Article
Health Care Sciences & Services
Veysel Harun Sahin, Ismail Oztel, Gozde Yolcu Oztel
Summary: This article introduces an Android mobile application based on deep learning that can be used to quickly identify and isolate infected individuals during human monkeypox outbreaks. The application collects images through the device's camera and uses a deep convolutional neural network for classification to detect monkeypox. The system has been successfully tested on three devices and achieved a classification accuracy rate of 91.11%.
JOURNAL OF MEDICAL SYSTEMS
(2022)
Article
Dentistry, Oral Surgery & Medicine
W. T. Fu, Q. K. Zhu, N. Li, Y. Q. Wang, S. L. Deng, H. P. Chen, J. Shen, L. Y. Meng, Z. Bian
Summary: The study proposed a novel 3D deep convolutional neural network algorithm, named PAL-Net, for quickly and accurately detecting and segmenting periapical lesions (PALs) associated with apical periodontitis (AP) on cone beam computed tomography (CBCT) images. The algorithm improved the diagnostic performance and speed of dentists and showed comparable or superior segmentation accuracy to existing state-of-the-art algorithms.
JOURNAL OF DENTAL RESEARCH
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Regine Mariette Perl, Rainer Grimmer, Tobias Hepp, Marius Stefan Horger
Summary: This study compared the performance of two approved computer-aided detection systems in detecting pulmonary solid nodules in an oncologic cohort, with results showing that the new deep learning-based CAD software (VD20A) had similar sensitivity to the conventional CAD software (VD10F) but significantly higher specificity.
INVESTIGATIVE RADIOLOGY
(2021)
Article
Medicine, General & Internal
Theyazn H. H. Aldhyani, Amit Verma, Mosleh Hmoud Al-Adhaileh, Deepika Koundal
Summary: Skin, as the primary protective layer of internal organs, is increasingly prone to various diseases due to pollution and other factors. To address this issue, a lightweight and efficient model for accurate classification of skin lesions is proposed, utilizing dynamic-sized kernels and ReLU/leakyReLU activation functions. The model achieves high overall accuracy and outperforms state-of-the-art heavy models.
Review
Medicine, General & Internal
Krishnaraj Chadaga, Srikanth Prabhu, Niranjana Sampathila, Sumith Nireshwalya, Swathi S. Katta, Ru-San Tan, U. Rajendra Acharya
Summary: Monkeypox or Mpox is an infectious virus mainly found in Africa. Symptoms include headaches, chills, fever, lumps, and rashes. Artificial intelligence models have been developed for accurate and early diagnosis.
Article
Computer Science, Information Systems
Natasha Nigar, Muhammad Umar, Muhammad Kashif Shahzad, Shahid Islam, Douhadji Abalo
Summary: In this paper, an explainable artificial intelligence (XAI) based skin lesion classification system is proposed to improve the accuracy of skin lesion classification and assist dermatologists in rational diagnosis. The XAI model is validated using ISIC 2019 dataset, achieving high classification accuracy and providing visual explanations using the LIME framework. The integration of explainability enhances the applicability of the model in real clinical practice.
Article
Automation & Control Systems
G. Reshma, Chiai Al-Atroshi, Vinay Kumar Nassa, B. T. Geetha, Gurram Sunitha, Mohammad Gouse Galety, S. Neelakandan
Summary: Intelligent automation in the healthcare sector is becoming more prevalent with the integration of AI techniques, assisting in better healthcare decision-making. Skin lesion segmentation and classification are crucial in intelligent systems for early and precise skin cancer diagnosis, despite challenges such as artifacts and variable lesion images. The presented IMLT-DL model incorporates various advanced techniques to achieve a high accuracy of 0.992 in skin lesion diagnosis.
INTELLIGENT AUTOMATION AND SOFT COMPUTING
(2022)
Article
Infectious Diseases
Amir Sorayaie Azar, Amin Naemi, Samin Babaei Rikan, Jamshid Bagherzadeh Mohasefi, Habibollah Pirnejad, Uffe Kock Wiil
Summary: In May 2022, the WHO European Region declared an atypical Monkeypox epidemic, which raised concerns about the global nature of the disease. Researchers have applied Deep Neural Networks (DNNs) to detect Monkeypox disease, achieving superior performance compared to previous studies. The utilization of LIME and Grad-Cam techniques enhances the understanding of affected areas and their relevance in diagnosing Monkeypox.
BMC INFECTIOUS DISEASES
(2023)
Article
Medicine, General & Internal
Yunchao Yin, Derya Yakar, Jules J. G. Slangen, Frederik J. H. Hoogwater, Thomas C. C. Kwee, Robbert J. J. de Haas
Summary: This study investigated the use of a convolutional neural network (CNN) to differentiate gallbladder cancer from benign gallbladder lesions. It was found that training the CNN using both the gallbladder and adjacent liver parenchyma improved its diagnostic performance. However, combining the CNN with radiological visual analysis did not further improve its ability to differentiate between the two.
Article
Medicine, General & Internal
Hiroaki Matsui, Shunsuke Kamba, Hideka Horiuchi, Sho Takahashi, Masako Nishikawa, Akihiro Fukuda, Aya Tonouchi, Natsumaro Kutsuna, Yuki Shimahara, Naoto Tamai, Kazuki Sumiyama
Summary: Researchers developed and evaluated a CADe system based on YOLO v3 for detecting and localizing colorectal lesions, demonstrating its accuracy and speed in detecting lesions from video data, reducing operator biases.
Article
Engineering, Multidisciplinary
Yousef Asiri, Hanan T. Halawani, Abeer D. Algarni, Adwan A. Alanazi
Summary: This study proposes an Intelligent Internet of Things with Deep learning Enabled Skin Lesion Diagnosis (IIoT-DLSLD) model for healthcare, focusing on the early detection of melanoma skin cancer. The model utilizes IoT devices to capture dermoscopic images and classify skin lesions. It employs Gaussian filtering for noise elimination and Otsu thresholding with swallow swarm optimization for lesion segmentation. For classification, it uses MobileNet v2 for feature extraction and emperor penguin optimizer based deep wavelet neural network. Experimental validation on ISIC dataset shows better performance compared to other state of the art skin lesion classifiers.
ALEXANDRIA ENGINEERING JOURNAL
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Alan A. Peters, Andreas Christe, Oyunbileg von Stackelberg, Moritz Pohl, Hans-Ulrich Kauczor, Claus Peter Heussel, Mark O. Wielpuetz, Lukas Ebner
Summary: This study evaluated and compared two different computer-aided diagnosis (CAD) systems in terms of measurement accuracy for artificial pulmonary nodules. The results showed that the volumetric inaccuracy of CAD systems may affect patient management and require supervision and/or manual correction by a radiologist.
EUROPEAN RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Arjan M. Groen, Rik Kraan, Shahira F. Amirkhan, Joost G. Daams, Mario Maas
Summary: This study provides a quantitative overview and discusses the implications of methodological choices for the explainability of computer aided diagnosis studies in radiology that use end-to-end deep learning. The results show that a considerable portion of these studies provide explainability for the purpose of model visualization and inspection, but the quality of these explanations is generally not measured.
EUROPEAN JOURNAL OF RADIOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Muhammad Ajmal, Muhammad Attique Khan, Tallha Akram, Abdullah Alqahtani, Majed Alhaisoni, Ammar Armghan, Sara A. Althubiti, Fayadh Alenezi
Summary: This study proposes a deep learning and fuzzy entropy slime mould algorithm-based architecture for multiclass skin lesion classification. Experimental results show that this method achieves better accuracy compared to other techniques on two datasets.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Multidisciplinary Sciences
Entesar Hamed I. Eliwa, Amr Mohamed El Koshiry, Tarek Abd El-Hafeez, Heba Mamdouh Farghaly
Summary: Monkeypox is a rare viral disease that can cause severe illness in humans, and accurately diagnosing it based on visual inspection of skin lesions can be challenging. This study proposes an approach using Convolutional Neural Networks (CNNs) to classify monkeypox skin lesions, optimizing the model using the Grey Wolf Optimizer (GWO) algorithm. The optimized model achieved an impressive accuracy of 95.3%, indicating its potential for improving monkeypox diagnosis and surveillance.
SCIENTIFIC REPORTS
(2023)
Article
Computer Science, Software Engineering
Mamoona Humayun, Mahmood Niazi, Noor Zaman Jhanjhi, Sajjad Mahmood, Mohammad Alshayeb
Summary: The importance of secure software code for application's secure operation is highlighted in this article. The author proposes a readiness model for Secure Software Coding (SSC), which helps organizations understand and develop secure software code by mapping SSC challenges and best practices.
SOFTWARE-PRACTICE & EXPERIENCE
(2023)
Article
Chemistry, Multidisciplinary
Maram Fahaad Almufareh, Mamoona Humayun
Summary: Security and performance (SAP) are critical NFRs that affect the success of software projects. However, there is a lack of awareness of the factors influencing SAP verification, making it difficult for businesses to improve their verification efforts. This research study aimed to identify the mediating factors (MFs) influencing SAP verification and their corresponding actions. Ten MFs were identified and mapped with their actions, and mathematical modeling was used to examine their effects on SAP verification. Case studies were conducted to better understand the role of these MFs in the verification process.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Mamoona Humayun, Muhammad Ibrahim Khalil, Saleh Naif Almuayqil, N. Z. Jhanjhi
Summary: Breast cancer is a leading cause of mortality, and recent advancements in gene expression research and deep learning techniques have improved the accuracy of risk prediction, enabling tailored screening and prevention decisions.
Article
Chemistry, Multidisciplinary
Mamoona Humayun, Maram Fahaad Almufareh, Fatima Al-Quayed, Sulaiman Abdullah Alateyah, Mohammed Alatiyyah
Summary: Healthcare is crucial for all nations, but people in remote areas often lack timely access to sufficient healthcare facilities. This research proposes a framework that utilizes ICT technologies, such as IoT, 5G, and cloud computing, to provide secure and accessible healthcare services, especially in rural areas with limited resources. The proposed approach involves remote consultation and sharing of healthcare resources, and it has been validated through mathematical modeling and a case study.
APPLIED SCIENCES-BASEL
(2023)
Article
Chemistry, Multidisciplinary
Mamoona Humayun, Mahmood Niazi, Mohammed Assiri, Mariem Haoues
Summary: Global software development (GSD) is becoming standard practice in the software industry, but it is important to include security practices in GSD projects. This article aims to identify critical security practices for GSD projects by selecting and evaluating practices from existing literature. The findings reveal that 16 out of 36 security practices are critical for GSD projects, belonging to different phases of GSDLC.
APPLIED SCIENCES-BASEL
(2023)
Article
Chemistry, Multidisciplinary
Mohammed Assiri, Mamoona Humayun
Summary: Audits are crucial for organizations, especially in software development. Software auditing is an ongoing activity that helps businesses stay ahead and predict potential software issues. Auditors play a significant role in confirming data accuracy and monitoring information security. Despite the existence of audit tools, frauds still occur, which makes a transparent and secure audit process essential. This study proposes a blockchain-enabled framework that simplifies and improves the auditing process.
APPLIED SCIENCES-BASEL
(2023)
Article
Medicine, General & Internal
Ghadah Alwakid, Walaa Gouda, Mamoona Humayun, N. Z. Jhanjhi
Summary: With the use of deep learning and computer vision, it is now possible to quickly and accurately determine the presence of melanoma. This research utilized Inception-V3 and InceptionResnet-V2 strategies for melanoma recognition, with data augmentation to fix the sample imbalance. The proposed models outperformed previous studies with effectiveness of 0.89 for Inception-V3 and 0.91 for InceptionResnet-V2.
Article
Medicine, General & Internal
Bader Aldughayfiq, Farzeen Ashfaq, N. Z. Jhanjhi, Mamoona Humayun
Summary: Retinoblastoma is a rare and aggressive form of childhood eye cancer. This project explores the use of LIME and SHAP to generate explanations for a deep learning model trained on retinoblastoma and non-retinoblastoma fundus images. The results demonstrate that LIME and SHAP effectively identify the regions and features contributing to the model's predictions, providing valuable insights into the decision-making process of the deep learning model. Additionally, the combination of deep learning and explainable AI achieved high accuracy on the test set, indicating the potential for improving retinoblastoma diagnosis and treatment.
Article
Computer Science, Information Systems
Asif Iqbal, Siffat Ullah Khan, Mahmood Niazi, Mamoona Humayun, Najm Us Sama, Arif Ali Khan, Aakash Ahmad
Summary: The value of data to a company means that it must be protected. When it comes to safeguarding their local and worldwide databases, businesses face a number of challenges. This systematic mapping study (SMS) analyzed 100 research publications and identified 20 challenges related to database security, including weak authorization system, weak access control, privacy issues/data leakage, lack of NOP security, and database attacks.
Article
Medicine, General & Internal
Ghadah Alwakid, Walaa Gouda, Mamoona Humayun
Summary: Diabetic retinopathy (DR) is a major cause of blindness in diabetic patients. This study used a deep learning model to classify and assess the severity of DR, using the APTOS 2019 Blindness Detection dataset. The proposed model achieved a test accuracy of 98.36% in detecting DR.
Article
Medicine, General & Internal
Bader Aldughayfiq, Farzeen Ashfaq, N. Z. Jhanjhi, Mamoona Humayun
Summary: Atrial fibrillation (AF) is a common cardiac arrhythmia with significant health risks. This study focuses on using photoplethysmogram (PPG) time series data and deep learning to classify AF and non-AF cases, taking advantage of the accessibility and ease of use of non-invasive methods such as Electrocardiogram (ECG) and PPG. The hybrid 1D CNN and BiLSTM model achieved a high accuracy of 95% in identifying AF, demonstrating its strong performance and reliable predictive capabilities.
Review
Health Care Sciences & Services
Maram Fahaad Almufareh, Sumaira Kausar, Mamoona Humayun, Samabia Tehsin
Summary: This manuscript explores the significance of motor imagery in assisting individuals with disabilities in their rehabilitation process, covering its fundamental mechanisms, applications, and potential advantages. It also highlights the need for further research and development in this field.
Article
Health Care Sciences & Services
Maram Fahaad Almufareh, Samabia Tehsin, Mamoona Humayun, Sumaira Kausar
Summary: Alzheimer's disease is a common neurological disorder and mental disability that impacts millions of people worldwide. This research introduces an attention-based mechanism for detecting Alzheimer's using MRI images and demonstrates its superior performance.