China
Africa
Explore chapters and articles related to this topic
Computer Analysis of Computer Tomography Images for Lung Nodule Detection
Published in Paolo Russo, Handbook of X-ray Imaging, 2017
Maria Evelina Fantacci, Alessandra Retico
Lung nodules can also be distinguished according to their CT contrast into solid and part-solid or ground-glass nodules (ground-glass opacities, GGOs). As lung nodules may differ either in shape or intensity, a CAD developer should characterize them by a large variety of features that the algorithms can interpret. Regardless of the type of nodule a CAD algorithm is optimized for, it can generally be schematized in three steps, as described in Figure 62.2: first the lung CT volume undergoes a preprocessing step, including filtering and resampling algorithms if necessary and, in many cases, the lung parenchyma segmentation (i.e., the identification of the lung tissue with respect to the surrounding different anatomical structures); then, the initial selection of nodule candidates is performed; finally, as many false-positive findings as possible are eliminated from the list of nodule candidates. Each step of this basic scheme is discussed in detail in the following sections.
A mask-guided attention deep learning model for COVID-19 diagnosis based on an integrated CT scan images database
Published in IISE Transactions on Healthcare Systems Engineering, 2023
Maede Maftouni, Bo Shen, Andrew Chung Chee Law, Niloofar Ayoobi Yazdi, Fahimeh Hadavand, Fereshte Ghiasvand, Zhenyu (James) Kong
Figure 4 depicts multiple statistics from the dataset. The country and gender distributions on the entire dataset are shown in the subfigures (a–b). Figure 4(a) indicates that the cases come from 13 countries, with Iran, Russia, and China ranking first through third. According to Figure 4(b) most of the cases are male, and this male dominance holds for all Normal, COVID-19, and Cap classes. Figure 4(c) compares the age distribution of the three classes and shows that all the age groups are represented in the dataset. The median age of Normal, COVID-19, and CAP classes are 50, 49, and 59, respectively. Figure 4(d) compares the prevalence of distinctive CT characteristics in the 796 COVID-19 cases with CT scan reports, highlighting that ground-glass opacities, bilateral involvements, and consolidation have frequently been reported. And patterns attributed to higher severity, such as diffuse distribution Lei et al. (2021), are also present. These statistics indicate that the dataset population is broad and representative, having cases from various ages, gender, nationality, and severity groups.
A feature-based affine registration method for capturing background lung tissue deformation for ground glass nodule tracking
Published in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2022
Yehuda K. Ben-Zikri, María Helguera, David Fetzer, David A. Shrier, Stephen. R. Aylward, Deepak Chittajallu, Marc Niethammer, Nathan D. Cahill, Cristian A. Linte
Thin-slice helical chest CT images are used as standard-of-care to identify pulmonary nodules Henschke et al. (1999) and classify them as either part-solid (also known as sub-solid) or solid nodules Hansell et al. (2008). When smaller than 1 cm in diameter, these nodules are typically classified as incidental, benign findings, and only require follow-up CT imaging Fischbach et al. (2003). Part-solid nodules, on the other hand, feature a ‘ground-glass appearance’ – hence they are commonly referred to as ground-glass opacities (GGOs) nodules or ground-glass nodules (GGNs) – and are characterised by hazy, increased lung tissue opacities that don’t completely obscure pulmonary structures; in contrast, pure GGNs only feature ground-glass appearance, with no solid components. Unlike GGNs, solid nodules appear as focal homogeneous regions that completely obscure other different lung structures.
GIL-CNN: A Novel Multipath Features for COVID-19 Detection Using CT-Scan Images
Published in IETE Journal of Research, 2022
N. Jagan Mohan, D. N. Kiran Pandiri
Globally, the COVID-19 cases [1] reached 40 million, of which5.7 million were dead by 11th February 2022, and the count is increasing continuously. The early diagnosis of COVID-19 is necessary to avoid reaching the patient's final phase of the virus. The traditional testing method relies on reverse transcription-polymerase chain reaction (RT–PCR), which is time-consuming, requires re-iteration, and has a high proportion of false-negative findings. Diagnosing the CT scan of the respiratory tract of the infected and suspected persons plays a vital role in better managing the health condition. Variations in CT scans such as ground-glass opacities and pulmonary consolidation are essential indicators for COVID-19 diagnosis. They can aid in rapidly identifying suspected cases, saving time, and allowing the patient to be isolated more quickly.