Dataset Information

Grayscale image statistics of COVID-19 patient CT scans characterize lung condition with machine and deep learning.

ABSTRACT:

Background

Grayscale image attributes of computed tomography (CT) of pulmonary scans contain valuable information relating to patients with respiratory ailments. These attributes are used to evaluate the severity of lung conditions of patients confirmed to be with and without COVID-19.

Method

Five hundred thirteen CT images relating to 57 patients (49 with COVID-19; 8 free of COVID-19) were collected at Namazi Medical Centre (Shiraz, Iran) in 2020 and 2021. Five visual scores (VS: 0, 1, 2, 3, or 4) are clinically assigned to these images with the score increasing with the severity of COVID-19-related lung conditions. Eleven deep learning and machine learning techniques (DL/ML) are used to distinguish the VS class based on 12 grayscale image attributes.

Results

The convolutional neural network achieves 96.49% VS accuracy (18 errors from 513 images) successfully distinguishing VS Classes 0 and 1, outperforming clinicians' visual inspections. An algorithmic score (AS), involving just five grayscale image attributes, is developed independently of clinicians' assessments (99.81% AS accuracy; 1 error from 513 images).

Conclusion

Grayscale CT image attributes can be successfully used to distinguish the severity of COVID-19 lung damage. The AS technique developed provides a suitable basis for an automated system using ML/DL methods and 12 image attributes.

SUBMITTER: Ghashghaei S

PROVIDER: S-EPMC9347876 | biostudies-literature | 2022 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Grayscale image statistics of COVID-19 patient CT scans characterize lung condition with machine and deep learning.

Ghashghaei Sara S Wood David A DA Sadatshojaei Erfan E Jalilpoor Mansooreh M

Chronic diseases and translational medicine 20220531 3

<h4>Background</h4>Grayscale image attributes of computed tomography (CT) of pulmonary scans contain valuable information relating to patients with respiratory ailments. These attributes are used to evaluate the severity of lung conditions of patients confirmed to be with and without COVID-19.<h4>Method</h4>Five hundred thirteen CT images relating to 57 patients (49 with COVID-19; 8 free of COVID-19) were collected at Namazi Medical Centre (Shiraz, Iran) in 2020 and 2021. Five visual scores (VS: ...[more]

PMID: 35942198

Similar Datasets

Project description:Background and purposeTo investigate the image quality and accurate bone mineral density (BMD) on quantitative CT (QCT) for osteoporosis screening by deep-learning image reconstruction (DLIR) based on a multi-phantom and patient study.Materials and methodsHigh-contrast spatial resolution, low-contrast detectability, modulation function test (MTF), noise power spectrum (NPS), and image noise were evaluated for physical image quality on Caphan 500 phantom. Three calcium hydroxyapatite (HA) inserts were used for accurate BMD measurement on European Spine Phantom (ESP). CT images were reconstructed with filtered back projection (FBP), adaptive statistical iterative reconstruction-veo 50% (ASiR-V50%), and three levels of DLIR(L/M/H). Subjective evaluation of the image high-contrast spatial resolution and low-contrast detectability were compared visually by qualified radiologists, whilst the statistical difference in the objective evaluation of the image high-contrast spatial resolution and low-contrast detectability, image noise, and relative measurement error were compared using one-way analysis of variance (ANOVA). Cohen's kappa coefficient (k) was performed to determine the interobserver agreement in qualitative evaluation between two radiologists.ResultsOverall, for three levels of DLIR, 50% MTF was about 4.50 (lp/cm), better than FBP (4.12 lp/cm) and ASiR-V50% (4.00 lp/cm); the 2 mm low-contrast object was clearly resolved at a 0.5% contrast level, while 3mm at FBP and ASiR-V50%. As the strength level decreased and radiation dose increased, DLIR at three levels showed a higher NPS peak frequency and lower noise level, leading to leftward and rightward shifts, respectively. Measured L1, L2, and L3 were slightly lower than that of nominal HA inserts (44.8, 95.9, 194.9 versus 50.2, 100.6, 199.2mg/cm3) with a relative measurement error of 9.84%, 4.08%, and 2.60%. Coefficients of variance for the L1, L2, and L3 HA inserts were 1.51%, 1.41%, and 1.18%. DLIR-M and DLIR-H scored significantly better than ASiR-V50% in image noise (4.83 ± 0.34, 4.50 ± 0.50 versus 4.17 ± 0.37), image contrast (4.67 ± 0.73, 4.50 ± 0.70 versus 3.80 ± 0.99), small structure visibility (4.83 ± 0.70, 4.17 ± 0.73 versus 3.83 ± 1.05), image sharpness (3.83 ± 1.12, 3.53 ± 0.90 versus 3.27 ± 1.16), and artifacts (3.83 ± 0.90, 3.42 ± 0.37 versus 3.10 ± 0.83). The CT value, image noise, contrast noise ratio, and image artifacts in DLIR-M and DLIR-H outperformed ASiR-V50% and FBP (P<0.001), whilst it showed no statistically significant between DLIR-L and ASiR-V50% (P>0.05). The prevalence of osteoporosis was 74 (24.67%) in women and 49 (11.79%) in men, whilst the osteoporotic vertebral fracture rate was 26 (8.67%) in women and (5.29%) in men.ConclusionImage quality with DLIR was high-qualified without affecting the accuracy of BMD measurement. It has a potential clinical utility in osteoporosis screening.

Project description:For image-guided small animal irradiations, the whole workflow of imaging, organ contouring, irradiation planning, and delivery is typically performed in a single session requiring continuous administration of anaesthetic agents. Automating contouring leads to a faster workflow, which limits exposure to anaesthesia and thereby, reducing its impact on experimental results and on animal wellbeing. Here, we trained the 2D and 3D U-Net architectures of no-new-Net (nnU-Net) for autocontouring of the thorax in mouse micro-CT images. We trained the models only on native CTs and evaluated their performance using an independent testing dataset (i.e., native CTs not included in the training and validation). Unlike previous studies, we also tested the model performance on an external dataset (i.e., contrast-enhanced CTs) to see how well they predict on CTs completely different from what they were trained on. We also assessed the interobserver variability using the generalized conformity index ([Formula: see text]) among three observers, providing a stronger human baseline for evaluating automated contours than previous studies. Lastly, we showed the benefit on the contouring time compared to manual contouring. The results show that 3D models of nnU-Net achieve superior segmentation accuracy and are more robust to unseen data than 2D models. For all target organs, the mean surface distance (MSD) and the Hausdorff distance (95p HD) of the best performing model for this task (nnU-Net 3d_fullres) are within 0.16 mm and 0.60 mm, respectively. These values are below the minimum required contouring accuracy of 1 mm for small animal irradiations, and improve significantly upon state-of-the-art 2D U-Net-based AIMOS method. Moreover, the conformity indices of the 3d_fullres model also compare favourably to the interobserver variability for all target organs, whereas the 2D models perform poorly in this regard. Importantly, the 3d_fullres model offers 98% reduction in contouring time.

Dataset Information

Grayscale image statistics of COVID-19 patient CT scans characterize lung condition with machine and deep learning.

Background

Method

Results

Conclusion

Publications

Grayscale image statistics of COVID-19 patient CT scans characterize lung condition with machine and deep learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets