparison of various diagnostic algorithms for dermoscopy showed no significant differences in their diagnostic performance. A thorough appraisal of the study characteristics showed that most of the studies were potentially influenced by verification bias. In conclusion, dermoscopy improves the diagnostic accuracy for melanoma in comparison with inspection by the unaided eye, but only for experienced examiners.

Dermoscopy of pigmented skin lesions: results of a consensus meeting via the Internet

Abstract: Background: There is a need for better standardization of the dermoscopic terminology in assessing pigmented skin lesions. Objective: The virtual Consensus Net Meeting on Dermoscopy was organized to investigate reproducibility and validity of the various features and diagnostic algorithms. Methods: Dermoscopic images of 108 lesions were evaluated via the Internet by 40 experienced dermoscopists using a 2-step diagnostic procedure. The first-step algorithm distinguished melanocytic versus nonmelanocytic lesions. The second step in the diagnostic procedure used 4 algorithms (pattern analysis, ABCD rule, Menzies method, and 7-point checklist) to distinguish melanoma versus benign melanocytic lesions. κ Values, log odds ratios, sensitivity, specificity, and positive likelihood ratios were estimated for all diagnostic algorithms and dermoscopic features. Results: Interobserver agreement was fair to good for all diagnostic methods, but it was poor for the majority of dermoscopic criteria. Intraobserver agreement was good to excellent for all algorithms and features considered. Pattern analysis allowed the best diagnostic performance (positive likelihood ratio: 5.1), whereas alternative algorithms revealed comparable sensitivity but less specificity. Interobserver agreement on management decisions made by dermoscopy was fairly good (mean κ value: 0.53). Conclusion: The virtual Consensus Net Meeting on Dermoscopy represents a valid tool for better standardization of the dermoscopic terminology and, moreover, opens up a new territory for diagnosing and managing pigmented skin lesions. (J Am Acad Dermatol 2003;48:679-93.) J Am Acad Dermatol 2003;48:679-93.

Automated melanoma recognition

Abstract: A system for the computerized analysis of images obtained from epiluminescence microscopy (ELM) has been developed to enhance the early recognition of malignant melanoma. As an initial step, the binary mask of the skin lesion is determined by several basic segmentation algorithms together with a fusion strategy. A set of features containing shape and radiometric features as well as local and global parameters is calculated to describe the malignancy of a lesion. Significant features are then selected from this set by application of statistical feature subset selection methods. The final kNN classification delivers a sensitivity of 87% with a specificity of 92%.

Dermatologist-level classification of skin cancer with deep neural networks

Abstract: Skin cancer, the most common human malignancy, is primarily diagnosed visually, beginning with an initial clinical screening and followed potentially by dermoscopic analysis, a biopsy and histopathological examination. Automated classification of skin lesions using images is a challenging task owing to the fine-grained variability in the appearance of skin lesions. Deep convolutional neural networks (CNNs) show potential for general and highly variable tasks across many fine-grained object categories. Here we demonstrate classification of skin lesions using a single CNN, trained end-to-end from images directly, using only pixels and disease labels as inputs. We train a CNN using a dataset of 129,450 clinical images-two orders of magnitude larger than previous datasets-consisting of 2,032 different diseases. We test its performance against 21 board-certified dermatologists on biopsy-proven clinical images with two critical binary classification use cases: keratinocyte carcinomas versus benign seborrheic keratoses; and malignant melanomas versus benign nevi. The first case represents the identification of the most common cancers, the second represents the identification of the deadliest skin cancer. The CNN achieves performance on par with all tested experts across both tasks, demonstrating an artificial intelligence capable of classifying skin cancer with a level of competence comparable to dermatologists. Outfitted with deep neural networks, mobile devices can potentially extend the reach of dermatologists outside of the clinic. It is projected that 6.3 billion smartphone subscriptions will exist by the year 2021 (ref. 13) and can therefore potentially provide low-cost universal access to vital diagnostic care.

Part 9: Post-Cardiac Arrest Care: 2010 American Heart Association Guidelines for Cardiopulmonary Resuscitation and Emergency Cardiovascular Care

Abstract: There is increasing recognition that systematic post–cardiac arrest care after return of spontaneous circulation (ROSC) can improve the likelihood of patient survival with good quality of life. This is based in part on the publication of results of randomized controlled clinical trials as well as a description of the post–cardiac arrest syndrome. 1–3 Post–cardiac arrest care has significant potential to reduce early mortality caused by hemodynamic instability and later morbidity and mortality from multiorgan failure and brain injury. 3,4 This section summarizes our evolving understanding of the hemodynamic, neurological, and metabolic abnormalities encountered in patients who are initially resuscitated from cardiac arrest. The initial objectives of post–cardiac arrest care are to ● Optimize cardiopulmonary function and vital organ perfusion. ● After out-of-hospital cardiac arrest, transport patient to an appropriate hospital with a comprehensive post–cardiac arrest treatment system of care that includes acute coronary interventions, neurological care, goal-directed critical care, and hypothermia. ● Transport the in-hospital post–cardiac arrest patient to an appropriate critical-care unit capable of providing comprehensive post–cardiac arrest care. ● Try to identify and treat the precipitating causes of the arrest and prevent recurrent arrest.