HSHeinz-Peter Schlemmer

Heinz-Peter Schlemmer

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Heinz-Peter Schlemmer has a total of 530 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Abstract: Automated Detection of Focal Bone Marrow Lesions from MRI

    by Jessica Kächele, Markus Wennmann, Arvin von Salomon, Peter Neher, Heinz-Peter Schlemmer, Klaus Maier-Hein

  • Open Access

    Abstract: LesionLocator

    by Maximilian Rokuss, Yannick Kirchhoff, Seval Akbal, Balint Kovacs, Saikat Roy, Constantin Ulrich, Tassilo Wald, Lukas T. Rotkopf, Heinz-Peter Schlemmer, Klaus Maier-Hein


  • Open Access

    Feasibility of opportunistic dental diagnostics in routine photon-counting CT examinations of the cervical spine

    by Stefan Sawall, Joscha Maier, Sinan Sen, Holger Gehrig, Ti-Sun Kim, Christian H. Ziener, Heinz-Peter Schlemmer, Stefan O. Schoenberg, Matthias F. Froelich, Marc Kachelrieß, et al.

    Background: This study evaluates the potential of routine clinical photon-counting computed tomography (PCCT) of the cervical spine for opportunistic dental diagnostics. Methods: Thirty-three patients undergoing routine PCCT were included in this study, with imaging performed at an average dose of 13 mGy. Images were reconstructed to a voxel size of 156 μm and a slice thickness of 0.4 mm. Quantitative image quality was assessed using the contrast-to-noise ratio (CNR) between dental structures, while qualitative assessment of structures like enamel, dentine, root canals, and cortical bone was conducted by two experienced readers using a five-point scale. Results: The inter-reader reproducibility and intra-class correlation coefficient were excellent (all > 0.947). CNRs ranged from 1.6 to 6.1 for all relevant contrasts, and qualitative scores were excellent for all dental structures. Dental pathologies were detected in a significant portion of patients: caries-induced decay in 9 patients (27%) at 26 sites, apical lesions in 12 patients (36%) at 26 sites, and alveolar bone loss in 12 patients (36%) at 12 sites. At least one pathology was present in 23 patients (70%). Conclusions: PCCT offers potential for opportunistic dental diagnostics, providing earlier detection of dental issues and potentially improving overall dental care outcomes.


  • Auf dem Weg zur Herzbildgebung – Max Levy Dorn und die Entwicklung der Orthoröntgenografie

    by Uwe Busch, Heinz-Peter Schlemmer

    Moderne Herzbildgebung mit CT und MRT spielt eine zentrale Rolle in der Versorgung von Herzpatientinnen und -patienten. Diese Entwicklung markiert einen bedeutenden Fortschritt, der auf jahrzehntelanger Forschung basiert. Ein früher Wegbereiter war der Arzt Max Levy-Dorn, dessen Arbeiten ein wichtiges Kapitel in der Geschichte der Herzbildgebung darstellen. Article published online: 16 December 2025 © 2026. Thieme. All rights reserved. Georg Thieme Verlag KG Oswald-Hesse-Straße 50, 70469 Stuttgart, Germany

  • Simulation of spin dephasing in arbitrary susceptibility fields using physics-informed neural networks

    by L. T. Rotkopf, J. C. Holzschuh, H.-P. Schlemmer, C. H. Ziener

    The signal dynamics in MRI are influenced by the geometry of the dephasing domain, as well as by diffusion and susceptibility effects. Analytical solutions exist only for simple models, and there is a clear need for improved simulation methods. The purpose of this work is to develop and validate a physics-informed neural network (PINN) framework for predicting MR signal dynamics from arbitrary local Larmor field distributions. We implemented a PINN-based simulation framework to solve the Bloch-Torrey equation including diffusion and susceptibility terms, with the complex Bloch-Torrey operator formulated with reflecting boundary conditions and an initially isotropic magnetization. The spatiotemporal magnetization distribution was represented as the output of a neural network, with spatial coordinates and time as inputs. We demonstrated that predicting local and total magnetization is feasible using the PINN-based framework for parameter regimes with intermediate oscillation frequencies, though adapted neural networks incorporating dual encoders or Fourier features were necessary, as conventional multilayer perceptrons failed to learn higher-frequency solutions. Most PINN algorithms performed similarly, except for the gradient-enhanced PINN algorithm, which failed to converge to a correct solution. Evidence of significant spectral bias was found and was partially alleviated by the use of Fourier features. We show that simulating the signal dynamics of MRI is possible using a PINN framework, demonstrating high accuracy and greater flexibility than conventional methods.

  • Open Access

    Lung cancer screening CT acquisition protocols for three generations of CT systems conforming to German legislation

    by Stefan Sawall, Joscha Maier, Christian H. Ziener, Heinz-Peter Schlemmer, Thuy D. Do, Hans-Ulrich Kauczor, Stefan O. Schoenberg, Matthias F. Froelich, Marc Kachelrieß


  • Open Access

    Combined radiomics and liquid biopsy reflect tumor biology towards multimodal non-invasive prostate cancer risk stratification

    by Anja Lisa Riediger, Clara Meinzer, Daniela Janscho, Samaneh Eickelschulte, Florian Janke, Olga Lazareva, Daniel Hübschmann, Oliver Stegle, Stefan Fröhling, David Bonekamp, et al.

    Accurate risk stratification is essential to prevent over- and undertreatment in newly diagnosed prostate cancer (PCa). In a pilot study with 49 men (36 PCa patients, 13 controls), we integrated non-invasive data modalities collected in a real-world clinical setting: radiomics from multiparametric magnetic resonance imaging (T2/ADC index-lesion features), routine and extended serological parameters, multimodal liquid biopsy features (copy number variations, chromosomal instability, methylation, fragmentation in plasma/urinary cfDNA), plus clinical and lifestyle factors. Pairwise Spearman analyses revealed significant inter-modality correlations. Our holistic PCa characterization showed that imaging phenotypes reflect tumor stage and molecular aggressiveness: lower ADC metrics correlated inversely with genomic cfDNA features, while ADC/T2 lesion volumes correlated positively with molecular signals. These results indicate that routine imaging and serological data may capture systemic tumor biology. Our proof-of-concept demonstrates feasibility of combining multiple data modalities in real-world clinical workflows and supports developing integrative models for non-invasive PCa risk stratification.

  • Open Access

    Navigating the AI revolution: will radiology sink or soar?

    by Heinz-Peter Schlemmer

    The rapid acceleration of digital transformation and artificial intelligence (AI) is fundamentally reshaping medicine. Much like previous technological revolutions, AI—driven by advances in computer technology and software including machine learning, computer vision, and generative models—is redefining cognitive work in healthcare. Radiology, as one of the first fully digitized medical specialties, is at the forefront of this transformation. AI is automating workflows, enhancing image acquisition and interpretation, and improving diagnostic precision, which collectively boost efficiency, reduce costs, and elevate patient care. Global data networks and AI-powered platforms are enabling borderless collaboration, empowering radiologists to focus on complex decision-making and patient interaction. Despite these profound opportunities, widespread AI adoption in radiology remains limited, often confined to specific use cases, such as chest, neuro, and musculoskeletal imaging. Concerns persist regarding transparency, explainability, and the ethical use of AI systems, while unresolved questions about workload, liability, and reimbursement present additional hurdles. Psychological and cultural barriers, including fears of job displacement and diminished professional autonomy, also slow acceptance. However, history shows that disruptive innovations often encounter initial resistance. Just as the discovery of X-rays over a century ago ushered in a new era, today, digitalization and artificial intelligence will drive another paradigm shift—this time through cognitive automation. To realize AI’s full potential, radiologists must maintain clinical oversight and safeguard their professional identity, viewing AI as a supportive tool rather than a threat. Embracing AI will allow radiologists to elevate their profession, enhance interdisciplinary collaboration, and help shape the future of medicine. Achieving this vision requires not only technological readiness but also early integration of AI education into medical training. Ultimately, radiology will not be replaced by AI, but by radiologists who effectively harness its capabilities.


  • Open Access

    Opportunistic Diagnostics of Dental Implants in Routine Clinical Photon-Counting CT Acquisitions

    by Maurice Ruetters, Holger Gehrig, Christian Mertens, Sinan Sen, Ti-Sun Kim, Heinz-Peter Schlemmer, Christian H. Ziener, Stefan Schoenberg, Matthias Froelich, Marc Kachelrieß, et al.

    Two-dimensional imaging is still commonly used in dentistry, but does not provide the three-dimensional information often required for the accurate assessment of dental structures. Photon-counting computed tomography (PCCT), a new three-dimensional modality mainly used in general medicine, has shown promising potential for dental applications. With growing digitalization and cross-disciplinary integration, using PCCT data from other medical fields is becoming increasingly relevant. Conventional CT scans, such as those of the cervical spine, have so far lacked the resolution to reliably evaluate dental structures or implants. This study evaluates the diagnostic utility of PCCT for visualizing peri-implant structures in routine clinical photon-counting CT acquisitions and assesses the influence of metal artifact reduction (MAR) algorithms on image quality. Ten dental implants were retrospectively included in this IRB-approved study. Standard PCCT scans were reconstructed at multiple keV levels with and without MAR. Quantitative image analysis was performed with respect to contrast and image noise. Qualitative evaluation of peri-implant tissues, implant shoulder, and apex was performed independently by two experienced dental professionals using a five-point Likert scale. Inter-reader agreement was measured using intraclass correlation coefficients (ICCs). PCCT enabled high-resolution imaging of all peri-implant regions with excellent inter-reader agreement (ICC > 0.75 for all structures). Non-MAR reconstructions consistently outperformed MAR reconstructions across all evaluated regions. MAR led to reduced clarity, particularly in immediate peri-implant areas, without significant benefit from energy level adjustments. All imaging protocols were deemed diagnostically acceptable. This is the first in vivo study demonstrating the feasibility of opportunistic dental diagnostics using PCCT in a clinical setting. While MAR reduces peripheral artifacts, it adversely affects image clarity near implants. PCCT offers excellent image quality for peri-implant assessments and enables incidental detection of dental pathologies without additional radiation exposure. PCCT opens new possibilities for opportunistic, three-dimensional dental diagnostics during non-dental CT scans, potentially enabling earlier detection of clinically significant pathologies.


  • Open Access

    Predicting the Malignancy Grade of Soft Tissue Sarcomas on MRI Using Conventional Image Reading and Radiomics

    by Fabian Schmitz, Hendrik Voigtländer, Hyungseok Jang, Heinz-Peter Schlemmer, Hans-Ulrich Kauczor, Sam Sedaghat

    Objectives: This study aims to investigate MRI features predicting the grade of STS malignancy using conventional image reading and radiomics. Methods: Pretherapeutic imaging data regarding size, tissue heterogeneity, peritumoral changes, necrosis, hemorrhage, and cystic degeneration were evaluated in conventional image reading. Furthermore, the tumors’ apparent diffusion coefficient (ADC) values and radiomics features were extracted and analyzed. A random forest machine learning algorithm was trained and evaluated based on the extracted features. Results: A total of 139 STS cases were included in this study. The mean tumor ADC and the ratio between tumor ADC to healthy muscle ADC were significantly lower in high-grade tumors (p = 0.001 and 0.005, respectively). Peritumoral edema (p < 0.001) and peritumoral contrast enhancement (p < 0.001) were significantly more extensive in high-grade tumors. Tumor heterogeneity was significantly increased in high-grade sarcomas, particularly in T2w- and contrast-enhanced sequences using conventional image reading (p < 0.001) as well as in the radiomics analysis (p < 0.001). Our trained random forest machine learning model predicted high-grade status with an area under the curve (AUC) of 0.97 and an F1 score of 0.93. Biopsy-underestimated tumors exhibited differences in tumor heterogeneity and peritumoral changes. Conclusions: Tumor heterogeneity is a key characteristic of high-grade STSs, which is discernible through conventional imaging reading and radiomics analysis. Higher STS grades are also associated with low ADC values, peritumoral edema, and peritumoral contrast enhancement.