RESUMEN
Intracranial aneurysms (IAs) are a common vascular pathology and are associated with a risk of rupture, which is often fatal. Aneurysm growth of more than 1 mm is considered a surrogate of rupture risk, therefore, this study presents a comprehensive analysis of intracranial aneurysm measurements utilizing a dataset comprising 358 IA from 248 computed tomography angiography (CTA) scans measured by four junior raters and one senior rater. The study explores the variability in sizing assessments by employing both human raters and an Artificial Intelligence (AI) system. Our findings reveal substantial inter- and intra-rater variability among junior raters, contrasting with the lower intra-rater variability observed in the senior rater. Standard deviations of all raters were above the threshold for IA growth (1 mm). Additionally, the study identifies a systemic bias, indicating a tendency for human experts to measure aneurysms smaller than the AI system. Our findings emphasize the challenges in human assessment while also showcasing the capacity of AI technology to improve the precision and reliability of intracranial aneurysm assessments, especially beneficial for junior raters. The potential of AI was particularly evident in the task of monitoring IA at various intervals, where the AI-based approach surpassed junior raters and achieved performance comparable to senior raters.
Asunto(s)
Inteligencia Artificial , Angiografía por Tomografía Computarizada , Aneurisma Intracraneal , Humanos , Aneurisma Intracraneal/diagnóstico por imagen , Aneurisma Intracraneal/patología , Masculino , Femenino , Angiografía por Tomografía Computarizada/métodos , Persona de Mediana Edad , Anciano , Reproducibilidad de los Resultados , Variaciones Dependientes del ObservadorRESUMEN
BACKGROUND: In the setting of primary hyperparathyroidism (PHPT), [18F]fluorocholine PET/CT (FCH-PET) has excellent diagnostic performance, with experienced practitioners achieving 97.7% accuracy in localising hyperfunctioning parathyroid tissue (HPTT). Due to the relative triviality of the task for human readers, we explored the performance of deep learning (DL) methods for HPTT detection and localisation on FCH-PET images in the setting of PHPT. PATIENTS AND METHODS: We used a dataset of 93 subjects with PHPT imaged using FCH-PET, of which 74 subjects had visible HPTT while 19 controls had no visible HPTT on FCH-PET. A conventional Resnet10 as well as a novel mPETResnet10 DL model were trained and tested to detect (present, not present) and localise (upper left, lower left, upper right or lower right) HPTT. Our mPETResnet10 architecture also contained a region-of-interest masking algorithm that we evaluated qualitatively in order to try to explain the model's decision process. RESULTS: The models detected the presence of HPTT with an accuracy of 83% and determined the quadrant of HPTT with an accuracy of 74%. The DL methods performed statistically worse (p < 0.001) in both tasks compared to human readers, who localise HPTT with the accuracy of 97.7%. The produced region-of-interest mask, while not showing a consistent added value in the qualitative evaluation of model's decision process, had correctly identified the foreground PET signal. CONCLUSIONS: Our experiment is the first reported use of DL analysis of FCH-PET in PHPT. We have shown that it is possible to utilize DL methods with FCH-PET to detect and localize HPTT. Given our small dataset of 93 subjects, results are nevertheless promising for further research.
Asunto(s)
Aprendizaje Profundo , Tomografía Computarizada por Tomografía de Emisión de Positrones , Humanos , Glándulas Paratiroides/diagnóstico por imagenRESUMEN
BACKGROUND: PET/CT imaging is widely used in oncology and provides both metabolic and anatomic information. Because of the relatively poor spatial resolution of PET, the detection of small lesions is limited. The low spatial resolution introduces the partial-volume effect (PVE) which negatively affects images both qualitatively and quantitatively. The aim of the study was to investigate the effect of small-voxel (2 mm in-line pixel size) vs. standard-voxel (4 mm in-line pixel size) reconstruction on lesion detection and image quality in a range of activity ratios. MATERIALS AND METHODS: The National Electrical Manufacturers Association (NEMA) body phantom and the Micro Hollow-Sphere phantom spheres were filled with a solution of [18F]fluorodeoxyglucose ([18F]FDG) in sphere-to-background ratios of 2:1, 3:1, 4:1 and 8:1. In all images reconstructed with 2 mm and 4 mm in-line pixel size the visual lesion delineation, contrast recovery coefficient (CRC) and contrast-to-noise ratio (CNR) were evaluated. RESULTS: For smaller (≤ 13 mm) phantom spheres, significantly higher CRC and CNR using small-voxel reconstructions were found, also improving visual lesion delineation. CRC did not differ significantly for larger (≥ 17 mm) spheres using 2 mm and 4 mm in-line pixel size, but CNR was significantly lower; however, lower CNR did not affect visual lesion delineation. CONCLUSIONS: Small-voxel reconstruction consistently improves precise small lesion delineation, lesion contrast and image quality.