Outlier-Based Autism Detection Using Longitudinal Structural MRI

Abstract

Diagnosis of Autism Spectrum Disorder (ASD) using clinical evaluation (cognitive tests) is challenging due to wide variations amongst individuals. Since no effective treatment exists, prompt and reliable ASD diagnosis can enable the effective preparation of treatment regimens. This paper proposes structural Magnetic Resonance Imaging (sMRI)-based ASD diagnosis via an outlier detection approach. To learn spatio-temporal patterns in structural brain connectivity, a Generative Adversarial Network (GAN) is trained exclusively with sMRI scans of healthy subjects. Given a stack of three adjacent slices as input, the GAN generator reconstructs the next three adjacent slices; the GAN discriminator then identifies ASD sMRI scan reconstructions as outliers. This model is compared against two other baselines-a simpler UNet and a sophisticated Self-Attention GAN. Axial, Coronal and Sagittal sMRI slices from the multi-site ABIDE II dataset are used for evaluation. Extensive experiments reveal that our ASD detection framework performs comparably with the state-of-the-art with far fewer training data. Furthermore, longitudinal data (two scans per subject over time) achieve 17-28% higher accuracy than cross-sectional data (one scan per subject). Among other findings, metrics employed for model training as well as reconstruction loss computation impact detection performance, and the coronal modality is found to best encode structural information for ASD detection.

Generative Adversarial Network (Generative Artificial Intelligence) in Pediatric Radiology: A Systematic Review

“…This increasing trend was in line with the one in radiology [ 1 , 77 , 78 , 79 , 80 , 81 , 82 , 83 , 84 , 85 , 86 , 87 , 88 , 89 , 90 , 91 , 92 , 93 , 94 , 95 , 96 , 97 , 98 , 99 , 100 , 101 , 102 , 103 , 104 , 105 , 106 , 107 , 108 , 109 , 110 , 111 , 112 , 113 ]. About half of the articles ( n = 17) were journal papers [ 77 , 78 , 82 , 84 , 87 , 90 , 92 , 97 , 98 , 99 , 100 , 101 , 102 , 103 , 105 , 109 , 111 ]. Around two-...…”

“…All identified articles were published over the last five years and the publication number increased every year with the highest number in 2022 [ 77 , 78 , 79 , 80 , 81 , 82 , 83 , 84 , 85 , 86 , 87 , 88 , 89 , 90 , 91 , 92 , 93 , 94 , 95 , 96 , 97 , 98 , 99 , 100 , 101 , 102 , 103 , 104 , 105 , 106 , 107 , 108 , 109 , 110 , 111 , 112 , 113 ]. This increasing trend was in line with the one in radiology [ 1 , 77 , 78 , 79 , 80 , 81 , 82 , 83 , 84 , 85 , 86 , 87 , 88 , 89 , 90 , 91 , 92 ,…”

“…All low-quality ones were conference papers ( n = 12) [ 79 , 80 , 81 , 83 , 85 , 86 , 91 , 93 , 94 , 95 , 104 , 108 ]. The GAN was commonly applied to MRI ( n = 18) [ 77 , 78 , 83 , 84 , 87 , 90 , 97 , 101 , 103 , 104 , 105 , 106 , 108 , 109 , 110 , 111 , 112 , 113 ] and X-ray ( n = 13) [ 79 , 80 , 89 , 91 , 92 , 94 , 95 , 96 , 98 , 99 , 100 , 102 , 107 ], and the others included computed tomography (CT) ( n = 4) [ 82 , 86 , 93 , 97 ], ultrasound ( n = 2) [ 85 , 88 ] and positron emission tomography (PET) ( n = 1) [ 81 ]. Although the basic GAN architecture was still popular among the included studies ( n = 11) [ 77 …”

Improved Super Resolution of MR Images Using CNNs and Vision Transformers

“…This is particularly relevant for medical image analysis where physics of the imaging systems limits the spatial resolution of radiological images (e.g. MRI, Xray) since obtaining HR images requires longer scanning time, and leads to lower signal-to-noise ratio and smaller spatial coverage [164,158,156,44,23,182,149], [53,159,45,12,110,32], [9,7,84,74], [199,147,95,71]. HR images provide more detailed information about local structures and textures resulting in higher accuracy in disease diagnosis and planning [18,55,70,113], [97,98,114], [117,67,66,69,125], [65,141,139], [138,150,60].…”

“…Also, CNN methods capture mostly local context information and do not explore the global aspects. Zhang et al in [191,153,152,155,157,24], [22,130,151], [79,51,78,49], [42,43,11], [90,77,88], [168,8,75,76] propose a squeeze and excitation network to capture the global characteristics thus leading to improved super resolution output. However, squeeze and excitation relies on CNN features to capture global context which is not optimal.…”