Andy Tsai | Search arXiv

arXiv2026

Evaluation of Image Noise from Computed Tomography in an Organ-Specific Anthropomorphic Phantom

Computed tomography (CT) is used ubiquitously for diagnostic imaging, with novel iterative reconstructions such as hybrid iterative reconstruction with partial model-based component (ASiR-V) and deep learning image reconstruction (DLIR) increasingly utilized. In conjunction, CT vendors have developed a noise index (NI) to reduce radiation dose during protocol development. However, it is unclear how these reconstruction algorithms reduce noise as NI changes, particularly across multiple organs. The goal of this study was to utilize an anthropomorphic phantom to evaluate image noise against the prescribed NI across different organs, determine if DLIR reduces image noise compared to ASiR-V, and use this relationship to determine the maximum volume CT dose index (CTDIvol) reduction at equivalent noise levels. Repeat images were acquired on a GE HealthCare Revolution Apex CT scanner across NI values in an anthropomorphic adult-sized phantom from Kyoto Kagaku with ASiR-V and DLIR. Organs-of-interest were contoured using TotalSegmentator in 3D Slicer. The correlation between the CTDIvol and NI was determined. The standard deviation of the difference in the repeat images was used as a noise metric (NM), correlated with NI, used to determine the NI at equivalent NM between ASiR-V and DLIR, then applied to determine the dose reduction and difference in NM. The relationship between NI and the resulting CTDIvol was found to be proportional to a power law of exponent -2.23. The maximum potential absolute dose reduction from using DLIR was found in the liver at 1.3 mGy with an NI of 7.9. Across all organs, the relative dose reduction increased, the NM-to-NI ratio decreased, and the noise reduction increased across NI. The relationship between image noise and the prescribed NI differed between ASiR-V and DLIR and varied by organ, with model-based dose reductions of up to 1.3 mGy in the liver.

physics.med-ph↗

arXiv2023

Masked Conditional Diffusion Models for Image Analysis with Application to Radiographic Diagnosis of Infant Abuse

The classic metaphyseal lesion (CML) is a distinct injury that is highly specific for infant abuse. It commonly occurs in the distal tibia. To aid radiologists detect these subtle fractures, we need to develop a model that can flag abnormal distal tibial radiographs (i.e. those with CMLs). Unfortunately, the development of such a model requires a large and diverse training database, which is often not available. To address this limitation, we propose a novel generative model for data augmentation. Unlike previous models that fail to generate data that span the diverse radiographic appearance of the distal tibial CML, our proposed masked conditional diffusion model (MaC-DM) not only generates realistic-appearing and wide-ranging synthetic images of the distal tibial radiographs with and without CMLs, it also generates their associated segmentation labels. To achieve these tasks, MaC-DM combines the weighted segmentation masks of the tibias and the CML fracture sites as additional conditions for classifier guidance. The augmented images from our model improved the performances of ResNet-34 in classifying normal radiographs and those with CMLs. Further, the augmented images and their associated segmentation masks enhanced the performance of the U-Net in labeling areas of the CMLs on distal tibial radiographs.

eess.IV↗