1
|
Zhang Z, Li G, Wang Z, Xia F, Zhao N, Nie H, Ye Z, Lin JS, Hui Y, Liu X. Deep-learning segmentation to select liver parenchyma for categorizing hepatic steatosis on multinational chest CT. Sci Rep 2024; 14:11987. [PMID: 38796521 PMCID: PMC11127985 DOI: 10.1038/s41598-024-62887-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2023] [Accepted: 05/22/2024] [Indexed: 05/28/2024] Open
Abstract
Unenhanced CT scans exhibit high specificity in detecting moderate-to-severe hepatic steatosis. Even though many CTs are scanned from health screening and various diagnostic contexts, their potential for hepatic steatosis detection has largely remained unexplored. The accuracy of previous methodologies has been limited by the inclusion of non-parenchymal liver regions. To overcome this limitation, we present a novel deep-learning (DL) based method tailored for the automatic selection of parenchymal portions in CT images. This innovative method automatically delineates circular regions for effectively detecting hepatic steatosis. We use 1,014 multinational CT images to develop a DL model for segmenting liver and selecting the parenchymal regions. The results demonstrate outstanding performance in both tasks. By excluding non-parenchymal portions, our DL-based method surpasses previous limitations, achieving radiologist-level accuracy in liver attenuation measurements and hepatic steatosis detection. To ensure the reproducibility, we have openly shared 1014 annotated CT images and the DL system codes. Our novel research contributes to the refinement the automated detection methodologies of hepatic steatosis on CT images, enhancing the accuracy and efficiency of healthcare screening processes.
Collapse
Affiliation(s)
- Zhongyi Zhang
- Department of Nephrology, Multidisciplinary Innovation Center for Nephrology, The Second Hospital of Shandong University, Shandong University, Jinan, 250033, Shandong, China
| | - Guixia Li
- Department of Nephrology, Shenzhen Third People's Hospital, the Second Affiliated Hospital of Southern University of Science and Technology, Shenzhen, 518112, Guangdong, China
| | - Ziqiang Wang
- Department of Nephrology, The First Affiliated Hospital of Hainan Medical University, Haikou, 570102, Hainan, China
| | - Feng Xia
- Department of Cardiovascular Surgery, Wuhan Asia General Hospital, Wuhan, 430000, Hubei, China
| | - Ning Zhao
- The First Clinical Medical School, Shanxi Medical University, Taiyuan, 030001, Shanxi, China
| | - Huibin Nie
- Department of Nephrology, Chengdu First People's Hospital, Chengdu, 610021, Sichuan, China
| | - Zezhong Ye
- Independent Researcher, Boston, MA, 02115, USA
| | - Joshua S Lin
- Keck School of Medicine, University of Southern California, Los Angeles, CA, 90033, USA
| | - Yiyi Hui
- Department of Medical Imaging, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, 250021, Shandong, China.
| | - Xiangchun Liu
- Department of Nephrology, Multidisciplinary Innovation Center for Nephrology, The Second Hospital of Shandong University, Shandong University, Jinan, 250033, Shandong, China.
| |
Collapse
|
2
|
Ramdani H, Benelhosni K, Billah NM, Nassar I. Chest CT in covid-19 pneumonia's follow-up: A 30 patients case series. Ann Med Surg (Lond) 2022; 84:104835. [PMID: 36373105 PMCID: PMC9637543 DOI: 10.1016/j.amsu.2022.104835] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/07/2022] [Revised: 09/29/2022] [Accepted: 10/30/2022] [Indexed: 11/09/2022] Open
Abstract
Background Lung abnormalities do not fully resolve in all Covid-19 survivors and may progress to fibrosis. Understanding post-COVID lung changes helps identify patients susceptible of post-COVID-19 sequelae. We analyzed scannographic residual lung abnormalities and the full resolution percentage on intermediate- and long-term follow-up (3 months or more). Methods Data from 30 RT-PCR positive COVID-19 patients undergoing at least one follow-up chest CT at Ibn Sina Hospital, with a minimal time interval of 3 months between the RT-PCR and the CT performance were gathered retrospectively. The following elements were analyzed: (1) lung opacities, (2) distribution, (3) dominant lung opacity, (4) Sub-pleural bands, (5) Interlobular septal thickening, (6) Vascular dilatation, (7) Bronchiectasis, (8) Honey combing, (9) Architectural distortion, (10) mosaic attenuation, and (11) Additional findings: Enlarged lymph nodes, Pleural and Pericardial fluid. To evaluate the degree of lung opacification, a score founded on visual evaluation of the lung involvement's percentage was employed. Patients were then subdivided into two categories: (1) no residual opacities and (2) remaining pulmonary opacities. Outcomes 30 patients were enrolled. The age ranged between 40 and 87 years. CT was indicated for symptoms or functional impairment. The time range between the positive RT-PCR and Follow-up CT varied between 3 and 12 months. CT severity score ranged between o and 23. Residual lung opacities were present in 24 cases (80%). The dominant lung opacities were Ground glass (46.7%), and linear/curvilinear opacities (23.3%). Signs of fibrosis were present in 9 patients (30%). Conclusion CT abnormalities following Covid-19 pneumonia's prevalence varies based on the extent of the original lung affection and the time gap since the acute phase. Residual anomalies' effects on respiratory physiology, symptoms, and quality of living are unknown. Maintained monitoring of COVID-19 survivors with clinical examination, iterative pulmonary function tests, and HRCT is advised.
Collapse
|
3
|
Bao G, Chen H, Liu T, Gong G, Yin Y, Wang L, Wang X. COVID-MTL: Multitask learning with Shift3D and random-weighted loss for COVID-19 diagnosis and severity assessment. PATTERN RECOGNITION 2022; 124:108499. [PMID: 34924632 PMCID: PMC8666107 DOI: 10.1016/j.patcog.2021.108499] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/31/2020] [Revised: 11/11/2021] [Accepted: 12/10/2021] [Indexed: 05/07/2023]
Abstract
There is an urgent need for automated methods to assist accurate and effective assessment of COVID-19. Radiology and nucleic acid test (NAT) are complementary COVID-19 diagnosis methods. In this paper, we present an end-to-end multitask learning (MTL) framework (COVID-MTL) that is capable of automated and simultaneous detection (against both radiology and NAT) and severity assessment of COVID-19. COVID-MTL learns different COVID-19 tasks in parallel through our novel random-weighted loss function, which assigns learning weights under Dirichlet distribution to prevent task dominance; our new 3D real-time augmentation algorithm (Shift3D) introduces space variances for 3D CNN components by shifting low-level feature representations of volumetric inputs in three dimensions; thereby, the MTL framework is able to accelerate convergence and improve joint learning performance compared to single-task models. By only using chest CT scans, COVID-MTL was trained on 930 CT scans and tested on separate 399 cases. COVID-MTL achieved AUCs of 0.939 and 0.846, and accuracies of 90.23% and 79.20% for detection of COVID-19 against radiology and NAT, respectively, which outperformed the state-of-the-art models. Meanwhile, COVID-MTL yielded AUC of 0.800 ± 0.020 and 0.813 ± 0.021 (with transfer learning) for classifying control/suspected, mild/regular, and severe/critically-ill cases. To decipher the recognition mechanism, we also identified high-throughput lung features that were significantly related (P < 0.001) to the positivity and severity of COVID-19.
Collapse
Affiliation(s)
- Guoqing Bao
- School of Computer Science, The University of Sydney, J12/1 Cleveland St, Darlington, Sydney, NSW 2008, Australia
| | - Huai Chen
- Department of Automation, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai 200240, China
| | - Tongliang Liu
- School of Computer Science, The University of Sydney, J12/1 Cleveland St, Darlington, Sydney, NSW 2008, Australia
| | - Guanzhong Gong
- Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan 250117, China
| | - Yong Yin
- Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan 250117, China
| | - Lisheng Wang
- Department of Automation, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai 200240, China
| | - Xiuying Wang
- School of Computer Science, The University of Sydney, J12/1 Cleveland St, Darlington, Sydney, NSW 2008, Australia
| |
Collapse
|
4
|
Moses ME, Hofmeyr S, Cannon JL, Andrews A, Gridley R, Hinga M, Leyba K, Pribisova A, Surjadidjaja V, Tasnim H, Forrest S. Spatially distributed infection increases viral load in a computational model of SARS-CoV-2 lung infection. PLoS Comput Biol 2021; 17:e1009735. [PMID: 34941862 PMCID: PMC8740970 DOI: 10.1371/journal.pcbi.1009735] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/24/2021] [Revised: 01/07/2022] [Accepted: 12/09/2021] [Indexed: 01/03/2023] Open
Abstract
A key question in SARS-CoV-2 infection is why viral loads and patient outcomes vary dramatically across individuals. Because spatial-temporal dynamics of viral spread and immune response are challenging to study in vivo, we developed Spatial Immune Model of Coronavirus (SIMCoV), a scalable computational model that simulates hundreds of millions of lung cells, including respiratory epithelial cells and T cells. SIMCoV replicates viral growth dynamics observed in patients and shows how spatially dispersed infections can lead to increased viral loads. The model also shows how the timing and strength of the T cell response can affect viral persistence, oscillations, and control. By incorporating spatial interactions, SIMCoV provides a parsimonious explanation for the dramatically different viral load trajectories among patients by varying only the number of initial sites of infection and the magnitude and timing of the T cell immune response. When the branching airway structure of the lung is explicitly represented, we find that virus spreads faster than in a 2D layer of epithelial cells, but much more slowly than in an undifferentiated 3D grid or in a well-mixed differential equation model. These results illustrate how realistic, spatially explicit computational models can improve understanding of within-host dynamics of SARS-CoV-2 infection.
Collapse
Affiliation(s)
- Melanie E. Moses
- Department of Computer Science, University of New Mexico, Albuquerque, New Mexico, United States of America
- Santa Fe Institute, Santa Fe, New Mexico, United States of America
| | - Steven Hofmeyr
- Lawrence Berkeley National Laboratory, Berkeley, California, United States of America
| | - Judy L. Cannon
- Department of Molecular Genetics and Microbiology, University of New Mexico School of Medicine, Albuquerque, New Mexico, United States of America
| | - Akil Andrews
- Department of Computer Science, University of New Mexico, Albuquerque, New Mexico, United States of America
| | - Rebekah Gridley
- Department of Molecular Genetics and Microbiology, University of New Mexico School of Medicine, Albuquerque, New Mexico, United States of America
| | - Monica Hinga
- Department of Computer Science, University of New Mexico, Albuquerque, New Mexico, United States of America
| | - Kirtus Leyba
- Biodesign Institute, Arizona State University, Tempe, Arizona, United States of America
| | - Abigail Pribisova
- Department of Computer Science, University of New Mexico, Albuquerque, New Mexico, United States of America
| | - Vanessa Surjadidjaja
- Department of Computer Science, University of New Mexico, Albuquerque, New Mexico, United States of America
| | - Humayra Tasnim
- Department of Computer Science, University of New Mexico, Albuquerque, New Mexico, United States of America
| | - Stephanie Forrest
- Santa Fe Institute, Santa Fe, New Mexico, United States of America
- Biodesign Institute, Arizona State University, Tempe, Arizona, United States of America
| |
Collapse
|
5
|
Abstract
The acute course of COVID-19 is variable and ranges from asymptomatic infection to fulminant respiratory failure. Patients recovering from COVID-19 can have persistent symptoms and CT abnormalities of variable severity. At 3 months after acute infection, a subset of patients will have CT abnormalities that include ground-glass opacity (GGO) and subpleural bands with concomitant pulmonary function abnormalities. At 6 months after acute infection, some patients have persistent CT changes to include the resolution of GGOs seen in the early recovery phase and the persistence or development of changes suggestive of fibrosis, such as reticulation with or without parenchymal distortion. The etiology of lung disease after COVID-19 may be a sequela of prolonged mechanical ventilation, COVID-19-induced acute respiratory distress syndrome (ARDS), or direct injury from the virus. Predictors of lung disease after COVID-19 include need for intensive care unit admission, mechanical ventilation, higher inflammatory markers, longer hospital stay, and a diagnosis of ARDS. Treatments of lung disease after COVID-19 are being investigated, including the potential of antifibrotic agents for prevention of lung fibrosis after COVID-19. Future research is needed to determine the long-term persistence of lung disease after COVID-19, its impact on patients, and methods to either prevent or treat it. © RSNA, 2021.
Collapse
Affiliation(s)
| | - Brooke Heyman
- Division of Pulmonary, Sleep and Critical Care Medicine, Department
of Medicine, NYU Langone Health, NYU Grossman School of Medicine, New York,
NY
| | - Jane P. Ko
- Department of Radiology, NYU Langone Health, NYU Grossman School of
Medicine, New York, NY
| | - Rany Condos
- Division of Pulmonary, Sleep and Critical Care Medicine, Department
of Medicine, NYU Langone Health, NYU Grossman School of Medicine, New York,
NY
| | - David A. Lynch
- Department of Radiology, National Jewish Health, Denver, CO,
USA
| |
Collapse
|