Zaawansowane modele AI do tworzenia pełnodawkowych zdjęć PET mózgu z rezonansu magnetycznego u pacjentów z epilepsją
Score-based generative diffusion models to synthesize full-dose FDG brain PET from MRI in epilepsy patients
W skrócie
Naukowcy przetestowali nowoczesne metody sztucznej inteligencji, aby tworzyć wysokiej jakości zdjęcia PET mózgu na podstawie rezonansu magnetycznego, bez potrzeby podawania pacjentom radioaktywnych znaczników. Badanie wykazało, że najlepszy model potrafi dokładnie odtworzyć diagnostyczne zdjęcia PET używając tylko zdjęć MRI, a wszystkie testowane modele działają jeszcze lepiej, gdy dostają dodatkowo bardzo małe dawki PET. Ta technologia może w przyszłości zmniejszyć lub wyeliminować promieniowanie rentgenowskie dla pacjentów z epilepsją, co jest szczególnie ważne dla młodych osób wymagających częstych badań.
Oryginalny abstract (angielski)
Fluorodeoxyglucose (FDG) PET to evaluate patients with epilepsy is one of the most common applications for simultaneous PET/MRI, given the need to image both brain structure and metabolism but is suboptimal due to the radiation dose in this young population. Little work has been done synthesizing diagnostic quality PET images from MRI data or MRI data with ultralow-dose PET using advanced generative AI methods, such as diffusion models, with attention to clinical evaluations tailored for the epilepsy population. We compared the performance of diffusion- and non-diffusion-based deep learning models for the MRI-to-PET image translation task for epilepsy imaging using simultaneous PET/MRI in 52 subjects (40 train/2 validate/10 hold-out test). We tested three different models: 2 score-based generative diffusion models (SGM-Karras Diffusion [SGM-KD] and SGM-variance preserving [SGM-VP]) and a Transformer-U-net. We report results on standard image processing metrics as well as clinically relevant metrics, including congruency measures (Congruence Index and Congruency Mean Absolute Error) that assess hemispheric metabolic asymmetry, which is a key part of the clinical analysis of these images. We compared the model performance using different inputs such as T1-weighted (T1w), T2 FLAIR (T2F), and 1% ultralow-dose PET images to evaluate the effect and necessity of each imaging contrast. The SGM-KD produced the best qualitative and quantitative results when synthesizing PET purely from T1w and T2 FLAIR images with the least mean absolute error in whole-brain specific uptake value ratio (SUVR) and highest intraclass correlation coefficient. When 1% low-dose PET images are included in the inputs, all models improve significantly and are interchangeable for quantitative performance and visual quality. SGMs hold great potential for pure MRI-to-PET translation, while all 3 model types can synthesize full-dose FDG-PET accurately using MRI and ultralow-dose PET. This suggests that deep learning diffusion models could reduce or eliminate radiation dose for patients being evaluated for epilepsy.