@article{Gottipati_Thumbur_2022, title={Predicting CT Images with Attenuation Correction Factor for Using Neighbourhood Approach}, volume={10}, url={https://ijisae.org/index.php/IJISAE/article/view/2137}, abstractNote={<p>Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) imaging were incorporated and correlated with each other. These two clinical were adjusted with the attenuation factor between them. As both the clinical imaging techniques use the same hardware leads to time consumption with a low rate of prediction in the existing systems. Therefore, in this paper, predicting CT (p-CT) images by accessing MRI data was implemented with nearest neighbor cluster method identification. The proposed model reduces the training cost and enhances the prediction rate by minimizing the time of execution. PET/MRI helps in understanding the regions of soft tissue and functional tissues, which includes the internal body parts. These datasets out to investigate scientific prerequisites that would perchance be acquired from brain PET/MRI imaging mainly primarily based absolutely on caseload. In this paper, the performance metrics compared are Peak Signal Noise Ratio (PSNR), Mean Absolute Error (MAE). The performance of PET/MRI to quit the imaging modality wish to investigate neurologic and oncologic stipulations related to handy tissues is highlighted. Clinical factors of PET/MRI and its software program to scientific conditions are illustrated with examples extracted from the authors’ prior experience.</p>}, number={3}, journal={International Journal of Intelligent Systems and Applications in Engineering}, author={Gottipati, Srinivas Babu and Thumbur, Gowri}, year={2022}, month={Oct.}, pages={46–51} }