1
|
Nkengue MJ, Zeng X, Koehl L, Tao X, Dassonville F, Dumont N, Ye-Lehmann S, Akwa Y, Ye H. An intelligent garment for long COVID-19 real-time monitoring. Comput Biol Med 2024; 181:109067. [PMID: 39182371 DOI: 10.1016/j.compbiomed.2024.109067] [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: 04/18/2024] [Revised: 08/13/2024] [Accepted: 08/21/2024] [Indexed: 08/27/2024]
Abstract
As monitoring and diagnostic tools for long COVID-19 cases, wearable systems and supervised learning-based medical image analysis have proven to be useful. Current research on these two technical roadmaps has various drawbacks, despite their respective benefits. Wearable systems allow only the real-time monitoring of physiological parameters (heart rate, temperature, blood oxygen saturation, or SpO2). Therefore, they are unable to conduct in-depth investigations or differentiate COVID-19 from other illnesses that share similar symptoms. Medical image analysis using supervised learning-based models can be used to conduct in-depth analyses and provide precise diagnostic decision support. However, these methods are rarely used for real-time monitoring. In this regard, we present an intelligent garment combining the precision of supervised learning-based models with real-time monitoring capabilities of wearable systems. Given the relevance of electrocardiogram (ECG) signals to long COVID-19 symptom severity, an explainable data fusion strategy based on multiple machine learning models uses heart rate, temperature, SpO2, and ECG signal analysis to accurately assess the patient's health status. Experiments show that the proposed intelligent garment achieves an accuracy of 97.5 %, outperforming most of the existing wearable systems. Furthermore, it was confirmed that the two physiological indicators most significantly affected by the presence of long COVID-19 were SpO2 and the ST intervals of ECG signals.
Collapse
Affiliation(s)
- Marc Junior Nkengue
- Univ. Lille, ENSAIT, Laboratoire Génie et Matériaux Textile (GEMTEX), F-59000, Lille, France; Univ. Lille, Ecole Centrale Lille, F-59000, Lille, France.
| | - Xianyi Zeng
- Univ. Lille, ENSAIT, Laboratoire Génie et Matériaux Textile (GEMTEX), F-59000, Lille, France
| | - Ludovic Koehl
- Univ. Lille, ENSAIT, Laboratoire Génie et Matériaux Textile (GEMTEX), F-59000, Lille, France
| | - Xuyuan Tao
- Univ. Lille, ENSAIT, Laboratoire Génie et Matériaux Textile (GEMTEX), F-59000, Lille, France
| | - François Dassonville
- Univ. Lille, ENSAIT, Laboratoire Génie et Matériaux Textile (GEMTEX), F-59000, Lille, France
| | - Nicolas Dumont
- Univ. Lille, ENSAIT, Laboratoire Génie et Matériaux Textile (GEMTEX), F-59000, Lille, France
| | - Shixin Ye-Lehmann
- Univ. Paris-Saclay, Diseases and Hormones of the Nervous System, F-94000, Paris, France
| | - Yvette Akwa
- Univ. Paris-Saclay, Diseases and Hormones of the Nervous System, F-94000, Paris, France
| | - Hanwen Ye
- Univ. Paris-Saclay, Diseases and Hormones of the Nervous System, F-94000, Paris, France
| |
Collapse
|
2
|
Sannasi Chakravarthy SR, Bharanidharan N, Vinothini C, Vinoth Kumar V, Mahesh TR, Guluwadi S. Adaptive Mish activation and ranger optimizer-based SEA-ResNet50 model with explainable AI for multiclass classification of COVID-19 chest X-ray images. BMC Med Imaging 2024; 24:206. [PMID: 39123118 PMCID: PMC11313131 DOI: 10.1186/s12880-024-01394-2] [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: 04/04/2024] [Accepted: 08/06/2024] [Indexed: 08/12/2024] Open
Abstract
A recent global health crisis, COVID-19 is a significant global health crisis that has profoundly affected lifestyles. The detection of such diseases from similar thoracic anomalies using medical images is a challenging task. Thus, the requirement of an end-to-end automated system is vastly necessary in clinical treatments. In this way, the work proposes a Squeeze-and-Excitation Attention-based ResNet50 (SEA-ResNet50) model for detecting COVID-19 utilizing chest X-ray data. Here, the idea lies in improving the residual units of ResNet50 using the squeeze-and-excitation attention mechanism. For further enhancement, the Ranger optimizer and adaptive Mish activation function are employed to improve the feature learning of the SEA-ResNet50 model. For evaluation, two publicly available COVID-19 radiographic datasets are utilized. The chest X-ray input images are augmented during experimentation for robust evaluation against four output classes namely normal, pneumonia, lung opacity, and COVID-19. Then a comparative study is done for the SEA-ResNet50 model against VGG-16, Xception, ResNet18, ResNet50, and DenseNet121 architectures. The proposed framework of SEA-ResNet50 together with the Ranger optimizer and adaptive Mish activation provided maximum classification accuracies of 98.38% (multiclass) and 99.29% (binary classification) as compared with the existing CNN architectures. The proposed method achieved the highest Kappa validation scores of 0.975 (multiclass) and 0.98 (binary classification) over others. Furthermore, the visualization of the saliency maps of the abnormal regions is represented using the explainable artificial intelligence (XAI) model, thereby enhancing interpretability in disease diagnosis.
Collapse
Affiliation(s)
- S R Sannasi Chakravarthy
- Department of Electronics and Communication Engineering, Bannari Amman Institute of Technology, Sathyamangalam, India
| | - N Bharanidharan
- School of Computer Science Engineering and Information Systems, Vellore Institute of Technology, Vellore, 632014, India
| | - C Vinothini
- Department of Computer Science and Engineering, Dayananda Sagar College of Engineering, Bangalore, India
| | - Venkatesan Vinoth Kumar
- School of Computer Science Engineering and Information Systems, Vellore Institute of Technology, Vellore, 632014, India
| | - T R Mahesh
- Department of Computer Science and Engineering, JAIN (Deemed-to-Be University), Bengaluru, 562112, India
| | - Suresh Guluwadi
- Adama Science and Technology University, Adama, 302120, Ethiopia.
| |
Collapse
|
3
|
Siddiqi R, Javaid S. Deep Learning for Pneumonia Detection in Chest X-ray Images: A Comprehensive Survey. J Imaging 2024; 10:176. [PMID: 39194965 DOI: 10.3390/jimaging10080176] [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: 06/11/2024] [Revised: 07/15/2024] [Accepted: 07/19/2024] [Indexed: 08/29/2024] Open
Abstract
This paper addresses the significant problem of identifying the relevant background and contextual literature related to deep learning (DL) as an evolving technology in order to provide a comprehensive analysis of the application of DL to the specific problem of pneumonia detection via chest X-ray (CXR) imaging, which is the most common and cost-effective imaging technique available worldwide for pneumonia diagnosis. This paper in particular addresses the key period associated with COVID-19, 2020-2023, to explain, analyze, and systematically evaluate the limitations of approaches and determine their relative levels of effectiveness. The context in which DL is applied as both an aid to and an automated substitute for existing expert radiography professionals, who often have limited availability, is elaborated in detail. The rationale for the undertaken research is provided, along with a justification of the resources adopted and their relevance. This explanatory text and the subsequent analyses are intended to provide sufficient detail of the problem being addressed, existing solutions, and the limitations of these, ranging in detail from the specific to the more general. Indeed, our analysis and evaluation agree with the generally held view that the use of transformers, specifically, vision transformers (ViTs), is the most promising technique for obtaining further effective results in the area of pneumonia detection using CXR images. However, ViTs require extensive further research to address several limitations, specifically the following: biased CXR datasets, data and code availability, the ease with which a model can be explained, systematic methods of accurate model comparison, the notion of class imbalance in CXR datasets, and the possibility of adversarial attacks, the latter of which remains an area of fundamental research.
Collapse
Affiliation(s)
- Raheel Siddiqi
- Computer Science Department, Karachi Campus, Bahria University, Karachi 73500, Pakistan
| | - Sameena Javaid
- Computer Science Department, Karachi Campus, Bahria University, Karachi 73500, Pakistan
| |
Collapse
|
4
|
Touati R, Trung Le W, Kadoury S. Multi-planar dual adversarial network based on dynamic 3D features for MRI-CT head and neck image synthesis. Phys Med Biol 2024; 69:155012. [PMID: 38981593 DOI: 10.1088/1361-6560/ad611a] [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: 04/23/2024] [Accepted: 07/09/2024] [Indexed: 07/11/2024]
Abstract
Objective.Head and neck radiotherapy planning requires electron densities from different tissues for dose calculation. Dose calculation from imaging modalities such as MRI remains an unsolved problem since this imaging modality does not provide information about the density of electrons.Approach.We propose a generative adversarial network (GAN) approach that synthesizes CT (sCT) images from T1-weighted MRI acquisitions in head and neck cancer patients. Our contribution is to exploit new features that are relevant for improving multimodal image synthesis, and thus improving the quality of the generated CT images. More precisely, we propose a Dual branch generator based on the U-Net architecture and on an augmented multi-planar branch. The augmented branch learns specific 3D dynamic features, which describe the dynamic image shape variations and are extracted from different view-points of the volumetric input MRI. The architecture of the proposed model relies on an end-to-end convolutional U-Net embedding network.Results.The proposed model achieves a mean absolute error (MAE) of18.76±5.167in the target Hounsfield unit (HU) space on sagittal head and neck patients, with a mean structural similarity (MSSIM) of0.95±0.09and a Frechet inception distance (FID) of145.60±8.38. The model yields a MAE of26.83±8.27to generate specific primary tumor regions on axial patient acquisitions, with a Dice score of0.73±0.06and a FID distance equal to122.58±7.55. The improvement of our model over other state-of-the-art GAN approaches is of 3.8%, on a tumor test set. On both sagittal and axial acquisitions, the model yields the best peak signal-to-noise ratio of27.89±2.22and26.08±2.95to synthesize MRI from CT input.Significance.The proposed model synthesizes both sagittal and axial CT tumor images, used for radiotherapy treatment planning in head and neck cancer cases. The performance analysis across different imaging metrics and under different evaluation strategies demonstrates the effectiveness of our dual CT synthesis model to produce high quality sCT images compared to other state-of-the-art approaches. Our model could improve clinical tumor analysis, in which a further clinical validation remains to be explored.
Collapse
Affiliation(s)
- Redha Touati
- MedICAL Laboratory, Polytechnique Montreal, Montreal, QC, Canada
| | - William Trung Le
- MedICAL Laboratory, Polytechnique Montreal, Montreal, QC, Canada
| | - Samuel Kadoury
- MedICAL Laboratory, Polytechnique Montreal, Montreal, QC, Canada
- CHUM Research Center, Montreal, QC, Canada
| |
Collapse
|
5
|
Kadhim YA, Guzel MS, Mishra A. A Novel Hybrid Machine Learning-Based System Using Deep Learning Techniques and Meta-Heuristic Algorithms for Various Medical Datatypes Classification. Diagnostics (Basel) 2024; 14:1469. [PMID: 39061605 PMCID: PMC11275302 DOI: 10.3390/diagnostics14141469] [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: 05/22/2024] [Revised: 06/27/2024] [Accepted: 07/02/2024] [Indexed: 07/28/2024] Open
Abstract
Medicine is one of the fields where the advancement of computer science is making significant progress. Some diseases require an immediate diagnosis in order to improve patient outcomes. The usage of computers in medicine improves precision and accelerates data processing and diagnosis. In order to categorize biological images, hybrid machine learning, a combination of various deep learning approaches, was utilized, and a meta-heuristic algorithm was provided in this research. In addition, two different medical datasets were introduced, one covering the magnetic resonance imaging (MRI) of brain tumors and the other dealing with chest X-rays (CXRs) of COVID-19. These datasets were introduced to the combination network that contained deep learning techniques, which were based on a convolutional neural network (CNN) or autoencoder, to extract features and combine them with the next step of the meta-heuristic algorithm in order to select optimal features using the particle swarm optimization (PSO) algorithm. This combination sought to reduce the dimensionality of the datasets while maintaining the original performance of the data. This is considered an innovative method and ensures highly accurate classification results across various medical datasets. Several classifiers were employed to predict the diseases. The COVID-19 dataset found that the highest accuracy was 99.76% using the combination of CNN-PSO-SVM. In comparison, the brain tumor dataset obtained 99.51% accuracy, the highest accuracy derived using the combination method of autoencoder-PSO-KNN.
Collapse
Affiliation(s)
- Yezi Ali Kadhim
- College of Engineering, University of Baghdad, Jadriyah, Baghdad 10071, Iraq;
- Department of Modeling and Design of Engineering Systems (MODES), Atilim University, Ankara 06830, Turkey
- Department of Electrical and Electronics Engineering, Atilim University, Incek, Ankara 06830, Turkey
| | - Mehmet Serdar Guzel
- Department of Computer Engineering, Ankara University, Yenimahalle, Ankara 06100, Turkey;
| | - Alok Mishra
- Faculty of Engineering, Norwegian University of Science and Technology, 7034 Trondheim, Norway
- Department of Software Engineering, Atilim University, Incek, Ankara 06830, Turkey
| |
Collapse
|
6
|
Wang X, Lu Z, Huang S, Ting Y, Ting JSZ, Chen W, Tan CH, Huang W. TransMVAN: Multi-view Aggregation Network with Transformer for Pneumonia Diagnosis. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024:10.1007/s10278-024-01169-9. [PMID: 38977615 DOI: 10.1007/s10278-024-01169-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/17/2024] [Revised: 04/30/2024] [Accepted: 05/01/2024] [Indexed: 07/10/2024]
Abstract
Automated and accurate classification of pneumonia plays a crucial role in improving the performance of computer-aided diagnosis systems for chest X-ray images. Nevertheless, it is a challenging task due to the difficulty of learning the complex structure information of lung abnormality from chest X-ray images. In this paper, we propose a multi-view aggregation network with Transformer (TransMVAN) for pneumonia classification in chest X-ray images. Specifically, we propose to incorporate the knowledge from glance and focus views to enrich the feature representation of lung abnormality. Moreover, to capture the complex relationships among different lung regions, we propose a bi-directional multi-scale vision Transformer (biMSVT), with which the informative messages between different lung regions are propagated through two directions. In addition, we also propose a gated multi-view aggregation (GMVA) to adaptively select the feature information from glance and focus views for further performance enhancement of pneumonia diagnosis. Our proposed method achieves AUCs of 0.9645 and 0.9550 for pneumonia classification on two different chest X-ray image datasets. In addition, it achieves an AUC of 0.9761 for evaluating positive and negative polymerase chain reaction (PCR). Furthermore, our proposed method also attains an AUC of 0.9741 for classifying non-COVID-19 pneumonia, COVID-19 pneumonia, and normal cases. Experimental results demonstrate the effectiveness of our method over other methods used for comparison in pneumonia diagnosis from chest X-ray images.
Collapse
Affiliation(s)
- Xiaohong Wang
- Institute for Infocomm Research (I²R), A*STAR, 138632, Singapore, Singapore
| | - Zhongkang Lu
- Institute for Infocomm Research (I²R), A*STAR, 138632, Singapore, Singapore
| | - Su Huang
- Institute for Infocomm Research (I²R), A*STAR, 138632, Singapore, Singapore
| | - Yonghan Ting
- Department of Diagnostic Radiology, Tan Tock Seng Hospital, 308433, Singapore, Singapore
| | - Jordan Sim Zheng Ting
- Department of Diagnostic Radiology, Tan Tock Seng Hospital, 308433, Singapore, Singapore
| | - Wenxiang Chen
- Department of Diagnostic Radiology, Tan Tock Seng Hospital, 308433, Singapore, Singapore
| | - Cher Heng Tan
- Department of Diagnostic Radiology, Tan Tock Seng Hospital, 308433, Singapore, Singapore
- Lee Kong Chian School of Medicine, Nanyang Technological University, 308232, Singapore, Singapore
| | - Weimin Huang
- Institute for Infocomm Research (I²R), A*STAR, 138632, Singapore, Singapore.
| |
Collapse
|
7
|
Li Y, Xin Y, Li X, Zhang Y, Liu C, Cao Z, Du S, Wang L. Omni-dimensional dynamic convolution feature coordinate attention network for pneumonia classification. Vis Comput Ind Biomed Art 2024; 7:17. [PMID: 38976189 PMCID: PMC11231110 DOI: 10.1186/s42492-024-00168-5] [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: 02/08/2024] [Accepted: 06/22/2024] [Indexed: 07/09/2024] Open
Abstract
Pneumonia is a serious disease that can be fatal, particularly among children and the elderly. The accuracy of pneumonia diagnosis can be improved by combining artificial-intelligence technology with X-ray imaging. This study proposes X-ODFCANet, which addresses the issues of low accuracy and excessive parameters in existing deep-learning-based pneumonia-classification methods. This network incorporates a feature coordination attention module and an omni-dimensional dynamic convolution (ODConv) module, leveraging the residual module for feature extraction from X-ray images. The feature coordination attention module utilizes two one-dimensional feature encoding processes to aggregate feature information from different spatial directions. Additionally, the ODConv module extracts and fuses feature information in four dimensions: the spatial dimension of the convolution kernel, input and output channel quantities, and convolution kernel quantity. The experimental results demonstrate that the proposed method can effectively improve the accuracy of pneumonia classification, which is 3.77% higher than that of ResNet18. The model parameters are 4.45M, which was reduced by approximately 2.5 times. The code is available at https://github.com/limuni/X-ODFCANET .
Collapse
Affiliation(s)
- Yufei Li
- School of Information Science and Technology, Northwest University, Xi'an, 710127, Shaanxi Province, China
| | - Yufei Xin
- School of Information Science and Technology, Northwest University, Xi'an, 710127, Shaanxi Province, China
| | - Xinni Li
- School of Information Science and Technology, Northwest University, Xi'an, 710127, Shaanxi Province, China
| | - Yinrui Zhang
- School of Information Science and Technology, Northwest University, Xi'an, 710127, Shaanxi Province, China
| | - Cheng Liu
- School of Information Science and Technology, Northwest University, Xi'an, 710127, Shaanxi Province, China
| | - Zhengwen Cao
- School of Information Science and Technology, Northwest University, Xi'an, 710127, Shaanxi Province, China
| | - Shaoyi Du
- Department of Ultrasound, the Second Affiliated Hospital of Xi'an Jiaotong University, Xi'an, Shaanxi Province, 710004, China.
- National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi Province, 710049, China.
| | - Lin Wang
- School of Information Science and Technology, Northwest University, Xi'an, 710127, Shaanxi Province, China.
| |
Collapse
|
8
|
Merrouchi M, Benyoussef Y, Skittou M, Atifi K, Gadi T. ConvCoroNet: a deep convolutional neural network optimized with iterative thresholding algorithm for Covid-19 detection using chest X-ray images. J Biomol Struct Dyn 2024; 42:5699-5712. [PMID: 37354142 DOI: 10.1080/07391102.2023.2227726] [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: 12/30/2022] [Accepted: 06/15/2023] [Indexed: 06/26/2023]
Abstract
Covid-19 is a global pandemic. Early and accurate detection of positive cases prevent the further spread of this epidemic and help to treat rapidly the infected patients. During the peak of this epidemic, there was an insufficiency of Covid-19 test kits. In addition, this technique takes a considerable time in the diagnosis. Hence the need to find fast, accurate and low-cost method to replace or supplement RT PCR-based methods. Covid-19 is a respiratory disease, chest X-ray images are often used to diagnose pneumonia. From this perspective, these images can play an important role in the Covid-19 detection. In this article, we propose ConvCoroNet, a deep convolutional neural network model optimized with new method based on iterative thresholding algorithm to detect coronavirus automatically from chest X-ray images. ConvCoroNet is trained on a dataset prepared by collecting chest X-ray images of Covid-19, pneumonia and normal cases from publically datasets. The experimental results of our proposed model show a high accuracy of 99.50%, sensitivity of 98.80% and specificity of 99.85% when detecting Covid-19 from chest X-ray images. ConvCoroNet achieves promising results in the automatic detection of Covid-19 from chest X-ray images. It may be able to help radiologists in the Covid-19 detection by reducing the examination time of X-ray images.Communicated by Ramaswamy H. Sarma.
Collapse
Affiliation(s)
- M Merrouchi
- Faculty of Science and Technology, Hassan First, Settat, Morocco
| | - Y Benyoussef
- National School of Applied Sciences, Hassan First, Berrechid, Morocco
| | - M Skittou
- Faculty of Science and Technology, Hassan First, Settat, Morocco
| | - K Atifi
- Faculty of Science and Technology, Hassan First, Settat, Morocco
| | - T Gadi
- Faculty of Science and Technology, Hassan First, Settat, Morocco
| |
Collapse
|
9
|
Talib MA, Afadar Y, Nasir Q, Nassif AB, Hijazi H, Hasasneh A. A tree-based explainable AI model for early detection of Covid-19 using physiological data. BMC Med Inform Decis Mak 2024; 24:179. [PMID: 38915001 PMCID: PMC11194929 DOI: 10.1186/s12911-024-02576-2] [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: 02/01/2024] [Accepted: 06/13/2024] [Indexed: 06/26/2024] Open
Abstract
With the outbreak of COVID-19 in 2020, countries worldwide faced significant concerns and challenges. Various studies have emerged utilizing Artificial Intelligence (AI) and Data Science techniques for disease detection. Although COVID-19 cases have declined, there are still cases and deaths around the world. Therefore, early detection of COVID-19 before the onset of symptoms has become crucial in reducing its extensive impact. Fortunately, wearable devices such as smartwatches have proven to be valuable sources of physiological data, including Heart Rate (HR) and sleep quality, enabling the detection of inflammatory diseases. In this study, we utilize an already-existing dataset that includes individual step counts and heart rate data to predict the probability of COVID-19 infection before the onset of symptoms. We train three main model architectures: the Gradient Boosting classifier (GB), CatBoost trees, and TabNet classifier to analyze the physiological data and compare their respective performances. We also add an interpretability layer to our best-performing model, which clarifies prediction results and allows a detailed assessment of effectiveness. Moreover, we created a private dataset by gathering physiological data from Fitbit devices to guarantee reliability and avoid bias.The identical set of models was then applied to this private dataset using the same pre-trained models, and the results were documented. Using the CatBoost tree-based method, our best-performing model outperformed previous studies with an accuracy rate of 85% on the publicly available dataset. Furthermore, this identical pre-trained CatBoost model produced an accuracy of 81% when applied to the private dataset. You will find the source code in the link: https://github.com/OpenUAE-LAB/Covid-19-detection-using-Wearable-data.git .
Collapse
Affiliation(s)
- Manar Abu Talib
- Department of Computer Science, College of Computing and Informatics, University of Sharjah, P.O. Box 27272, Sharjah, UAE.
| | - Yaman Afadar
- Department of Computer Engineering, College of Computing and Informatics, University of Sharjah, Sharjah, UAE
| | - Qassim Nasir
- Department of Computer Engineering, College of Computing and Informatics, University of Sharjah, Sharjah, UAE
| | - Ali Bou Nassif
- Department of Computer Engineering, College of Computing and Informatics, University of Sharjah, Sharjah, UAE
| | - Haytham Hijazi
- Centre for Informatics and Systems of the University of Coimbra (CISUC), University of Coimbra, Coimbra, P-3030-290, Portugal
- Intelligent Systems Department, Ahliya University, Bethlehem, P-150-199, Palestine
| | - Ahmad Hasasneh
- Department of Natural, Engineering and Technology Sciences, Faculty of Graduate Studies, Arab American University, P.O. Box 240, Ramallah, Palestine
| |
Collapse
|
10
|
Nair SSK, David LR, Shariff A, Maskari SA, Mawali AA, Weis S, Fouad T, Ozsahin DU, Alshuweihi A, Obaideen A, Elshami W. CovMediScanX: A medical imaging solution for COVID-19 diagnosis from chest X-ray images. J Med Imaging Radiat Sci 2024; 55:272-280. [PMID: 38594085 DOI: 10.1016/j.jmir.2024.03.046] [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: 09/27/2023] [Revised: 02/17/2024] [Accepted: 03/19/2024] [Indexed: 04/11/2024]
Abstract
INTRODUCTION Radiologists have extensively employed the interpretation of chest X-rays (CXR) to identify visual markers indicative of COVID-19 infection, offering an alternative approach for the screening of infected individuals. This research article presents CovMediScanX, a deep learning-based framework designed for a rapid and automated diagnosis of COVID-19 from CXR scan images. METHODS The proposed approach encompasses gathering and preprocessing CXR image datasets, training deep learning-based custom-made Convolutional Neural Network (CNN), pre-trained and hybrid transfer learning models, identifying the highest-performing model based on key evaluation metrics, and embedding this model into a web interface called CovMediScanX, designed for radiologists to detect the COVID-19 status in new CXR images. RESULTS The custom-made CNN model obtained a remarkable testing accuracy of 94.32% outperforming other models. CovMediScanX, employing the custom-made CNN underwent evaluation with an independent dataset also. The images in the independent dataset are sourced from a scanning machine that is entirely different from those used for the training dataset, highlighting a clear distinction of datasets in their origins. The evaluation outcome highlighted the framework's capability to accurately detect COVID-19 cases, showcasing encouraging results with a precision of 73% and a recall of 84% for positive cases. However, the model requires further enhancement, particularly in improving its detection of normal cases, as evidenced by lower precision and recall rates. CONCLUSION The research proposes CovMediScanX framework that demonstrates promising potential in automatically identifying COVID-19 cases from CXR images. While the model's overall performance on independent data needs improvement, it is evident that addressing bias through the inclusion of diverse data sources during training could further enhance accuracy and reliability.
Collapse
Affiliation(s)
| | - Leena R David
- Department of Medical Diagnostic Imaging, College of Health Sciences, University of Sharjah, United Arab Emirates.
| | - Abdulwahid Shariff
- Department of Postgraduate Studies, University of Dar es Salaam, Tanzania
| | - Saqar Al Maskari
- Department of Computing and Electronics Engineering, Middle East College, Sultanate of Oman
| | - Adhra Al Mawali
- Quality Assurance and Planning, German University of Technology (GUtech), Sultanate of Oman
| | - Sammy Weis
- University Hospital, Sharjah, United Arab Emirates
| | - Taha Fouad
- University Hospital, Sharjah, United Arab Emirates
| | - Dilber Uzun Ozsahin
- Department of Medical Diagnostic Imaging, College of Health Sciences, University of Sharjah, United Arab Emirates
| | | | | | - Wiam Elshami
- Department of Medical Diagnostic Imaging, College of Health Sciences, University of Sharjah, United Arab Emirates
| |
Collapse
|
11
|
Cao R, Liu Y, Wen X, Liao C, Wang X, Gao Y, Tan T. Reinvestigating the performance of artificial intelligence classification algorithms on COVID-19 X-Ray and CT images. iScience 2024; 27:109712. [PMID: 38689643 PMCID: PMC11059117 DOI: 10.1016/j.isci.2024.109712] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2023] [Revised: 03/01/2024] [Accepted: 04/07/2024] [Indexed: 05/02/2024] Open
Abstract
There are concerns that artificial intelligence (AI) algorithms may create underdiagnosis bias by mislabeling patient individuals with certain attributes (e.g., female and young) as healthy. Addressing this bias is crucial given the urgent need for AI diagnostics facing rapidly spreading infectious diseases like COVID-19. We find the prevalent AI diagnostic models show an underdiagnosis rate among specific patient populations, and the underdiagnosis rate is higher in some intersectional specific patient populations (for example, females aged 20-40 years). Additionally, we find training AI models on heterogeneous datasets (positive and negative samples from different datasets) may lead to poor model generalization. The model's classification performance varies significantly across test sets, with the accuracy of the better performance being over 40% higher than that of the poor performance. In conclusion, we developed an AI bias analysis pipeline to help researchers recognize and address biases that impact medical equality and ethics.
Collapse
Affiliation(s)
- Rui Cao
- School of Software, Taiyuan University of Technology, Taiyuan 030024, China
| | - Yanan Liu
- School of Software, Taiyuan University of Technology, Taiyuan 030024, China
| | - Xin Wen
- School of Software, Taiyuan University of Technology, Taiyuan 030024, China
| | - Caiqing Liao
- School of Software, Taiyuan University of Technology, Taiyuan 030024, China
| | - Xin Wang
- Department of Radiology, Netherlands Cancer Institute (NKI), Plesmanlaan 121, Amsterdam 1066 CX, the Netherlands
- Department of Radiology and Nuclear Medicine, Radboud University Medical Centre, Geert Grooteplein 10, 6525 GA Nijmegen, the Netherlands
- GROW School for Oncology and Development Biology, Maastricht University, MD, Maastricht 6200, the Netherlands
| | - Yuan Gao
- Department of Radiology, Netherlands Cancer Institute (NKI), Plesmanlaan 121, Amsterdam 1066 CX, the Netherlands
- GROW School for Oncology and Development Biology, Maastricht University, MD, Maastricht 6200, the Netherlands
| | - Tao Tan
- Department of Radiology, Netherlands Cancer Institute (NKI), Plesmanlaan 121, Amsterdam 1066 CX, the Netherlands
- Department of Radiology and Nuclear Medicine, Radboud University Medical Centre, Geert Grooteplein 10, 6525 GA Nijmegen, the Netherlands
- Faculty of Applied Sciences, Macao Polytechnic University, Macao SAR 999078, China
| |
Collapse
|
12
|
Yuan Y, Liu L, Yang X, Liu L, Huang Q. Multi-scale Lesion Feature Fusion and Location-Aware for Chest Multi-disease Detection. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024:10.1007/s10278-024-01133-7. [PMID: 38760643 DOI: 10.1007/s10278-024-01133-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/03/2024] [Revised: 04/14/2024] [Accepted: 04/29/2024] [Indexed: 05/19/2024]
Abstract
Accurately identifying and locating lesions in chest X-rays has the potential to significantly enhance diagnostic efficiency, quality, and interpretability. However, current methods primarily focus on detecting of specific diseases in chest X-rays, disregarding the presence of multiple diseases in a single chest X-ray scan. Moreover, the diversity in lesion locations and attributes introduces complexity in accurately discerning specific traits for each lesion, leading to diminished accuracy when detecting multiple diseases. To address these issues, we propose a novel detection framework that enhances multi-scale lesion feature extraction and fusion, improving lesion position perception and subsequently boosting chest multi-disease detection performance. Initially, we construct a multi-scale lesion feature extraction network to tackle the uniqueness of various lesion features and locations, strengthening the global semantic correlation between lesion features and their positions. Following this, we introduce an instance-aware semantic enhancement network that dynamically amalgamates instance-specific features with high-level semantic representations across various scales. This adaptive integration effectively mitigates the loss of detailed information within lesion regions. Additionally, we perform lesion region feature mapping using candidate boxes to preserve crucial positional information, enhancing the accuracy of chest disease detection across multiple scales. Experimental results on the VinDr-CXR dataset reveal a 6% increment in mean average precision (mAP) and an 8.4% improvement in mean recall (mR) when compared to state-of-the-art baselines. This demonstrates the effectiveness of the model in accurately detecting multiple chest diseases by capturing specific features and location information.
Collapse
Affiliation(s)
- Yubo Yuan
- School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, 650500, China
| | - Lijun Liu
- School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, 650500, China.
- Key Laboratory of Application in Computer Technology in Yunnan Province, Kunming, 650500, China.
| | - Xiaobing Yang
- Department of State-Owned Assets and Laboratory Management, Kunming University of Science and Technology, Kunming, 650500, China
| | - Li Liu
- School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, 650500, China
| | - Qingsong Huang
- School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, 650500, China
- Department of State-Owned Assets and Laboratory Management, Kunming University of Science and Technology, Kunming, 650500, China
| |
Collapse
|
13
|
Bennour A, Ben Aoun N, Khalaf OI, Ghabban F, Wong WK, Algburi S. Contribution to pulmonary diseases diagnostic from X-ray images using innovative deep learning models. Heliyon 2024; 10:e30308. [PMID: 38707425 PMCID: PMC11068804 DOI: 10.1016/j.heliyon.2024.e30308] [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: 02/15/2024] [Revised: 04/09/2024] [Accepted: 04/23/2024] [Indexed: 05/07/2024] Open
Abstract
Pulmonary disease identification and characterization are among the most intriguing research topics of recent years since they require an accurate and prompt diagnosis. Although pulmonary radiography has helped in lung disease diagnosis, the interpretation of the radiographic image has always been a major concern for doctors and radiologists to reduce diagnosis errors. Due to their success in image classification and segmentation tasks, cutting-edge artificial intelligence techniques like machine learning (ML) and deep learning (DL) are widely encouraged to be applied in the field of diagnosing lung disorders and identifying them using medical images, particularly radiographic ones. For this end, the researchers are concurring to build systems based on these techniques in particular deep learning ones. In this paper, we proposed three deep-learning models that were trained to identify the presence of certain lung diseases using thoracic radiography. The first model, named "CovCXR-Net", identifies the COVID-19 disease (two cases: COVID-19 or normal). The second model, named "MDCXR3-Net", identifies the COVID-19 and pneumonia diseases (three cases: COVID-19, pneumonia, or normal), and the last model, named "MDCXR4-Net", is destined to identify the COVID-19, pneumonia and the pulmonary opacity diseases (4 cases: COVID-19, pneumonia, pulmonary opacity or normal). These models have proven their superiority in comparison with the state-of-the-art models and reached an accuracy of 99,09 %, 97.74 %, and 90,37 % respectively with three benchmarks.
Collapse
Affiliation(s)
- Akram Bennour
- LAMIS Laboratiry, Echahid Cheikh Larbi Tebessi University, Tebessa, Algeria
| | - Najib Ben Aoun
- College of Computer Science and Information Technology, Al-Baha University, Al Baha, Saudi Arabia
- REGIM-Lab: Research Groups in Intelligent Machines, National School of Engineers of Sfax (ENIS), University of Sfax, Tunisia
| | - Osamah Ibrahim Khalaf
- Department of Solar, Al-Nahrain Research Center for Renewable Energy, Al-Nahrain University, Jadriya, Baghdad, Iraq
| | - Fahad Ghabban
- College of Computer Science and Engineering, Taibah University, Medina, Saudi Arabia
| | | | - Sameer Algburi
- Al-Kitab University, College of Engineering Techniques, Kirkuk, Iraq
| |
Collapse
|
14
|
Zhang J, Wang S, Jiang Z, Chen Z, Bai X. CD-Net: Cascaded 3D Dilated convolutional neural network for pneumonia lesion segmentation. Comput Biol Med 2024; 173:108311. [PMID: 38513395 DOI: 10.1016/j.compbiomed.2024.108311] [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: 09/25/2023] [Revised: 02/22/2024] [Accepted: 03/12/2024] [Indexed: 03/23/2024]
Abstract
COVID-19 is a global pandemic that has caused significant global, social, and economic disruption. To effectively assist in screening and monitoring diagnosed cases, it is crucial to accurately segment lesions from Computer Tomography (CT) scans. Due to the lack of labeled data and the presence of redundant parameters in 3D CT, there are still significant challenges in diagnosing COVID-19 in related fields. To address the problem, we have developed a new model called the Cascaded 3D Dilated convolutional neural network (CD-Net) for directly processing CT volume data. To reduce memory consumption when cutting volume data into small patches, we initially design a cascade architecture in CD-Net to preserve global information. Then, we construct a Multi-scale Parallel Dilated Convolution (MPDC) block to aggregate features of different sizes and simultaneously reduce the parameters. Moreover, to alleviate the shortage of labeled data, we employ classical transfer learning, which requires only a small amount of data while achieving better performance. Experimental results conducted on the different public-available datasets verify that the proposed CD-Net has reduced the negative-positive ratio and outperformed other existing segmentation methods while requiring less data.
Collapse
Affiliation(s)
- Jinli Zhang
- Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China.
| | - Shaomeng Wang
- Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China.
| | - Zongli Jiang
- Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China.
| | - Zhijie Chen
- Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China.
| | - Xiaolu Bai
- Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China.
| |
Collapse
|
15
|
Yin X, Zhu W, Tang X, Yang G, Zhao X, Zhao K, Jiang L, Li X, Zhao H, Wang X, Yan Y, Xing L, Yu J, Meng X, Zhao H. Phase I/II clinical trial of efficacy and safety of EGCG oxygen nebulization inhalation in the treatment of COVID-19 pneumonia patients with cancer. BMC Cancer 2024; 24:486. [PMID: 38632501 PMCID: PMC11022442 DOI: 10.1186/s12885-024-12228-3] [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: 11/14/2023] [Accepted: 04/05/2024] [Indexed: 04/19/2024] Open
Abstract
BACKGROUND The antiviral drug Nirmatrelvir was found to be a key drug in controlling the progression of pneumonia during the infectious phase of COVID-19. However, there are very few options for effective treatment for cancer patients who have viral pneumonia. Glucocorticoids is one of the effective means to control pneumonia, but there are many adverse events. EGCG is a natural low toxic compound with anti-inflammatory function. Thus, this study was designed to investigate the safety and efficacy of epigallocatechin-3-gallate (EGCG) aerosol to control COVID-19 pneumonia in cancer populations. METHODS The study was designed as a prospective, single-arm, open-label phase I/II trial at Shandong Cancer Hospital and Institute, between January 5, 2023 to March 31,2023 with viral pneumonia on radiographic signs after confirmed novel coronavirus infection. These patients were treated with EGCG nebulization 10 ml three times daily for at least seven days. EGCG concentrations were increased from 1760-8817umol/L to 4 levels with dose escalation following a standard Phase I design of 3-6 patients per level. Any grade adverse event caused by EGCG was considered a dose-limiting toxicity (DLT). The maximum tolerated dose (MTD) is defined as the highest dose with less than one-third of patients experiencing dose limiting toxicity (DLT) due to EGCG. The primary end points were the toxicity of EGCG and CT findings, and the former was graded by Common Terminology Criteria for Adverse Events (CTCAE) v. 5.0. The secondary end point was the laboratory parameters before and after treatment. RESULT A total of 60 patients with high risk factors for severe COVID-19 pneumonia (factors such as old age, smoking and combined complications)were included in this phase I-II study. The 54 patients in the final analysis were pathologically confirmed to have tumor burden and completed the whole course of treatment. A patient with bucking at a level of 1760 umol/L and no acute toxicity associated with EGCG has been reported at the second or third dose gradients. At dose escalation to 8817umol/L, Grade 1 adverse events of nausea and stomach discomfort occurred in two patients, which resolved spontaneously within 1 hour. After one week of treatment, CT showed that the incidence of non-progression of pneumonia was 82% (32/39), and the improvement rate of pneumonia was 56.4% (22/39). There was no significant difference in inflammation-related laboratory parameters (white blood cell count, lymphocyte count, IL-6, ferritin, C-reactive protein and lactate dehydrogenase) before and after treatment. CONCLUSION Aerosol inhalation of EGCG is well tolerated, and preliminary investigation in cancer population suggests that EGCG may be effective in COVID-19-induced pneumonia, which can promote the improvement of patients with moderate pneumonia or prevent them from developing into severe pneumonia. TRIAL REGISTRATION ClinicalTrials.gov Identifier: NCT05758571. Date of registration: 8 February 2023.
Collapse
Affiliation(s)
- Xiaoyan Yin
- Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University, Shandong Academy of Medical Sciences, Jiyan Road 440, 250117, Jinan, Shandong, China
| | - Wanqi Zhu
- Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University, Shandong Academy of Medical Sciences, Jiyan Road 440, 250117, Jinan, Shandong, China
| | - Xiaoyong Tang
- Department of Medical Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University, Shandong Academy of Medical Science, 250117, Jinan, Shandong Province, China
| | - Guangjian Yang
- Department of Medical Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University, Shandong Academy of Medical Science, 250117, Jinan, Shandong Province, China
| | - Xianguang Zhao
- Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University, Shandong Academy of Medical Sciences, Jiyan Road 440, 250117, Jinan, Shandong, China
| | - Kaikai Zhao
- Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University, Shandong Academy of Medical Sciences, Jiyan Road 440, 250117, Jinan, Shandong, China
| | - Liyang Jiang
- Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University, Shandong Academy of Medical Sciences, Jiyan Road 440, 250117, Jinan, Shandong, China
| | - Xiaolin Li
- Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University, Shandong Academy of Medical Sciences, Jiyan Road 440, 250117, Jinan, Shandong, China
| | - Hong Zhao
- Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University, Shandong Academy of Medical Sciences, Jiyan Road 440, 250117, Jinan, Shandong, China
| | - Xin Wang
- Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University, Shandong Academy of Medical Sciences, Jiyan Road 440, 250117, Jinan, Shandong, China
| | - Yuanyuan Yan
- Department of Radiology, Shandong Cancer Hospital and Institute, Shandong First Medical University, Shandong Academy of Medical Science, 250117, Jinan, Shandong Province, China
| | - Ligang Xing
- Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University, Shandong Academy of Medical Sciences, Jiyan Road 440, 250117, Jinan, Shandong, China
| | - Jinming Yu
- Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University, Shandong Academy of Medical Sciences, Jiyan Road 440, 250117, Jinan, Shandong, China
| | - Xiangjiao Meng
- Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University, Shandong Academy of Medical Sciences, Jiyan Road 440, 250117, Jinan, Shandong, China.
| | - Hanxi Zhao
- Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University, Shandong Academy of Medical Sciences, Jiyan Road 440, 250117, Jinan, Shandong, China.
| |
Collapse
|
16
|
Kabir MM, Mridha M, Rahman A, Hamid MA, Monowar MM. Detection of COVID-19, pneumonia, and tuberculosis from radiographs using AI-driven knowledge distillation. Heliyon 2024; 10:e26801. [PMID: 38444490 PMCID: PMC10912466 DOI: 10.1016/j.heliyon.2024.e26801] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/10/2023] [Revised: 01/30/2024] [Accepted: 02/20/2024] [Indexed: 03/07/2024] Open
Abstract
Chest radiography is an essential diagnostic tool for respiratory diseases such as COVID-19, pneumonia, and tuberculosis because it accurately depicts the structures of the chest. However, accurate detection of these diseases from radiographs is a complex task that requires the availability of medical imaging equipment and trained personnel. Conventional deep learning models offer a viable automated solution for this task. However, the high complexity of these models often poses a significant obstacle to their practical deployment within automated medical applications, including mobile apps, web apps, and cloud-based platforms. This study addresses and resolves this dilemma by reducing the complexity of neural networks using knowledge distillation techniques (KDT). The proposed technique trains a neural network on an extensive collection of chest X-ray images and propagates the knowledge to a smaller network capable of real-time detection. To create a comprehensive dataset, we have integrated three popular chest radiograph datasets with chest radiographs for COVID-19, pneumonia, and tuberculosis. Our experiments show that this knowledge distillation approach outperforms conventional deep learning methods in terms of computational complexity and performance for real-time respiratory disease detection. Specifically, our system achieves an impressive average accuracy of 0.97, precision of 0.94, and recall of 0.97.
Collapse
Affiliation(s)
- Md Mohsin Kabir
- Department of Computer Science & Engineering, Bangladesh University of Business & Technology, Dhaka-1216, Bangladesh
| | - M.F. Mridha
- Department of Computer Science, American International University-Bangladesh, Dhaka-1229, Bangladesh
| | - Ashifur Rahman
- Department of Computer Science & Engineering, Bangladesh University of Business & Technology, Dhaka-1216, Bangladesh
| | - Md. Abdul Hamid
- Department of Information Technology, Faculty of Computing & Information Technology, King Abdulaziz University, Jeddah-21589, Kingdom of Saudi Arabia
| | - Muhammad Mostafa Monowar
- Department of Information Technology, Faculty of Computing & Information Technology, King Abdulaziz University, Jeddah-21589, Kingdom of Saudi Arabia
| |
Collapse
|
17
|
Ahmed F, Abbas S, Athar A, Shahzad T, Khan WA, Alharbi M, Khan MA, Ahmed A. Identification of kidney stones in KUB X-ray images using VGG16 empowered with explainable artificial intelligence. Sci Rep 2024; 14:6173. [PMID: 38486010 PMCID: PMC10940612 DOI: 10.1038/s41598-024-56478-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/19/2023] [Accepted: 03/06/2024] [Indexed: 03/18/2024] Open
Abstract
A kidney stone is a solid formation that can lead to kidney failure, severe pain, and reduced quality of life from urinary system blockages. While medical experts can interpret kidney-ureter-bladder (KUB) X-ray images, specific images pose challenges for human detection, requiring significant analysis time. Consequently, developing a detection system becomes crucial for accurately classifying KUB X-ray images. This article applies a transfer learning (TL) model with a pre-trained VGG16 empowered with explainable artificial intelligence (XAI) to establish a system that takes KUB X-ray images and accurately categorizes them as kidney stones or normal cases. The findings demonstrate that the model achieves a testing accuracy of 97.41% in identifying kidney stones or normal KUB X-rays in the dataset used. VGG16 model delivers highly accurate predictions but lacks fairness and explainability in their decision-making process. This study incorporates the Layer-Wise Relevance Propagation (LRP) technique, an explainable artificial intelligence (XAI) technique, to enhance the transparency and effectiveness of the model to address this concern. The XAI technique, specifically LRP, increases the model's fairness and transparency, facilitating human comprehension of the predictions. Consequently, XAI can play an important role in assisting doctors with the accurate identification of kidney stones, thereby facilitating the execution of effective treatment strategies.
Collapse
Affiliation(s)
- Fahad Ahmed
- School of Computer Science, National College of Business Administration and Economics, Lahore, 54000, Pakistan
| | - Sagheer Abbas
- Department of Computer Sciences, Bahria University, Lahore Campus, Lahore, 54000, Pakistan
| | - Atifa Athar
- Department of Computer Science, Comsats University Islamabad, Lahore Campus, Lahore, 54000, Pakistan
| | - Tariq Shahzad
- Department of Computer Sciences, COMSATS University Islamabad, Sahiwal Campus, Sahiwal, 57000, Pakistan
| | - Wasim Ahmad Khan
- School of Computer Science, National College of Business Administration and Economics, Lahore, 54000, Pakistan
| | - Meshal Alharbi
- Department of Computer Science, College of Computer Engineering and Sciences, Prince Sattam Bin Abdulaziz University, 11942, Alkharj, Saudi Arabia
| | - Muhammad Adnan Khan
- School of Computing, Skyline University College, University City Sharjah, 1797, Sharjah, UAE.
- Department of Software, Faculty of Artificial Intelligence and Software, Gachon University, Seongnam-si, 13120, Republic of Korea.
- Riphah School of Computing and Innovation, Faculty of Computing, Riphah International University, Lahore Campus, Lahore, 54000, Pakistan.
| | - Arfan Ahmed
- AI Center for Precision Health, Weill Cornell Medicine-Qatar, Doha, Qatar.
| |
Collapse
|
18
|
Schoonhoven R, Skorikov A, Palenstijn WJ, Pelt DM, Hendriksen AA, Batenburg KJ. How auto-differentiation can improve CT workflows: classical algorithms in a modern framework. OPTICS EXPRESS 2024; 32:9019-9041. [PMID: 38571146 DOI: 10.1364/oe.502920] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/08/2023] [Accepted: 01/09/2024] [Indexed: 04/05/2024]
Abstract
Many of the recent successes of deep learning-based approaches have been enabled by a framework of flexible, composable computational blocks with their parameters adjusted through an automatic differentiation mechanism to implement various data processing tasks. In this work, we explore how the same philosophy can be applied to existing "classical" (i.e., non-learning) algorithms, focusing on computed tomography (CT) as application field. We apply four key design principles of this approach for CT workflow design: end-to-end optimization, explicit quality criteria, declarative algorithm construction by building the forward model, and use of existing classical algorithms as computational blocks. Through four case studies, we demonstrate that auto-differentiation is remarkably effective beyond the boundaries of neural-network training, extending to CT workflows containing varied combinations of classical and machine learning algorithms.
Collapse
|
19
|
Ju H, Cui Y, Su Q, Juan L, Manavalan B. CODENET: A deep learning model for COVID-19 detection. Comput Biol Med 2024; 171:108229. [PMID: 38447500 DOI: 10.1016/j.compbiomed.2024.108229] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/11/2023] [Revised: 02/20/2024] [Accepted: 02/25/2024] [Indexed: 03/08/2024]
Abstract
Conventional COVID-19 testing methods have some flaws: they are expensive and time-consuming. Chest X-ray (CXR) diagnostic approaches can alleviate these flaws to some extent. However, there is no accurate and practical automatic diagnostic framework with good interpretability. The application of artificial intelligence (AI) technology to medical radiography can help to accurately detect the disease, reduce the burden on healthcare organizations, and provide good interpretability. Therefore, this study proposes a new deep neural network (CNN) based on CXR for COVID-19 diagnosis - CodeNet. This method uses contrastive learning to make full use of latent image data to enhance the model's ability to extract features and generalize across different data domains. On the evaluation dataset, the proposed method achieves an accuracy as high as 94.20%, outperforming several other existing methods used for comparison. Ablation studies validate the efficacy of the proposed method, while interpretability analysis shows that the method can effectively guide clinical professionals. This work demonstrates the superior detection performance of a CNN using contrastive learning techniques on CXR images, paving the way for computer vision and artificial intelligence technologies to leverage massive medical data for disease diagnosis.
Collapse
Affiliation(s)
- Hong Ju
- Heilongjiang Agricultural Engineering Vocational College, China
| | - Yanyan Cui
- Beidahuang Industry Group General Hospital, Harbin, China
| | - Qiaosen Su
- Department of Integrative Biotechnology, College of Biotechnology and Bioengineering, Sungkyunkwan University, Suwon, 16419, Gyeonggi-do, Republic of Korea
| | - Liran Juan
- School of Life Science and Technology, Harbin Institute of Technology, Harbin, 150001, China.
| | - Balachandran Manavalan
- Department of Integrative Biotechnology, College of Biotechnology and Bioengineering, Sungkyunkwan University, Suwon, 16419, Gyeonggi-do, Republic of Korea.
| |
Collapse
|
20
|
Asiaee M, Nourbakhsh M, Vahedian-Azimi A, Zare M, Jafari R, Atashi SS, Keramatfar A. The feasibility of using acoustic measures for predicting the Total Opacity Scores of chest computed tomography scans in patients with COVID-19. CLINICAL LINGUISTICS & PHONETICS 2024; 38:97-115. [PMID: 36592050 DOI: 10.1080/02699206.2022.2160659] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/30/2021] [Revised: 12/10/2022] [Accepted: 12/13/2022] [Indexed: 06/17/2023]
Abstract
To study the possibility of using acoustic parameters, i.e., Acoustic Voice Quality Index (AVQI) and Maximum Phonation Time (MPT) for predicting the degree of lung involvement in COVID-19 patients. This cross-sectional case-control study was conducted on the voice samples collected from 163 healthy individuals and 181 patients with COVID-19. Each participant produced a sustained vowel/a/, and a phonetically balanced Persian text containing 36 syllables. AVQI and MPT were measured using Praat scripts. Each patient underwent a non-enhanced chest computed tomographic scan and the Total Opacity score was rated to assess the degree of lung involvement. The results revealed significant differences between patients with COVID-19 and healthy individuals in terms of AVQI and MPT. A significant difference was also observed between male and female participants in AVQI and MPT. The results from the receiver operating characteristic curve analysis and area under the curve indicated that MPT (0.909) had higher diagnostic accuracy than AVQI (0.771). A significant relationship was observed between AVQI and TO scores. In the case of MPT, however, no such relationship was observed. The findings indicated that MPT was a better classifier in differentiating patients from healthy individuals, in comparison with AVQI. The results also showed that AVQI can be used as a predictor of the degree of patients' and recovered individuals' lung involvement. A formula is suggested for calculating the degree of lung involvement using AVQI.
Collapse
Affiliation(s)
- Maral Asiaee
- Department of Linguistics, Faculty of Literature, Alzahra University, Tehran, Iran
| | - Mandana Nourbakhsh
- Department of Linguistics, Faculty of Literature, Alzahra University, Tehran, Iran
| | - Amir Vahedian-Azimi
- Trauma Research Center, Nursing faculty, Baqiyatallah University of Medical Sciences, Tehran, Iran
| | - Mohammad Zare
- Department of Statistics, Faculty of Mathematics and Computer Science, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran
| | - Ramezan Jafari
- Department of Radiology, Health Research Center, Lifestyle Institute, Baqiyatallah University of Medical Sciences, Tehran, Iran
| | - Seyed Shahab Atashi
- Department of Food and Drug control, Jundishapour University of Medical Sciences, Ahvaz, Iran
| | | |
Collapse
|
21
|
Ali MU, Zafar A, Tanveer J, Khan MA, Kim SH, Alsulami MM, Lee SW. Deep learning network selection and optimized information fusion for enhanced COVID‐19 detection. INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY 2024; 34. [DOI: 10.1002/ima.23001] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/09/2023] [Accepted: 11/12/2023] [Indexed: 08/25/2024]
Abstract
AbstractThis study proposes a wrapper‐based technique to improve the classification performance of chest infection (including COVID‐19) detection using X‐rays. Deep features were extracted using pretrained deep learning models. Ten optimization techniques, including poor and rich optimization, path finder algorithm, Henry gas solubility optimization, Harris hawks optimization, atom search optimization, manta‐ray foraging optimization, equilibrium optimizer, slime mold algorithm, generalized normal distribution optimization, and marine predator algorithm, were used to determine the optimal features using a support vector machine. Moreover, a network selection technique was used to select the deep learning models. An online chest infection detection X‐ray scan dataset was used to validate the proposed approach. The results suggest that the proposed wrapper‐based automatic deep learning network selection and feature optimization framework has a high classification rate of 97.7%. The comparative analysis further validates the credibility of the framework in COVID‐19 and other chest infection classifications, suggesting that the proposed approach can help doctors in clinical practice.
Collapse
Affiliation(s)
- Muhammad Umair Ali
- Department of Intelligent Mechatronics Engineering Sejong University Seoul Republic of Korea
| | - Amad Zafar
- Department of Intelligent Mechatronics Engineering Sejong University Seoul Republic of Korea
| | - Jawad Tanveer
- Department of Computer Science and Engineering Sejong University Seoul Republic of Korea
| | | | - Seong Han Kim
- Department of Intelligent Mechatronics Engineering Sejong University Seoul Republic of Korea
| | - Mashael M. Alsulami
- Department of Information Technology, College of Computers and Information Technology Taif University Taif Saudi Arabia
| | - Seung Won Lee
- Department of Precision Medicine Sungkyunkwan University School of Medicine Suwon Republic of Korea
| |
Collapse
|
22
|
Abdulahi AT, Ogundokun RO, Adenike AR, Shah MA, Ahmed YK. PulmoNet: a novel deep learning based pulmonary diseases detection model. BMC Med Imaging 2024; 24:51. [PMID: 38418987 PMCID: PMC10903074 DOI: 10.1186/s12880-024-01227-2] [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: 03/02/2023] [Accepted: 02/11/2024] [Indexed: 03/02/2024] Open
Abstract
Pulmonary diseases are various pathological conditions that affect respiratory tissues and organs, making the exchange of gas challenging for animals inhaling and exhaling. It varies from gentle and self-limiting such as the common cold and catarrh, to life-threatening ones, such as viral pneumonia (VP), bacterial pneumonia (BP), and tuberculosis, as well as a severe acute respiratory syndrome, such as the coronavirus 2019 (COVID-19). The cost of diagnosis and treatment of pulmonary infections is on the high side, most especially in developing countries, and since radiography images (X-ray and computed tomography (CT) scan images) have proven beneficial in detecting various pulmonary infections, many machine learning (ML) models and image processing procedures have been utilized to identify these infections. The need for timely and accurate detection can be lifesaving, especially during a pandemic. This paper, therefore, suggested a deep convolutional neural network (DCNN) founded image detection model, optimized with image augmentation technique, to detect three (3) different pulmonary diseases (COVID-19, bacterial pneumonia, and viral pneumonia). The dataset containing four (4) different classes (healthy (10,325), COVID-19 (3,749), BP (883), and VP (1,478)) was utilized as training/testing data for the suggested model. The model's performance indicates high potential in detecting the three (3) classes of pulmonary diseases. The model recorded average detection accuracy of 94%, 95.4%, 99.4%, and 98.30%, and training/detection time of about 60/50 s. This result indicates the proficiency of the suggested approach when likened to the traditional texture descriptors technique of pulmonary disease recognition utilizing X-ray and CT scan images. This study introduces an innovative deep convolutional neural network model to enhance the detection of pulmonary diseases like COVID-19 and pneumonia using radiography. This model, notable for its accuracy and efficiency, promises significant advancements in medical diagnostics, particularly beneficial in developing countries due to its potential to surpass traditional diagnostic methods.
Collapse
Affiliation(s)
- AbdulRahman Tosho Abdulahi
- Department of Computer Science, Institute of Information and Communication Technology, Kwara State Polytechnic, Ilorin, Nigeria
| | - Roseline Oluwaseun Ogundokun
- Department of Multimedia Engineering, Kaunas University of Technology, Kaunas, Lithuania
- Department of Computer Science, Landmark University Omu Aran, Omu Aran, Nigeria
| | - Ajiboye Raimot Adenike
- Department of Statistics, Institute of Applied Sciences, Kwara State Polytechnic, Ilorin, Nigeria
| | - Mohd Asif Shah
- Department of Economics, Kebri Dehar University, Kebri Dehar, 250, Somali, Ethiopia.
- Centre of Research Impact and Outcome, Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, Punjab, 140401, India.
- Chitkara Centre for Research and Development, Chitkara University, Baddi, Himachal Pradesh, 174103, India.
| | - Yusuf Kola Ahmed
- Department of Biomedical Engineering, University of Ilorin, Ilorin, Nigeria
- Department of Occupational Therapy, University of Alberta, Edmonton, Canada
| |
Collapse
|
23
|
Yin M, Xu C, Zhu J, Xue Y, Zhou Y, He Y, Lin J, Liu L, Gao J, Liu X, Shen D, Fu C. Automated machine learning for the identification of asymptomatic COVID-19 carriers based on chest CT images. BMC Med Imaging 2024; 24:50. [PMID: 38413923 PMCID: PMC10900643 DOI: 10.1186/s12880-024-01211-w] [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: 05/11/2023] [Accepted: 01/24/2024] [Indexed: 02/29/2024] Open
Abstract
BACKGROUND Asymptomatic COVID-19 carriers with normal chest computed tomography (CT) scans have perpetuated the ongoing pandemic of this disease. This retrospective study aimed to use automated machine learning (AutoML) to develop a prediction model based on CT characteristics for the identification of asymptomatic carriers. METHODS Asymptomatic carriers were from Yangzhou Third People's Hospital from August 1st, 2020, to March 31st, 2021, and the control group included a healthy population from a nonepizootic area with two negative RT‒PCR results within 48 h. All CT images were preprocessed using MATLAB. Model development and validation were conducted in R with the H2O package. The models were built based on six algorithms, e.g., random forest and deep neural network (DNN), and a training set (n = 691). The models were improved by automatically adjusting hyperparameters for an internal validation set (n = 306). The performance of the obtained models was evaluated based on a dataset from Suzhou (n = 178) using the area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and F1 score. RESULTS A total of 1,175 images were preprocessed with high stability. Six models were developed, and the performance of the DNN model ranked first, with an AUC value of 0.898 for the test set. The sensitivity, specificity, PPV, NPV, F1 score and accuracy of the DNN model were 0.820, 0.854, 0.849, 0.826, 0.834 and 0.837, respectively. A plot of a local interpretable model-agnostic explanation demonstrated how different variables worked in identifying asymptomatic carriers. CONCLUSIONS Our study demonstrates that AutoML models based on CT images can be used to identify asymptomatic carriers. The most promising model for clinical implementation is the DNN-algorithm-based model.
Collapse
Affiliation(s)
- Minyue Yin
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, 215006, Suzhou, Jiangsu, China
- Suzhou Clinical Center of Digestive Diseases, 215006, Suzhou, Jiangsu, China
| | - Chao Xu
- Department of Radiotherapy, The First Affiliated Hospital of Soochow University, 215006, Suzhou, Jiangsu, China
| | - Jinzhou Zhu
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, 215006, Suzhou, Jiangsu, China
- The 23th ward, Yangzhou Third People's Hospital, 225000, Yangzhou, Jiangsu, China
- Suzhou Clinical Center of Digestive Diseases, 215006, Suzhou, Jiangsu, China
| | - Yuhan Xue
- Medical School, Soochow University, 215006, Suzhou, Jiangsu, China
| | - Yijia Zhou
- Medical School, Soochow University, 215006, Suzhou, Jiangsu, China
| | - Yu He
- Medical School, Soochow University, 215006, Suzhou, Jiangsu, China
| | - Jiaxi Lin
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, 215006, Suzhou, Jiangsu, China
- Suzhou Clinical Center of Digestive Diseases, 215006, Suzhou, Jiangsu, China
| | - Lu Liu
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, 215006, Suzhou, Jiangsu, China
- Suzhou Clinical Center of Digestive Diseases, 215006, Suzhou, Jiangsu, China
| | - Jingwen Gao
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, 215006, Suzhou, Jiangsu, China
- Suzhou Clinical Center of Digestive Diseases, 215006, Suzhou, Jiangsu, China
| | - Xiaolin Liu
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, 215006, Suzhou, Jiangsu, China
- Suzhou Clinical Center of Digestive Diseases, 215006, Suzhou, Jiangsu, China
| | - Dan Shen
- Department of Respiratory Medicine, The First Affiliated Hospital of Soochow University, 215006, Suzhou, Jiangsu, China.
| | - Cuiping Fu
- Department of Respiratory Medicine, The First Affiliated Hospital of Soochow University, 215006, Suzhou, Jiangsu, China.
| |
Collapse
|
24
|
Baddal B, Taner F, Uzun Ozsahin D. Harnessing of Artificial Intelligence for the Diagnosis and Prevention of Hospital-Acquired Infections: A Systematic Review. Diagnostics (Basel) 2024; 14:484. [PMID: 38472956 DOI: 10.3390/diagnostics14050484] [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: 12/16/2023] [Revised: 01/23/2024] [Accepted: 02/19/2024] [Indexed: 03/14/2024] Open
Abstract
Healthcare-associated infections (HAIs) are the most common adverse events in healthcare and constitute a major global public health concern. Surveillance represents the foundation for the effective prevention and control of HAIs, yet conventional surveillance is costly and labor intensive. Artificial intelligence (AI) and machine learning (ML) have the potential to support the development of HAI surveillance algorithms for the understanding of HAI risk factors, the improvement of patient risk stratification as well as the prediction and timely detection and prevention of infections. AI-supported systems have so far been explored for clinical laboratory testing and imaging diagnosis, antimicrobial resistance profiling, antibiotic discovery and prediction-based clinical decision support tools in terms of HAIs. This review aims to provide a comprehensive summary of the current literature on AI applications in the field of HAIs and discuss the future potentials of this emerging technology in infection practice. Following the PRISMA guidelines, this study examined the articles in databases including PubMed and Scopus until November 2023, which were screened based on the inclusion and exclusion criteria, resulting in 162 included articles. By elucidating the advancements in the field, we aim to highlight the potential applications of AI in the field, report related issues and shortcomings and discuss the future directions.
Collapse
Affiliation(s)
- Buket Baddal
- Department of Medical Microbiology and Clinical Microbiology, Faculty of Medicine, Near East University, North Cyprus, Mersin 10, 99138 Nicosia, Turkey
- DESAM Research Institute, Near East University, North Cyprus, Mersin 10, 99138 Nicosia, Turkey
| | - Ferdiye Taner
- Department of Medical Microbiology and Clinical Microbiology, Faculty of Medicine, Near East University, North Cyprus, Mersin 10, 99138 Nicosia, Turkey
- DESAM Research Institute, Near East University, North Cyprus, Mersin 10, 99138 Nicosia, Turkey
| | - Dilber Uzun Ozsahin
- Department of Medical Diagnostic Imaging, College of Health Science, University of Sharjah, Sharjah 27272, United Arab Emirates
- Research Institute for Medical and Health Sciences, University of Sharjah, Sharjah 27272, United Arab Emirates
- Operational Research Centre in Healthcare, Near East University, North Cyprus, Mersin 10, 99138 Nicosia, Turkey
| |
Collapse
|
25
|
Chatterjee S, Saad F, Sarasaen C, Ghosh S, Krug V, Khatun R, Mishra R, Desai N, Radeva P, Rose G, Stober S, Speck O, Nürnberger A. Exploration of Interpretability Techniques for Deep COVID-19 Classification Using Chest X-ray Images. J Imaging 2024; 10:45. [PMID: 38392093 PMCID: PMC10889835 DOI: 10.3390/jimaging10020045] [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: 01/08/2024] [Revised: 01/24/2024] [Accepted: 02/05/2024] [Indexed: 02/24/2024] Open
Abstract
The outbreak of COVID-19 has shocked the entire world with its fairly rapid spread, and has challenged different sectors. One of the most effective ways to limit its spread is the early and accurate diagnosing of infected patients. Medical imaging, such as X-ray and computed tomography (CT), combined with the potential of artificial intelligence (AI), plays an essential role in supporting medical personnel in the diagnosis process. Thus, in this article, five different deep learning models (ResNet18, ResNet34, InceptionV3, InceptionResNetV2, and DenseNet161) and their ensemble, using majority voting, have been used to classify COVID-19, pneumoniæ and healthy subjects using chest X-ray images. Multilabel classification was performed to predict multiple pathologies for each patient, if present. Firstly, the interpretability of each of the networks was thoroughly studied using local interpretability methods-occlusion, saliency, input X gradient, guided backpropagation, integrated gradients, and DeepLIFT-and using a global technique-neuron activation profiles. The mean micro F1 score of the models for COVID-19 classifications ranged from 0.66 to 0.875, and was 0.89 for the ensemble of the network models. The qualitative results showed that the ResNets were the most interpretable models. This research demonstrates the importance of using interpretability methods to compare different models before making a decision regarding the best performing model.
Collapse
Affiliation(s)
- Soumick Chatterjee
- Data and Knowledge Engineering Group, Otto von Guericke University, 39106 Magdeburg, Germany
- Faculty of Computer Science, Otto von Guericke University, 39106 Magdeburg, Germany
- Genomics Research Centre, Human Technopole, 20157 Milan, Italy
| | - Fatima Saad
- Institute for Medical Engineering, Otto von Guericke University, 39106 Magdeburg, Germany
- Research Campus STIMULATE, Otto von Guericke University, 39106 Magdeburg, Germany
| | - Chompunuch Sarasaen
- Institute for Medical Engineering, Otto von Guericke University, 39106 Magdeburg, Germany
- Research Campus STIMULATE, Otto von Guericke University, 39106 Magdeburg, Germany
- Biomedical Magnetic Resonance, Otto von Guericke University, 39106 Magdeburg, Germany
| | - Suhita Ghosh
- Faculty of Computer Science, Otto von Guericke University, 39106 Magdeburg, Germany
- Artificial Intelligence Lab, Otto von Guericke University, 39106 Magdeburg, Germany
| | - Valerie Krug
- Faculty of Computer Science, Otto von Guericke University, 39106 Magdeburg, Germany
- Artificial Intelligence Lab, Otto von Guericke University, 39106 Magdeburg, Germany
| | - Rupali Khatun
- Department of Mathematics and Computer Science, University of Barcelona, 08028 Barcelona, Spain
- Translational Radiobiology, Department of Radiation Oncology, Universitätsklinikum Erlangen, 91054 Erlangen, Germany
| | | | | | - Petia Radeva
- Department of Mathematics and Computer Science, University of Barcelona, 08028 Barcelona, Spain
- Computer Vision Centre, 08193 Cerdanyola, Spain
| | - Georg Rose
- Institute for Medical Engineering, Otto von Guericke University, 39106 Magdeburg, Germany
- Research Campus STIMULATE, Otto von Guericke University, 39106 Magdeburg, Germany
- Centre for Behavioural Brain Sciences, 39106 Magdeburg, Germany
| | - Sebastian Stober
- Faculty of Computer Science, Otto von Guericke University, 39106 Magdeburg, Germany
- Artificial Intelligence Lab, Otto von Guericke University, 39106 Magdeburg, Germany
| | - Oliver Speck
- Research Campus STIMULATE, Otto von Guericke University, 39106 Magdeburg, Germany
- Biomedical Magnetic Resonance, Otto von Guericke University, 39106 Magdeburg, Germany
- Centre for Behavioural Brain Sciences, 39106 Magdeburg, Germany
- German Centre for Neurodegenerative Diseases, 39106 Magdeburg, Germany
| | - Andreas Nürnberger
- Data and Knowledge Engineering Group, Otto von Guericke University, 39106 Magdeburg, Germany
- Faculty of Computer Science, Otto von Guericke University, 39106 Magdeburg, Germany
- Centre for Behavioural Brain Sciences, 39106 Magdeburg, Germany
| |
Collapse
|
26
|
Roy R, Mazumdar S, Chowdhury AS. ADGAN: Attribute-Driven Generative Adversarial Network for Synthesis and Multiclass Classification of Pulmonary Nodules. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024; 35:2484-2495. [PMID: 35853058 DOI: 10.1109/tnnls.2022.3190331] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Lung cancer is the leading cause of cancer-related deaths worldwide. According to the American Cancer Society, early diagnosis of pulmonary nodules in computed tomography (CT) scans can improve the five-year survival rate up to 70% with proper treatment planning. In this article, we propose an attribute-driven Generative Adversarial Network (ADGAN) for synthesis and multiclass classification of Pulmonary Nodules. A self-attention U-Net (SaUN) architecture is proposed to improve the generation mechanism of the network. The generator is designed with two modules, namely, self-attention attribute module (SaAM) and a self-attention spatial module (SaSM). SaAM generates a nodule image based on given attributes whereas SaSM specifies the nodule region of the input image to be altered. A reconstruction loss along with an attention localization loss (AL) is used to produce an attention map prioritizing the nodule regions. To avoid resemblance between a generated image and a real image, we further introduce an adversarial loss containing a regularization term based on KL divergence. The discriminator part of the proposed model is designed to achieve the multiclass nodule classification task. Our proposed approach is validated over two challenging publicly available datasets, namely LIDC-IDRI and LUNGX. Exhaustive experimentation on these two datasets clearly indicate that we have achieved promising classification accuracy as compared to other state-of-the-art methods.
Collapse
|
27
|
Haque SBU, Zafar A. Robust Medical Diagnosis: A Novel Two-Phase Deep Learning Framework for Adversarial Proof Disease Detection in Radiology Images. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024; 37:308-338. [PMID: 38343214 PMCID: PMC11266337 DOI: 10.1007/s10278-023-00916-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/31/2023] [Revised: 09/23/2023] [Accepted: 10/08/2023] [Indexed: 03/02/2024]
Abstract
In the realm of medical diagnostics, the utilization of deep learning techniques, notably in the context of radiology images, has emerged as a transformative force. The significance of artificial intelligence (AI), specifically machine learning (ML) and deep learning (DL), lies in their capacity to rapidly and accurately diagnose diseases from radiology images. This capability has been particularly vital during the COVID-19 pandemic, where rapid and precise diagnosis played a pivotal role in managing the spread of the virus. DL models, trained on vast datasets of radiology images, have showcased remarkable proficiency in distinguishing between normal and COVID-19-affected cases, offering a ray of hope amidst the crisis. However, as with any technological advancement, vulnerabilities emerge. Deep learning-based diagnostic models, although proficient, are not immune to adversarial attacks. These attacks, characterized by carefully crafted perturbations to input data, can potentially disrupt the models' decision-making processes. In the medical context, such vulnerabilities could have dire consequences, leading to misdiagnoses and compromised patient care. To address this, we propose a two-phase defense framework that combines advanced adversarial learning and adversarial image filtering techniques. We use a modified adversarial learning algorithm to enhance the model's resilience against adversarial examples during the training phase. During the inference phase, we apply JPEG compression to mitigate perturbations that cause misclassification. We evaluate our approach on three models based on ResNet-50, VGG-16, and Inception-V3. These models perform exceptionally in classifying radiology images (X-ray and CT) of lung regions into normal, pneumonia, and COVID-19 pneumonia categories. We then assess the vulnerability of these models to three targeted adversarial attacks: fast gradient sign method (FGSM), projected gradient descent (PGD), and basic iterative method (BIM). The results show a significant drop in model performance after the attacks. However, our defense framework greatly improves the models' resistance to adversarial attacks, maintaining high accuracy on adversarial examples. Importantly, our framework ensures the reliability of the models in diagnosing COVID-19 from clean images.
Collapse
Affiliation(s)
- Sheikh Burhan Ul Haque
- Department of Computer Science, Aligarh Muslim University, Uttar Pradesh, Aligarh, 202002, India.
| | - Aasim Zafar
- Department of Computer Science, Aligarh Muslim University, Uttar Pradesh, Aligarh, 202002, India
| |
Collapse
|
28
|
Appel JM. Artificial intelligence in medicine and the negative outcome penalty paradox. JOURNAL OF MEDICAL ETHICS 2024:jme-2023-109848. [PMID: 38290853 DOI: 10.1136/jme-2023-109848] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/28/2023] [Accepted: 01/18/2024] [Indexed: 02/01/2024]
Abstract
Artificial intelligence (AI) holds considerable promise for transforming clinical diagnostics. While much has been written both about public attitudes toward the use of AI tools in medicine and about uncertainty regarding legal liability that may be delaying its adoption, the interface of these two issues has so far drawn less attention. However, understanding this interface is essential to determining how jury behaviour is likely to influence adoption of AI by physicians. One distinctive concern identified in this paper is a 'negative outcome penalty paradox' (NOPP) in which physicians risk being penalised by juries in cases with negative outcomes, whether they overrule AI determinations or accept them. The paper notes three reasons why AI in medicine is uniquely susceptible to the NOPP and urges serious further consideration of this complex dilemma.
Collapse
Affiliation(s)
- Jacob M Appel
- Psychiatry, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| |
Collapse
|
29
|
Prince R, Niu Z, Khan ZY, Emmanuel M, Patrick N. COVID-19 detection from chest X-ray images using CLAHE-YCrCb, LBP, and machine learning algorithms. BMC Bioinformatics 2024; 25:28. [PMID: 38233764 PMCID: PMC10792799 DOI: 10.1186/s12859-023-05427-5] [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: 02/11/2023] [Accepted: 07/20/2023] [Indexed: 01/19/2024] Open
Abstract
BACKGROUND COVID-19 is a disease that caused a contagious respiratory ailment that killed and infected hundreds of millions. It is necessary to develop a computer-based tool that is fast, precise, and inexpensive to detect COVID-19 efficiently. Recent studies revealed that machine learning and deep learning models accurately detect COVID-19 using chest X-ray (CXR) images. However, they exhibit notable limitations, such as a large amount of data to train, larger feature vector sizes, enormous trainable parameters, expensive computational resources (GPUs), and longer run-time. RESULTS In this study, we proposed a new approach to address some of the above-mentioned limitations. The proposed model involves the following steps: First, we use contrast limited adaptive histogram equalization (CLAHE) to enhance the contrast of CXR images. The resulting images are converted from CLAHE to YCrCb color space. We estimate reflectance from chrominance using the Illumination-Reflectance model. Finally, we use a normalized local binary patterns histogram generated from reflectance (Cr) and YCb as the classification feature vector. Decision tree, Naive Bayes, support vector machine, K-nearest neighbor, and logistic regression were used as the classification algorithms. The performance evaluation on the test set indicates that the proposed approach is superior, with accuracy rates of 99.01%, 100%, and 98.46% across three different datasets, respectively. Naive Bayes, a probabilistic machine learning algorithm, emerged as the most resilient. CONCLUSION Our proposed method uses fewer handcrafted features, affordable computational resources, and less runtime than existing state-of-the-art approaches. Emerging nations where radiologists are in short supply can adopt this prototype. We made both coding materials and datasets accessible to the general public for further improvement. Check the manuscript's availability of the data and materials under the declaration section for access.
Collapse
Affiliation(s)
- Rukundo Prince
- Department of Computer Science and Technology, Beijing Institute of Technology, Beijing, China
| | - Zhendong Niu
- Department of Computer Science and Technology, Beijing Institute of Technology, Beijing, China.
| | - Zahid Younas Khan
- Computer Science and Information Technology, University of Azad Jammu and Kashmir, Kashmir, Pakistan
| | - Masabo Emmanuel
- Software Engineering, African Center of Excellence in Data Science(ACE-DS), and the African Center of Excellence in Internet of Things(ACEIoT), University of Rwanda, Kigali, Rwanda
| | - Niyishaka Patrick
- Computer and Information Sciences, University of Hyderabad, Hyderabad, India
| |
Collapse
|
30
|
Kaur BP, Singh H, Hans R, Sharma SK, Kaushal C, Hassan MM, Shah MA. An augmentation aided concise CNN based architecture for COVID-19 diagnosis in real time. Sci Rep 2024; 14:1136. [PMID: 38212647 PMCID: PMC10784465 DOI: 10.1038/s41598-024-51317-y] [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: 08/28/2023] [Accepted: 01/03/2024] [Indexed: 01/13/2024] Open
Abstract
Over 6.5 million people around the world have lost their lives due to the highly contagious COVID 19 virus. The virus increases the danger of fatal health effects by damaging the lungs severely. The only method to reduce mortality and contain the spread of this disease is by promptly detecting it. Recently, deep learning has become one of the most prominent approaches to CAD, helping surgeons make more informed decisions. But deep learning models are computation hungry and devices with TPUs and GPUs are needed to run these models. The current focus of machine learning research is on developing models that can be deployed on mobile and edge devices. To this end, this research aims to develop a concise convolutional neural network-based computer-aided diagnostic system for detecting the COVID 19 virus in X-ray images, which may be deployed on devices with limited processing resources, such as mobile phones and tablets. The proposed architecture aspires to use the image enhancement in first phase and data augmentation in the second phase for image pre-processing, additionally hyperparameters are also optimized to obtain the optimal parameter settings in the third phase that provide the best results. The experimental analysis has provided empirical evidence of the impact of image enhancement, data augmentation, and hyperparameter tuning on the proposed convolutional neural network model, which increased accuracy from 94 to 98%. Results from the evaluation show that the suggested method gives an accuracy of 98%, which is better than popular transfer learning models like Xception, Resnet50, and Inception.
Collapse
Affiliation(s)
- Balraj Preet Kaur
- Department of Computer Science and Engineering, DAV University, Jalandhar, India
| | - Harpreet Singh
- Department of Computer Science and Engineering, Thapar Institute of Engineering and Technology, Patiala, India
| | - Rahul Hans
- Department of Computer Science and Engineering, DAV University, Jalandhar, India
| | - Sanjeev Kumar Sharma
- Department of Computer Science and Applications, DAV University, Jalandhar, India
| | - Chetna Kaushal
- Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab, 140401, India
| | - Md Mehedi Hassan
- Computer Science and Engineering Discipline, Khulna University, Khulna, 9208, Bangladesh
| | - Mohd Asif Shah
- Department of Economics, Kebri Dehar University, Kebri Dehar, 250, Ethiopia.
- Centre of Research Impact and Outcome, Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, 140401, Punjab, India.
- Division of Research and Development, Lovely Professional University, Phagwara, 144001, Punjab, India.
| |
Collapse
|
31
|
Hussein AM, Sharifai AG, Alia OM, Abualigah L, Almotairi KH, Abujayyab SKM, Gandomi AH. Auto-detection of the coronavirus disease by using deep convolutional neural networks and X-ray photographs. Sci Rep 2024; 14:534. [PMID: 38177156 PMCID: PMC10766625 DOI: 10.1038/s41598-023-47038-3] [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: 05/02/2023] [Accepted: 11/08/2023] [Indexed: 01/06/2024] Open
Abstract
The most widely used method for detecting Coronavirus Disease 2019 (COVID-19) is real-time polymerase chain reaction. However, this method has several drawbacks, including high cost, lengthy turnaround time for results, and the potential for false-negative results due to limited sensitivity. To address these issues, additional technologies such as computed tomography (CT) or X-rays have been employed for diagnosing the disease. Chest X-rays are more commonly used than CT scans due to the widespread availability of X-ray machines, lower ionizing radiation, and lower cost of equipment. COVID-19 presents certain radiological biomarkers that can be observed through chest X-rays, making it necessary for radiologists to manually search for these biomarkers. However, this process is time-consuming and prone to errors. Therefore, there is a critical need to develop an automated system for evaluating chest X-rays. Deep learning techniques can be employed to expedite this process. In this study, a deep learning-based method called Custom Convolutional Neural Network (Custom-CNN) is proposed for identifying COVID-19 infection in chest X-rays. The Custom-CNN model consists of eight weighted layers and utilizes strategies like dropout and batch normalization to enhance performance and reduce overfitting. The proposed approach achieved a classification accuracy of 98.19% and aims to accurately classify COVID-19, normal, and pneumonia samples.
Collapse
Affiliation(s)
- Ahmad MohdAziz Hussein
- Department of Computer Science, Faculty of Information Technology, Middle East University, Amman, Jordan.
| | - Abdulrauf Garba Sharifai
- Department of Computer Sciences, Yusuf Maitama Sule University, Kofar Nassarawa, Kano, 700222, Nigeria
| | - Osama Moh'd Alia
- Department of Computer Science, Faculty of Computes and Information Technology, University of Tabuk, 71491, Tabuk, Saudi Arabia
| | - Laith Abualigah
- Computer Science Department, Prince Hussein Bin Abdullah Faculty for Information Technology, Al Al-Bayt University, Mafraq, 25113, Jordan
- Department of Electrical and Computer Engineering, Lebanese American University, Byblos, 13-5053, Lebanon
- Hourani Center for Applied Scientific Research, Al-Ahliyya Amman University, Amman, 19328, Jordan
- Applied Science Research Center, Applied Science Private University, Amman, 11931, Jordan
- School of Engineering and Technology, Sunway University Malaysia, 27500, Petaling Jaya, Malaysia
- School of Computer Sciences, Universiti Sains Malaysia, 11800, Pulau Pinang, Malaysia
| | - Khaled H Almotairi
- Computer Engineering Department, Computer and Information Systems College, Umm Al-Qura University, 21955, Makkah, Saudi Arabia
| | | | - Amir H Gandomi
- Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW, 2007, Australia.
- University Research and Innovation Center (EKIK), Óbuda University, Budapest, 1034, Hungary.
| |
Collapse
|
32
|
Chauhan S, Edla DR, Boddu V, Rao MJ, Cheruku R, Nayak SR, Martha S, Lavanya K, Nigat TD. Detection of COVID-19 using edge devices by a light-weight convolutional neural network from chest X-ray images. BMC Med Imaging 2024; 24:1. [PMID: 38166813 PMCID: PMC10759384 DOI: 10.1186/s12880-023-01155-7] [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: 09/21/2023] [Accepted: 11/14/2023] [Indexed: 01/05/2024] Open
Abstract
Deep learning is a highly significant technology in clinical treatment and diagnostics nowadays. Convolutional Neural Network (CNN) is a new idea in deep learning that is being used in the area of computer vision. The COVID-19 detection is the subject of our medical study. Researchers attempted to increase the detection accuracy but at the cost of high model complexity. In this paper, we desire to achieve better accuracy with little training space and time so that this model easily deployed in edge devices. In this paper, a new CNN design is proposed that has three stages: pre-processing, which removes the black padding on the side initially; convolution, which employs filter banks; and feature extraction, which makes use of deep convolutional layers with skip connections. In order to train the model, chest X-ray images are partitioned into three sets: learning(0.7), validation(0.1), and testing(0.2). The models are then evaluated using the test and training data. The LMNet, CoroNet, CVDNet, and Deep GRU-CNN models are the other four models used in the same experiment. The propose model achieved 99.47% & 98.91% accuracy on training and testing respectively. Additionally, it achieved 97.54%, 98.19%, 99.49%, and 97.86% scores for precision, recall, specificity, and f1-score respectively. The proposed model obtained nearly equivalent accuracy and other similar metrics when compared with other models but greatly reduced the model complexity. Moreover, it is found that proposed model is less prone to over fitting as compared to other models.
Collapse
Affiliation(s)
- Sohamkumar Chauhan
- Department of Computer Science and Engineering, National Institute of Technology Goa, Ponda, 403401, Goa, India
| | - Damoder Reddy Edla
- Department of Computer Science and Engineering, National Institute of Technology Goa, Ponda, 403401, Goa, India
| | - Vijayasree Boddu
- Department of Electronics and Communication Engineering, National Institute of Technology Warangal, Hanamkonda, 506004, Telangana, India
| | - M Jayanthi Rao
- Department of CSE, Aditya Institute of Technology and Management, Kotturu, Tekkali, Andhra Pradesh, India
| | - Ramalingaswamy Cheruku
- Department of Computer Science and Engineering, National Institute of Technology Warangal, Hanamkonda, 506004, Telangana, India
| | - Soumya Ranjan Nayak
- School of Computer Engineering, KIIT Deemed to be University, Bhubaneswar, 751024, Odisha, India
| | - Sheshikala Martha
- School of Computer Science and Artificial Intelligence, SR University, Warangal, 506004, Telangana, India
| | - Kamppa Lavanya
- University College of Sciences, Acharya Nagarjuna Univesity, Guntur, Andhra Pradesh, India
| | - Tsedenya Debebe Nigat
- Faculty of Computing and Informatics, Jimma Institute of Technology, Jimma, Oromia, Ethiopia.
| |
Collapse
|
33
|
Singh K, Kaur N, Prabhu A. Combating COVID-19 Crisis using Artificial Intelligence (AI) Based Approach: Systematic Review. Curr Top Med Chem 2024; 24:737-753. [PMID: 38318824 DOI: 10.2174/0115680266282179240124072121] [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: 10/18/2023] [Revised: 12/19/2023] [Accepted: 12/27/2023] [Indexed: 02/07/2024]
Abstract
BACKGROUND SARS-CoV-2, the unique coronavirus that causes COVID-19, has wreaked damage around the globe, with victims displaying a wide range of difficulties that have encouraged medical professionals to look for innovative technical solutions and therapeutic approaches. Artificial intelligence-based methods have contributed a significant part in tackling complicated issues, and some institutions have been quick to embrace and tailor these solutions in response to the COVID-19 pandemic's obstacles. Here, in this review article, we have covered a few DL techniques for COVID-19 detection and diagnosis, as well as ML techniques for COVID-19 identification, severity classification, vaccine and drug development, mortality rate prediction, contact tracing, risk assessment, and public distancing. This review illustrates the overall impact of AI/ML tools on tackling and managing the outbreak. PURPOSE The focus of this research was to undertake a thorough evaluation of the literature on the part of Artificial Intelligence (AI) as a complete and efficient solution in the battle against the COVID-19 epidemic in the domains of detection and diagnostics of disease, mortality prediction and vaccine as well as drug development. METHODS A comprehensive exploration of PubMed, Web of Science, and Science Direct was conducted using PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) regulations to find all possibly suitable papers conducted and made publicly available between December 1, 2019, and August 2023. COVID-19, along with AI-specific words, was used to create the query syntax. RESULTS During the period covered by the search strategy, 961 articles were published and released online. Out of these, a total of 135 papers were chosen for additional investigation. Mortality rate prediction, early detection and diagnosis, vaccine as well as drug development, and lastly, incorporation of AI for supervising and controlling the COVID-19 pandemic were the four main topics focused entirely on AI applications used to tackle the COVID-19 crisis. Out of 135, 60 research papers focused on the detection and diagnosis of the COVID-19 pandemic. Next, 19 of the 135 studies applied a machine-learning approach for mortality rate prediction. Another 22 research publications emphasized the vaccine as well as drug development. Finally, the remaining studies were concentrated on controlling the COVID-19 pandemic by applying AI AI-based approach to it. CONCLUSION We compiled papers from the available COVID-19 literature that used AI-based methodologies to impart insights into various COVID-19 topics in this comprehensive study. Our results suggest crucial characteristics, data types, and COVID-19 tools that can aid in medical and translational research facilitation.
Collapse
Affiliation(s)
- Kavya Singh
- Department of Biotechnology, Banasthali University, Banasthali Vidyapith, Banasthali, 304022, Rajasthan, India
| | - Navjeet Kaur
- Department of Chemistry & Division of Research and Development, Lovely Professional University, Phagwara, 144411, Punjab, India
| | - Ashish Prabhu
- Biotechnology Department, NIT Warangal, Warangal, 506004, Telangana, India
| |
Collapse
|
34
|
Gopatoti A, Jayakumar R, Billa P, Patteeswaran V. DDA-SSNets: Dual decoder attention-based semantic segmentation networks for COVID-19 infection segmentation and classification using chest X-Ray images. JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY 2024; 32:623-649. [PMID: 38607728 DOI: 10.3233/xst-230421] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/14/2024]
Abstract
BACKGROUND COVID-19 needs to be diagnosed and staged to be treated accurately. However, prior studies' diagnostic and staging abilities for COVID-19 infection needed to be improved. Therefore, new deep learning-based approaches are required to aid radiologists in detecting and quantifying COVID-19-related lung infections. OBJECTIVE To develop deep learning-based models to classify and quantify COVID-19-related lung infections. METHODS Initially, Dual Decoder Attention-based Semantic Segmentation Networks (DDA-SSNets) such as Dual Decoder Attention-UNet (DDA-UNet) and Dual Decoder Attention-SegNet (DDA-SegNet) are proposed to facilitate the dual segmentation tasks such as lung lobes and infection segmentation in chest X-ray (CXR) images. The lung lobe and infection segmentations are mapped to grade the severity of COVID-19 infection in both the lungs of CXRs. Later, a Genetic algorithm-based Deep Convolutional Neural Network classifier with the optimum number of layers, namely GADCNet, is proposed to classify the extracted regions of interest (ROI) from the CXR lung lobes into COVID-19 and non-COVID-19. RESULTS The DDA-SegNet shows better segmentation with an average BCSSDC of 99.53% and 99.97% for lung lobes and infection segmentations, respectively, compared with DDA-UNet with an average BCSSDC of 99.14% and 99.92%. The proposed DDA-SegNet with GADCNet classifier offered excellent classification results with an average BCCAC of 99.98%, followed by the GADCNet with DDA-UNet with an average BCCAC of 99.92% after extensive testing and analysis. CONCLUSIONS The results show that the proposed DDA-SegNet has superior performance in the segmentation of lung lobes and COVID-19-infected regions in CXRs, along with improved severity grading compared to the DDA-UNet and improved accuracy of the GADCNet classifier in classifying the CXRs into COVID-19, and non-COVID-19.
Collapse
Affiliation(s)
- Anandbabu Gopatoti
- Department of Electronics and Communication Engineering, Hindusthan College of Engineering and Technology, Coimbatore, Tamil Nadu, India
| | - Ramya Jayakumar
- Department of Electronics and Communication Engineering, Hindusthan College of Engineering and Technology, Coimbatore, Tamil Nadu, India
| | - Poornaiah Billa
- Department of Electronics and Communication Engineering, Lakireddy Bali Reddy College of Engineering, Mylavaram, Andhra Pradesh, India
| | - Vijayalakshmi Patteeswaran
- Department of Electronics and Communication Engineering, Hindusthan College of Engineering and Technology, Coimbatore, Tamil Nadu, India
| |
Collapse
|
35
|
DeGrave AJ, Cai ZR, Janizek JD, Daneshjou R, Lee SI. Auditing the inference processes of medical-image classifiers by leveraging generative AI and the expertise of physicians. Nat Biomed Eng 2023:10.1038/s41551-023-01160-9. [PMID: 38155295 DOI: 10.1038/s41551-023-01160-9] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/30/2023] [Accepted: 10/30/2023] [Indexed: 12/30/2023]
Abstract
The inferences of most machine-learning models powering medical artificial intelligence are difficult to interpret. Here we report a general framework for model auditing that combines insights from medical experts with a highly expressive form of explainable artificial intelligence. Specifically, we leveraged the expertise of dermatologists for the clinical task of differentiating melanomas from melanoma 'lookalikes' on the basis of dermoscopic and clinical images of the skin, and the power of generative models to render 'counterfactual' images to understand the 'reasoning' processes of five medical-image classifiers. By altering image attributes to produce analogous images that elicit a different prediction by the classifiers, and by asking physicians to identify medically meaningful features in the images, the counterfactual images revealed that the classifiers rely both on features used by human dermatologists, such as lesional pigmentation patterns, and on undesirable features, such as background skin texture and colour balance. The framework can be applied to any specialized medical domain to make the powerful inference processes of machine-learning models medically understandable.
Collapse
Affiliation(s)
- Alex J DeGrave
- Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle, WA, USA
- Medical Scientist Training Program, University of Washington, Seattle, WA, USA
| | - Zhuo Ran Cai
- Program for Clinical Research and Technology, Department of Dermatology, Stanford University School of Medicine, Stanford, CA, USA
| | - Joseph D Janizek
- Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle, WA, USA
- Medical Scientist Training Program, University of Washington, Seattle, WA, USA
| | - Roxana Daneshjou
- Department of Dermatology, Stanford University School of Medicine, Stanford, CA, USA.
- Department of Biomedical Data Science, Stanford University School of Medicine, Stanford, CA, USA.
| | - Su-In Lee
- Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle, WA, USA.
| |
Collapse
|
36
|
Wu D, Ni J, Fan W, Jiang Q, Wang L, Sun L, Cai Z. Opportunities and challenges of computer aided diagnosis in new millennium: A bibliometric analysis from 2000 to 2023. Medicine (Baltimore) 2023; 102:e36703. [PMID: 38134105 PMCID: PMC10735127 DOI: 10.1097/md.0000000000036703] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/30/2023] [Accepted: 11/27/2023] [Indexed: 12/24/2023] Open
Abstract
BACKGROUND After entering the new millennium, computer-aided diagnosis (CAD) is rapidly developing as an emerging technology worldwide. Expanding the spectrum of CAD-related diseases is a possible future research trend. Nevertheless, bibliometric studies in this area have not yet been reported. This study aimed to explore the hotspots and frontiers of research on CAD from 2000 to 2023, which may provide a reference for researchers in this field. METHODS In this paper, we use bibliometrics to analyze CAD-related literature in the Web of Science database between 2000 and 2023. The scientometric softwares VOSviewer and CiteSpace were used to visually analyze the countries, institutions, authors, journals, references and keywords involved in the literature. Keywords burst analysis were utilized to further explore the current state and development trends of research on CAD. RESULTS A total of 13,970 publications were included in this study, with a noticeably rising annual publication trend. China and the United States are major contributors to the publication, with the United States being the dominant position in CAD research. The American research institutions, lead by the University of Chicago, are pioneers of CAD. Acharya UR, Zheng B and Chan HP are the most prolific authors. Institute of Electrical and Electronics Engineers Transactions on Medical Imaging focuses on CAD and publishes the most articles. New computer technologies related to CAD are in the forefront of attention. Currently, CAD is used extensively in breast diseases, pulmonary diseases and brain diseases. CONCLUSION Expanding the spectrum of CAD-related diseases is a possible future research trend. How to overcome the lack of large sample datasets and establish a universally accepted standard for the evaluation of CAD system performance are urgent issues for CAD development and validation. In conclusion, this paper provides valuable information on the current state of CAD research and future developments.
Collapse
Affiliation(s)
- Di Wu
- Department of Proctology, Yongchuan Hospital of Traditional Chinese Medicine, Chongqing Medical University, Chongqing, China
- Department of Proctology, Bishan Hospital of Traditional Chinese Medicine, Chongqing, China
- Chongqing College of Traditional Chinese Medicine, Chongqing, China
| | - Jiachun Ni
- Department of Coloproctology, Yueyang Hospital of Integrated Traditional Chinese and Western Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai, China
| | - Wenbin Fan
- Department of Proctology, Bishan Hospital of Traditional Chinese Medicine, Chongqing, China
- Chongqing College of Traditional Chinese Medicine, Chongqing, China
| | - Qiong Jiang
- Chongqing College of Traditional Chinese Medicine, Chongqing, China
| | - Ling Wang
- Department of Proctology, Yongchuan Hospital of Traditional Chinese Medicine, Chongqing Medical University, Chongqing, China
| | - Li Sun
- Department of Proctology, Yongchuan Hospital of Traditional Chinese Medicine, Chongqing Medical University, Chongqing, China
| | - Zengjin Cai
- Department of Proctology, Yongchuan Hospital of Traditional Chinese Medicine, Chongqing Medical University, Chongqing, China
| |
Collapse
|
37
|
Amgothu S, Koppu S. COVID-19 prediction using Caviar Squirrel Jellyfish Search Optimization technique in fog-cloud based architecture. PLoS One 2023; 18:e0295599. [PMID: 38127990 PMCID: PMC10735048 DOI: 10.1371/journal.pone.0295599] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/15/2023] [Accepted: 11/24/2023] [Indexed: 12/23/2023] Open
Abstract
In the pandemic of COVID-19 patients approach to the hospital for prescription, yet due to extreme line up the patient gets treatment after waiting for more than one hour. Generally, wearable devices directly measure the preliminary data of the patient stored in capturing mode. In order to store the data, the hospitals require large storage devices that make the progression of data more complex. To bridge this gap, a potent scheme is established for COVID-19 prediction based fog-cloud named Caviar Squirrel Jellyfish Search Optimization (CSJSO). Here, CSJSO is the amalgamation of CAViar Squirrel Search Algorithm (CSSA) and Jellyfish Search Optimization (JSO), where CSSA is blended by the Conditional Autoregressive Value-at-Risk (CAViar) and Squirrel Search Algorithm (SSA). This architecture comprises the healthcare IoT sensor layer, fog layer and cloud layer. In the healthcare IoT sensor layer, the routing process with the collection of patient health condition data is carried out. On the other hand, in the fog layer COVID-19 detection is performed by employing a Deep Neuro Fuzzy Network (DNFN) trained by the proposed Remora Namib Beetle JSO (RNBJSO). Here, RNBJSO is the combination of Namib Beetle Optimization (NBO), Remora Optimization Algorithm (ROA) and Jellyfish Search optimization (JSO). Finally, in the cloud layer, the detection of COVID-19 employing Deep Long Short Term Memory (Deep LSTM) trained utilizing proposed CSJSO is performed. The evaluation measures utilized for CSJSO_Deep LSTM in database-1, such as Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) observed 0.062 and 0.252 in confirmed cases. The measures employed in database-2 are accuracy, sensitivity and specificity achieved 0.925, 0.928 and 0.925 in K-set.
Collapse
Affiliation(s)
- Shanthi Amgothu
- School of Computer Science Engineering and Information Systems, Vellore, India
| | - Srinivas Koppu
- School of Computer Science Engineering and Information Systems, Vellore, India
| |
Collapse
|
38
|
Guo K, Cheng J, Li K, Wang L, Lv Y, Cao D. Diagnosis and detection of pneumonia using weak-label based on X-ray images: a multi-center study. BMC Med Imaging 2023; 23:209. [PMID: 38087255 PMCID: PMC10717871 DOI: 10.1186/s12880-023-01174-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/13/2023] [Accepted: 12/05/2023] [Indexed: 12/18/2023] Open
Abstract
PURPOSE Development and assessment the deep learning weakly supervised algorithm for the classification and detection pneumonia via X-ray. METHODS This retrospective study analyzed two publicly available dataset that contain X-ray images of pneumonia cases and normal cases. The first dataset from Guangzhou Women and Children's Medical Center. It contains a total of 5,856 X-ray images, which are divided into training, validation, and test sets with 8:1:1 ratio for algorithm training and testing. The deep learning algorithm ResNet34 was employed to build diagnostic model. And the second public dataset were collated by researchers from Qatar University and the University of Dhaka along with collaborators from Pakistan and Malaysia and some medical doctors. A total of 1,300 images of COVID-19 positive cases, 1,300 normal images and 1,300 images of viral pneumonia for external validation. Class activation map (CAM) were used to location the pneumonia lesions. RESULTS The ResNet34 model for pneumonia detection achieved an AUC of 0.9949 [0.9910-0.9981] (with an accuracy of 98.29% a sensitivity of 99.29% and a specificity of 95.57%) in the test dataset. And for external validation dataset, the model obtained an AUC of 0.9835[0.9806-0.9864] (with an accuracy of 94.62%, a sensitivity of 92.35% and a specificity of 99.15%). Moreover, the CAM can accurately locate the pneumonia area. CONCLUSION The deep learning algorithm can accurately detect pneumonia and locate the pneumonia area based on weak supervision information, which can provide potential value for helping radiologists to improve their accuracy of detection pneumonia patients through X-ray images.
Collapse
Affiliation(s)
- Kairou Guo
- Department of Biomedical Engineering, Chinese PLA General Hospital, Beijing, 100853, P.R. China
| | - Jiangbo Cheng
- Department of Biomedical Engineering, Chinese PLA General Hospital, Beijing, 100853, P.R. China
| | - Kaiyuan Li
- Department of Biomedical Engineering, Chinese PLA General Hospital, Beijing, 100853, P.R. China
| | - Lanhui Wang
- Department of Biomedical Engineering, Chinese PLA General Hospital, Beijing, 100853, P.R. China
| | - Yadong Lv
- Department of Biomedical Engineering, Chinese PLA General Hospital, Beijing, 100853, P.R. China
| | - Desen Cao
- Department of Biomedical Engineering, Chinese PLA General Hospital, Beijing, 100853, P.R. China.
| |
Collapse
|
39
|
Zhang L, Guo W, Lv C. Modern technologies and solutions to enhance surveillance and response systems for emerging zoonotic diseases. SCIENCE IN ONE HEALTH 2023; 3:100061. [PMID: 39077381 PMCID: PMC11262286 DOI: 10.1016/j.soh.2023.100061] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 08/22/2023] [Accepted: 10/29/2023] [Indexed: 07/31/2024]
Abstract
Background Zoonotic diseases originating in animals pose a significant threat to global public health. Recent outbreaks, such as coronavirus disease 2019 (COVID-19), have caused widespread illness, death, and socioeconomic disruptions worldwide. To cope with these diseases effectively, it is crucial to strengthen surveillance capabilities and establish rapid response systems. Aim The aim of this review to examine the modern technologies and solutions that have the potential to enhance zoonotic disease surveillance and outbreak responses and provide valuable insights into how cutting-edge innovations could be leveraged to prevent, detect, and control emerging zoonotic disease outbreaks. Herein, we discuss advanced tools including big data analytics, artificial intelligence, the Internet of Things, geographic information systems, remote sensing, molecular diagnostics, point-of-care testing, telemedicine, digital contact tracing, and early warning systems. Results These technologies enable real-time monitoring, the prediction of outbreak risks, early anomaly detection, rapid diagnosis, and targeted interventions during outbreaks. When integrated through collaborative partnerships, these strategies can significantly improve the speed and effectiveness of zoonotic disease control. However, several challenges persist, particularly in resource-limited settings, such as infrastructure limitations, costs, data integration and training requirements, and ethical implementation. Conclusion With strategic planning and coordinated efforts, modern technologies and solutions offer immense potential to bolster surveillance and outbreak responses, and serve as a critical resource against emerging zoonotic disease threats worldwide.
Collapse
Affiliation(s)
- Li Zhang
- Huazhong Agricultural University, Wuhan 430070, China
| | - Wenqiang Guo
- Huazhong Agricultural University, Wuhan 430070, China
| | - Chenrui Lv
- Huazhong Agricultural University, Wuhan 430070, China
| |
Collapse
|
40
|
Liu F, Zhu T, Wu X, Yang B, You C, Wang C, Lu L, Liu Z, Zheng Y, Sun X, Yang Y, Clifton L, Clifton DA. A medical multimodal large language model for future pandemics. NPJ Digit Med 2023; 6:226. [PMID: 38042919 PMCID: PMC10693607 DOI: 10.1038/s41746-023-00952-2] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/08/2023] [Accepted: 10/24/2023] [Indexed: 12/04/2023] Open
Abstract
Deep neural networks have been integrated into the whole clinical decision procedure which can improve the efficiency of diagnosis and alleviate the heavy workload of physicians. Since most neural networks are supervised, their performance heavily depends on the volume and quality of available labels. However, few such labels exist for rare diseases (e.g., new pandemics). Here we report a medical multimodal large language model (Med-MLLM) for radiograph representation learning, which can learn broad medical knowledge (e.g., image understanding, text semantics, and clinical phenotypes) from unlabelled data. As a result, when encountering a rare disease, our Med-MLLM can be rapidly deployed and easily adapted to them with limited labels. Furthermore, our model supports medical data across visual modality (e.g., chest X-ray and CT) and textual modality (e.g., medical report and free-text clinical note); therefore, it can be used for clinical tasks that involve both visual and textual data. We demonstrate the effectiveness of our Med-MLLM by showing how it would perform using the COVID-19 pandemic "in replay". In the retrospective setting, we test the model on the early COVID-19 datasets; and in the prospective setting, we test the model on the new variant COVID-19-Omicron. The experiments are conducted on 1) three kinds of input data; 2) three kinds of downstream tasks, including disease reporting, diagnosis, and prognosis; 3) five COVID-19 datasets; and 4) three different languages, including English, Chinese, and Spanish. All experiments show that our model can make accurate and robust COVID-19 decision-support with little labelled data.
Collapse
Affiliation(s)
- Fenglin Liu
- Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK.
| | - Tingting Zhu
- Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK
| | - Xian Wu
- Jarvis Research Center, Tencent YouTu Lab, Beijing, China
| | - Bang Yang
- School of Computer Science, Peking University, Beijing, China
| | | | - Chenyang Wang
- Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK
| | - Lei Lu
- Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK
| | - Zhangdaihong Liu
- Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK
- Oxford-Suzhou Centre for Advanced Research, Suzhou, China
| | - Yefeng Zheng
- Jarvis Research Center, Tencent YouTu Lab, Beijing, China
| | - Xu Sun
- School of Computer Science, Peking University, Beijing, China
| | - Yang Yang
- School of Public Health, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Lei Clifton
- Nuffield Department of Population Health, University of Oxford, Oxford, UK
| | - David A Clifton
- Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK.
- Oxford-Suzhou Centre for Advanced Research, Suzhou, China.
| |
Collapse
|
41
|
Shi C, Shao Y, Shan F, Shen J, Huang X, Chen C, Lu Y, Zhan Y, Shi N, Wu J, Wang K, Gao Y, Shi Y, Song F. Development and validation of a deep learning model for multicategory pneumonia classification on chest computed tomography: a multicenter and multireader study. Quant Imaging Med Surg 2023; 13:8641-8656. [PMID: 38106268 PMCID: PMC10722067 DOI: 10.21037/qims-23-1097] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/01/2023] [Accepted: 09/14/2023] [Indexed: 12/19/2023]
Abstract
Background Accurate diagnosis of pneumonia is vital for effective disease management and mortality reduction, but it can be easily confused with other conditions on chest computed tomography (CT) due to an overlap in imaging features. We aimed to develop and validate a deep learning (DL) model based on chest CT for accurate classification of viral pneumonia (VP), bacterial pneumonia (BP), fungal pneumonia (FP), pulmonary tuberculosis (PTB), and no pneumonia (NP) conditions. Methods In total, 1,776 cases from five hospitals in different regions were retrospectively collected from September 2019 to June 2023. All cases were enrolled according to inclusion and exclusion criteria, and ultimately 1,611 cases were used to develop the DL model with 5-fold cross-validation, with 165 cases being used as the external test set. Five radiologists blindly reviewed the images from the internal and external test sets first without and then with DL model assistance. Precision, recall, F1-score, weighted F1-average, and area under the curve (AUC) were used to evaluate the model performance. Results The F1-scores of the DL model on the internal and external test sets were, respectively, 0.947 [95% confidence interval (CI): 0.936-0.958] and 0.933 (95% CI: 0.916-0.950) for VP, 0.511 (95% CI: 0.487-0.536) and 0.591 (95% CI: 0.557-0.624) for BP, 0.842 (95% CI: 0.824-0.860) and 0.848 (95% CI: 0.824-0.873) for FP, 0.843 (95% CI: 0.826-0.861) and 0.795 (95% CI: 0.767-0.822) for PTB, and 0.975 (95% CI: 0.968-0.983) and 0.976 (95% CI: 0.965-0.986) for NP, with a weighted F1-average of 0.883 (95% CI: 0.867-0.898) and 0.846 (95% CI: 0.822-0.871), respectively. The model performed well and showed comparable performance in both the internal and external test sets. The F1-score of the DL model was higher than that of radiologists, and with DL model assistance, radiologists achieved a higher F1-score. On the external test set, the F1-score of the DL model (F1-score 0.848; 95% CI: 0.824-0.873) was higher than that of the radiologists (F1-score 0.541; 95% CI: 0.507-0.575) as was its precision for the other three pneumonia conditions (all P values <0.001). With DL model assistance, the F1-score for FP (F1-score 0.541; 95% CI: 0.507-0.575) was higher than that achieved without assistance (F1-score 0.778; 95% CI: 0.750-0.807) as was its precision for the other three pneumonia conditions (all P values <0.001). Conclusions The DL approach can effectively classify pneumonia and can help improve radiologists' performance, supporting the full integration of DL results into the routine workflow of clinicians.
Collapse
Affiliation(s)
- Chunzi Shi
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University, School of Medicine, Shanghai, China
- Qingdao Institute, School of Life Medicine, Department of Radiology, Shanghai Public Health Clinical Center, Fudan University, Qingdao, China
| | - Ying Shao
- R&D Department, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China
| | - Fei Shan
- Department of Radiology, Shanghai Public Health Clinical Center, Fudan University, Shanghai, China
| | - Jie Shen
- Department of Radiology, Shanghai Public Health Clinical Center, Fudan University, Shanghai, China
| | - Xueni Huang
- Department of Radiology, Shanghai Public Health Clinical Center, Fudan University, Shanghai, China
- Medical Imaging Department, First Affiliated Hospital of Ningbo University, Ningbo, China
| | - Chuan Chen
- Department of Radiology, Shanghai Public Health Clinical Center, Fudan University, Shanghai, China
| | - Yang Lu
- Department of Radiology, Shanghai Public Health Clinical Center, Fudan University, Shanghai, China
| | - Yi Zhan
- Department of Radiology, Shanghai Public Health Clinical Center, Fudan University, Shanghai, China
| | - Nannan Shi
- Department of Radiology, Shanghai Public Health Clinical Center, Fudan University, Shanghai, China
| | - Jili Wu
- Department of Radiology, Fourth People’s Hospital of Taiyuan, Taiyuan, China
| | - Keying Wang
- Department of Radiology, Jinshan Hospital, Fudan University, Shanghai, China
| | - Yaozong Gao
- R&D Department, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China
| | - Yuxin Shi
- Department of Radiology, Shanghai Public Health Clinical Center, Fudan University, Shanghai, China
| | - Fengxiang Song
- Department of Radiology, Shanghai Public Health Clinical Center, Fudan University, Shanghai, China
| |
Collapse
|
42
|
Yigci D, Atçeken N, Yetisen AK, Tasoglu S. Loop-Mediated Isothermal Amplification-Integrated CRISPR Methods for Infectious Disease Diagnosis at Point of Care. ACS OMEGA 2023; 8:43357-43373. [PMID: 38027359 PMCID: PMC10666231 DOI: 10.1021/acsomega.3c04422] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 06/21/2023] [Accepted: 09/26/2023] [Indexed: 12/01/2023]
Abstract
Infectious diseases continue to pose an imminent threat to global public health, leading to high numbers of deaths every year and disproportionately impacting developing countries where access to healthcare is limited. Biological, environmental, and social phenomena, including climate change, globalization, increased population density, and social inequity, contribute to the emergence of novel communicable diseases. Rapid and accurate diagnoses of infectious diseases are essential to preventing the transmission of infectious diseases. Although some commonly used diagnostic technologies provide highly sensitive and specific measurements, limitations including the requirement for complex equipment/infrastructure and refrigeration, the need for trained personnel, long sample processing times, and high cost remain unresolved. To ensure global access to affordable diagnostic methods, loop-mediated isothermal amplification (LAMP) integrated clustered regularly interspaced short palindromic repeat (CRISPR) based pathogen detection has emerged as a promising technology. Here, LAMP-integrated CRISPR-based nucleic acid detection methods are discussed in point-of-care (PoC) pathogen detection platforms, and current limitations and future directions are also identified.
Collapse
Affiliation(s)
- Defne Yigci
- School
of Medicine, Koç University, Istanbul 34450, Turkey
| | - Nazente Atçeken
- Koç
University Translational Medicine Research Center (KUTTAM), Koç University, Istanbul 34450, Turkey
| | - Ali K. Yetisen
- Department
of Chemical Engineering, Imperial College
London, London SW7 2AZ, U.K.
| | - Savas Tasoglu
- Koç
University Translational Medicine Research Center (KUTTAM), Koç University, Istanbul 34450, Turkey
- Boğaziçi
Institute of Biomedical Engineering, Boğaziçi
University, Istanbul 34684, Turkey
- Koç
University Arçelik Research Center for Creative Industries
(KUAR), Koç University, Istanbul 34450, Turkey
- Physical
Intelligence Department, Max Planck Institute
for Intelligent Systems, Stuttgart 70569, Germany
| |
Collapse
|
43
|
Tehrani SSM, Zarvani M, Amiri P, Ghods Z, Raoufi M, Safavi-Naini SAA, Soheili A, Gharib M, Abbasi H. Visual transformer and deep CNN prediction of high-risk COVID-19 infected patients using fusion of CT images and clinical data. BMC Med Inform Decis Mak 2023; 23:265. [PMID: 37978393 PMCID: PMC10656999 DOI: 10.1186/s12911-023-02344-8] [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: 01/08/2023] [Accepted: 10/16/2023] [Indexed: 11/19/2023] Open
Abstract
BACKGROUND Despite the globally reducing hospitalization rates and the much lower risks of Covid-19 mortality, accurate diagnosis of the infection stage and prediction of outcomes are clinically of interest. Advanced current technology can facilitate automating the process and help identifying those who are at higher risks of developing severe illness. This work explores and represents deep-learning-based schemes for predicting clinical outcomes in Covid-19 infected patients, using Visual Transformer and Convolutional Neural Networks (CNNs), fed with 3D data fusion of CT scan images and patients' clinical data. METHODS We report on the efficiency of Video Swin Transformers and several CNN models fed with fusion datasets and CT scans only vs. a set of conventional classifiers fed with patients' clinical data only. A relatively large clinical dataset from 380 Covid-19 diagnosed patients was used to train/test the models. RESULTS Results show that the 3D Video Swin Transformers fed with the fusion datasets of 64 sectional CT scans + 67 clinical labels outperformed all other approaches for predicting outcomes in Covid-19-infected patients amongst all techniques (i.e., TPR = 0.95, FPR = 0.40, F0.5 score = 0.82, AUC = 0.77, Kappa = 0.6). CONCLUSIONS We demonstrate how the utility of our proposed novel 3D data fusion approach through concatenating CT scan images with patients' clinical data can remarkably improve the performance of the models in predicting Covid-19 infection outcomes. SIGNIFICANCE Findings indicate possibilities of predicting the severity of outcome using patients' CT images and clinical data collected at the time of admission to hospital.
Collapse
Affiliation(s)
| | - Maral Zarvani
- Faculty of Engineering, Alzahra University, Tehran, Iran
| | - Paria Amiri
- University of Erlangen-Nuremberg, Bavaria, Germany
| | - Zahra Ghods
- Faculty of Engineering, Alzahra University, Tehran, Iran
| | - Masoomeh Raoufi
- Department of Radiology, School of Medicine, Imam Hossein Hospital, Shahid Beheshti, University of Medical Sciences, Tehran, Iran
| | - Seyed Amir Ahmad Safavi-Naini
- Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Amirali Soheili
- School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | | | - Hamid Abbasi
- Auckland Bioengineering Institute, University of Auckland, Auckland, 1010, New Zealand.
| |
Collapse
|
44
|
Zsidai B, Hilkert AS, Kaarre J, Narup E, Senorski EH, Grassi A, Ley C, Longo UG, Herbst E, Hirschmann MT, Kopf S, Seil R, Tischer T, Samuelsson K, Feldt R. A practical guide to the implementation of AI in orthopaedic research - part 1: opportunities in clinical application and overcoming existing challenges. J Exp Orthop 2023; 10:117. [PMID: 37968370 PMCID: PMC10651597 DOI: 10.1186/s40634-023-00683-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/24/2023] [Accepted: 10/21/2023] [Indexed: 11/17/2023] Open
Abstract
Artificial intelligence (AI) has the potential to transform medical research by improving disease diagnosis, clinical decision-making, and outcome prediction. Despite the rapid adoption of AI and machine learning (ML) in other domains and industry, deployment in medical research and clinical practice poses several challenges due to the inherent characteristics and barriers of the healthcare sector. Therefore, researchers aiming to perform AI-intensive studies require a fundamental understanding of the key concepts, biases, and clinical safety concerns associated with the use of AI. Through the analysis of large, multimodal datasets, AI has the potential to revolutionize orthopaedic research, with new insights regarding the optimal diagnosis and management of patients affected musculoskeletal injury and disease. The article is the first in a series introducing fundamental concepts and best practices to guide healthcare professionals and researcher interested in performing AI-intensive orthopaedic research studies. The vast potential of AI in orthopaedics is illustrated through examples involving disease- or injury-specific outcome prediction, medical image analysis, clinical decision support systems and digital twin technology. Furthermore, it is essential to address the role of human involvement in training unbiased, generalizable AI models, their explainability in high-risk clinical settings and the implementation of expert oversight and clinical safety measures for failure. In conclusion, the opportunities and challenges of AI in medicine are presented to ensure the safe and ethical deployment of AI models for orthopaedic research and clinical application. Level of evidence IV.
Collapse
Affiliation(s)
- Bálint Zsidai
- Sahlgrenska Sports Medicine Center, Gothenburg, Sweden.
- Department of Orthopaedics, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden.
| | - Ann-Sophie Hilkert
- Department of Computer Science and Engineering, Chalmers University of Technology, Gothenburg, Sweden
- Medfield Diagnostics AB, Gothenburg, Sweden
| | - Janina Kaarre
- Sahlgrenska Sports Medicine Center, Gothenburg, Sweden
- Department of Orthopaedics, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
- Department of Orthopaedic Surgery, UPMC Freddie Fu Sports Medicine Center, University of Pittsburgh, Pittsburgh, USA
| | - Eric Narup
- Sahlgrenska Sports Medicine Center, Gothenburg, Sweden
- Department of Orthopaedics, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
| | - Eric Hamrin Senorski
- Sahlgrenska Sports Medicine Center, Gothenburg, Sweden
- Department of Health and Rehabilitation, Institute of Neuroscience and Physiology, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
- Sportrehab Sports Medicine Clinic, Gothenburg, Sweden
| | - Alberto Grassi
- Department of Orthopaedics, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
- IIa Clinica Ortopedica E Traumatologica, IRCCS Istituto Ortopedico Rizzoli, Bologna, Italy
| | - Christophe Ley
- Department of Mathematics, University of Luxembourg, Esch-Sur-Alzette, Luxembourg
| | - Umile Giuseppe Longo
- Department of Orthopaedic and Trauma Surgery, Campus Bio-Medico University, Rome, Italy
| | - Elmar Herbst
- Department of Trauma, Hand and Reconstructive Surgery, University Hospital Münster, Münster, Germany
| | - Michael T Hirschmann
- Department of Orthopedic Surgery and Traumatology, Head Knee Surgery and DKF Head of Research, Kantonsspital Baselland, 4101, Bruderholz, Switzerland
| | - Sebastian Kopf
- Center of Orthopaedics and Traumatology, University Hospital Brandenburg a.d.H., Brandenburg Medical School Theodor Fontane, 14770, Brandenburg a.d.H., Germany
- Faculty of Health Sciences Brandenburg, Brandenburg Medical School Theodor Fontane, 14770, Brandenburg a.d.H., Germany
| | - Romain Seil
- Department of Orthopaedic Surgery, Centre Hospitalier Luxembourg and Luxembourg Institute of Health, Luxembourg, Luxembourg
| | - Thomas Tischer
- Clinic for Orthopaedics and Trauma Surgery, Malteser Waldkrankenhaus St. Marien, Erlangen, Germany
| | - Kristian Samuelsson
- Sahlgrenska Sports Medicine Center, Gothenburg, Sweden
- Department of Orthopaedics, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
- Department of Orthopaedics, Sahlgrenska University Hospital, Mölndal, Sweden
| | - Robert Feldt
- Department of Orthopaedics, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
| |
Collapse
|
45
|
Sun J, Shi W, Giuste FO, Vaghani YS, Tang L, Wang MD. Improving explainable AI with patch perturbation-based evaluation pipeline: a COVID-19 X-ray image analysis case study. Sci Rep 2023; 13:19488. [PMID: 37945586 PMCID: PMC10636093 DOI: 10.1038/s41598-023-46493-2] [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: 03/21/2023] [Accepted: 11/01/2023] [Indexed: 11/12/2023] Open
Abstract
Recent advances in artificial intelligence (AI) have sparked interest in developing explainable AI (XAI) methods for clinical decision support systems, especially in translational research. Although using XAI methods may enhance trust in black-box models, evaluating their effectiveness has been challenging, primarily due to the absence of human (expert) intervention, additional annotations, and automated strategies. In order to conduct a thorough assessment, we propose a patch perturbation-based approach to automatically evaluate the quality of explanations in medical imaging analysis. To eliminate the need for human efforts in conventional evaluation methods, our approach executes poisoning attacks during model retraining by generating both static and dynamic triggers. We then propose a comprehensive set of evaluation metrics during the model inference stage to facilitate the evaluation from multiple perspectives, covering a wide range of correctness, completeness, consistency, and complexity. In addition, we include an extensive case study to showcase the proposed evaluation strategy by applying widely-used XAI methods on COVID-19 X-ray imaging classification tasks, as well as a thorough review of existing XAI methods in medical imaging analysis with evaluation availability. The proposed patch perturbation-based workflow offers model developers an automated and generalizable evaluation strategy to identify potential pitfalls and optimize their proposed explainable solutions, while also aiding end-users in comparing and selecting appropriate XAI methods that meet specific clinical needs in real-world clinical research and practice.
Collapse
Affiliation(s)
- Jimin Sun
- School of Computer Science and Engineering, Georgia Institute of Technology, Atlanta, 30322, USA
| | - Wenqi Shi
- School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, 30322, USA
| | - Felipe O Giuste
- The Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, 30322, USA
| | - Yog S Vaghani
- The Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, 30322, USA
| | - Lingzi Tang
- The Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, 30322, USA
| | - May D Wang
- The Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, 30322, USA.
| |
Collapse
|
46
|
Ahmad I, Merla A, Ali F, Shah B, AlZubi AA, AlZubi MA. A deep transfer learning approach for COVID-19 detection and exploring a sense of belonging with Diabetes. Front Public Health 2023; 11:1308404. [PMID: 38026271 PMCID: PMC10657998 DOI: 10.3389/fpubh.2023.1308404] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/06/2023] [Accepted: 10/18/2023] [Indexed: 12/01/2023] Open
Abstract
COVID-19 is an epidemic disease that results in death and significantly affects the older adult and those afflicted with chronic medical conditions. Diabetes medication and high blood glucose levels are significant predictors of COVID-19-related death or disease severity. Diabetic individuals, particularly those with preexisting comorbidities or geriatric patients, are at a higher risk of COVID-19 infection, including hospitalization, ICU admission, and death, than those without Diabetes. Everyone's lives have been significantly changed due to the COVID-19 outbreak. Identifying patients infected with COVID-19 in a timely manner is critical to overcoming this challenge. The Real-Time Polymerase Chain Reaction (RT-PCR) diagnostic assay is currently the gold standard for COVID-19 detection. However, RT-PCR is a time-consuming and costly technique requiring a lab kit that is difficult to get in crises and epidemics. This work suggests the CIDICXR-Net50 model, a ResNet-50-based Transfer Learning (TL) method for COVID-19 detection via Chest X-ray (CXR) image classification. The presented model is developed by substituting the final ResNet-50 classifier layer with a new classification head. The model is trained on 3,923 chest X-ray images comprising a substantial dataset of 1,360 viral pneumonia, 1,363 normal, and 1,200 COVID-19 CXR images. The proposed model's performance is evaluated in contrast to the results of six other innovative pre-trained models. The proposed CIDICXR-Net50 model attained 99.11% accuracy on the provided dataset while maintaining 99.15% precision and recall. This study also explores potential relationships between COVID-19 and Diabetes.
Collapse
Affiliation(s)
- Ijaz Ahmad
- Digital Transition, Innovation and Health Service, Leonardo da Vinci Telematic University, Chieti, Italy
| | - Arcangelo Merla
- Department of Engineering and Geology (INGEO) University "G. d’Annunzio" Chieti-Pescara, Pescara, Italy
| | - Farman Ali
- Department of Computer Science and Engineering, School of Convergence, College of Computing and Informatics, Sungkyunkwan University, Seoul, Republic of Korea
| | - Babar Shah
- College of Technological Innovation, Zayed University, Dubai, United Arab Emirates
| | - Ahmad Ali AlZubi
- Department of Computer Science, Community College, King Saud University, Riyadh, Saudi Arabia
| | - Mallak Ahmad AlZubi
- Faculty of Medicine, Jordan University of Science and Technology, Irbid, Jordan
| |
Collapse
|
47
|
Saha PK, Nadeem SA, Comellas AP. A Survey on Artificial Intelligence in Pulmonary Imaging. WILEY INTERDISCIPLINARY REVIEWS. DATA MINING AND KNOWLEDGE DISCOVERY 2023; 13:e1510. [PMID: 38249785 PMCID: PMC10796150 DOI: 10.1002/widm.1510] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/18/2022] [Accepted: 06/21/2023] [Indexed: 01/23/2024]
Abstract
Over the last decade, deep learning (DL) has contributed a paradigm shift in computer vision and image recognition creating widespread opportunities of using artificial intelligence in research as well as industrial applications. DL has been extensively studied in medical imaging applications, including those related to pulmonary diseases. Chronic obstructive pulmonary disease, asthma, lung cancer, pneumonia, and, more recently, COVID-19 are common lung diseases affecting nearly 7.4% of world population. Pulmonary imaging has been widely investigated toward improving our understanding of disease etiologies and early diagnosis and assessment of disease progression and clinical outcomes. DL has been broadly applied to solve various pulmonary image processing challenges including classification, recognition, registration, and segmentation. This paper presents a survey of pulmonary diseases, roles of imaging in translational and clinical pulmonary research, and applications of different DL architectures and methods in pulmonary imaging with emphasis on DL-based segmentation of major pulmonary anatomies such as lung volumes, lung lobes, pulmonary vessels, and airways as well as thoracic musculoskeletal anatomies related to pulmonary diseases.
Collapse
Affiliation(s)
- Punam K Saha
- Departments of Radiology and Electrical and Computer Engineering, University of Iowa, Iowa City, IA, 52242
| | | | | |
Collapse
|
48
|
Nahiduzzaman M, Goni MOF, Hassan R, Islam MR, Syfullah MK, Shahriar SM, Anower MS, Ahsan M, Haider J, Kowalski M. Parallel CNN-ELM: A multiclass classification of chest X-ray images to identify seventeen lung diseases including COVID-19. EXPERT SYSTEMS WITH APPLICATIONS 2023; 229:120528. [PMID: 37274610 PMCID: PMC10223636 DOI: 10.1016/j.eswa.2023.120528] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 05/01/2022] [Revised: 05/19/2023] [Accepted: 05/19/2023] [Indexed: 06/06/2023]
Abstract
Numerous epidemic lung diseases such as COVID-19, tuberculosis (TB), and pneumonia have spread over the world, killing millions of people. Medical specialists have experienced challenges in correctly identifying these diseases due to their subtle differences in Chest X-ray images (CXR). To assist the medical experts, this study proposed a computer-aided lung illness identification method based on the CXR images. For the first time, 17 different forms of lung disorders were considered and the study was divided into six trials with each containing two, two, three, four, fourteen, and seventeen different forms of lung disorders. The proposed framework combined robust feature extraction capabilities of a lightweight parallel convolutional neural network (CNN) with the classification abilities of the extreme learning machine algorithm named CNN-ELM. An optimistic accuracy of 90.92% and an area under the curve (AUC) of 96.93% was achieved when 17 classes were classified side by side. It also accurately identified COVID-19 and TB with 99.37% and 99.98% accuracy, respectively, in 0.996 microseconds for a single image. Additionally, the current results also demonstrated that the framework could outperform the existing state-of-the-art (SOTA) models. On top of that, a secondary conclusion drawn from this study was that the prospective framework retained its effectiveness over a range of real-world environments, including balanced-unbalanced or large-small datasets, large multiclass or simple binary class, and high- or low-resolution images. A prototype Android App was also developed to establish the potential of the framework in real-life implementation.
Collapse
Affiliation(s)
- Md Nahiduzzaman
- Department of Electrical & Computer Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh
| | - Md Omaer Faruq Goni
- Department of Electrical & Computer Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh
| | - Rakibul Hassan
- Department of Electrical & Computer Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh
| | - Md Robiul Islam
- Department of Electrical & Computer Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh
| | - Md Khalid Syfullah
- Department of Electrical & Computer Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh
| | - Saleh Mohammed Shahriar
- Department of Electrical & Computer Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh
| | - Md Shamim Anower
- Department of Electrical & Electronic Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh
| | - Mominul Ahsan
- Department of Computer Science, University of York, Deramore Lane, Heslington, York YO10 5GH, UK
| | - Julfikar Haider
- Department of Engineering, Manchester Metropolitan University, Chester St, Manchester M1 5GD, UK
| | - Marcin Kowalski
- Institute of Optoelectronics, Military University of Technology, Gen. S. Kaliskiego 2, 00-908 Warsaw, Poland
| |
Collapse
|
49
|
Miyazaki A, Ikejima K, Nishio M, Yabuta M, Matsuo H, Onoue K, Matsunaga T, Nishioka E, Kono A, Yamada D, Oba K, Ishikura R, Murakami T. Computer-aided diagnosis of chest X-ray for COVID-19 diagnosis in external validation study by radiologists with and without deep learning system. Sci Rep 2023; 13:17533. [PMID: 37845348 PMCID: PMC10579343 DOI: 10.1038/s41598-023-44818-9] [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: 12/12/2022] [Accepted: 10/12/2023] [Indexed: 10/18/2023] Open
Abstract
To evaluate the diagnostic performance of our deep learning (DL) model of COVID-19 and investigate whether the diagnostic performance of radiologists was improved by referring to our model. Our datasets contained chest X-rays (CXRs) for the following three categories: normal (NORMAL), non-COVID-19 pneumonia (PNEUMONIA), and COVID-19 pneumonia (COVID). We used two public datasets and private dataset collected from eight hospitals for the development and external validation of our DL model (26,393 CXRs). Eight radiologists performed two reading sessions: one session was performed with reference to CXRs only, and the other was performed with reference to both CXRs and the results of the DL model. The evaluation metrics for the reading session were accuracy, sensitivity, specificity, and area under the curve (AUC). The accuracy of our DL model was 0.733, and that of the eight radiologists without DL was 0.696 ± 0.031. There was a significant difference in AUC between the radiologists with and without DL for COVID versus NORMAL or PNEUMONIA (p = 0.0038). Our DL model alone showed better diagnostic performance than that of most radiologists. In addition, our model significantly improved the diagnostic performance of radiologists for COVID versus NORMAL or PNEUMONIA.
Collapse
Affiliation(s)
- Aki Miyazaki
- Department of Radiology, Kobe University Graduate School of Medicine, 7-5-2 Kusunoki-Cho, Chuo-Ku, Kobe, 650-0017, Japan
| | - Kengo Ikejima
- Department of Radiology, St. Luke's International Hospital, 9-1 Akashi-Cho, Chuo-Ku, Tokyo, 104-8560, Japan
| | - Mizuho Nishio
- Department of Radiology, Kobe University Graduate School of Medicine, 7-5-2 Kusunoki-Cho, Chuo-Ku, Kobe, 650-0017, Japan.
| | - Minoru Yabuta
- Department of Radiology, St. Luke's International Hospital, 9-1 Akashi-Cho, Chuo-Ku, Tokyo, 104-8560, Japan
| | - Hidetoshi Matsuo
- Department of Radiology, Kobe University Graduate School of Medicine, 7-5-2 Kusunoki-Cho, Chuo-Ku, Kobe, 650-0017, Japan
| | - Koji Onoue
- Department of Radiology, Kobe City Medical Center General Hospital, 2-1-1 Minatojimaminamimachi, Chuo-Ku, Kobe, 650-0047, Japan
- Department of Diagnostic Imaging and Interventional Radiology, Kyoto Katsura Hospital, 17 Yamada-Hirao, Nishikyo-Ku, Kyoto, 615-8256, Japan
| | - Takaaki Matsunaga
- Department of Radiology, Kobe University Graduate School of Medicine, 7-5-2 Kusunoki-Cho, Chuo-Ku, Kobe, 650-0017, Japan
| | - Eiko Nishioka
- Department of Radiology, Kobe University Graduate School of Medicine, 7-5-2 Kusunoki-Cho, Chuo-Ku, Kobe, 650-0017, Japan
| | - Atsushi Kono
- Department of Radiology, Kobe University Graduate School of Medicine, 7-5-2 Kusunoki-Cho, Chuo-Ku, Kobe, 650-0017, Japan
| | - Daisuke Yamada
- Department of Radiology, St. Luke's International Hospital, 9-1 Akashi-Cho, Chuo-Ku, Tokyo, 104-8560, Japan
| | - Ken Oba
- Department of Radiology, St. Luke's International Hospital, 9-1 Akashi-Cho, Chuo-Ku, Tokyo, 104-8560, Japan
| | - Reiichi Ishikura
- Department of Radiology, Kobe City Medical Center General Hospital, 2-1-1 Minatojimaminamimachi, Chuo-Ku, Kobe, 650-0047, Japan
| | - Takamichi Murakami
- Department of Radiology, Kobe University Graduate School of Medicine, 7-5-2 Kusunoki-Cho, Chuo-Ku, Kobe, 650-0017, Japan
| |
Collapse
|
50
|
Socha M, Prażuch W, Suwalska A, Foszner P, Tobiasz J, Jaroszewicz J, Gruszczynska K, Sliwinska M, Nowak M, Gizycka B, Zapolska G, Popiela T, Przybylski G, Fiedor P, Pawlowska M, Flisiak R, Simon K, Walecki J, Cieszanowski A, Szurowska E, Marczyk M, Polanska J. Pathological changes or technical artefacts? The problem of the heterogenous databases in COVID-19 CXR image analysis. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2023; 240:107684. [PMID: 37356354 PMCID: PMC10278898 DOI: 10.1016/j.cmpb.2023.107684] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/20/2023] [Revised: 06/11/2023] [Accepted: 06/18/2023] [Indexed: 06/27/2023]
Abstract
BACKGROUND When the COVID-19 pandemic commenced in 2020, scientists assisted medical specialists with diagnostic algorithm development. One scientific research area related to COVID-19 diagnosis was medical imaging and its potential to support molecular tests. Unfortunately, several systems reported high accuracy in development but did not fare well in clinical application. The reason was poor generalization, a long-standing issue in AI development. Researchers found many causes of this issue and decided to refer to them as confounders, meaning a set of artefacts and methodological errors associated with the method. We aim to contribute to this steed by highlighting an undiscussed confounder related to image resolution. METHODS 20 216 chest X-ray images (CXR) from worldwide centres were analyzed. The CXRs were bijectively projected into the 2D domain by performing Uniform Manifold Approximation and Projection (UMAP) embedding on the radiomic features (rUMAP) or CNN-based neural features (nUMAP) from the pre-last layer of the pre-trained classification neural network. Additional 44 339 thorax CXRs were used for validation. The comprehensive analysis of the multimodality of the density distribution in rUMAP/nUMAP domains and its relation to the original image properties was used to identify the main confounders. RESULTS nUMAP revealed a hidden bias of neural networks towards the image resolution, which the regular up-sampling procedure cannot compensate for. The issue appears regardless of the network architecture and is not observed in a high-resolution dataset. The impact of the resolution heterogeneity can be partially diminished by applying advanced deep-learning-based super-resolution networks. CONCLUSIONS rUMAP and nUMAP are great tools for image homogeneity analysis and bias discovery, as demonstrated by applying them to COVID-19 image data. Nonetheless, nUMAP could be applied to any type of data for which a deep neural network could be constructed. Advanced image super-resolution solutions are needed to reduce the impact of the resolution diversity on the classification network decision.
Collapse
Affiliation(s)
- Marek Socha
- Department of Data Science and Engineering, Silesian University of Technology, Gliwice, Poland
| | - Wojciech Prażuch
- Department of Data Science and Engineering, Silesian University of Technology, Gliwice, Poland
| | - Aleksandra Suwalska
- Department of Data Science and Engineering, Silesian University of Technology, Gliwice, Poland
| | - Paweł Foszner
- Department of Data Science and Engineering, Silesian University of Technology, Gliwice, Poland; Department of Computer Graphics, Vision and Digital Systems, Silesian University of Technology, Gliwice, Poland
| | - Joanna Tobiasz
- Department of Data Science and Engineering, Silesian University of Technology, Gliwice, Poland; Department of Computer Graphics, Vision and Digital Systems, Silesian University of Technology, Gliwice, Poland
| | - Jerzy Jaroszewicz
- Department of Infectious Diseases and Hepatology, Medical University of Silesia, Katowice, Poland
| | - Katarzyna Gruszczynska
- Department of Radiology and Nuclear Medicine, Medical University of Silesia, Katowice, Poland
| | - Magdalena Sliwinska
- Department of Diagnostic Imaging, Voivodship Specialist Hospital, Wroclaw, Poland
| | - Mateusz Nowak
- Department of Radiology, Silesian Hospital, Cieszyn, Poland
| | - Barbara Gizycka
- Department of Imaging Diagnostics, MEGREZ Hospital, Tychy, Poland
| | | | - Tadeusz Popiela
- Department of Radiology, Jagiellonian University Medical College, Krakow, Poland
| | - Grzegorz Przybylski
- Department of Lung Diseases, Cancer and Tuberculosis, Kujawsko-Pomorskie Pulmonology Center, Bydgoszcz, Poland
| | - Piotr Fiedor
- Department of General and Transplantation Surgery, Medical University of Warsaw, Warsaw, Poland
| | - Malgorzata Pawlowska
- Department of Infectious Diseases and Hepatology, Collegium Medicum in Bydgoszcz, Nicolaus Copernicus University, Torun, Poland
| | - Robert Flisiak
- Department of Infectious Diseases and Hepatology, Medical University of Bialystok, Bialystok, Poland
| | - Krzysztof Simon
- Department of Infectious Diseases and Hepatology, Wroclaw Medical University, Wroclaw, Poland
| | - Jerzy Walecki
- Department of Radiology, Centre of Postgraduate Medical Education, Central Clinical Hospital of the Ministry of Interior in Warsaw, Poland
| | - Andrzej Cieszanowski
- Department of Radiology I, The Maria Sklodowska-Curie National Research Institute of Oncology, Warsaw, Poland
| | - Edyta Szurowska
- 2nd Department of Radiology, Medical University of Gdansk, Poland
| | - Michal Marczyk
- Department of Data Science and Engineering, Silesian University of Technology, Gliwice, Poland; Yale Cancer Center, Yale School of Medicine, New Haven, CT, USA
| | - Joanna Polanska
- Department of Data Science and Engineering, Silesian University of Technology, Gliwice, Poland.
| |
Collapse
|