1
|
Mahbod A, Schaefer G, Dorffner G, Hatamikia S, Ecker R, Ellinger I. A dual decoder U-Net-based model for nuclei instance segmentation in hematoxylin and eosin-stained histological images. Front Med (Lausanne) 2022; 9:978146. [PMID: 36438040 PMCID: PMC9691672 DOI: 10.3389/fmed.2022.978146] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/25/2022] [Accepted: 10/28/2022] [Indexed: 11/03/2023] Open
Abstract
Even in the era of precision medicine, with various molecular tests based on omics technologies available to improve the diagnosis process, microscopic analysis of images derived from stained tissue sections remains crucial for diagnostic and treatment decisions. Among other cellular features, both nuclei number and shape provide essential diagnostic information. With the advent of digital pathology and emerging computerized methods to analyze the digitized images, nuclei detection, their instance segmentation and classification can be performed automatically. These computerized methods support human experts and allow for faster and more objective image analysis. While methods ranging from conventional image processing techniques to machine learning-based algorithms have been proposed, supervised convolutional neural network (CNN)-based techniques have delivered the best results. In this paper, we propose a CNN-based dual decoder U-Net-based model to perform nuclei instance segmentation in hematoxylin and eosin (H&E)-stained histological images. While the encoder path of the model is developed to perform standard feature extraction, the two decoder heads are designed to predict the foreground and distance maps of all nuclei. The outputs of the two decoder branches are then merged through a watershed algorithm, followed by post-processing refinements to generate the final instance segmentation results. Moreover, to additionally perform nuclei classification, we develop an independent U-Net-based model to classify the nuclei predicted by the dual decoder model. When applied to three publicly available datasets, our method achieves excellent segmentation performance, leading to average panoptic quality values of 50.8%, 51.3%, and 62.1% for the CryoNuSeg, NuInsSeg, and MoNuSAC datasets, respectively. Moreover, our model is the top-ranked method in the MoNuSAC post-challenge leaderboard.
Collapse
Affiliation(s)
- Amirreza Mahbod
- Institute for Pathophysiology and Allergy Research, Medical University of Vienna, Vienna, Austria
- Research Center for Medical Image Analysis and Artificial Intelligence, Department of Medicine, Danube Private University, Krems an der Donau, Austria
| | - Gerald Schaefer
- Department of Computer Science, Loughborough University, Loughborough, United Kingdom
| | - Georg Dorffner
- Institute of Artificial Intelligence, Medical University of Vienna, Vienna, Austria
| | - Sepideh Hatamikia
- Research Center for Medical Image Analysis and Artificial Intelligence, Department of Medicine, Danube Private University, Krems an der Donau, Austria
- Austrian Center for Medical Innovation and Technology, Wiener Neustadt, Austria
| | - Rupert Ecker
- Department of Research and Development, TissueGnostics GmbH, Vienna, Austria
| | - Isabella Ellinger
- Institute for Pathophysiology and Allergy Research, Medical University of Vienna, Vienna, Austria
| |
Collapse
|
2
|
Rana A, Chakraborty C, Sharma S, Dhawan S, Pani SK, Ashraf I. Internet of Medical Things-Based Secure and Energy-Efficient Framework for Health Care. BIG DATA 2022; 10:18-33. [PMID: 34958234 DOI: 10.1089/big.2021.0202] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/05/2023]
Abstract
The Internet of Medical Things (IoMT) is a collection of medical equipment and software that can help patients get better care. The purpose of this study is to improve the security of data collected through remote health monitoring of patients utilizing Constrained Application Protocol (CoAP). Asymmetric cryptography techniques may be used to assure the security of such sensor networks. For communication between different IoMT devices and a remote server, the safe CoAP is compatible with the Datagram Transport Layer Security (DTLS) protocol for creating a secure session using existing algorithms such as Lightweight Establishment of Secure Session. The DTLS layer of CoAP, in contrast, has shortcomings in key control, session establishment, and multicast message exchange. As a consequence, for IoMT communication, the creation of an efficient protocol for safe CoAP session establishment is needed. Thus, to solve the existing problems related to key management and multicast security in CoAP, we have proposed an efficient and secure communication technique to establish a secure session key between IoMT devices and distant servers using lightweight Energy-Efficient and Secure CoAP Elliptic Curve Cryptography (E2SCEC2). The advantage of using E2SCEC2 over other identification methods such as Rivest-Shamir-Adleman (RSA) is its compact key size, which allows it to use a smaller key size. This article also compares these algorithms on parameters such as time spent generating keys, signature generation, and verification of E2SCEC2 and RSA algorithms, as well as energy consumption and radio duty cycle, to see if they are compatible in constrained environments.
Collapse
Affiliation(s)
- Arun Rana
- Department of Electronics and Communication Engineering, Maharishi Markandeshwar (Deemed to be University), Mullana, India
| | - Chinmay Chakraborty
- Department of Electronics and Communication Engineering, Birla Institute of Technology, Jharkhand, India
| | - Sharad Sharma
- Department of Electronics and Communication Engineering, Maharishi Markandeshwar (Deemed to be University), Mullana, India
| | - Sachin Dhawan
- NSUT East Campus (Formerly Ambedkar Institute of Advanced Communication Technology and Research), Delhi, India
| | - Subhendu Kumar Pani
- Department of Computer Application, Krupajal Computer Academy, Odisha, India
| | - Imran Ashraf
- Department of Computer Application, Yeungnam University, Gyeongsan-si, Korea
| |
Collapse
|
3
|
Yasin S, Iqbal N, Ali T, Draz U, Alqahtani A, Irfan M, Rehman A, Glowacz A, Alqhtani S, Proniewska K, Brumercik F, Wzorek L. Severity Grading and Early Retinopathy Lesion Detection through Hybrid Inception-ResNet Architecture. SENSORS 2021; 21:s21206933. [PMID: 34696146 PMCID: PMC8537739 DOI: 10.3390/s21206933] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/21/2021] [Revised: 10/06/2021] [Accepted: 10/10/2021] [Indexed: 12/14/2022]
Abstract
Diabetic retinopathy (DR) is a diabetes disorder that disturbs human vision. It starts due to the damage in the light-sensitive tissues of blood vessels at the retina. In the beginning, DR may show no symptoms or only slight vision issues, but in the long run, it could be a permanent source of impaired vision, simply known as blindness in the advanced as well as in developing nations. This could be prevented if DR is identified early enough, but it can be challenging as we know the disease frequently shows rare signs until it is too late to deliver an effective cure. In our work, we recommend a framework for severity grading and early DR detection through hybrid deep learning Inception-ResNet architecture with smart data preprocessing. Our proposed method is composed of three steps. Firstly, the retinal images are preprocessed with the help of augmentation and intensity normalization. Secondly, the preprocessed images are given to the hybrid Inception-ResNet architecture to extract the vector image features for the categorization of different stages. Lastly, to identify DR and decide its stage (e.g., mild DR, moderate DR, severe DR, or proliferative DR), a classification step is used. The studies and trials have to reveal suitable outcomes when equated with some other previously deployed approaches. However, there are specific constraints in our study that are also discussed and we suggest methods to enhance further research in this field.
Collapse
Affiliation(s)
- Sana Yasin
- Faculty of Computing, University of Okara, Okara 56141, Pakistan; (S.Y.); (N.I.)
| | - Nasrullah Iqbal
- Faculty of Computing, University of Okara, Okara 56141, Pakistan; (S.Y.); (N.I.)
| | - Tariq Ali
- Department of Computer Science, COMSATS University Islamabad (CUI), Sahiwal Campus, Sahiwal 57000, Pakistan;
| | - Umar Draz
- Department of Computer Science, University of Sahiwal, Sahiwal 57000, Pakistan
- Computer Science Department, CUI, Lahore Campus, Lahore 54000, Pakistan
- Correspondence:
| | - Ali Alqahtani
- College of Computer Science and Information Systems, Najran University, Najran 11001, Saudi Arabia; (A.A.); (S.A.)
| | - Muhammad Irfan
- Electrical Engineering Department, College of Engineering, Najran University Saudi Arabia, Najran 61441, Saudi Arabia;
| | - Abdul Rehman
- IT Department, Superior University, Lahore 120000, Pakistan;
| | - Adam Glowacz
- Department of Automatic Control and Robotics, Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, AGH University of Science and Technology, al. A. Mickiewicza 30, 30-059 Krakow, Poland;
| | - Samar Alqhtani
- Electrical Engineering Department, College of Engineering, Najran University Saudi Arabia, Najran 61441, Saudi Arabia;
| | - Klaudia Proniewska
- Department of Bioinformatics and Telemedicine, Jagiellonian University Medical College, Anny 12, 31-008 Krakow, Poland;
| | - Frantisek Brumercik
- Department of Design and Machine Elements, Faculty of Mechanical Engineering, University of Zilina, Univerzitna 1, 010 26 Zilina, Slovakia;
| | - Lukasz Wzorek
- Wzorek. Systems, ul. Kapelanka 10/18, 30-347 Krakow, Poland;
| |
Collapse
|
4
|
Image processing algorithms in the assessment of grain damage degree. BIO-ALGORITHMS AND MED-SYSTEMS 2021. [DOI: 10.1515/bams-2021-0063] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
Abstract
Objectives
The paper presents preliminary results on the assessment of algorithms used in image processing of the grain damage degree. The purpose of the work is developing a tool allowing to analyse sample cross-sections of rye germs.
Methods
The analysis of the grain cross-sections was carried out on the basis of a series their photos taken at equal time intervals at a set depth. The cross-sections will be used to create additional virtual cross-sections allowing to analyse the whole sample volume. The ultimate plan is to generate two cross-sections perpendicular to each other. Based on volumetric data read from the sample section, a three-dimensional model of an object will be generated.
Results
The analysis of model surface will allowed us to detect possible grain damage. The developed method of preparing the research material and the proprietary application allowed for the identification of internal defects in the biological material (cereal grains).
Conclusions
The presented methodology may be used in the agri-food industry in the future. However, much research remains to be done. These works should primarily aim at significantly reducing the time-consuming nature of individual stages, as well as improving the quality of the reconstructed image.
Collapse
|
5
|
Ayyad SM, Shehata M, Shalaby A, Abou El-Ghar M, Ghazal M, El-Melegy M, Abdel-Hamid NB, Labib LM, Ali HA, El-Baz A. Role of AI and Histopathological Images in Detecting Prostate Cancer: A Survey. SENSORS (BASEL, SWITZERLAND) 2021; 21:2586. [PMID: 33917035 PMCID: PMC8067693 DOI: 10.3390/s21082586] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/05/2021] [Revised: 03/29/2021] [Accepted: 04/04/2021] [Indexed: 02/07/2023]
Abstract
Prostate cancer is one of the most identified cancers and second most prevalent among cancer-related deaths of men worldwide. Early diagnosis and treatment are substantial to stop or handle the increase and spread of cancer cells in the body. Histopathological image diagnosis is a gold standard for detecting prostate cancer as it has different visual characteristics but interpreting those type of images needs a high level of expertise and takes too much time. One of the ways to accelerate such an analysis is by employing artificial intelligence (AI) through the use of computer-aided diagnosis (CAD) systems. The recent developments in artificial intelligence along with its sub-fields of conventional machine learning and deep learning provide new insights to clinicians and researchers, and an abundance of research is presented specifically for histopathology images tailored for prostate cancer. However, there is a lack of comprehensive surveys that focus on prostate cancer using histopathology images. In this paper, we provide a very comprehensive review of most, if not all, studies that handled the prostate cancer diagnosis using histopathological images. The survey begins with an overview of histopathological image preparation and its challenges. We also briefly review the computing techniques that are commonly applied in image processing, segmentation, feature selection, and classification that can help in detecting prostate malignancies in histopathological images.
Collapse
Affiliation(s)
- Sarah M. Ayyad
- Computers and Systems Department, Faculty of Engineering, Mansoura University, Mansoura 35511, Egypt; (S.M.A.); (N.B.A.-H.); (L.M.L.); (H.A.A.)
| | - Mohamed Shehata
- BioImaging Laboratory, Bioengineering Department, University of Louisville, Louisville, KY 40292, USA; (M.S.); (A.S.)
| | - Ahmed Shalaby
- BioImaging Laboratory, Bioengineering Department, University of Louisville, Louisville, KY 40292, USA; (M.S.); (A.S.)
| | - Mohamed Abou El-Ghar
- Department of Radiology, Urology and Nephrology Center, Mansoura University, Mansoura 35516, Egypt;
| | - Mohammed Ghazal
- Department of Electrical and Computer Engineering, College of Engineering, Abu Dhabi University, Abu Dhabi 59911, United Arab Emirates;
| | - Moumen El-Melegy
- Department of Electrical Engineering, Assiut University, Assiut 71511, Egypt;
| | - Nahla B. Abdel-Hamid
- Computers and Systems Department, Faculty of Engineering, Mansoura University, Mansoura 35511, Egypt; (S.M.A.); (N.B.A.-H.); (L.M.L.); (H.A.A.)
| | - Labib M. Labib
- Computers and Systems Department, Faculty of Engineering, Mansoura University, Mansoura 35511, Egypt; (S.M.A.); (N.B.A.-H.); (L.M.L.); (H.A.A.)
| | - H. Arafat Ali
- Computers and Systems Department, Faculty of Engineering, Mansoura University, Mansoura 35511, Egypt; (S.M.A.); (N.B.A.-H.); (L.M.L.); (H.A.A.)
| | - Ayman El-Baz
- BioImaging Laboratory, Bioengineering Department, University of Louisville, Louisville, KY 40292, USA; (M.S.); (A.S.)
| |
Collapse
|
6
|
Abstract
The amazing fusion of the internet of things (IoT) into traditional health monitoring systems has produced remarkable advances in the field of e-health. Different wireless body area network devices and sensors are providing real-time health monitoring services. As the number of IoT devices is rapidly booming, technological and security challenges are also rising day by day. The data generated from sensor-based devices need confidentiality, integrity, authenticity, and end-to-end security for safe communication over the public network. IoT-based health monitoring systems work in a layered manner, comprising a perception layer, a network layer, and an application layer. Each layer has some security, and privacy concerns that need to be addressed accordingly. A lot of research has been conducted to resolve these security issues in different domains of IoT. Several frameworks for the security of IoT-based e-health systems have also been developed. This paper introduces a security framework for real-time health monitoring systems to ensure data confidentiality, integrity, and authenticity by using two common IoT protocols, namely constrained application protocol (CoAP) and message query telemetry transports (MQTT). This security framework aims to defend sensor data against the security loopholes while it is continuously transmitting over the layers and uses hypertext transfer protocols (HTTPs) for this purpose. As a result, it shields from the breach with a very low ratio of risk. The methodology of this paper focuses on how the security framework of IoT-based real-time health systems is protected under the tiers of CoAP and HTTPs. CoAP works alongside HTTPs and is responsible for providing end-to-end security solutions.
Collapse
|
7
|
Irfan M, Iftikhar MA, Yasin S, Draz U, Ali T, Hussain S, Bukhari S, Alwadie AS, Rahman S, Glowacz A, Althobiani F. Role of Hybrid Deep Neural Networks (HDNNs), Computed Tomography, and Chest X-rays for the Detection of COVID-19. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2021; 18:3056. [PMID: 33809665 PMCID: PMC8002268 DOI: 10.3390/ijerph18063056] [Citation(s) in RCA: 36] [Impact Index Per Article: 12.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/12/2021] [Revised: 02/28/2021] [Accepted: 03/04/2021] [Indexed: 12/28/2022]
Abstract
COVID-19 syndrome has extensively escalated worldwide with the induction of the year 2020 and has resulted in the illness of millions of people. COVID-19 patients bear an elevated risk once the symptoms deteriorate. Hence, early recognition of diseased patients can facilitate early intervention and avoid disease succession. This article intends to develop a hybrid deep neural networks (HDNNs), using computed tomography (CT) and X-ray imaging, to predict the risk of the onset of disease in patients suffering from COVID-19. To be precise, the subjects were classified into 3 categories namely normal, Pneumonia, and COVID-19. Initially, the CT and chest X-ray images, denoted as 'hybrid images' (with resolution 1080 × 1080) were collected from different sources, including GitHub, COVID-19 radiography database, Kaggle, COVID-19 image data collection, and Actual Med COVID-19 Chest X-ray Dataset, which are open source and publicly available data repositories. The 80% hybrid images were used to train the hybrid deep neural network model and the remaining 20% were used for the testing purpose. The capability and prediction accuracy of the HDNNs were calculated using the confusion matrix. The hybrid deep neural network showed a 99% classification accuracy on the test set data.
Collapse
Affiliation(s)
- Muhammad Irfan
- Electrical Engineering Department, College of Engineering, Najran University, Najran 61441, Saudi Arabia; (M.I.); (A.S.A.); (S.R.)
| | - Muhammad Aksam Iftikhar
- Department of Computer Science, Lahore Campus, COMSATS University Islamabad, Lahore 54000, Pakistan;
| | - Sana Yasin
- Department of Computer Science, University of OKara, Okara 56130, Pakistan;
| | - Umar Draz
- Department of Computer Science, University of Sahiwal, Sahiwal 57000, Pakistan; (U.D.); (S.H.)
| | - Tariq Ali
- Computer Science Department, Sahiwal Campus, COMSATS University Islamabad, Sahiwal 57000, Pakistan
| | - Shafiq Hussain
- Department of Computer Science, University of Sahiwal, Sahiwal 57000, Pakistan; (U.D.); (S.H.)
| | - Sarah Bukhari
- Department of Computer Science, National Fertilizer Corporation Institute of Engineering and Technology, Multan 60000, Pakistan;
| | - Abdullah Saeed Alwadie
- Electrical Engineering Department, College of Engineering, Najran University, Najran 61441, Saudi Arabia; (M.I.); (A.S.A.); (S.R.)
| | - Saifur Rahman
- Electrical Engineering Department, College of Engineering, Najran University, Najran 61441, Saudi Arabia; (M.I.); (A.S.A.); (S.R.)
| | - Adam Glowacz
- Department of Automatic Control and Robotics, Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, AGH University of Science and Technology, 30-059 Kraków, Poland;
| | - Faisal Althobiani
- Faculty of Maritime Studies, King Abdulaziz University, Jeddah 21577, Saudi Arabia;
| |
Collapse
|