Simulated deep CT characterization of liver metastases with high-resolution filtered back projection reconstruction Journal Article


Authors: Wiedeman, C.; Lorraine, P.; Wang, G.; Do, R.; Simpson, A.; Peoples, J.; De Man, B.
Article Title: Simulated deep CT characterization of liver metastases with high-resolution filtered back projection reconstruction
Abstract: Early diagnosis and accurate prognosis of colorectal cancer is critical for determining optimal treatment plans and maximizing patient outcomes, especially as the disease progresses into liver metastases. Computed tomography (CT) is a frontline tool for this task; however, the preservation of predictive radiomic features is highly dependent on the scanning protocol and reconstruction algorithm. We hypothesized that image reconstruction with a high-frequency kernel could result in a better characterization of liver metastases features via deep neural networks. This kernel produces images that appear noisier but preserve more sinogram information. A simulation pipeline was developed to study the effects of imaging parameters on the ability to characterize the features of liver metastases. This pipeline utilizes a fractal approach to generate a diverse population of shapes representing virtual metastases, and then it superimposes them on a realistic CT liver region to perform a virtual CT scan using CatSim. Datasets of 10,000 liver metastases were generated, scanned, and reconstructed using either standard or high-frequency kernels. These data were used to train and validate deep neural networks to recover crafted metastases characteristics, such as internal heterogeneity, edge sharpness, and edge fractal dimension. In the absence of noise, models scored, on average, 12.2% (α=0.012) and 7.5% (α=0.049) lower squared error for characterizing edge sharpness and fractal dimension, respectively, when using high-frequency reconstructions compared to standard. However, the differences in performance were statistically insignificant when a typical level of CT noise was simulated in the clinical scan. Our results suggest that high-frequency reconstruction kernels can better preserve information for downstream artificial intelligence-based radiomic characterization, provided that noise is limited. Future work should investigate the information-preserving kernels in datasets with clinical labels. © The Author(s) 2024.
Keywords: clinical trial; pathology; liver metastasis; computerized tomography; diagnosis; patient treatment; diseases; image reconstruction; computed tomography; colorectal liver metastases; colorectal liver metastasis; deep learning; radiomics; virtual clinical trials; deep neural networks; pipelines; e-learning; radiomic; images reconstruction; high frequency hf; fractal dimension; edge sharpness; virtual clinical trial
Journal Title: Visual Computing for Industry, Biomedicine, and Art
Volume: 7
ISSN: 2096-496X
Publisher: Springer Nature  
Date Published: 2024-06-11
Start Page: 13
Language: English
DOI: 10.1186/s42492-024-00161-y
PROVIDER: scopus
PMCID: PMC11166620
PUBMED: 38861067
DOI/URL:
Notes: Article -- Source: Scopus
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
  1. Kinh Gian Do
    257 Do