Michael Kunz

Michael Kunz

Auto-generated profile, based on publicly available information

Michael Kunz

Department of Dermatology, University Hospital of Basel, Basel, Switzerland

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 June 2023 in European Journal of Cancer
Verified
Journal Article
Open access
SCSara E. Cerminara
Sara E. Cerminara
PCPhil Cheng
Phil Cheng
LKLisa Kostner
Lisa Kostner
SHStephanie Huber
Stephanie Huber
MKMichael Kunz
Michael Kunz
LMLara Valeska Maul
Lara Valeska Maul
Convolutional neural networks (CNNs) have outperformed dermatologists in classifying pigmented skin lesions under artificial conditions. We investigated, for the first time, the performance of three-dimensional (3D) and two-dimensional (2D) CNNs and dermatologists in the early detection of melanoma in a real-world setting. In this prospective study, 1690 melanocytic lesions in 143 patients with high-risk criteria for melanoma were evaluated by dermatologists, 2D-FotoFinder-ATBM and 3D-Vectra WB360 total body photography (TBP). Excision was based on the dermatologists' dichotomous decision, an elevated CNN risk score (study-specific malignancy cut-off: FotoFinder >0.5, Vectra >5.0) and/or the second dermatologist's assessment with CNN support. The diagnostic accuracy of the 2D and 3D CNN classification was compared with that of the dermatologists and the augmented intelligence based on histopathology and dermatologists' assessment. Secondary end-points included reproducibility of risk scores and naevus counts per patient by medical staff (gold standard) compared to automated 3D and 2D TBP CNN counts. The sensitivity, specificity, and receiver operating characteristics area under the curve (ROC-AUC) for risk-score-assessments compared to histopathology of 3D-CNN with 95% confidence intervals (CI) were 90.0%, 64.6% and 0.92 (CI 0.85-1.00), respectively. While dermatologists and augmented intelligence achieved the same sensitivity (90%) and comparable classification ROC-AUC (0.91 [CI 0.80-1.00], 0.88 [CI 0.77-1.00]) with 3D-CNN, their specificity was superior (92.3% and 86.2%, respectively). The 2D-CNN (sensitivity: 70%, specificity: 40%, ROC-AUC: 0.68 [CI 0.46-0.90]) was outperformed by 3D CNN and dermatologists. The 3D-CNN showed a higher correlation coefficient for repeated measurements of 246 lesions (R = 0.89) than the 2D-CNN (R = 0.79). The mean naevus count per patient varied significantly (gold standard: 210 lesions; 3D-CNN: 469; 2D-CNN: 1324; p < 0.0001). Our study emphasises the importance of validating the classification of CNNs in real life. The novel 3D-CNN device outperformed the 2D-CNN and achieved comparable sensitivity with dermatologists. The low specificity of CNNs and the lack of automated counting of TBP nevi currently limit the use of augmented intelligence in clinical practice.

28 April 2023 in Experimental Dermatology
Verified
Journal Article
Open access
RARishika Agarwal
Rishika Agarwal
TDTanja Dittmar
Tanja Dittmar
Hans-Dietmar BeerHans-Dietmar Beer
Hans-Dietmar Beer
MKMichael Kunz
Michael Kunz
SMSimon Mueller
Simon Mueller
Alexander NavariniAlexander Navarini
Alexander Navarini
The translatability of research is highly dependent on models that recapitulate human tissues and organs. Here, we describe a procedure for the generation of human epidermis organotypic cultures (HEOCs) from primary keratinocytes isolated from foreskin and adult skin as well as from an immortalized keratinocyte cell line (KerTr). We tested several media conditions to develop a defined HEOC growing and expansion media. We characterized the HEOCs and show that in optimal culture conditions they express the proliferation marker Ki67, the basement membrane protein collagen 17 (col17) and the epidermal differentiation markers keratin 15 (K15), keratin 14 (K14), keratin 5 (K5), keratin 10 (K10), keratin 1 (K1), transglutaminase 1 (TGM1), transglutaminase 3 (TGM3) and filaggrin (FLG). Thus, they recapitulate the human epidermis and are stratified from the basal layer to the stratum corneum. These HEOC can be generated reproducibly on a large scale, making it an invaluable model for screening therapeutic compounds and also for the study of pathologies affecting the epidermis.

18 May 2018 in Case Reports in Dermatology
Verified
Journal Article
Open access
PDF file
MKMichael Kunz
Michael Kunz
KKKatrin Kerl
Katrin Kerl
RBRalph Peter Braun
Ralph Peter Braun
Basal cell carcinoma (BCC) is the most common cancer in humans worldwide. Many highly specific dermoscopic criteria for BCC are well established in the literature. On the contrary, other malignant or benign skin tumors may mimic BCC by exhibiting similar or even the same dermoscopic features and therefore obscuring the diagnosis of BCC in certain situations. We herein report a case of BCC with dermoscopic features of both BCC and desmoplastic trichoepithelioma (DT). We would like to remind of the often neglected differential diagnosis of DT in a lesion with arborizing vessels and otherwise unusual dermoscopic presentation.

16 June 2018
Verified
Book Chapter
Closed access
PDF file
HCHoracio Cabo
Horacio Cabo
ALAimilios Lallas
Aimilios Lallas
WSWilhem Stolz
Wilhem Stolz
ZAZoe Apalla
Zoe Apalla
MKMichael Kunz
Michael Kunz
RBRalph P. Braun
Ralph P. Braun

18 November 2022 in Journal of Investigative Dermatology
Verified
Journal Article
Closed access
AMA.M. Mueller
A.M. Mueller
EGE. Gössinger
E. Gössinger
LKL. Kostner
L. Kostner
MAM. Amaral
M. Amaral
SHS. Huber
S. Huber
LMLara Valeska Maul
Lara Valeska Maul