An end-to-end deep learning pipeline to derive blood input with partial volume corrections for automated parametric brain PET mapping.

Dynamic 2-[18F] fluoro-2-deoxy-D-glucose positron emission tomography (dFDG-PET) for human brain imaging has considerable clinical potential, yet its utilization remains limited. A key challenge in the quantitative analysis of dFDG-PET is characterizing a patient-specific blood input function, traditionally reliant on invasive arterial blood sampling. This research introduces a novel approach employing non-invasive deep learning model-based computations from the internal carotid arteries (ICA) with partial volume (PV) corrections, thereby eliminating the need for invasive arterial sampling. We present an end-to-end pipeline incorporating a 3D U-Net based ICA-net for ICA segmentation, alongside a Recurrent Neural Network (RNN) based MCIF-net for the derivation of a model-corrected blood input function (MCIF) with PV corrections. The developed 3D U-Net and RNN was trained and validated using a 5-fold cross-validation approach on 50 human brain FDG PET scans. The ICA-net achieved an average Dice score of 82.18% and an Intersection over Union of 68.54% across all tested scans. Furthermore, the MCIF-net exhibited a minimal root mean squared error of 0.0052. The application of this pipeline to ground truth data for dFDG-PET brain scans resulted in the precise localization of seizure onset regions, which contributed to a successful clinical outcome, with the patient achieving a seizure-free state after treatment. These results underscore the efficacy of the ICA-net and MCIF-net deep learning pipeline in learning the ICA structure's distribution and automating MCIF computation with PV corrections. This advancement marks a significant leap in non-invasive neuroimaging.

KUB-UNet: Segmentation of Organs of Urinary System from a KUB X-ray Image.

PURPOSE: The alarming increase in diseases of urinary system is a cause of concern for the populace and health experts. The traditional techniques used for the diagnosis of these diseases are inconvenient for patients, require high cost, and additional waiting time for generating the reports. The objective of this research is to utilize the proven potential of Artificial Intelligence for organ segmentation. Correct identification and segmentation of the region of interest in a medical image are important to enhance the accuracy of disease diagnosis. Also, it improves the reliability of the system by ensuring the extraction of features only from the region of interest. METHOD: A lot of research works are proposed in the literature for the segmentation of organs using MRI, CT scans, and ultrasound images. But, the segmentation of kidneys, ureters, and bladder from KUB X-ray images is found under explored. Also, there is a lack of validated datasets comprising KUB X-ray images. These challenges motivated the authors to tie up with the team of radiologists and gather the anonymous and validated dataset that can be used to automate the diagnosis of diseases of the urinary system. Further, they proposed a KUB-UNet model for semantic segmentation of the urinary system. RESULTS: The proposed KUB-UNet model reported the highest accuracy of 99.18% for segmentation of organs of urinary system. CONCLUSION: The comparative analysis of its performance with state-of-the-art models and validation of results by radiology experts prove its reliability, robustness, and supremacy. This segmentation phase may prove useful in extracting the features only from the region of interest and improve the accuracy diagnosis.