Anjalie Gulati

Background: Around 1 in 59 individuals is diagnosed with Autism Spectrum Disorder (ASD), according to CDS statistics. Conventionally, ASD has been diagnosed using functional brain regions, regions of interest, or multi-tissue-based training in artificial intelligence models. The objective of the exhibit study is to develop an efficient deep learning network for identifying ASD using structural magnetic resonance imaging (MRI)-based brain scans. Methods: In this work, we developed a VGG-based deep learning network capable of diagnosing autism using whole brain gray matter (GM) tissues. We trained our deep network with 132 MRI T1 images from normal controls and 140 MRI T1 images from ASD patients sourced from the Autism Brain Imaging Data Exchange (ABIDE) dataset. Results: The number of participants in both ASD and normal control (CN) subject groups was not statistically different (p = 0.23). The mean age of the CN subject group was 14.62 years (standard deviation: 4.34), and the ASD group had mean age of 14.89 years (standard deviation: 4.29). Our deep learning model accomplished a training accuracy of 97% and a validation accuracy of 96% over 50 epochs without overfitting. Conclusions: To the best of our knowledge, this is the first study to use GM tissue alone for diagnosing ASD using VGG-Net.

Background: Around 1 in 59 individuals is diagnosed with Autism Spectrum Disorder (ASD), according to CDS statistics. Conventionally, ASD has been diagnosed using functional brain regions, regions of interest, or multi-tissue-based training in artificial intelligence models. The objective of the exhibit study is to develop an efficient deep learning network for identifying ASD using structural magnetic resonance imaging (MRI) based brain scans. Methods: In this work, we developed a VGG-based deep learning network capable of diagnosing autism using whole brain gray matter (GM) tissues. We trained our deep network with 132 MRI T1 images from normal controls and 140 MRI T1 images from ASD patients sourced from the Autism Brain Imaging Data Exchange (ABIDE) dataset. Results: The number of participants in both ASD and normal control (CN) subject groups was not statistically different (p=0.23). The mean age of CN subject was 14.62 years( standard deviation : 4.34 ), and ASD group had mean age of 14.89 years (standard deviation : 4.29). Our deep learning model accomplished a training accuracy of 97% and a validation accuracy of 96% over 50 epochs without overfitting. Conclusions: To the best of our knowledge, this is the first study to use GM tissue alone for diagnosing ASD.

Objective: We aimed to investigate if the use of read-out segmented echoplanar imaging with additional two-dimensional navigator correction (Readout Segmentation of Long Variable Echo, RESOLVE) for acquiring prostate diffusion-weighted imaging (DWI) improves image quality, compared to single-shot echoplanar imaging (ss-EPI). Methods: This single-center prospective study cohort included 162 males with suspected prostate cancer, who underwent 3 Tesla multiparametric MRI (3T-mpMRI). Two abdominal radiologists, blinded to the clinical information, separately reviewed each 3T-mpMRI study to rank geometrical distortion, degree of rectal distention, lesion conspicuity, and anatomic details delineation first on ss-EPI-DWI and later on RESOLVE-DWI using 5-point scales (1 = excellent, 5 = poor). The average of the ranking scores given by two readers was generated and used as the final score. Results: There was good-to-excellent interreader agreement for scoring image quality parameters on both ss-EPI and RESOLVE. Geometrical distortion scores > 3 was seen in 12.3% (20/162) of ss-EPI images, with all having geometrical distortion score <3 on RESOLVE (p < .001). The mean image distortion score was significantly less on RESOLVE than ss-EPI (1.16 vs 1.61, p < .01 regardless of rectal gas, p< .05 when stratified by the degree of rectal distention ). RESOLVE was superior to ss-EPI for lesion conspicuity (mean 1.35 vs 1.53, p< .002) and anatomic delineation (2.60 vs 2.68, p< .001) of prostate on DWI. Conclusion: Compared to conventional ss-EPI, the use of RESOLVE for acquisition of prostate DWI resulted in significantly enhanced image quality and reduced geometrical distortion. Advances in knowledge: RESOLVE could be an alternative or replacement of ss-EPI for acquiring prostate DWI with significantly less geometrical distortion and significantly improved lesion conspicuity and anatomic delineation.