SySCOM: epileptogenic focus localisation using synthetic interictal SPECT images in SISCOM

Interictal SPECT is a critical component of SISCOM analysis for presurgical localisation of epileptogenic regions. However, its clinical reliability can be affected by uncertainty regarding whether the interictal scan is a true representation of a seizure free baseline (i.e., the interictal state). In addition, most patients will also have an interictal FDG PET scan and MRI performed, and it would be useful if the number of scans required could be reduced. This study explores the use of machine learning synthesised interictal SPECT within the SISCOM framework (i.e., SySCOM) as an alternative baseline to the acquired interictal SPECT scan. PET scans from 40 patients with refractory focal epilepsy were used to train a three-dimensional generative adversarial network to synthesise interictal SPECT images. Synthesis performance was evaluated on an independent validation cohort of nine unseen patients using standard image quality metrics (i.e., SSIM, PSNR, RMSE). Both real and synthetic interictal SPECT images were used to generate SISCOM outputs following standard clinical protocols. Five clinicians experienced in the interpretation of SPECT images in epilepsy performed blinded visual localisation of regions of hyperperfusion across 18 predefined anatomical regions. Observer based similarity, agreement, and reproducibility between SISCOM and SySCOM were assessed. Synthetic interictal SPECT images demonstrated high similarity to real images (mean SSIM = 0.94, mean PSNR = 27.9 dB, mean RMSE = 0.041). Visual localisation based comparison of SISCOM with SySCOM demonstrated good agreement between the methods (Dice score = 70%), with an overall 89% agreement across all subjects and regions. Individual reader agreement between sessions remained high, indicating stable interpretation across image types. Machine learning-generated interictal SPECT can be used to produce SySCOM, which is visually and quantitatively comparable to SISCOM, as confirmed by expert readers. The findings demonstrate consistent localisation patterns, high observer agreement, and stable reader reproducibility. This work addresses uncertainty associated with confirming a true seizure-free baseline during interictal SPECT acquisition. SySCOM can therefore be considered a feasible approach that requires further clinical validation before routine clinical implementation. In this retrospective study, synthetic interictal SPECT images generated using a deep learning model produced SISCOM maps that closely resembled those obtained using real interictal SPECT. The spatial localisation of regions of increased perfusion was preserved, and observers demonstrated high agreement when interpreting synthetic and real SISCOM images.