WFWahid Fattal

Wahid Fattal

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Wahid Fattal has a total of 32 co-authors. Here are the top co-authors by number of shared publications:

  • Caelán Max Haney

    Department of Urology and Urosurgery University Medical Center Mannheim, Medical Faculty of the University of Heidelberg Mannheim Germany

    2 shared publications
  • Karl-Friedrich Kowalewski

    Department of Urology and Urosurgery, University Medical Center Mannheim, Medical Faculty of the University of Heidelberg, Theodor-Kutzer-Ufer 1-3, 68167 Mannheim, Germany

    2 shared publications
  • Lena Maier-Hein

    German Cancer Research Center

    2 shared publications
  • Maurice Stephan Michel

    Department of Urology and Urosurgery University Medical Center Mannheim, Medical Faculty of the University of Heidelberg Mannheim Germany

    2 shared publications
  • Alexander Rathenborg

    Department of Urology and Urosurgery University Medical Center Mannheim, Medical Faculty of the University of Heidelberg Mannheim Germany

    1 shared publication
  • Antonia Thiele

    German Cancer Research Center (DKFZ) Heidelberg, Intelligent Systems and Robotics in Urology, Heidelberg, Germany

    1 shared publication

Latest Publications

  • Open Access

    ManUSPECTRAL – the Mannheim Urology HyperSPECTRAL Imaging Atlas of 17 Physiological Human Organs

    by Alexander Rathenborg, Vera Klütz, Paula Grützner, Luisa Hartung, Greta Demmel, Christoph Julien Bender, Jan Sellner, Silvia Seidlitz, Caelan Max Haney‐Aubert, Wahid Fattal, et al.

    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

    Artificial Intelligence–Assisted Prostate Cancer Diagnosis on Transrectal Microultrasound—A Pilot Study for the DeepTRUS Model

    by Caelán Max Haney-Aubert, Balint Kovacs, Ophelia Elise Marie Aubert, Wahid Fattal, Maurin Helen Mangold, Antonia Thiele, Nektarios Winter, Karina Kämpfert, Maximilian Philip Wessendorf, Christoph Brochhausen, et al.

    Purpose: Microultrasound might serve as a viable alternative to MRI for initial prostate cancer detection. This study developed a deep learning model to detect clinically significant prostate cancer (csPCa) on microultrasound and evaluated its impact on diagnostic performance among novice readers. Materials and Methods: One hundred microultrasound sweeps (50 csPCa, 50 benign) were used to train a deep learning model. Model performance was assessed using the area under the receiver operating characteristics curve (AUC) and Dice similarity coefficient (DSC). In an independent test set (25 csPCa, 25 benign), 5 novice readers each evaluated 2 unique sets of 10 sweeps before and after a structured microultrasound training. In both sessions, they first reviewed sweeps unaided and then with algorithm-generated heatmaps. Results: On the training set, DeepTRUS achieved an AUC of 0.687 (95% confidence interval 0.583-0.791) and a DSC of 0.30 (0.21-0.39). In the test set, reader AUC improved from 0.459 (0.294-0.624) to 0.556 (0.394-0.718) before training, and from 0.610 (0.452-0.767) to 0.782 (0.656-0.908) after training, with DeepTRUS assistance. Sensitivity increased from 60% to 72% pretraining and from 80% to 88% posttraining. The interaction between training and DeepTRUS assistance was significant ( P = .006). Conclusions: This pilot study demonstrates the feasibility of training deep learning models on microultrasound data and their potential to enhance diagnostic performance when combined with reader training. The findings provide proof of concept for artificial intelligence–assisted microultrasound interpretation and inform the design of larger validation studies.