Felix J. Dorfner

Felix J. Dorfner

Auto-generated profile, based on publicly available information

Felix J. Dorfner

Department of Radiology, Charité - Universitätsmedizin Berlin corporate member of Freie Universität Berlin and Humboldt Universität zu Berlin, Berlin, 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
3 January 2025 in npj Precision Oncology
Verified
Journal Article
Open access
PDF file
FDFelix J. Dorfner
Felix J. Dorfner
JPJay B. Patel
Jay B. Patel
JKJayashree Kalpathy-Cramer
Jayashree Kalpathy-Cramer
EGElizabeth R. Gerstner
Elizabeth R. Gerstner
CBChristopher P. Bridge
Christopher P. Bridge
Recent progress in deep learning (DL) is producing a new generation of tools across numerous clinical applications. Within the analysis of brain tumors in magnetic resonance imaging, DL finds applications in tumor segmentation, quantification, and classification. It facilitates objective and reproducible measurements crucial for diagnosis, treatment planning, and disease monitoring. Furthermore, it holds the potential to pave the way for personalized medicine through the prediction of tumor type, grade, genetic mutations, and patient survival outcomes. In this review, we explore the transformative potential of DL for brain tumor care and discuss existing applications, limitations, and future directions and opportunities.

1 August 2024 in Radiology
Verified
Journal Article
Closed access
LALisa Adams
Lisa Adams
DTDaniel Truhn
Daniel Truhn
FBFelix Busch
Felix Busch
FDFelix Dorfner
Felix Dorfner
JNJawed Nawabi
Jawed Nawabi
KBKeno Bressem
Keno Bressem
Meta’s Llama 3, an open-source large language model, performed on par with larger proprietary models, such as OpenAI’s GPT-4 and Anthropic’s Claude 3 Opus, on a subset of radiology board-style examination questions, highlighting the potential of open-source artificial intelligence in radiology.

1 October 2024 in Radiology
Verified
Journal Article
Closed access
FDFelix J. Dorfner
Felix J. Dorfner
LJLiv Jürgensen
Liv Jürgensen
LDLeonhard Donle
Leonhard Donle
FMFares Al Mohamad
Fares Al Mohamad
TBTobias R. Bodenmann
Tobias R. Bodenmann
CBChristopher P. Bridge
Christopher P. Bridge
Privacy-preserving open-source large language models show potential as an alternative to OpenAI’s GPT-4 for accurate chest radiograph report classification.

1 November 2025 in Radiology: Artificial Intelligence
Verified
Journal Article
Closed access
HHHartmut Häntze
Hartmut Häntze
LXLina Xu
Lina Xu
CMChristian J. Mertens
Christian J. Mertens
FDFelix J. Dorfner
Felix J. Dorfner
LDLeonhard Donle
Leonhard Donle
KBKeno Bressem
Keno Bressem
MRSegmentator accurately segmented 40 anatomic structures on MRI and CT across three external datasets.

23 December 2024 in RMD Open
Verified
Journal Article
Open access
PDF file
FDFelix J. Dorfner
Felix J. Dorfner
JVJanis Lucas Vahldiek
Janis Lucas Vahldiek
LDLeonhard Donle
Leonhard Donle
AZAndrei Zhukov
Andrei Zhukov
LXLina Xu
Lina Xu
KBKeno Bressem
Keno Bressem
Purpose To examine whether incorporating anatomy-centred deep learning can improve generalisability and enable prediction of disease progression. Methods This retrospective multicentre study included conventional pelvic radiographs of four different patient cohorts focusing on axial spondyloarthritis collected at university and community hospitals. The first cohort, which consisted of 1483 radiographs, was split into training (n=1261) and validation (n=222) sets. The other cohorts comprising 436, 340 and 163 patients, respectively, were used as independent test datasets. For the second cohort, follow-up data of 311 patients was used to examine progression prediction capabilities. Two neural networks were trained, one on images cropped to the bounding box of the sacroiliac joints (anatomy-centred) and the other one on full radiographs. The performance of the models was compared using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity and specificity. Results On the three test datasets, the standard model achieved AUC scores of 0.853, 0.817, 0.947, with an accuracy of 0.770, 0.724, 0.850. Whereas the anatomy-centred model achieved AUC scores of 0.899, 0.846, 0.957, with an accuracy of 0.821, 0.744, 0.906, respectively. The patients who were identified as high risk by the anatomy-centred model had an OR of 2.16 (95% CI 1.19, 3.86) for having progression of radiographic sacroiliitis within 2 years. Conclusion Anatomy-centred deep learning can improve the generalisability of models in detecting radiographic sacroiliitis. The model is published as fully open source alongside this study.

17 September 2025 in International Journal of Medical Informatics
Verified
Journal Article
Open access
PPPhilipp Prucker
Philipp Prucker
TLTristan Lemke
Tristan Lemke
CMChristian J. Mertens
Christian J. Mertens
SZSebastian Ziegelmayer
Sebastian Ziegelmayer
MGMarkus M. Graf
Markus M. Graf
FBFelix Busch
Felix Busch
To prospectively assess the diagnostic performance, workflow efficiency, and clinical impact of three commercial deep-learning tools (BoneView, Rayvolve, RBfracture) for routine musculoskeletal radiograph interpretation. From January to March 2025, two radiologists (4 and 5 years' experience) independently interpreted 1,037 adult musculoskeletal studies (2,926 radiographs) first unaided and, after 14-day washouts, with each AI tool in a randomized crossover design. Ground truth was established by confirmatory CT when available. Outcomes included sensitivity, specificity, accuracy, area under the receiver operating characteristic curve (AUC), interpretation time, diagnostic confidence (5-point Likert), and rates of additional CT recommendations and senior consultations. DeLong tests compared AUCs; Mann-Whitney U and χ2 tests assessed secondary endpoints. AI assistance did not significantly change performance for fractures, dislocations, or effusions. For fractures, AUCs were comparable to baseline (Reader 1: 96.50 % vs. 96.30-96.50 %; Reader 2: 95.35 % vs. 95.97 %; all p > 0.11). For dislocations, baseline AUCs (Reader 1: 92.66 %; Reader 2: 90.68 %) were unchanged with AI (92.76-93.95 % and 92.00 %; p ≥ 0.280). For effusions, baseline AUCs (Reader 1: 92.52 %; Reader 2: 96.75 %) were similar with AI (93.12 % and 96.99 %; p ≥ 0.157). Median interpretation times decreased with AI (Reader 1: 34 s to 21-25 s; Reader 2: 30 s to 21-26 s; all p < 0.001). Confidence improved across tools: BoneView increased combined "very good/excellent" ratings versus unaided reads (Reader 1: 509 vs. 449, p < 0.001; Reader 2: 483 vs. 439, p < 0.001); Rayvolve (Reader 1: 456 vs. 449, p = 0.029; Reader 2: 449 vs. 439, p < 0.001) and RBfracture (Reader 1: 457 vs. 449, p = 0.017; Reader 2: 448 vs. 439, p = 0.001) yielded smaller but significant gains. Reader 1 recommended fewer CT scans with AI assistance (33 vs. 22-23, p = 0.007). In a real-world clinical setting, AI-assisted interpretation of musculoskeletal radiographs reduced reading time and increased diagnostic confidence without materially affecting diagnostic performance. These findings support AI assistance as a lever for workflow efficiency and potential cost-effectiveness at scale.