Open AccessComputational approaches to detect small lesions in 18 F‐FDG PET/CT scans
Author(s) -
Nichols Kenneth J.,
DiFilippo Frank P.,
Palestro Christopher J.
Publication year - 2021
Publication title -
journal of applied clinical medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.83
H-Index - 48
ISSN - 1526-9914
DOI - 10.1002/acm2.13451
Subject(s) - imaging phantom , nuclear medicine , voxel , visibility , image quality , medicine , radiology , artificial intelligence , computer science , physics , optics , image (mathematics)
Purpose When physicians interpret 18 F‐FDG PET/CT scans, they rely on their subjective visual impression of the presence of small lesions, the criteria for which may vary among readers. Our investigation used physical phantom scans to evaluate whether image texture analysis metrics reliably correspond to visual criteria used to identify lesions and accurately differentiate background regions from sub‐centimeter simulated lesions. Methods Routinely collected quality assurance test data were processed retrospectively for 65 different 18 F‐FDG PET scans performed of standardized phantoms on eight different PET/CT systems. Phantoms included 8‐, 12‐, 16‐, and 25‐mm diameter cylinders embedded in a cylindrical water bath, prepared with 2.5:1 activity‐to‐background ratio emulating typical whole‐body PET protocols. Voxel values in cylinder regions and background regions were sampled to compute several classes of image metrics. Two experienced physicists, blinded to quantified image metrics and to each other's readings, independently graded cylinder visibility on a 5‐level scale (0 = definitely not visible to 4 = definitely visible). Results The three largest cylinders were visible in 100% of cases with a mean visibility score of 3.3 ± 1.2, while the smallest 8‐mm cylinder was visible in 58% of cases with a significantly lower mean visibility score of 1.5±1.1 ( P < 0.0001). By ROC analysis, the polynomial‐fit signal‐to‐noise ratio was the most accurate at discriminating 8‐mm cylinders from the background, with accuracy greater than visual detection (93% ± 2% versus 76% ± 4%, P = 0.0001), and better sensitivity (94% versus 58%, P < 0.0001). Conclusion Image texture analysis metrics are more sensitive than visual impressions for detecting sub‐centimeter simulated lesions. Therefore, image texture analysis metrics are potentially clinically useful for 18 F‐FDG PET/CT studies.