Lukas Heinlein

Lukas Heinlein

Auto-generated profile, based on publicly available information

Lukas Heinlein

Digital Biomarkers for Oncology Group, German Cancer Research Center (DKFZ), Heidelberg, Germany

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
11 September 2024 in Communications Medicine
Verified
Journal Article
Open access
PDF file
LHLukas Heinlein
Lukas Heinlein
RMRoman C. Maron
Roman C. Maron
AHAchim Hekler
Achim Hekler
SHSarah Haggenmüller
Sarah Haggenmüller
CWChristoph Wies
Christoph Wies
TBTitus Josef Brinker
Titus Josef Brinker
Background: Early detection of melanoma, a potentially lethal type of skin cancer with high prevalence worldwide, improves patient prognosis. In retrospective studies, artificial intelligence (AI) has proven to be helpful for enhancing melanoma detection. However, there are few prospective studies confirming these promising results. Existing studies are limited by low sample sizes, too homogenous datasets, or lack of inclusion of rare melanoma subtypes, preventing a fair and thorough evaluation of AI and its generalizability, a crucial aspect for its application in the clinical setting. Methods: Therefore, we assessed “All Data are Ext” (ADAE), an established open-source ensemble algorithm for detecting melanomas, by comparing its diagnostic accuracy to that of dermatologists on a prospectively collected, external, heterogeneous test set comprising eight distinct hospitals, four different camera setups, rare melanoma subtypes, and special anatomical sites. We advanced the algorithm with real test-time augmentation (R-TTA, i.e., providing real photographs of lesions taken from multiple angles and averaging the predictions), and evaluated its generalization capabilities. Results: Overall, the AI shows higher balanced accuracy than dermatologists (0.798, 95% confidence interval (CI) 0.779–0.814 vs. 0.781, 95% CI 0.760–0.802; p = 4.0e−145), obtaining a higher sensitivity (0.921, 95% CI 0.900–0.942 vs. 0.734, 95% CI 0.701–0.770; p = 3.3e−165) at the cost of a lower specificity (0.673, 95% CI 0.641–0.702 vs. 0.828, 95% CI 0.804–0.852; p = 3.3e−165). Conclusion: As the algorithm exhibits a significant performance advantage on our heterogeneous dataset exclusively comprising melanoma-suspicious lesions, AI may offer the potential to support dermatologists, particularly in diagnosing challenging cases.

17 January 2025 in Nature Communications
Verified
Journal Article
Open access
PDF file
SHSarah Haggenmüller
Sarah Haggenmüller
CWChristoph Wies
Christoph Wies
JAJulia Abels
Julia Abels
JWJana Winterstein
Jana Winterstein
LHLukas Heinlein
Lukas Heinlein
TBTitus Josef Brinker
Titus Josef Brinker
Accurate melanoma diagnosis is crucial for patient outcomes and reliability of AI diagnostic tools. We assess interrater variability among eight expert pathologists reviewing histopathological images and clinical metadata of 792 melanoma-suspicious lesions prospectively collected at eight German hospitals. Moreover, we provide access to the largest panel-validated dataset featuring dermoscopic and histopathological images with metadata. Complete agreement is achieved in 53.5% of cases (424/792), and a majority vote ( ≥ five pathologists) in 90.9% (720/792). Considerable discordance is observed for non-invasive melanomas (complete agreement in only 10/73 cases). The expert panel disagrees with the local pathologists’ and dermatologists’ diagnoses in 14.9% and 33.5% of cases, respectively. This variability highlights the diagnostic challenges of early-stage melanomas and the need to reconsider how ground truth is established in routine care and AI research. Including at least two pathologists or virtual panels may contribute to more consistent diagnostic results.