Skip to main content

Detail

Sorry, this content is only available in German!
Philipp Tschandl
Priv.Doz. Dr. Philipp Tschandl, PhD

Department of Dermatology
Position: Doctor-in-training

ORCID: 0000-0003-0391-7810

Further Information

Keywords

Dermoscopy; Diagnostic Imaging; Early Detection of Cancer; Image Interpretation, Computer-Assisted; Neural Networks (Computer); Nevi and Melanomas

Research interests

My research focus is to understand and develop automated systems for dermatologic image analysis. The research is focused on making highly complex systems like neural networks applicable and explainable for clinical practice. Secondly, I use these systems in combination with computational modeling to gain insight into biologic behaviour of dermatologic diseases.

Techniques, methods & infrastructure

Structured digital dermatopathologic slide scans and dermatoscopic image data originating from different sources are used for research. Image processing is performed with open-source python modules, and analysis is performed primarily through neural network models realised in PyTorch or Tensorflow.

Grants

  • Die Rolle aktivierender BRAF Mutationen in Nävi aus welchen Melanome entstanden sind (2011)
    Source of Funding: Margarethe Hehberger Stiftung,
    Principal Investigator

Selected publications

  1. Tschandl, P. et al., 2019. Comparison of the accuracy of human readers versus machine-learning algorithms for pigmented skin lesion classification: an open, web-based, international, diagnostic study. The Lancet Oncology. Available at: http://dx.doi.org/10.1016/S1470-2045(19)30333-X.
  2. Tschandl, P. et al., 2019. Expert-Level Diagnosis of Nonpigmented Skin Cancer by Combined Convolutional Neural Networks. JAMA Dermatology, 155(1), p.58. Available at: http://dx.doi.org/10.1001/jamadermatol.2018.4378.
  3. Tschandl, P., Sinz, C. & Kittler, H., 2019. Domain-specific classification-pretrained fully convolutional network encoders for skin lesion segmentation. Computers in Biology and Medicine, 104, pp.111–116. Available at: http://dx.doi.org/10.1016/j.compbiomed.2018.11.010.
  4. Tschandl, P. et al., 2018. Diagnostic accuracy of content-based dermatoscopic image retrieval with deep classification features. British Journal of Dermatology. Available at: http://dx.doi.org/10.1111/bjd.17189.
  5. Tschandl, P., Rosendahl, C. & Kittler, H., 2018. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Scientific Data, 5, p.180161. Available at: http://dx.doi.org/10.1038/sdata.2018.161.