1
|
Ammar HM, Tammam AF, Selim IM, Eassa M. Automated system utilizing non-invasive technique mammograms for breast cancer detection. BMC Med Imaging 2024; 24:205. [PMID: 39112928 PMCID: PMC11304668 DOI: 10.1186/s12880-024-01363-9] [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: 10/26/2023] [Accepted: 07/12/2024] [Indexed: 08/11/2024] Open
Abstract
In order to increase the likelihood of obtaining treatment and achieving a complete recovery, early illness identification and diagnosis are crucial. Artificial intelligence is helpful with this process by allowing us to rapidly start the necessary protocol for treatment in the early stages of disease development. Artificial intelligence is a major contributor to the improvement of medical treatment for patients. In order to prevent and foresee this problem on the individual, family, and generational levels, Monitoring the patient's therapy and recovery is crucial. This study's objective is to outline a non-invasive method for using mammograms to detect breast abnormalities, classify breast disorders, and identify cancerous or benign tumor tissue in the breast. We used classification models on a dataset that has been pre-processed so that the number of samples is balanced, unlike previous work on the same dataset. Identifying cancerous or benign breast tissue requires the use of supervised learning techniques and algorithms, such as random forest (RF) and decision tree (DT) classifiers, to examine up to thirty features, such as breast size, mass, diameter, circumference, and the nature of the tumor (solid or cystic). To ascertain if the tissue is malignant or benign, the examination's findings are employed. These features are mostly what determines how effectively anything may be categorized. The DT classifier was able to get a score of 95.32%, while the RF satisfied a far higher 98.83 percent.
Collapse
Affiliation(s)
- Hazem M Ammar
- Computer Science Department, Thebes Higher Institute for Engineering, Cairo, Egypt
- Computer Engineering Department, Faculty of Engineering and Technology, Arab Academy for Science, Technology & Maritime Transport (AASTMT), Cairo, Egypt
| | - Ashraf F Tammam
- Computer Engineering Department, Faculty of Engineering and Technology, Arab Academy for Science, Technology & Maritime Transport (AASTMT), Cairo, Egypt.
| | - Ibrahim M Selim
- Faculty of Computers and Artificial Intelligence, Sadat City University, Sadat City, Egypt
| | - Mohamed Eassa
- Computer Science Department, Thebes Higher Institute for Engineering, Cairo, Egypt
- Computer Science Department, Faculty of Information Systems and Computer Science, October 6 University, Giza, Egypt
| |
Collapse
|
2
|
Tudor MS, Gheorman V, Simeanu GM, Dobrinescu A, Pădureanu V, Dinescu VC, Forțofoiu MC. Evolutive Models, Algorithms and Predictive Parameters for the Progression of Hepatic Steatosis. Metabolites 2024; 14:198. [PMID: 38668326 PMCID: PMC11052048 DOI: 10.3390/metabo14040198] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/12/2024] [Revised: 03/29/2024] [Accepted: 04/01/2024] [Indexed: 04/28/2024] Open
Abstract
The utilization of evolutive models and algorithms for predicting the evolution of hepatic steatosis holds immense potential benefits. These computational approaches enable the analysis of complex datasets, capturing temporal dynamics and providing personalized prognostic insights. By optimizing intervention planning and identifying critical transition points, they promise to revolutionize our approach to understanding and managing hepatic steatosis progression, ultimately leading to enhanced patient care and outcomes in clinical settings. This paradigm shift towards a more dynamic, personalized, and comprehensive approach to hepatic steatosis progression signifies a significant advancement in healthcare. The application of evolutive models and algorithms allows for a nuanced characterization of disease trajectories, facilitating tailored interventions and optimizing clinical decision-making. Furthermore, these computational tools offer a framework for integrating diverse data sources, creating a more holistic understanding of hepatic steatosis progression. In summary, the potential benefits encompass the ability to analyze complex datasets, capture temporal dynamics, provide personalized prognostic insights, optimize intervention planning, identify critical transition points, and integrate diverse data sources. The application of evolutive models and algorithms has the potential to revolutionize our understanding and management of hepatic steatosis, ultimately leading to improved patient outcomes in clinical settings.
Collapse
Affiliation(s)
- Marinela Sînziana Tudor
- Doctoral School, University of Medicine and Pharmacy of Craiova, Petru Rareș 2 Str, 200349 Craiova, Romania; (M.S.T.); (G.-M.S.)
| | - Veronica Gheorman
- Department 3 Medical Semiology, University of Medicine and Pharmacy of Craiova, Petru Rareș 2 Str, 200349 Craiova, Romania;
| | - Georgiana-Mihaela Simeanu
- Doctoral School, University of Medicine and Pharmacy of Craiova, Petru Rareș 2 Str, 200349 Craiova, Romania; (M.S.T.); (G.-M.S.)
| | - Adrian Dobrinescu
- Department of Thoracic Surgery, University of Medicine and Pharmacy of Craiova, Petru Rareș 2 Str, 200349 Craiova, Romania
| | - Vlad Pădureanu
- Department 3 Medical Semiology, University of Medicine and Pharmacy of Craiova, Petru Rareș 2 Str, 200349 Craiova, Romania;
| | - Venera Cristina Dinescu
- Department of Health Promotion and Occupational Medicine, University of Medicine and Pharmacy of Craiova, Petru Rareș 2 Str, 200349 Craiova, Romania;
| | - Mircea-Cătălin Forțofoiu
- Department 3 Medical Semiology, University of Medicine and Pharmacy of Craiova, Clinical Municipal Hospital “Philanthropy” of Craiova, 200143 Craiova, Romania;
| |
Collapse
|
3
|
Zamanian H, Shalbaf A, Zali MR, Khalaj AR, Dehghan P, Tabesh M, Hatami B, Alizadehsani R, Tan RS, Acharya UR. Application of artificial intelligence techniques for non-alcoholic fatty liver disease diagnosis: A systematic review (2005-2023). COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024; 244:107932. [PMID: 38008040 DOI: 10.1016/j.cmpb.2023.107932] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/19/2023] [Revised: 11/13/2023] [Accepted: 11/15/2023] [Indexed: 11/28/2023]
Abstract
BACKGROUND AND OBJECTIVES Non-alcoholic fatty liver disease (NAFLD) is a common liver disease with a rapidly growing incidence worldwide. For prognostication and therapeutic decisions, it is important to distinguish the pathological stages of NAFLD: steatosis, steatohepatitis, and liver fibrosis, which are definitively diagnosed on invasive biopsy. Non-invasive ultrasound (US) imaging, including US elastography technique, and clinical parameters can be used to diagnose and grade NAFLD and its complications. Artificial intelligence (AI) is increasingly being harnessed for developing NAFLD diagnostic models based on clinical, biomarker, or imaging data. In this work, we systemically reviewed the literature for AI-enabled NAFLD diagnostic models based on US (including elastography) and clinical (including serological) data. METHODS We performed a comprehensive search on Google Scholar, Scopus, and PubMed search engines for articles published between January 2005 and June 2023 related to AI models for NAFLD diagnosis based on US and/or clinical parameters using the following search terms: "non-alcoholic fatty liver disease", "non-alcoholic steatohepatitis", "deep learning", "machine learning", "artificial intelligence", "ultrasound imaging", "sonography", "clinical information". RESULTS We reviewed 64 published models that used either US (including elastography) or clinical data input to detect the presence of NAFLD, non-alcoholic steatohepatitis, and/or fibrosis, and in some cases, the severity of steatosis, inflammation, and/or fibrosis as well. The performances of the published models were summarized, and stratified by data input and algorithms used, which could be broadly divided into machine and deep learning approaches. CONCLUSION AI models based on US imaging and clinical data can reliably detect NAFLD and its complications, thereby reducing diagnostic costs and the need for invasive liver biopsy. The models offer advantages of efficiency, accuracy, and accessibility, and serve as virtual assistants for specialists to accelerate disease diagnosis and reduce treatment costs for patients and healthcare systems.
Collapse
Affiliation(s)
- H Zamanian
- Department of Biomedical Engineering and Medical Physics, School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - A Shalbaf
- Department of Biomedical Engineering and Medical Physics, School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
| | - M R Zali
- Gastroenterology and Liver Diseases Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - A R Khalaj
- Tehran obesity treatment center, Department of Surgery, Faculty of Medicine, Shahed University, Tehran, Iran
| | - P Dehghan
- Department of Radiology, Imaging Department, Taleghani Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - M Tabesh
- Cardiac Primary Prevention Research Center, Cardiovascular Diseases Research, Tehran University of Medical Sciences, Tehran, Iran
| | - B Hatami
- Gastroenterology and Liver Diseases Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - R Alizadehsani
- Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Waurn Ponds, VIC, Australia
| | - Ru-San Tan
- National Heart Centre Singapore, Singapore 169609, Singapore; Duke-NUS Medical School, Singapore
| | - U Rajendra Acharya
- School of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba, QLD, Australia; Centre for Health Research, University of Southern Queensland, Australia
| |
Collapse
|
4
|
Nduma BN, Al-Ajlouni YA, Njei B. The Application of Artificial Intelligence (AI)-Based Ultrasound for the Diagnosis of Fatty Liver Disease: A Systematic Review. Cureus 2023; 15:e50601. [PMID: 38222117 PMCID: PMC10788148 DOI: 10.7759/cureus.50601] [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] [Accepted: 12/14/2023] [Indexed: 01/16/2024] Open
Abstract
Fatty liver disease, also known as hepatic steatosis, poses a significant global health concern due to the excessive accumulation of fat within the liver. If left untreated, this condition can give rise to severe complications. Recent advances in artificial intelligence (AI, specifically AI-based ultrasound imaging) offer promising tools for diagnosing this condition. This review endeavors to explore the current state of research concerning AI's role in diagnosing fatty liver disease, with a particular emphasis on imaging methods. To this end, a comprehensive search was conducted across electronic databases, including Google Scholar and Embase, to identify relevant studies published between January 2010 and May 2023, with keywords such as "fatty liver disease" and "artificial intelligence (AI)." The article selection process adhered to the PRISMA framework, ultimately resulting in the inclusion of 13 studies. These studies leveraged AI-assisted ultrasound due to its accessibility and cost-effectiveness, and they hailed from diverse countries, including India, China, Singapore, the United States, Egypt, Iran, Poland, Malaysia, and Korea. These studies employed a variety of AI classifiers, such as support vector machines, convolutional neural networks, multilayer perceptron, fuzzy Sugeno, and probabilistic neural networks, all of which demonstrated a remarkable level of precision. Notably, one study even achieved a diagnostic accuracy rate of 100%, underscoring AI's potential in diagnosing fatty liver disease. Nevertheless, the review acknowledged certain limitations within the included studies, with the majority featuring relatively small sample sizes, often encompassing fewer than 100 patients. Additionally, the variability in AI algorithms and imaging techniques added complexity to the comparative analysis. In conclusion, this review emphasizes the potential of AI in enhancing the diagnosis and management of fatty liver disease through advanced imaging techniques. Future research endeavors should prioritize the execution of large-scale studies that employ standardized AI algorithms and imaging techniques to validate AI's utility in diagnosing this prevalent health condition.
Collapse
Affiliation(s)
- Basil N Nduma
- Internal Medicine, Merit Health Wesley, Hattiesburg, USA
| | | | - Basile Njei
- Medicine, Yale School of Medicine, New Haven, USA
| |
Collapse
|
5
|
Yao Y, Zhang Z, Peng B, Tang J. Bio-Inspired Network for Diagnosing Liver Steatosis in Ultrasound Images. Bioengineering (Basel) 2023; 10:768. [PMID: 37508795 PMCID: PMC10376777 DOI: 10.3390/bioengineering10070768] [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: 04/26/2023] [Revised: 06/15/2023] [Accepted: 06/23/2023] [Indexed: 07/30/2023] Open
Abstract
Using ultrasound imaging to diagnose liver steatosis is of great significance for preventing diseases such as cirrhosis and liver cancer. Accurate diagnosis under conditions of low quality, noise and poor resolutions is still a challenging task. Physiological studies have shown that the visual cortex of the biological visual system has selective attention neural mechanisms and feedback regulation of high features to low features. When processing visual information, these cortical regions selectively focus on more sensitive information and ignore unimportant details, which can effectively extract important features from visual information. Inspired by this, we propose a new diagnostic network for hepatic steatosis. In order to simulate the selection mechanism and feedback regulation of the visual cortex in the ventral pathway, it consists of a receptive field feature extraction module, parallel attention module and feedback connection. The receptive field feature extraction module corresponds to the inhibition of the non-classical receptive field of V1 neurons on the classical receptive field. It processes the input image to suppress the unimportant background texture. Two types of attention are adopted in the parallel attention module to process the same visual information and extract different important features for fusion, which improves the overall performance of the model. In addition, we construct a new dataset of fatty liver ultrasound images and validate the proposed model on this dataset. The experimental results show that the network has good performance in terms of sensitivity, specificity and accuracy for the diagnosis of fatty liver disease.
Collapse
Affiliation(s)
- Yuan Yao
- General Practice Medical Center, West China Hospital, Sichuan University, Chengdu 610044, China
| | - Zhenguang Zhang
- School of Automation, Guangxi University of Science and Technology, Liuzhou 545006, China
| | - Bo Peng
- School of Computing and Artificial Intelligent, Southwest Jiaotong University, Chengdu 611756, China
| | - Jin Tang
- Tiaodenghe Community Health Service Center, Chengdu 610066, China
| |
Collapse
|
6
|
Manjunath RV, Ghanshala A, Kwadiki K. Deep learning algorithm performance evaluation in detection and classification of liver disease using CT images. MULTIMEDIA TOOLS AND APPLICATIONS 2023:1-18. [PMID: 37362702 PMCID: PMC10183675 DOI: 10.1007/s11042-023-15627-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 05/19/2022] [Revised: 08/10/2022] [Accepted: 04/22/2023] [Indexed: 06/28/2023]
Abstract
To diagnose the liver diseases computed tomography images are used. Most of the time even experienced radiologists find it very tough to note the type, size, and severity of the tumor from computed tomography images due to various complexities involved around the liver. In recent years it is very much essential to develop a computer-assisted imaging technique to diagnose liver disease in turn which improves the diagnosis of a doctor. This paper explains a novel deep learning model for detecting a liver disease tumor and its classification. Tumor from computed tomography images has been classified between Metastasis and Cholangiocarcinoma. We demonstrate that our model predominantly performs very well concerning the accuracy, dice similarity coefficient, and specificity parameters compared to well-known existing algorithms, and adapts very well for different datasets. A dice similarity coefficient value of 98.59% indicates the supremacy of the model.
Collapse
Affiliation(s)
- R. V. Manjunath
- Department of Electronics &Communication Engineering, Dayananda Sagar Academy of Technology and Management, Bangalore-82, India
| | | | - Karibasappa Kwadiki
- Department of CS&IT, Graphic Era Deemed to be University, Dehradun, 248002 India
| |
Collapse
|
7
|
An efficient classification of cirrhosis liver disease using hybrid convolutional neural network-capsule network. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2022.104152] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
|
8
|
Combined CNN and Pixel Feature Image for Fatty Liver Ultrasound Image Classification. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2022; 2022:9385734. [PMID: 36561737 PMCID: PMC9767727 DOI: 10.1155/2022/9385734] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/16/2022] [Revised: 11/17/2022] [Accepted: 11/19/2022] [Indexed: 12/15/2022]
Abstract
Recent revolutionary results of deep learning indicate the advent of reliable classifiers to perform difficult tasks in medical diagnosis. Fatty liver is a common liver disease, and it is also one of the major challenges people face in disease prevention. It will cause many complications, which need to be found and treated in time. In the field of automatic diagnosis of fatty liver ultrasound images, there are problems of less data amount, and the pathological images of different severity are similar. Therefore, this paper proposes a classification method through combining convolutional neural network with the differential image patches based on pixel-level features for fatty liver ultrasonic images. It can automatically diagnose the ultrasonic images of normal liver, low-grade fatty liver, moderate grade fatty liver, and severe fatty liver. The proposed method not only solves the problem of less data amount but also improves the accuracy of classification. Compared with other deep learning methods and traditional methods, the experimental results show that our method has better accuracy than other classification methods.
Collapse
|
9
|
Mitani Y, Fisher RB, Fujita Y, Hamamoto Y, Sakaida I. Image Correction Methods for Regions of Interest in Liver Cirrhosis Classification on CNNs. SENSORS (BASEL, SWITZERLAND) 2022; 22:3378. [PMID: 35591069 PMCID: PMC9105852 DOI: 10.3390/s22093378] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 03/31/2022] [Revised: 04/24/2022] [Accepted: 04/26/2022] [Indexed: 06/15/2023]
Abstract
The average error rate in liver cirrhosis classification on B-mode ultrasound images using the traditional pattern recognition approach is still too high. In order to improve the liver cirrhosis classification performance, image correction methods and a convolution neural network (CNN) approach are focused on. The impact of image correction methods on region of interest (ROI) images that are input into the CNN for the purpose of classifying liver cirrhosis based on data from B-mode ultrasound images is investigated. In this paper, image correction methods based on tone curves are developed. The experimental results show positive benefits from the image correction methods by improving the image quality of ROI images. By enhancing the image contrast of ROI images, the image quality improves and thus the generalization ability of the CNN also improves.
Collapse
Affiliation(s)
- Yoshihiro Mitani
- National Institute of Technology, Ube College, Ube 755-8555, Japan
| | - Robert B. Fisher
- School of Informatics, The University of Edinburgh, Edinburgh EH8 9BT, UK;
| | - Yusuke Fujita
- Faculty of Engineering, Yamaguchi University, Ube 755-8611, Japan; (Y.F.); (Y.H.)
| | - Yoshihiko Hamamoto
- Faculty of Engineering, Yamaguchi University, Ube 755-8611, Japan; (Y.F.); (Y.H.)
| | - Isao Sakaida
- School of Medicine and Health Sciences, Yamaguchi University, Ube 755-8505, Japan;
| |
Collapse
|