Computational Patient Models

headed by Dr. Kristina Giske

We are physicists, medical informaticians, computer scientists, mathematicians, and radiooncologists working together for the benefit of the patient.

You also want to join our team within your →thesis project? Get in touch

focussing to

Our research is dedicated to in-silico radiotherapy simulation of cancer patients undergoing curative irradiation treatment. The challenge for technically precise radiation therapy lies in adapting dose delivery to deformations in the patient’s anatomy induced by motion and physiological changes. Our vision is to create a virtual patient model or a digital twin, serving as a proxy for treatment simulation by accumulating the physical dose and predicting the therapeutic effect of the planned treatment. This empowers treating physicians to tailor the treatment to the specific needs of the patient before irradiation. Algorithm development, advancements in computer technology, and our passion for unusual solutions are our tools in the fight against cancer.

working on

• Utilzing CBCTs for dose computation (phantom measurements, CBCT reconstruction, dose re-optimization, image registration, CNN style transfer, cycleGANs)
  
• Clinical Target Volume definition (image segmentation, inter-observer variability, expert guidelines, expert conformance, ANNs, nn-Unet, neuro-symbolic AI) 
• MR-guided treatment and MR-only treatment planning (MR-DECT imaging studies, CNN style transfer, segmentation & regression, deformable image regsitration)
• Biomechanical motion modelling (Multi-body phsics, Finite Element models)
• CT generation and extrapolation of anatomy (Statistical models, Data generators, Diffusion models)
• GPGPU parallelisation for image processing algorithms (CUDA kernels, multi-GPU scheduling)
• Voxelized, tessellated, and analytical patient representation (Dosimetric impact for small structures)

Accurate motion estimation between medical scans of different modalities (e.g. CT, MRI) is crucial for adaptive radiation therapy. The widely used intesity-based deformable image registration is limited by the absence of physical constraints during deformation. The KinematicDIR project studies the use of a biomechanical model for biofidelic image registration. For the head and neck area, it focusses on a kinematically articulated skeleton model as the driving motion model.

In this BMBF*-funded doctoral project Cornelius Bauer investigates the best approach to incorporate the body model into the registration task and assesses the accuracy and robustness - but also limitations - of the model-based approach. follow me for more details...

*ARTEMIS Project (#13GW0436B) in collaboration with UKHD & HIT (Jürgen Debus, Oliver Jäkel)

based on PuppetMaster preceding projects by Hendrik Teske and Kathrin Bartelheimer

associated project by Sina Thürwächter

Stopping power ratio (SPR) maps are essential for dose deposition calculations in ion beam cancer treatments and are usually estimated from single energy CT (SECT) in clinical practice. Dual-energy CT (DECT), which involves the acquisition of two energy spectra, captures both material-specific information and tissue characterization, showing promise in enhancing patient-tailored SPR map conversion.

In this BMBF*-funded doctoral project Ama Katseena Yawson scrutinises the capability of deep learning models to convert MRI scans into pseudo-CTs or pseudo-SPR maps. follow me for more details...

*ARTEMIS Project (#13GW0436B) in collaboration with UKHD & HIT (Jürgen Debus, Oliver Jäkel)

associated project by Nora Wolf

Patient-tailored contours of target volumes are crucial for radiation treatment planning, significantly influencing the outcome of cancer treatment. Clinical target volume delineation on planning CT scans poses challenges for human experts, proving to be extremely time-consuming and displaying substantial variation between observers. State-of-the-art machine learning algorithms achieve high accuracy on the automatically segmenting anatomical structures, but this success doesn't seamlessly extend to target volumes without additional constraints. The translation of expert guidelines into the machine learning realm has the potential to advance automated target volume delineation, facilitating guideline conformance and clinical use.

In this HIDSS4Health-funded doctoral project Alexandra Walter tackles the implications of supervised learning on data prone to inter-observer variabilities and patient-individual differences utilizing mathematical rules provided by human experts. follow me for more details...

collaboration with Martin Frank (KIT)

associated project by Jakob Kreft and by Marc Buckmakowski

CBCT imaging has become an integral component of photon radiotherapy devices. However, its image quality is restricted in its ability to faacilitate precise patient positioning. The primary objective of the project is to bridge the gap toward achieving image quality comparable to planning CTs, thereby enabling on-couch treatment plan adaptation based solely on CBCTs.

In this Varian-funded doctoral project Goran Stanic investigates the impact of typical image quality shortcomings of CBCT on the degradation of plan quality. Additionally, generative deep learning models are employed to generate synthetic CTs from the lower-quality CBCT images. follow me for more details..

collaboration with Niklas Wahl (E0404) (PI: Oliver Jäkel), Fabian Weykamp (KKE UKHD-DKFZ)

collaboration with Bálint Kovács (MIC DKFZ)

with support by Florian Eber 

Reseach progress in medicine relies on patient-sensitive data, particularly in radiation therapy, which involves the most diverse and frequent imaging requirements for each patient within its precise image-guided adaptive treatment options. Sharing such rich connected data in compliance with ethical and legal requirements necessitates thorough preparations in long-term projects. Technological short-term projects cannot share in-house data, preventing a direct comparison of competing algorithm designs. Creating a data cohort of non-existent but patient-representative radiotherapy-relevant scans could be made openly accessible for radiotherapy research.

In this AI Health Innovation Cluster-funded infrastructural project Pedro Rodrigues scrutinises cutting-edge AI image generator technologies for their capability to mimic medical scans with consistently realistic patient anatomies. follow me for more details...

collaboration with Jens Fleckenstein (UMM)