ESTRO 2022 - Abstract Book

S1397

Abstract book

ESTRO 2022

the Nitroglycerin trial (registration number NCT01210378, n=19). The original HX4-PET images in the first cohort were used for the development of the models; the second cohort for testing. We explored both paired and unpaired translation approaches. We used the paired Pix2Pix, which is state-of-the art, as the reference method. We introduced unpaired translation with CycleGANs. Since naively applying the default CycleGAN system to our use case is a flawed strategy because the invertibility assumption of CycleGAN is seriously violated here, we proposed a design modification to CycleGAN training for circumventing this issue. Image pre-processing included image-registration, SUV standardisation (Figure 1A), and cropping/resampling (Figure1B). We performed an extensive evaluation of the GANs by first testing on a simulated translation task, followed by comprehensively evaluating on the above-mentioned datasets. We, additionally performed a set of clinically relevant downstream tasks (e.g. hypoxia score in the tumour region) on the synthetic HX4-PET images to determine their clinical value. Quantitative analysis included a variety of image similar similarity metrics, and an additional visual inspection of the images to identify artificially generated artefacts.

Results Our experiments show that the modified CycleGAN attains high image-level performance, close to the ones of Pix2Pix (Figure 2). Furthermore, our adapted cycle GAN performed better in the downstream task of reproducing hypoxia levels in the tumour regions.

Conclusion Our experiments show that the modified CycleGAN attains high image-level performance, close to that of Pix2Pix, and although our synthetic HX4-PET images may not yet meet the clinical standard, the results suggest that unpaired translation approaches could be more suitable for the task due to their immunity to noise induced in the training data by spatial misalignments. It is worth noticing that we used only 15 images for models' development, compared to conventional deep learning algorithms employing datasets that are at least an order of magnitude larger.

PO-1610 Evaluation of Compressed Sensing acceleration for 3D radiotherapy MRI

F. Crop 1 , O. Guillaud 2 , A. Gaignierre 2 , C. Barre 3 , C. Fayard 2 , M. Ben Haj Amor 2 , R. Mouttet-Audouard 3 , X. Mirabel 3

1 Centre Oscar Lambret, Medical Physics, Lille, France; 2 Centre Oscar Lambret, Radiology, Lille, France; 3 Centre Oscar Lambret, Radiotherapy, Lille, France Purpose or Objective Radiotherapy preparation MRI is often based on 3D sequences. However, the use of immobilization devices and flexible coils lead to reduced Signal to Noise ratio (SNR). Compressed Sensing is a novel acceleration technique for 3D acquisitions. We investigated Compressed Sensing (CS) acceleration and compared it with CAIPIRINHA k-space based acceleration.