Christoph Julien Bender
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Christoph Julien Bender has a total of 56 co-authors. Here are the top co-authors by number of shared publications:
- Lena Maier-Hein
German Cancer Research Center
5 shared publications - Alexander Seitel
German Cancer Research Center (DKFZ), Division of Intelligent Medical Systems, Heidelberg, Germany
3 shared publications - Kris K. Dreher
German Cancer Research Center (DKFZ), Division of Intelligent Medical Systems, Heidelberg, Germany
3 shared publications - Jan-Hinrich Nölke
German Cancer Research Center (DKFZ), Division of Intelligent Medical Systems, Heidelberg, Germany
2 shared publications Julius Kempf
Department of Vascular Surgery, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany
2 shared publicationsMilenko Caranovic
Department of Vascular Surgery, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany
2 shared publications
Latest Publications
- Open Access
- 7 October 2026
- Published by Wiley in BJU International
ManUSPECTRAL – the Mannheim Urology HyperSPECTRAL Imaging Atlas of 17 Physiological Human Organs
Objectives: To establish a standardised intraoperative hyperspectral imaging (HSI) human organ reference dataset and to characterise spectral signatures across organ classes as a foundation for future computational and clinical applications. Subjects and Methods: Intraoperative assessment of anatomical structures and tissue quality such as perfusion or malignancy remains largely subjective and lacks quantitative, spatially resolved standards. Spectral imaging is a promising technology to address this ambition containing information content far beyond regular red, green, and blue light (RGB) imaging. While HSI is progressively establishing itself in medicine with certified devices, the lack of human organ‐specific reference datasets appears to be the key bottleneck for future applications. In this prospective observational study, 1095 hyperspectral recordings spanning a spectral range of 500–1000 nm were acquired during 159 urological procedures. Data were obtained using medically‐certified HSI systems and expert‐annotations across 17 anatomical organ classes. Median reflectance spectra and derived physiological indices (tissue oxygenation index, near‐infrared perfusion index, tissue water index, organ haemoglobin index, tissue haemoglobin index) were analysed, and dimensionality reduction (principal component analysis, t‐distributed stochastic neighbour embedding), cosine distance, linear mixed model (LMM) and centred kernel alignment were used to assess spectral differentiability. Results: Human organs demonstrated distinct and consistent spectral fingerprints. Cosine distance showed very low within‐organ distances of 0.001–0.003, indicating high consistency of normalised spectra across subjects (i.e., patients) for the same organs. There were several organ pairs with elevated distances, e.g., bone vs multiple soft tissues with values up to ~0.042 indicating clearer spectral dissimilarity between those pairs. A LMM could quantify the spectral effects of the three influencing factors to be 49.51% for organ, 18.17% for subject and 32.32% for residuals (including repetition) as mean values across the recorded spectrum. Conclusion: The Mannheim Urology hyperSPECTRAL imaging atlas dataset (ManUSPECTRAL) ( https://spectralverse‐heidelberg.org/ ) provides the first standardised multi‐organ hyperspectral reference dataset for human organs. By demonstrating consistent and separable organ‐specific signatures, it establishes a quantitative foundation for future computational modelling and clinical validation studies for intraoperative tissue characterisation in surgery.
- 7 October 2026
- Published by Wiley in BJU International
Open AccessManUSPECTRAL – the Mannheim Urology HyperSPECTRAL Imaging Atlas of 17 Physiological Human Organs
Objectives: To establish a standardised intraoperative hyperspectral imaging (HSI) human organ reference dataset and to characterise spectral signatures across organ classes as a foundation for future computational and clinical applications. Subjects and Methods: Intraoperative assessment of anatomical structures and tissue quality such as perfusion or malignancy remains largely subjective and lacks quantitative, spatially resolved standards. Spectral imaging is a promising technology to address this ambition containing information content far beyond regular red, green, and blue light (RGB) imaging. While HSI is progressively establishing itself in medicine with certified devices, the lack of human organ‐specific reference datasets appears to be the key bottleneck for future applications. In this prospective observational study, 1095 hyperspectral recordings spanning a spectral range of 500–1000 nm were acquired during 159 urological procedures. Data were obtained using medically‐certified HSI systems and expert‐annotations across 17 anatomical organ classes. Median reflectance spectra and derived physiological indices (tissue oxygenation index, near‐infrared perfusion index, tissue water index, organ haemoglobin index, tissue haemoglobin index) were analysed, and dimensionality reduction (principal component analysis, t‐distributed stochastic neighbour embedding), cosine distance, linear mixed model (LMM) and centred kernel alignment were used to assess spectral differentiability. Results: Human organs demonstrated distinct and consistent spectral fingerprints. Cosine distance showed very low within‐organ distances of 0.001–0.003, indicating high consistency of normalised spectra across subjects (i.e., patients) for the same organs. There were several organ pairs with elevated distances, e.g., bone vs multiple soft tissues with values up to ~0.042 indicating clearer spectral dissimilarity between those pairs. A LMM could quantify the spectral effects of the three influencing factors to be 49.51% for organ, 18.17% for subject and 32.32% for residuals (including repetition) as mean values across the recorded spectrum. Conclusion: The Mannheim Urology hyperSPECTRAL imaging atlas dataset (ManUSPECTRAL) ( https://spectralverse‐heidelberg.org/ ) provides the first standardised multi‐organ hyperspectral reference dataset for human organs. By demonstrating consistent and separable organ‐specific signatures, it establishes a quantitative foundation for future computational modelling and clinical validation studies for intraoperative tissue characterisation in surgery.
- Open Access
- 13 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1) , 18695
Photoacoustic device fingerprints induce bias in deep learning models
Deep learning (DL) models developed for established medical imaging modalities have shown increasing performance and reliability as a result of scaling efforts. In contrast, model development for emerging modalities such as photoacoustic imaging (PAI) remains challenged by data sparsity, which limits model generalizability and raises the susceptibility to bias. While recent studies in PAI have started to investigate subject-related confounders, the impact of hardware-related confounders remains unexplored, posing a critical risk for failure in multicentric deployment scenarios. We are the first to provide a multicentric analysis of hardware-induced bias in PAI. We analyzed device-specific characteristics in images from four device instances and two peripheral artery disease studies, and trained DL models to classify device origin and disease under varying levels of device–health correlations in the data. We showed that 1) multiple instances of the same PAI device type embed identifiable fingerprints in the images, 2) that DL models can leverage these fingerprints to reach $$100\,\%$$ accuracy in device detection and critically, 3) when a correlation between device instance and health status is present, models trained for disease diagnosis exploit these device-specific signatures as shortcuts, thereby producing biased and clinically misleading predictions. This research highlights the risk of overestimating algorithm performance when such confounding is overlooked, emphasizing the importance of bias evaluation and explainable artificial intelligence methods to identify potential shortcuts, finally enabling multicentric PAI studies.- 13 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1) , 18695
Open AccessPhotoacoustic device fingerprints induce bias in deep learning models
Deep learning (DL) models developed for established medical imaging modalities have shown increasing performance and reliability as a result of scaling efforts. In contrast, model development for emerging modalities such as photoacoustic imaging (PAI) remains challenged by data sparsity, which limits model generalizability and raises the susceptibility to bias. While recent studies in PAI have started to investigate subject-related confounders, the impact of hardware-related confounders remains unexplored, posing a critical risk for failure in multicentric deployment scenarios. We are the first to provide a multicentric analysis of hardware-induced bias in PAI. We analyzed device-specific characteristics in images from four device instances and two peripheral artery disease studies, and trained DL models to classify device origin and disease under varying levels of device–health correlations in the data. We showed that 1) multiple instances of the same PAI device type embed identifiable fingerprints in the images, 2) that DL models can leverage these fingerprints to reach $$100\,\%$$ accuracy in device detection and critically, 3) when a correlation between device instance and health status is present, models trained for disease diagnosis exploit these device-specific signatures as shortcuts, thereby producing biased and clinically misleading predictions. This research highlights the risk of overestimating algorithm performance when such confounding is overlooked, emphasizing the importance of bias evaluation and explainable artificial intelligence methods to identify potential shortcuts, finally enabling multicentric PAI studies. - Open Access
- 1 July 2025
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 30 (07) , 1-15
Anthropomorphic tissue-mimicking phantoms for oximetry validation in multispectral optical imaging
SignificanceOptical imaging of blood oxygenation (sO2) can be achieved based on the differential absorption spectra of oxy- and deoxyhemoglobin. A key challenge in realizing clinical validation of the sO2 biomarkers is the absence of reliable sO2 reference standards, including test objects.AimTo enable quantitative testing of multispectral imaging methods for assessment of sO2 by introducing anthropomorphic phantoms with appropriate tissue-mimicking optical properties.ApproachWe used the stable copolymer-in-oil base material to create physical anthropomorphic structures and optimized dyes to mimic the optical absorption of blood across a wide spectral range. Using 3D-printed phantom molds generated from a magnetic resonance image of a human forearm, we molded the material into an anthropomorphic shape. Using both reflectance hyperspectral imaging (HSI) and photoacoustic tomography (PAT), we acquired images of the forearm phantoms and evaluated the performance of linear spectral unmixing (LSU).ResultsBased on 10 fabricated forearm phantoms with vessel-like structures featuring five distinct sO2 levels (between 0 and 100%), we showed that the measured absorption spectra of the material correlated well with HSI and PAT data with a Pearson correlation coefficient consistently above 0.8. Further, the application of LSU enabled a quantification of the mean absolute error in sO2 assessment with HSI and PAT.ConclusionsOur anthropomorphic tissue-mimicking phantoms hold potential to provide a robust tool for developing, standardising, and validating optical imaging of sO2.
- 1 July 2025
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 30 (07) , 1-15
Open AccessAnthropomorphic tissue-mimicking phantoms for oximetry validation in multispectral optical imaging
SignificanceOptical imaging of blood oxygenation (sO2) can be achieved based on the differential absorption spectra of oxy- and deoxyhemoglobin. A key challenge in realizing clinical validation of the sO2 biomarkers is the absence of reliable sO2 reference standards, including test objects.AimTo enable quantitative testing of multispectral imaging methods for assessment of sO2 by introducing anthropomorphic phantoms with appropriate tissue-mimicking optical properties.ApproachWe used the stable copolymer-in-oil base material to create physical anthropomorphic structures and optimized dyes to mimic the optical absorption of blood across a wide spectral range. Using 3D-printed phantom molds generated from a magnetic resonance image of a human forearm, we molded the material into an anthropomorphic shape. Using both reflectance hyperspectral imaging (HSI) and photoacoustic tomography (PAT), we acquired images of the forearm phantoms and evaluated the performance of linear spectral unmixing (LSU).ResultsBased on 10 fabricated forearm phantoms with vessel-like structures featuring five distinct sO2 levels (between 0 and 100%), we showed that the measured absorption spectra of the material correlated well with HSI and PAT data with a Pearson correlation coefficient consistently above 0.8. Further, the application of LSU enabled a quantification of the mean absolute error in sO2 assessment with HSI and PAT.ConclusionsOur anthropomorphic tissue-mimicking phantoms hold potential to provide a robust tool for developing, standardising, and validating optical imaging of sO2.
- Open Access
- 9 May 2025
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 20 (7) , 1325-1333
Shortcut learning leads to sex bias in deep learning models for photoacoustic tomography
Purpose: Shortcut learning has been identified as a source of algorithmic unfairness in medical imaging artificial intelligence (AI), but its impact on photoacoustic tomography (PAT), particularly concerning sex bias, remains underexplored. This study investigates this issue using peripheral artery disease (PAD) diagnosis as a specific clinical application. Methods: To examine the potential for sex bias due to shortcut learning in convolutional neural network (CNNs) and assess how such biases might affect diagnostic predictions, we created training and test datasets with varying PAD prevalence between sexes. Using these datasets, we explored (1) whether CNNs can classify the sex from imaging data, (2) how sex-specific prevalence shifts impact PAD diagnosis performance and underdiagnosis disparity between sexes, and (3) how similarly CNNs encode sex and PAD features. Results: Our study with 147 individuals demonstrates that CNNs can classify the sex from calf muscle PAT images, achieving an AUROC of 0.75. For PAD diagnosis, models trained on data with imbalanced sex-specific disease prevalence experienced significant performance drops (up to 0.21 AUROC) when applied to balanced test sets. Additionally, greater imbalances in sex-specific prevalence within the training data exacerbated underdiagnosis disparities between sexes. Finally, we identify evidence of shortcut learning by demonstrating the effective reuse of learned feature representations between PAD diagnosis and sex classification tasks. Conclusion: CNN-based models trained on PAT data may engage in shortcut learning by leveraging sex-related features, leading to biased and unreliable diagnostic predictions. Addressing demographic-specific prevalence imbalances and preventing shortcut learning is critical for developing models in the medical field that are both accurate and equitable across diverse patient populations.
- 9 May 2025
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 20 (7) , 1325-1333
Open AccessShortcut learning leads to sex bias in deep learning models for photoacoustic tomography
Purpose: Shortcut learning has been identified as a source of algorithmic unfairness in medical imaging artificial intelligence (AI), but its impact on photoacoustic tomography (PAT), particularly concerning sex bias, remains underexplored. This study investigates this issue using peripheral artery disease (PAD) diagnosis as a specific clinical application. Methods: To examine the potential for sex bias due to shortcut learning in convolutional neural network (CNNs) and assess how such biases might affect diagnostic predictions, we created training and test datasets with varying PAD prevalence between sexes. Using these datasets, we explored (1) whether CNNs can classify the sex from imaging data, (2) how sex-specific prevalence shifts impact PAD diagnosis performance and underdiagnosis disparity between sexes, and (3) how similarly CNNs encode sex and PAD features. Results: Our study with 147 individuals demonstrates that CNNs can classify the sex from calf muscle PAT images, achieving an AUROC of 0.75. For PAD diagnosis, models trained on data with imbalanced sex-specific disease prevalence experienced significant performance drops (up to 0.21 AUROC) when applied to balanced test sets. Additionally, greater imbalances in sex-specific prevalence within the training data exacerbated underdiagnosis disparities between sexes. Finally, we identify evidence of shortcut learning by demonstrating the effective reuse of learned feature representations between PAD diagnosis and sex classification tasks. Conclusion: CNN-based models trained on PAT data may engage in shortcut learning by leveraging sex-related features, leading to biased and unreliable diagnostic predictions. Addressing demographic-specific prevalence imbalances and preventing shortcut learning is critical for developing models in the medical field that are both accurate and equitable across diverse patient populations.
- Open Access
- 1 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 43 (9) , 3366-3376
Photoacoustic Quantification of Tissue Oxygenation Using Conditional Invertible Neural Networks
Intelligent systems in interventional healthcare depend on the reliable perception of the environment. In this context, photoacoustic tomography (PAT) has emerged as a non-invasive, functional imaging modality with great clinical potential. Current research focuses on converting the high-dimensional, not human-interpretable spectral data into the underlying functional information, specifically the blood oxygenation. One of the largely unexplored issues stalling clinical advances is the fact that the quantification problem is ambiguous, i.e. that radically different tissue parameter configurations could lead to almost identical photoacoustic spectra. In the present work, we tackle this problem with conditional Invertible Neural Networks (cINNs). Going beyond traditional point estimates, our network is used to compute an approximation of the conditional posterior density of tissue parameters given the measurement. To this end, an automatic mode detection algorithm extracts the plausible solution from the sample-based posterior. According to a comprehensive validation study based on both synthetic and real images, our approach is well-suited for exploring ambiguity in quantitative PAT.
- 1 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 43 (9) , 3366-3376
Open AccessPhotoacoustic Quantification of Tissue Oxygenation Using Conditional Invertible Neural Networks
Intelligent systems in interventional healthcare depend on the reliable perception of the environment. In this context, photoacoustic tomography (PAT) has emerged as a non-invasive, functional imaging modality with great clinical potential. Current research focuses on converting the high-dimensional, not human-interpretable spectral data into the underlying functional information, specifically the blood oxygenation. One of the largely unexplored issues stalling clinical advances is the fact that the quantification problem is ambiguous, i.e. that radically different tissue parameter configurations could lead to almost identical photoacoustic spectra. In the present work, we tackle this problem with conditional Invertible Neural Networks (cINNs). Going beyond traditional point estimates, our network is used to compute an approximation of the conditional posterior density of tissue parameters given the measurement. To this end, an automatic mode detection algorithm extracts the plausible solution from the sample-based posterior. According to a comprehensive validation study based on both synthetic and real images, our approach is well-suited for exploring ambiguity in quantitative PAT.