1
|
Antar S, Abd El-Sattar HKH, Abdel-Rahman MH, F M Ghaleb F. COVID-19 infection segmentation using hybrid deep learning and image processing techniques. Sci Rep 2023; 13:22737. [PMID: 38123587 PMCID: PMC10733411 DOI: 10.1038/s41598-023-49337-1] [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: 05/20/2023] [Accepted: 12/07/2023] [Indexed: 12/23/2023] Open
Abstract
The coronavirus disease 2019 (COVID-19) epidemic has become a worldwide problem that continues to affect people's lives daily, and the early diagnosis of COVID-19 has a critical importance on the treatment of infected patients for medical and healthcare organizations. To detect COVID-19 infections, medical imaging techniques, including computed tomography (CT) scan images and X-ray images, are considered some of the helpful medical tests that healthcare providers carry out. However, in addition to the difficulty of segmenting contaminated areas from CT scan images, these approaches also offer limited accuracy for identifying the virus. Accordingly, this paper addresses the effectiveness of using deep learning (DL) and image processing techniques, which serve to expand the dataset without the need for any augmentation strategies, and it also presents a novel approach for detecting COVID-19 virus infections in lung images, particularly the infection prediction issue. In our proposed method, to reveal the infection, the input images are first preprocessed using a threshold then resized to 128 × 128. After that, a density heat map tool is used for coloring the resized lung images. The three channels (red, green, and blue) are then separated from the colored image and are further preprocessed through image inverse and histogram equalization, and are subsequently fed, in independent directions, into three separate U-Nets with the same architecture for segmentation. Finally, the segmentation results are combined and run through a convolution layer one by one to get the detection. Several evaluation metrics using the CT scan dataset were used to measure the performance of the proposed approach in comparison with other state-of-the-art techniques in terms of accuracy, sensitivity, precision, and the dice coefficient. The experimental results of the proposed approach reached 99.71%, 0.83, 0.87, and 0.85, respectively. These results show that coloring the CT scan images dataset and then dividing each image into its RGB image channels can enhance the COVID-19 detection, and it also increases the U-Net power in the segmentation when merging the channel segmentation results. In comparison to other existing segmentation techniques employing bigger 512 × 512 images, this study is one of the few that can rapidly and correctly detect the COVID-19 virus with high accuracy on smaller 128 × 128 images using the metrics of accuracy, sensitivity, precision, and dice coefficient.
Collapse
Affiliation(s)
- Samar Antar
- Computer Science Division, Department of Mathematics, Faculty of Science, Ain Shams University, Abbassia, Cairo, 11566, Egypt
| | | | - Mohammad H Abdel-Rahman
- Computer Science Division, Department of Mathematics, Faculty of Science, Ain Shams University, Abbassia, Cairo, 11566, Egypt
| | - Fayed F M Ghaleb
- Computer Science Division, Department of Mathematics, Faculty of Science, Ain Shams University, Abbassia, Cairo, 11566, Egypt
| |
Collapse
|
2
|
Zhang YF, Gao SS, Li JL, Zuo WS, Qiu YW, Xiao YC. Comparison and correlation study of synovial ultrasound indices and serum VEGF in rheumatoid wrist arthritis before and after treatment. Clin Rheumatol 2022; 41:2677-2683. [PMID: 35622172 DOI: 10.1007/s10067-022-06213-z] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/15/2022] [Revised: 04/26/2022] [Accepted: 05/14/2022] [Indexed: 11/03/2022]
Abstract
OBJECTIVE Rheumatoid wrist arthritis is a chronic autoimmune disease, resulting in joint deformity and functional impairment. We aimed to compare the wrist synovial ultrasound indices and serum vascular endothelial growth factor (VEGF) level in patients with RA before and after treatment, and to explore the correlation between the two. METHODS Forty patients with RA in wrist underwent ultrasound examination to determine wrist synovial thickness, synovial blood flow grade, and synovial artery resistive index (RI) before and after treatment. The serum level of VEGF was detected by enzyme-linked immunosorbent assay. Correlation between synovial ultrasound indices and serum VEGF level was assessed. RESULTS Pre-treatment synovial thickness, synovial artery RI, and serum VEGF level were 8.60 ± 2.82 mm, 0.62 ± 0.07, and 419.49 ± 19.27 pg/mL, respectively. The corresponding post-treatment levels were 4.05 ± 1.89 mm, 0.83 ± 0.10, and 199.30 ± 16.18 pg/mL. Pre-treatment distribution of synovial blood flow grades was as follows: grade 0, nil; grade I, 1 case; grade II, 17 cases; grade III, 22 cases. The post-treatment distribution was as follows: grade 0, 6 cases; grade I, 23 cases; grade II, 11 cases; and grade III, nil. There were significant differences between pre- and post-treatment wrist synovial thickness, artery RI, and blood flow grading. Wrist synovial thickness and synovial blood flow grade showed a strong positive correlation with serum VEGF level (P < 0.01). There was strong negative correlation between wrist synovial artery RI and serum VEGF level (P < 0.01). CONCLUSION The strong correlation between wrist synovial ultrasound indicators and serum VEGF may be clinically useful for diagnosis and therapy.
Collapse
Affiliation(s)
- Yan-Fen Zhang
- Department of Ultrasound Diagnostics, The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China, Yuhua District, No. 161 Shaoshan South Road, Changsha, 410004, China
| | - Shan-Shan Gao
- Department of Ultrasound, Zibo Infectious Disease Hospital (The Fourth People's Hospital of Zibo City), Zibo, China
| | - Jia-Li Li
- Department of Rheumatology and Immunology, University of South China Affiliated Changsha Central Hospital, 161 South Shaoshan Road, Changsha, 410008, Hunan, China
| | - Wen-Si Zuo
- Department of Ultrasound Diagnostics, The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China, Yuhua District, No. 161 Shaoshan South Road, Changsha, 410004, China
| | - Yue-Wen Qiu
- Department of Ultrasound Diagnostics, The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China, Yuhua District, No. 161 Shaoshan South Road, Changsha, 410004, China
| | - Yao-Cheng Xiao
- Department of Ultrasound Diagnostics, The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China, Yuhua District, No. 161 Shaoshan South Road, Changsha, 410004, China.
| |
Collapse
|
3
|
Afifi N, M Medhat B, Abdel Ghani AM, Mohamed Ali Hassan HGE, Behiry ME. Value of Albumin-Fibrinogen Ratio and CRP-Albumin Ratio as Predictor Marker of Disease Activity in Egyptian RA Patients, Correlated with Musculoskeletal Sonography. Open Access Rheumatol 2020; 12:241-248. [PMID: 33173359 PMCID: PMC7646446 DOI: 10.2147/oarrr.s268668] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/20/2020] [Accepted: 09/25/2020] [Indexed: 01/04/2023] Open
Abstract
Purpose To evaluate the albumin-fibrinogen ratio (AFR) and C-reactive protein-albumin ratio (CAR) as inflammatory markers in rheumatoid arthritis (RA) and to investigate their association with disease activity correlating with musculoskeletal ultrasonographic findings. Patients and Methods A total of 125 cases of RA patients were consecutively enrolled in a multicenter cross-sectional study compared to 100 healthy controls, all subjects were investigated for fibrinogen, albumin, CRP, erythrocyte sedimentation rate, AFR, and CAR measurements. Patients' disease activity was assessed by disease activity score (DAS28-ESR), and they were subjected to high-frequency ultrasound both in greyscale and power Doppler. Results RA patients had lower AFR and higher CAR than those in the control group (P < 0.001). A positive correlation was demonstrated between CAR and DAS score (r=0.589, P = 0.0001), whilst there was a precise negative correlation between AFR and DAS 28-ESR (r=-0.74, p<0.001). ROC curve analyses revealed fibrinogen showed the best sensitivity (92.1%) for the area under the curve of 0.928, at a criterion of 2.47, while AFR has an area under the curve of 0.826 with sensitivity and specificity (86.84% and 75%, respectively) at cut-off value 1.46. Actively diseased patients had elevated CAR than those in remission (P < 0.001). Patients with synovial thickening and bone erosions had lower AFR than those without, CAR was higher in patients with power doppler changes than those without (p=0.015). Conclusion Higher CAR and lower AFR were expressed in active RA than those in remission. CAR and AFR could be useful markers of ongoing inflammation and joint affection detected by musculoskeletal ultrasonography.
Collapse
Affiliation(s)
- Naglaa Afifi
- Internal Medicine and Rheumatology, Faculty of Medicine, Ain Shams University, Cairo, Egypt.,Internal Medicine, Armed Forces College of Medicine (AFCM), Cairo, Egypt
| | - Basma M Medhat
- Rheumatology and Rehabilitation, Faculty of Medicine, Cairo University, Cairo, Egypt
| | | | | | - Mervat E Behiry
- Internal Medicine, Armed Forces College of Medicine (AFCM), Cairo, Egypt.,Internal Medicine, and Rheumatology, Faculty of Medicine, Cairo University, Cairo, Egypt
| |
Collapse
|
4
|
Fazekas ML, Sugimoto D, Cianci A, Minor JL, Corrado GD, d'Hemecourt PA. Ultrasound examination and patellar tendinopathy scores in asymptomatic college jumpers. PHYSICIAN SPORTSMED 2018; 46:477-484. [PMID: 30122090 DOI: 10.1080/00913847.2018.1513756] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/08/2023]
Abstract
OBJECTIVE To investigate the prevalence of hypoechoic areas by US and its' association with VISA-P scores among asymptomatic jumpers while highlighting sex comparisons. DESIGN Cross-sectional study. SETTING Pre-participation exam at a National Collegiate Athletic Association (NCAA) division I college. PARTICIPANTS Thirty-one college athletes who engage in jumping sports. MAIN OUTCOME MEASURES Hypoechoic images of patellar tendon captured by ultrasound examination were compared to a self-reported knee functional survey, the Victorian Institute of Sport Assessment for patellar tendinopathy (VISA-P) scale (0-100). RESULTS With a total of 31 athletes (13 males and 18 females), prevalence rate of the hypoechoic areas of patellar tendon was 19.4% (6/31) in the right knee and 29.0% (9/31) in the left knee. There was no proportional difference in a comparison of prevalence rate of hypoechoic area [(+) or (-)] by sex in either right or left knee. The VISA-P scores were significantly lower in US (+) than US (-) in the right knee (p = 0.003, Cohen's d = 1.675), but not the left knee (p = 0.250, Cohen's d = 0.512). The receiver operating characteristics curve analysis indicated the most sensitive and specific VISA-P values based on status [(+) or (-)] of hypoechoic area was 89.5 with 86.4% and 77.7% of sensitivity and specificity. CONCLUSION In short, hypoechoic areas were detected by US examination among self-reported asymptomatic jumpers. There was an association between hypoechoic areas and VISA-P scores in the right knee, but not in left knee. VISA-P scores may be used as a screening tool for the presence of hypoechoic areas.
Collapse
Affiliation(s)
- Matthew L Fazekas
- a Department of Orthopaedic Surgery , Joe DiMaggio Children's Hospital , Hollywood , FL , USA
| | - Dai Sugimoto
- b The Micheli Center for Sports Injury Prevention , Waltham , MA , USA.,c Division of Sports Medicine, Department of Orthopaedics , Boston Children's Hospital , Boston , MA , USA.,d Department of Orthopaedic Surgery , Harvard Medical School , Boston , MA , USA
| | - Andrea Cianci
- c Division of Sports Medicine, Department of Orthopaedics , Boston Children's Hospital , Boston , MA , USA
| | - Jonathan L Minor
- e Sports Medicine, Rehabilitation, and Concussion Center , Tucson , AZ , USA
| | - Gianmichel D Corrado
- b The Micheli Center for Sports Injury Prevention , Waltham , MA , USA.,c Division of Sports Medicine, Department of Orthopaedics , Boston Children's Hospital , Boston , MA , USA.,d Department of Orthopaedic Surgery , Harvard Medical School , Boston , MA , USA
| | - Pierre A d'Hemecourt
- b The Micheli Center for Sports Injury Prevention , Waltham , MA , USA.,c Division of Sports Medicine, Department of Orthopaedics , Boston Children's Hospital , Boston , MA , USA.,d Department of Orthopaedic Surgery , Harvard Medical School , Boston , MA , USA
| |
Collapse
|