2015/06/23 by Estanislao Oubel, Oubel, Estanislao, Hubert Beaumont +3
Computer Science · Medicine · #Advanced Image Processing Techniques #FOS: Physical sciences #MRI in cancer diagnosis #Medical Physics (physics.med-ph) #Prostate Cancer Diagnosis and Treatment
paper · pdf · doi:10.48550/arxiv.1506.07364
openalex publication_date 2015/06/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Accuracy and precision of measurements are important for patient follow up in\noncology but, unfortunately, partial volume effects introduce an undesired\nvariability between observers. Super resolution techniques (SR) combine\nmultiple acquisitions of an object into a single image richer in details.\nHerein, the use of SR for reducing variability is investigated in the specific\ncontext of prostate measurements. Prostate is typically imaged by T2-weighted\nMRI in three perpendicular low resolution images, each of them presenting\npartial volume effects in the direction of the slice selection gradient. SR\ntechniques allow to combine these images into an image presenting the same\nlevel of details in all directions. This is expected to increase the accuracy\nand reproducibility of volume measurements, which in turn improves other\nderived measurements like PSA density.\n