Search

Manual segmentation of brain tumors using structural magnetic resonance imaging (MRI) is an arduous and time-consuming task. Therefore, automatic and robust segmentation will considerably influence neuro-oncological clinical trials by reducing excessive manual annotation time. Herein, we propose a deep learning model that automatically segments brain tumors even in cases of missing MRI sequences, which are common in practical clinical settings. To address this issue, we enhance a generative adversarial network (GAN) by incorporating a squeeze-and-excitation (SE) attention module into its generator and a PatchGAN into its discriminator. The SE module recalibrates channel responses by explicitly modeling interdependencies, enabling the network to focus on critical regions such as tumor areas. Our proposed generative model is optimized using a combination of adversarial, structural similarity, and mean absolute error losses to synthesize missing MRI sequences more effectively. This enhancement allows our model to synthesize the missing MRI sequence (fluid attenuated inversion recovery [FLAIR]) by leveraging information from other available sequences (T1-weighted, T2-weighted, or contrast-enhanced T1-weighted [T1ce]). For the segmentation task, we employ an optimized nnU-Net model, which is trained using existing sequences and evaluated using both available and synthesized sequences (including missing ones), mimicking real-world scenarios where often only limited MRI sequences are available or usable. Our findings reveal a notable enhancement in brain tumor segmentation, as indicated by a significant increase in overall the Dice similarity coefficient (DSC) from 0.688% (when FLAIR is missing) to 0.873% (when using synthesized FLAIR derived from T2). This improvement brings the segmentation performance closer to what was achieved when real FLAIR was available, where the DSC reaches 0.901%. Moreover, our synthesizing model was also tested on two additional datasets: the BraTS 2020 validation set and BraTS Africa 2023 training set, which produces results comparable to those of BraTS 2021, thereby proving its robustness and generalizability. In addition, the resulting tumor segmentations are subsequently employed to assess the response to treatment in cases where all sequences were available and when synthesis was employed, according to response assessment in neuro-oncology criteria. [Display omitted] [ABSTRACT FROM AUTHOR]

Computed tomography (CT) is a widely used imaging technique in medical diagnosis. Among the latest advances in CT imaging techniques, the use of cone-beam X-ray projections, instead of the usual planar fan beam, promises faster yet safer 3D imaging in comparison to the previous CT imaging methodologies. This technique is called Cone Beam CT (CBCT). However, these advantages come at the expense of a more challenging 3D reconstruction problem that is still an active research area to improve the speed and quality of image reconstruction. In this paper, we propose a rapid parallel Multiplicative Algebraic Reconstruction Technique (rpMART) via a vectorization process for CBCT which gives more accurate and faster reconstruction even with a lower number of projections via parallel computing. We have compared rpMART with the parallel version of Algebraic Reconstruction Technique (pART) and the conventional non-parallel versions of npART, npMART and Feldkamp, Davis, and Kress (npFDK) techniques. The results indicate that the reconstructed volume images from rpMART provide a higher image quality index of 0.99 than the indices of pART and npFDK of 0.80 and 0.39, respectively. Also the proposed implementation of rpMART and pART via parallel computing significantly reduce the reconstruction time from more than 6 h with npART and npMART to 580 and 560 s with the full 360° projections data, respectively. We consider that rpMART could be a better image reconstruction technique for CBCT in clinical applications instead of the widely used FDK method. [ABSTRACT FROM AUTHOR]