1
|
Hemalakshmi GR, Murugappan M, Sikkandar MY, Santhi D, Prakash NB, Mohanarathinam A. PE-Ynet: a novel attention-based multi-task model for pulmonary embolism detection using CT pulmonary angiography (CTPA) scan images. Phys Eng Sci Med 2024; 47:863-880. [PMID: 38546819 DOI: 10.1007/s13246-024-01410-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2023] [Accepted: 02/19/2024] [Indexed: 09/18/2024]
Abstract
Pulmonary Embolism (PE) has diverse manifestations with different etiologies such as venous thromboembolism, septic embolism, and paradoxical embolism. In this study, a novel attention-based multi-task model is proposed for PE segmentation and detection from Computed Tomography Pulmonary Angiography (CTPA) images. A Y-Net architecture is used to implement this model, which facilitates segmentation and classification jointly, improving performance and efficiency. It is leveraged with Multi Head Attention (MHA), which allows the model to focus on important regions of the image while suppressing irrelevant information, improving the accuracy of the segmentation and detection tasks. The proposed PE-YNet model is tested with two public datasets, achieving a maximum mean detection and segmentation accuracy of 99.89% and 99.83%, respectively, on the CAD-PE challenge dataset. Similarly, it also achieves a detection accuracy of 99.75% and a segmentation accuracy of 99.81% on the FUMPE dataset. Additionally, sensitivity analysis also shows a high sensitivity of 0.9885 for the localization error ɛ = 0 for the CAD-PE dataset, demonstrating the model's robustness against false predictions compared to state-of-the-art models. Further, this model also exhibits lower inference time, size, and memory usage compared to representative models. An automated PE-YNet tool can assist physicians with PE diagnosis, treatment, and prognosis monitoring in the clinical management of CoVID-19.
Collapse
Affiliation(s)
- G R Hemalakshmi
- School of Computing Science and Engineering, Vellore Institute of Technology, Bhopal, Madhya Pradesh, India
| | - M Murugappan
- Intelligent Signal Processing (ISP) Research Lab, Department of Electronics and Communication Engineering, Kuwait College of Science and Technology, Block 4, 13133, Doha, Kuwait.
- Department of Electronics and Communication Engineering, School of Engineering, Vels Institute of Sciences, Technology, and Advanced Studies, Chennai, Tamil Nadu, India.
- Center of Excellence for Unmanned Aerial Systems (CoEUAS), Universiti Malaysia Perlis, 02600, Arau, Perlis, Malaysia.
| | - Mohamed Yacin Sikkandar
- Biomedical Equipment Technology, College of Applied Medical Sciences, Majmaah University, Al Majma'ah, Saudi Arabia
| | - D Santhi
- Department of Biomedical Engineering, Mepco Schlenk Engineering College, Sivakasi, India
| | - N B Prakash
- Department of Electrical and Electronics Engineering, National Engineering College, Kovilpatti, India
| | - A Mohanarathinam
- Department of Electronics and Communication Engineering, Karpagam Academy of Higher Education, Coimbatore, Tamil Nadu, 641021, India
| |
Collapse
|
2
|
Newson KS, Benoit DM, Beavis AW. Encoder-decoder convolutional neural network for simple CT segmentation of COVID-19 infected lungs. PeerJ Comput Sci 2024; 10:e2178. [PMID: 39145207 PMCID: PMC11323195 DOI: 10.7717/peerj-cs.2178] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/06/2023] [Accepted: 06/17/2024] [Indexed: 08/16/2024]
Abstract
This work presents the application of an Encoder-Decoder convolutional neural network (ED-CNN) model to automatically segment COVID-19 computerised tomography (CT) data. By doing so we are producing an alternative model to current literature, which is easy to follow and reproduce, making it more accessible for real-world applications as little training would be required to use this. Our simple approach achieves results comparable to those of previously published studies, which use more complex deep-learning networks. We demonstrate a high-quality automated segmentation prediction of thoracic CT scans that correctly delineates the infected regions of the lungs. This segmentation automation can be used as a tool to speed up the contouring process, either to check manual contouring in place of a peer checking, when not possible or to give a rapid indication of infection to be referred for further treatment, thus saving time and resources. In contrast, manual contouring is a time-consuming process in which a professional would contour each patient one by one to be later checked by another professional. The proposed model uses approximately 49 k parameters while others average over 1,000 times more parameters. As our approach relies on a very compact model, shorter training times are observed, which make it possible to easily retrain the model using other data and potentially afford "personalised medicine" workflows. The model achieves similarity scores of Specificity (Sp) = 0.996 ± 0.001, Accuracy (Acc) = 0.994 ± 0.002 and Mean absolute error (MAE) = 0.0075 ± 0.0005.
Collapse
Affiliation(s)
- Kiri S. Newson
- Department of Physics and Mathematics, University of Hull, Hull, United Kingdom
| | - David M. Benoit
- E. A. Milne Centre for Astrophysics, Department of Physics and Mathematics, University of Hull, Hull, United Kingdom
| | - Andrew W. Beavis
- Medical Physics Department, Queen’s Centre for Oncology, Hull University Teaching Hospitals NHS Trust, Cottingham, Hull, United Kingdom
- Medical Physics and Biomedical Engineering, University College London, University of London, London, United Kingdom
- Hull York Medical School, University of Hull, Hull, United Kingdom
| |
Collapse
|
3
|
Buongiorno R, Del Corso G, Germanese D, Colligiani L, Python L, Romei C, Colantonio S. Enhancing COVID-19 CT Image Segmentation: A Comparative Study of Attention and Recurrence in UNet Models. J Imaging 2023; 9:283. [PMID: 38132701 PMCID: PMC10744014 DOI: 10.3390/jimaging9120283] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/17/2023] [Revised: 12/09/2023] [Accepted: 12/13/2023] [Indexed: 12/23/2023] Open
Abstract
Imaging plays a key role in the clinical management of Coronavirus disease 2019 (COVID-19) as the imaging findings reflect the pathological process in the lungs. The visual analysis of High-Resolution Computed Tomography of the chest allows for the differentiation of parenchymal abnormalities of COVID-19, which are crucial to be detected and quantified in order to obtain an accurate disease stratification and prognosis. However, visual assessment and quantification represent a time-consuming task for radiologists. In this regard, tools for semi-automatic segmentation, such as those based on Convolutional Neural Networks, can facilitate the detection of pathological lesions by delineating their contour. In this work, we compared four state-of-the-art Convolutional Neural Networks based on the encoder-decoder paradigm for the binary segmentation of COVID-19 infections after training and testing them on 90 HRCT volumetric scans of patients diagnosed with COVID-19 collected from the database of the Pisa University Hospital. More precisely, we started from a basic model, the well-known UNet, then we added an attention mechanism to obtain an Attention-UNet, and finally we employed a recurrence paradigm to create a Recurrent-Residual UNet (R2-UNet). In the latter case, we also added attention gates to the decoding path of an R2-UNet, thus designing an R2-Attention UNet so as to make the feature representation and accumulation more effective. We compared them to gain understanding of both the cognitive mechanism that can lead a neural model to the best performance for this task and the good compromise between the amount of data, time, and computational resources required. We set up a five-fold cross-validation and assessed the strengths and limitations of these models by evaluating the performances in terms of Dice score, Precision, and Recall defined both on 2D images and on the entire 3D volume. From the results of the analysis, it can be concluded that Attention-UNet outperforms the other models by achieving the best performance of 81.93%, in terms of 2D Dice score, on the test set. Additionally, we conducted statistical analysis to assess the performance differences among the models. Our findings suggest that integrating the recurrence mechanism within the UNet architecture leads to a decline in the model's effectiveness for our particular application.
Collapse
Affiliation(s)
- Rossana Buongiorno
- Institute of Information Science and Technologies, National Research Council of Italy (ISTI-CNR), 56124 Pisa, PI, Italy; (G.D.C.); (S.C.)
| | - Giulio Del Corso
- Institute of Information Science and Technologies, National Research Council of Italy (ISTI-CNR), 56124 Pisa, PI, Italy; (G.D.C.); (S.C.)
| | - Danila Germanese
- Institute of Information Science and Technologies, National Research Council of Italy (ISTI-CNR), 56124 Pisa, PI, Italy; (G.D.C.); (S.C.)
| | - Leonardo Colligiani
- Department of Translational Research, Academic Radiology, University of Pisa, 56124 Pisa, PI, Italy;
| | - Lorenzo Python
- 2nd Radiology Unit, Pisa University Hospital, 56124 Pisa, PI, Italy; (L.P.)
| | - Chiara Romei
- 2nd Radiology Unit, Pisa University Hospital, 56124 Pisa, PI, Italy; (L.P.)
| | - Sara Colantonio
- Institute of Information Science and Technologies, National Research Council of Italy (ISTI-CNR), 56124 Pisa, PI, Italy; (G.D.C.); (S.C.)
| |
Collapse
|
4
|
肖 汉, 李 焕, 冉 智, 张 启, 张 勃, 韦 羽, 祝 秀. [Corona virus disease 2019 lesion segmentation network based on an adaptive joint loss function]. SHENG WU YI XUE GONG CHENG XUE ZA ZHI = JOURNAL OF BIOMEDICAL ENGINEERING = SHENGWU YIXUE GONGCHENGXUE ZAZHI 2023; 40:743-752. [PMID: 37666765 PMCID: PMC10477394 DOI: 10.7507/1001-5515.202206051] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Subscribe] [Scholar Register] [Received: 06/26/2022] [Revised: 05/30/2023] [Indexed: 09/06/2023]
Abstract
Corona virus disease 2019 (COVID-19) is an acute respiratory infectious disease with strong contagiousness, strong variability, and long incubation period. The probability of misdiagnosis and missed diagnosis can be significantly decreased with the use of automatic segmentation of COVID-19 lesions based on computed tomography images, which helps doctors in rapid diagnosis and precise treatment. This paper introduced the level set generalized Dice loss function (LGDL) in conjunction with the level set segmentation method based on COVID-19 lesion segmentation network and proposed a dual-path COVID-19 lesion segmentation network (Dual-SAUNet++) to address the pain points such as the complex symptoms of COVID-19 and the blurred boundaries that are challenging to segment. LGDL is an adaptive weight joint loss obtained by combining the generalized Dice loss of the mask path and the mean square error of the level set path. On the test set, the model achieved Dice similarity coefficient of (87.81 ± 10.86)%, intersection over union of (79.20 ± 14.58)%, sensitivity of (94.18 ± 13.56)%, specificity of (99.83 ± 0.43)% and Hausdorff distance of 18.29 ± 31.48 mm. Studies indicated that Dual-SAUNet++ has a great anti-noise capability and it can segment multi-scale lesions while simultaneously focusing on their area and border information. The method proposed in this paper assists doctors in judging the severity of COVID-19 infection by accurately segmenting the lesion, and provides a reliable basis for subsequent clinical treatment.
Collapse
Affiliation(s)
- 汉光 肖
- 重庆理工大学 两江人工智能学院(重庆 401135)School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401135, P. R. China
| | - 焕琪 李
- 重庆理工大学 两江人工智能学院(重庆 401135)School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401135, P. R. China
| | - 智强 冉
- 重庆理工大学 两江人工智能学院(重庆 401135)School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401135, P. R. China
| | - 启航 张
- 重庆理工大学 两江人工智能学院(重庆 401135)School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401135, P. R. China
| | - 勃龙 张
- 重庆理工大学 两江人工智能学院(重庆 401135)School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401135, P. R. China
| | - 羽佳 韦
- 重庆理工大学 两江人工智能学院(重庆 401135)School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401135, P. R. China
| | - 秀红 祝
- 重庆理工大学 两江人工智能学院(重庆 401135)School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401135, P. R. China
| |
Collapse
|
5
|
Alshomrani S, Arif M, Al Ghamdi MA. SAA-UNet: Spatial Attention and Attention Gate UNet for COVID-19 Pneumonia Segmentation from Computed Tomography. Diagnostics (Basel) 2023; 13:diagnostics13091658. [PMID: 37175049 PMCID: PMC10178408 DOI: 10.3390/diagnostics13091658] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/06/2023] [Revised: 04/12/2023] [Accepted: 04/25/2023] [Indexed: 05/15/2023] Open
Abstract
The disaster of the COVID-19 pandemic has claimed numerous lives and wreaked havoc on the entire world due to its transmissible nature. One of the complications of COVID-19 is pneumonia. Different radiography methods, particularly computed tomography (CT), have shown outstanding performance in effectively diagnosing pneumonia. In this paper, we propose a spatial attention and attention gate UNet model (SAA-UNet) inspired by spatial attention UNet (SA-UNet) and attention UNet (Att-UNet) to deal with the problem of infection segmentation in the lungs. The proposed method was applied to the MedSeg, Radiopaedia 9P, combination of MedSeg and Radiopaedia 9P, and Zenodo 20P datasets. The proposed method showed good infection segmentation results (two classes: infection and background) with an average Dice similarity coefficient of 0.85, 0.94, 0.91, and 0.93 and a mean intersection over union (IOU) of 0.78, 0.90, 0.86, and 0.87, respectively, on the four datasets mentioned above. Moreover, it also performed well in multi-class segmentation with average Dice similarity coefficients of 0.693, 0.89, 0.87, and 0.93 and IOU scores of 0.68, 0.87, 0.78, and 0.89 on the four datasets, respectively. Classification accuracies of more than 97% were achieved for all four datasets. The F1-scores for the MedSeg, Radiopaedia P9, combination of MedSeg and Radiopaedia P9, and Zenodo 20P datasets were 0.865, 0.943, 0.917, and 0.926, respectively, for the binary classification. For multi-class classification, accuracies of more than 96% were achieved on all four datasets. The experimental results showed that the framework proposed can effectively and efficiently segment COVID-19 infection on CT images with different contrast and utilize this to aid in diagnosing and treating pneumonia caused by COVID-19.
Collapse
Affiliation(s)
- Shroog Alshomrani
- Department of Computer Science, Umm Al-Qura University, Makkah 24382, Saudi Arabia
| | - Muhammad Arif
- Department of Computer Science, Umm Al-Qura University, Makkah 24382, Saudi Arabia
| | - Mohammed A Al Ghamdi
- Department of Computer Science, Umm Al-Qura University, Makkah 24382, Saudi Arabia
| |
Collapse
|
6
|
Krinski BA, Ruiz DV, Laroca R, Todt E. DACov: a deeper analysis of data augmentation on the computed tomography segmentation problem. COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING: IMAGING & VISUALIZATION 2023. [DOI: 10.1080/21681163.2023.2183807] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/09/2023]
Affiliation(s)
- Bruno A. Krinski
- Department of Informatics, Federal University of Paraná, Curitiba, Brazil
| | - Daniel V. Ruiz
- Department of Informatics, Federal University of Paraná, Curitiba, Brazil
| | - Rayson Laroca
- Department of Informatics, Federal University of Paraná, Curitiba, Brazil
| | - Eduardo Todt
- Department of Informatics, Federal University of Paraná, Curitiba, Brazil
| |
Collapse
|
7
|
Velu S. An efficient, lightweight MobileNetV2-based fine-tuned model for COVID-19 detection using chest X-ray images. MATHEMATICAL BIOSCIENCES AND ENGINEERING : MBE 2023; 20:8400-8427. [PMID: 37161204 DOI: 10.3934/mbe.2023368] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/11/2023]
Abstract
In recent years, deep learning's identification of cancer, lung disease and heart disease, among others, has contributed to its rising popularity. Deep learning has also contributed to the examination of COVID-19, which is a subject that is currently the focus of considerable scientific debate. COVID-19 detection based on chest X-ray (CXR) images primarily depends on convolutional neural network transfer learning techniques. Moreover, the majority of these methods are evaluated by using CXR data from a single source, which makes them prohibitively expensive. On a variety of datasets, current methods for COVID-19 detection may not perform as well. Moreover, most current approaches focus on COVID-19 detection. This study introduces a rapid and lightweight MobileNetV2-based model for accurate recognition of COVID-19 based on CXR images; this is done by using machine vision algorithms that focused largely on robust and potent feature-learning capabilities. The proposed model is assessed by using a dataset obtained from various sources. In addition to COVID-19, the dataset includes bacterial and viral pneumonia. This model is capable of identifying COVID-19, as well as other lung disorders, including bacterial and viral pneumonia, among others. Experiments with each model were thoroughly analyzed. According to the findings of this investigation, MobileNetv2, with its 92% and 93% training validity and 88% precision, was the most applicable and reliable model for this diagnosis. As a result, one may infer that this study has practical value in terms of giving a reliable reference to the radiologist and theoretical significance in terms of establishing strategies for developing robust features with great presentation ability.
Collapse
Affiliation(s)
- Shubashini Velu
- Department of Management Information System, College of Business, Prince Mohammad Bin Fahd University, 617, Al Jawharah, Khobar, Dhahran, Saudi Arabia
| |
Collapse
|
8
|
Önder M, Evli C, Türk E, Kazan O, Bayrakdar İŞ, Çelik Ö, Costa ALF, Gomes JPP, Ogawa CM, Jagtap R, Orhan K. Deep-Learning-Based Automatic Segmentation of Parotid Gland on Computed Tomography Images. Diagnostics (Basel) 2023; 13:581. [PMID: 36832069 PMCID: PMC9955422 DOI: 10.3390/diagnostics13040581] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/10/2022] [Revised: 01/23/2023] [Accepted: 02/02/2023] [Indexed: 02/08/2023] Open
Abstract
This study aims to develop an algorithm for the automatic segmentation of the parotid gland on CT images of the head and neck using U-Net architecture and to evaluate the model's performance. In this retrospective study, a total of 30 anonymized CT volumes of the head and neck were sliced into 931 axial images of the parotid glands. Ground truth labeling was performed with the CranioCatch Annotation Tool (CranioCatch, Eskisehir, Turkey) by two oral and maxillofacial radiologists. The images were resized to 512 × 512 and split into training (80%), validation (10%), and testing (10%) subgroups. A deep convolutional neural network model was developed using U-net architecture. The automatic segmentation performance was evaluated in terms of the F1-score, precision, sensitivity, and the Area Under Curve (AUC) statistics. The threshold for a successful segmentation was determined by the intersection of over 50% of the pixels with the ground truth. The F1-score, precision, and sensitivity of the AI model in segmenting the parotid glands in the axial CT slices were found to be 1. The AUC value was 0.96. This study has shown that it is possible to use AI models based on deep learning to automatically segment the parotid gland on axial CT images.
Collapse
Affiliation(s)
- Merve Önder
- Department of Dentomaxillofacial Radiology, Faculty of Dentistry, Ankara University, Ankara 06000, Turkey
| | - Cengiz Evli
- Department of Dentomaxillofacial Radiology, Faculty of Dentistry, Ankara University, Ankara 06000, Turkey
| | - Ezgi Türk
- Dentomaxillofacial Radiology, Oral and Dental Health Center, Hatay 31040, Turkey
| | - Orhan Kazan
- Health Services Vocational School, Gazi University, Ankara 06560, Turkey
| | - İbrahim Şevki Bayrakdar
- Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Eskisehir Osmangazi University, Eskişehir 26040, Turkey
- Eskisehir Osmangazi University Center of Research and Application for Computer-Aided Diagnosis and Treatment in Health, Eskişehir 26040, Turkey
- Division of Oral and Maxillofacial Radiology, Department of Care Planning and Restorative Sciences, University of Mississippi Medical Center School of Dentistry, Jackson, MS 39216, USA
| | - Özer Çelik
- Eskisehir Osmangazi University Center of Research and Application for Computer-Aided Diagnosis and Treatment in Health, Eskişehir 26040, Turkey
- Department of Mathematics-Computer, Faculty of Science, Eskisehir Osmangazi University, Eskişehir 26040, Turkey
| | - Andre Luiz Ferreira Costa
- Postgraduate Program in Dentistry, Cruzeiro do Sul University (UNICSUL), São Paulo 01506-000, SP, Brazil
| | - João Pedro Perez Gomes
- Department of Stomatology, Division of General Pathology, School of Dentistry, University of São Paulo (USP), São Paulo 13560-970, SP, Brazil
| | - Celso Massahiro Ogawa
- Postgraduate Program in Dentistry, Cruzeiro do Sul University (UNICSUL), São Paulo 01506-000, SP, Brazil
| | - Rohan Jagtap
- Division of Oral and Maxillofacial Radiology, Department of Care Planning and Restorative Sciences, University of Mississippi Medical Center School of Dentistry, Jackson, MS 39216, USA
| | - Kaan Orhan
- Department of Dentomaxillofacial Radiology, Faculty of Dentistry, Ankara University, Ankara 06000, Turkey
- Department of Dental and Maxillofacial Radiodiagnostics, Medical University of Lublin, 20-093 Lublin, Poland
- Ankara University Medical Design Application and Research Center (MEDITAM), Ankara 06000, Turkey
| |
Collapse
|
9
|
Vinod DN, Prabaharan SRS. COVID-19-The Role of Artificial Intelligence, Machine Learning, and Deep Learning: A Newfangled. ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING : STATE OF THE ART REVIEWS 2023; 30:2667-2682. [PMID: 36685135 PMCID: PMC9843670 DOI: 10.1007/s11831-023-09882-4] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/28/2022] [Accepted: 01/05/2023] [Indexed: 05/29/2023]
Abstract
The absolute previously infected novel coronavirus (COVID-19) was found in Wuhan, China, in December 2019. The COVID-19 epidemic has spread to more than 220 nations and territories globally and has altogether influenced each part of our day-to-day lives. As of 9th March 2022, a total aggregate of 44,78,82,185 (60,07,317) contaminated (dead) COVID-19 cases were accounted for all over the world. The quantities of contaminated cases passing despite everything increment essentially and do not indicate a controlled circumstance. The scope of this paper is to address this issue by presenting a comprehensive and comparative analysis of the existing Machine Learning (ML), Deep Learning (DL) and Artificial Intelligence (AI) based approaches used in significance in reacting to the COVID-19 epidemic and diagnosing the severe impacts. The paper provides, firstly, an overview of COVID-19 infection and highlights of this article; Secondly, an overview of exploring various executive innovations by utilizing different resources to stop the spread of COVID-19; Thirdly, a comparison of existing predicting methods of COVID-19 in the literature, with focus on ML, DL and AI-driven techniques with performance metrics; and finally, a discussion on the results of the work as well as future scope.
Collapse
Affiliation(s)
- Dasari Naga Vinod
- Department of Electronics and Communication Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, Chennai, Tamil Nadu 600062 India
| | - S. R. S. Prabaharan
- Sathyabama Centre for Advanced Studies, Sathyabama Institute of Science and Technology, Rajiv Gandhi Salai, Chennai, Tamil Nadu 600119 India
| |
Collapse
|
10
|
Interactive framework for Covid-19 detection and segmentation with feedback facility for dynamically improved accuracy and trust. PLoS One 2022; 17:e0278487. [PMID: 36548288 PMCID: PMC9778629 DOI: 10.1371/journal.pone.0278487] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/21/2022] [Accepted: 11/17/2022] [Indexed: 12/24/2022] Open
Abstract
Due to the severity and speed of spread of the ongoing Covid-19 pandemic, fast but accurate diagnosis of Covid-19 patients has become a crucial task. Achievements in this respect might enlighten future efforts for the containment of other possible pandemics. Researchers from various fields have been trying to provide novel ideas for models or systems to identify Covid-19 patients from different medical and non-medical data. AI-based researchers have also been trying to contribute to this area by mostly providing novel approaches of automated systems using convolutional neural network (CNN) and deep neural network (DNN) for Covid-19 detection and diagnosis. Due to the efficiency of deep learning (DL) and transfer learning (TL) models in classification and segmentation tasks, most of the recent AI-based researches proposed various DL and TL models for Covid-19 detection and infected region segmentation from chest medical images like X-rays or CT images. This paper describes a web-based application framework for Covid-19 lung infection detection and segmentation. The proposed framework is characterized by a feedback mechanism for self learning and tuning. It uses variations of three popular DL models, namely Mask R-CNN, U-Net, and U-Net++. The models were trained, evaluated and tested using CT images of Covid patients which were collected from two different sources. The web application provide a simple user friendly interface to process the CT images from various resources using the chosen models, thresholds and other parameters to generate the decisions on detection and segmentation. The models achieve high performance scores for Dice similarity, Jaccard similarity, accuracy, loss, and precision values. The U-Net model outperformed the other models with more than 98% accuracy.
Collapse
|
11
|
Automatic COVID-19 Lung Infection Segmentation through Modified Unet Model. JOURNAL OF HEALTHCARE ENGINEERING 2022; 2022:6566982. [PMID: 35422980 PMCID: PMC9002904 DOI: 10.1155/2022/6566982] [Citation(s) in RCA: 18] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/12/2022] [Revised: 02/23/2022] [Accepted: 02/28/2022] [Indexed: 11/23/2022]
Abstract
The coronavirus (COVID-19) pandemic has had a terrible impact on human lives globally, with far-reaching consequences for the health and well-being of many people around the world. Statistically, 305.9 million people worldwide tested positive for COVID-19, and 5.48 million people died due to COVID-19 up to 10 January 2022. CT scans can be used as an alternative to time-consuming RT-PCR testing for COVID-19. This research work proposes a segmentation approach to identifying ground glass opacity or ROI in CT images developed by coronavirus, with a modified structure of the Unet model having been used to classify the region of interest at the pixel level. The problem with segmentation is that the GGO often appears indistinguishable from a healthy lung in the initial stages of COVID-19, and so, to cope with this, the increased set of weights in contracting and expanding the Unet path and an improved convolutional module is added in order to establish the connection between the encoder and decoder pipeline. This has a major capacity to segment the GGO in the case of COVID-19, with the proposed model being referred to as “convUnet.” The experiment was performed on the Medseg1 dataset, and the addition of a set of weights at each layer of the model and modification in the connected module in Unet led to an improvement in overall segmentation results. The quantitative results obtained using accuracy, recall, precision, dice-coefficient, F1score, and IOU were 93.29%, 93.01%, 93.67%, 92.46%, 93.34%, 86.96%, respectively, which is better than that obtained using Unet and other state-of-the-art models. Therefore, this segmentation approach proved to be more accurate, fast, and reliable in helping doctors to diagnose COVID-19 quickly and efficiently.
Collapse
|
12
|
Zhang L, Zhang J. Ultrasound image denoising using generative adversarial networks with residual dense connectivity and weighted joint loss. PeerJ Comput Sci 2022; 8:e873. [PMID: 35494868 PMCID: PMC9044345 DOI: 10.7717/peerj-cs.873] [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: 11/01/2021] [Accepted: 01/11/2022] [Indexed: 06/12/2023]
Abstract
BACKGROUND Ultrasound imaging has been recognized as a powerful tool in clinical diagnosis. Nonetheless, the presence of speckle noise degrades the signal-to-noise of ultrasound images. Various denoising algorithms cannot fully reduce speckle noise and retain image features well for ultrasound imaging. The application of deep learning in ultrasound image denoising has attracted more and more attention in recent years. METHODS In the article, we propose a generative adversarial network with residual dense connectivity and weighted joint loss (GAN-RW) to avoid the limitations of traditional image denoising algorithms and surpass the most advanced performance of ultrasound image denoising. The denoising network is based on U-Net architecture which includes four encoder and four decoder modules. Each of the encoder and decoder modules is replaced with residual dense connectivity and BN to remove speckle noise. The discriminator network applies a series of convolutional layers to identify differences between the translated images and the desired modality. In the training processes, we introduce a joint loss function consisting of a weighted sum of the L1 loss function, binary cross-entropy with a logit loss function and perceptual loss function. RESULTS We split the experiments into two parts. First, experiments were performed on Berkeley segmentation (BSD68) datasets corrupted by a simulated speckle. Compared with the eight existing denoising algorithms, the GAN-RW achieved the most advanced despeckling performance in terms of the peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and subjective visual effect. When the noise level was 15, the average value of the GAN-RW increased by approximately 3.58% and 1.23% for PSNR and SSIM, respectively. When the noise level was 25, the average value of the GAN-RW increased by approximately 3.08% and 1.84% for PSNR and SSIM, respectively. When the noise level was 50, the average value of the GAN-RW increased by approximately 1.32% and 1.98% for PSNR and SSIM, respectively. Secondly, experiments were performed on the ultrasound images of lymph nodes, the foetal head, and the brachial plexus. The proposed method shows higher subjective visual effect when verifying on the ultrasound images. In the end, through statistical analysis, the GAN-RW achieved the highest mean rank in the Friedman test.
Collapse
Affiliation(s)
- Lun Zhang
- School of Information Science and Engineering, Yunnan University, Kunming, Yunnan, China
- Yunnan Vocational Institute of Energy Technology, Qujing, Yunnan, China
| | - Junhua Zhang
- School of Information Science and Engineering, Yunnan University, Kunming, Yunnan, China
| |
Collapse
|
13
|
Prakash NB, Murugappan M, Hemalakshmi GR, Jayalakshmi M, Mahmud M. Deep transfer learning for COVID-19 detection and infection localization with superpixel based segmentation. SUSTAINABLE CITIES AND SOCIETY 2021; 75:103252. [PMID: 34422549 PMCID: PMC8364837 DOI: 10.1016/j.scs.2021.103252] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/28/2021] [Revised: 08/01/2021] [Accepted: 08/09/2021] [Indexed: 05/07/2023]
Abstract
The evolution the novel corona virus disease (COVID-19) as a pandemic has inflicted several thousand deaths per day endangering the lives of millions of people across the globe. In addition to thermal scanning mechanisms, chest imaging examinations provide valuable insights to the detection of this virus, diagnosis and prognosis of the infections. Though Chest CT and Chest X-ray imaging are common in the clinical protocols of COVID-19 management, the latter is highly preferred, attributed to its simple image acquisition procedure and mobility of the imaging mechanism. However, Chest X-ray images are found to be less sensitive compared to Chest CT images in detecting infections in the early stages. In this paper, we propose a deep learning based framework to enhance the diagnostic values of these images for improved clinical outcomes. It is realized as a variant of the conventional SqueezeNet classifier with segmentation capabilities, which is trained with deep features extracted from the Chest X-ray images of a standard dataset for binary and multi class classification. The binary classifier achieves an accuracy of 99.53% in the discrimination of COVID-19 and Non COVID-19 images. Similarly, the multi class classifier performs classification of COVID-19, Viral Pneumonia and Normal cases with an accuracy of 99.79%. This model called the COVID-19 Super pixel SqueezNet (COVID-SSNet) performs super pixel segmentation of the activation maps to extract the regions of interest which carry perceptual image features and constructs an overlay of the Chest X-ray images with these regions. The proposed classifier model adds significant value to the Chest X-rays for an integral examination of the image features and the image regions influencing the classifier decisions to expedite the COVID-19 treatment regimen.
Collapse
Affiliation(s)
- N B Prakash
- Department of Electrical and Electronics Engineering, National Engineering College, Tamil Nadu, India
| | - M Murugappan
- Intelligent Signal Processing (ISP) Research Lab, Department of Electronics and Communication Engineering, Kuwait College of Science and Technology, Kuwait
| | - G R Hemalakshmi
- Department of Computer Science and Engineering, National Engineering College, Tamil Nadu, India
| | - M Jayalakshmi
- Department of Computer Science and Engineering, National Engineering College, Tamil Nadu, India
| | - Mufti Mahmud
- Department of Computer Science, Nottingham Trent University, Clifton, Nottingham NG11 8NS, UK
- Medical Technologies Innovation Facility, Nottingham Trent University, Clifton, Nottingham NG11 8NS, UK
- Computing and Informatics Research Centre, Nottingham Trent University, Clifton, Nottingham NG11 8NS, UK
| |
Collapse
|
14
|
Nguyen HT, Bao Tran T, Luong HH, Nguyen Huynh TK. Decoders configurations based on Unet family and feature pyramid network for COVID-19 segmentation on CT images. PeerJ Comput Sci 2021; 7:e719. [PMID: 34616895 PMCID: PMC8459784 DOI: 10.7717/peerj-cs.719] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/17/2021] [Accepted: 08/26/2021] [Indexed: 06/13/2023]
Abstract
Coronavirus Disease 2019 (COVID-19) pandemic has been ferociously destroying global health and economics. According to World Health Organisation (WHO), until May 2021, more than one hundred million infected cases and 3.2 million deaths have been reported in over 200 countries. Unfortunately, the numbers are still on the rise. Therefore, scientists are making a significant effort in researching accurate, efficient diagnoses. Several studies advocating artificial intelligence proposed COVID diagnosis methods on lung images with high accuracy. Furthermore, some affected areas in the lung images can be detected accurately by segmentation methods. This work has considered state-of-the-art Convolutional Neural Network architectures, combined with the Unet family and Feature Pyramid Network (FPN) for COVID segmentation tasks on Computed Tomography (CT) scanner samples from the Italian Society of Medical and Interventional Radiology dataset. The experiments show that the decoder-based Unet family has reached the best (a mean Intersection Over Union (mIoU) of 0.9234, 0.9032 in dice score, and a recall of 0.9349) with a combination between SE ResNeXt and Unet++. The decoder with the Unet family obtained better COVID segmentation performance in comparison with Feature Pyramid Network. Furthermore, the proposed method outperforms recent segmentation state-of-the-art approaches such as the SegNet-based network, ADID-UNET, and A-SegNet + FTL. Therefore, it is expected to provide good segmentation visualizations of medical images.
Collapse
Affiliation(s)
- Hai Thanh Nguyen
- College of Information and Communication Technology, Can Tho University, Can Tho, Vietnam
| | - Toan Bao Tran
- Center of Software Engineering, Duy Tan University, Da Nang, Vietnam
- Institute of Research and Development, Duy Tan University, Da Nang, Vietnam
| | | | | |
Collapse
|