Christian Hinge

As a master’s student in mathematical modeling and computation at the Technical University of Denmark, I am passionate about using cutting-edge technologies to solve real-world problems. My current work at the Clinically Applied Artificial Intelligence section at Rigshospitalet, Denmark involves the application of deep learning methods to assist clinicians in medical imaging routines. My interests lie in the areas of unsupervised deep learning, multimodal representation learning, model predictive control and medical imaging, including whole-body PET/CT and brain PET/MRI. I am particularly interested in the development of digital twins for personalized treatment and assessment of patients.

I am excited to be at the forefront of developing new technologies and techniques to improve patient care and optimize clinical workflow. Through my work, I hope to contribute to the advancement of medical imaging and AI-assisted diagnosis, making healthcare more efficient and effective for patients. My ultimate goal is to make a positive impact on society by developing innovative solutions that will benefit patients and clinicians alike.

News

Nov 24, 2022	Our paper on personalized analysis of FDG-PET has been published.

Publications

A zero-dose synthetic baseline for the personalized analysis of [18F]FDG-PET: Application in Alzheimer’s disease

Christian Hinge, Otto Mølby Henriksen, Ulrich Lindberg, and 5 more authors

Frontiers in Neuroscience, Dec 2022

Abs Bib HTML PDF

Purpose: Brain 2-Deoxy-2-[18F]fluoroglucose ([18F]FDG-PET) is widely used in the diagnostic workup of Alzheimer’s disease (AD). Current tools for uptake analysis rely on non-personalized templates, which poses a challenge as decreased glucose uptake could reflect neuronal dysfunction, or heterogeneous brain morphology associated with normal aging. Overcoming this, we propose a deep learning method for synthesizing a personalized [18F]FDG-PET baseline from the patient’s own MRI, and showcase its applicability in detecting AD pathology. Methods: We included [18F]FDG-PET/MRI data from 123 patients of a local cohort and 600 patients from ADNI. A supervised, adversarial model with two connected Generative Adversarial Networks (GANs) was trained on cognitive normal (CN) patients with transfer-learning to generate full synthetic baseline volumes (sbPET) (192 × 192 × 192) which reflect healthy uptake conditioned on brain anatomy. Synthetic accuracy was measured by absolute relative %-difference (Abs%), relative %-difference (RD%), and peak signal-to-noise ratio (PSNR). Lastly, we deployed the sbPET images in a fully personalized method for localizing metabolic abnormalities. Results: The model achieved a spatially uniform Abs% of 9.4%, RD% of 0.5%, and a PSNR of 26.3 for CN subjects. The sbPET images conformed to the anatomical information dictated by the MRI and proved robust in presence of atrophy. The personalized abnormality method correctly mapped the pathology of AD subjects while showing little to no anomalies for CN subjects. Conclusion: This work demonstrated the feasibility of synthesizing fully personalized, healthy-appearing [18F]FDG-PET images. Using these, we showcased a promising application in diagnosing AD, and theorized the potential value of sbPET images in other neuroimaging routines.
@article{zerodose, title = {A zero-dose synthetic baseline for the personalized analysis of [18F]FDG-PET: Application in Alzheimer's disease}, author = {Hinge, Christian and Henriksen, Otto Mølby and Lindberg, Ulrich and Hasselbalch, Steen Gregers and Højgaard, Liselotte and Law, Ian and Andersen, Flemming Littrup and Ladefoged, Claes Nøhr}, journal = {Frontiers in Neuroscience}, year = {2022}, month = dec, volume = {16}, issn = {1662453x, 16624548}, publisher = {Frontiers Media S.A.}, doi = {10.3389/fnins.2022.1053783}, url = {https://www.frontiersin.org/articles/10.3389/fnins.2022.1053783/full}, dimensions = {true}, language = {eng}, format = {article}, }