A smartphone-based application for an early skin disease prognosis: Towards a lean healthcare system via computer-based vision

Shahin, Mohammad; Chen, F. Frank; Hosseinzadeh, Ali Zare; Koodiani, Hamid Khodadadi; Shahin, Awni; Nafi, Omar

doi:10.1016/j.aei.2023.102036

Cited by 27 publications

(7 citation statements)

References 199 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After that we analyzed the type of skin images in our data set. We get perfect information about each type of image shown in figure 4 of our classification model, showcasing its competency in making accurate predictions across various aspects, and emphasizing its potential utility in practical applications [18], [19].…”

Section: Resultsmentioning

confidence: 91%

Integration of Multimodal Data Sources for Enhanced Skin Disease Classification and Cancer Prediction: A Study Leveraging Pre-Trained Models on HAM_10000 Metadata and Squamous Cell Carcinoma (SCC) Images.

Khan,

S.,

Gangodkar

2024

Preprint

View full text Add to dashboard Cite

Skin diseases, disorders, and deficiencies are fundamental issues in the human body. Over the last few decades, they have become widely prevalent, often leading to cancer. This spectrum of ailments ranges from benign conditions to potentially life-threatening cancers, posing significant challenges to global health. Accurate classification of these diseases and timely prediction of malignant transformations are crucial for effective diagnosis and treatment planning. In our research paper, we propose an innovative approach that levitation multimodal data integration to enhance the precision of skin disease classification and improve the prediction of cancerous transformations. The study utilizes the HAM_10000 Metadata, a dataset comprising diverse skin lesions, along with 100 high-resolution images of Squamous Cell Carcinoma (SCC). Pre-trained models, specifically multi-model CNNs, are employed to extract intricate patterns and features. By amalgamating information from these heterogeneous sources and implementing advanced machine learning techniques, the results highlight the effectiveness of this integrative methodology. This approach can revolutionize the fields of dermatology and oncology by providing patients with skin diseases accurate, efficient, and early diagnoses of skin disease. Through this method, it was discovered that SCC images might hold a higher priority for skin cancer identification, achieving an accuracy rate of 92% on the original dataset.

show abstract

Section: Resultsmentioning

confidence: 91%

Integration of Multimodal Data Sources for Enhanced Skin Disease Classification and Cancer Prediction: A Study Leveraging Pre-Trained Models on HAM_10000 Metadata and Squamous Cell Carcinoma (SCC) Images.

Khan,

S.,

Gangodkar

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Pooling or subsampling layers intersperse between convolutional layers, predominantly to reduce dimensionality, focus on dominant features, and enhance computational efficiency. Max-pooling is a favored technique, where the maximum value from a group of importance in the feature map is chosen, effectively condensing the data [100,101]. Deep CNN models usually integrate several convolutional and pooling layers in sequence, with each successive layer aiming to recognize more complex features.…”

Section: Custom-built Cnnmentioning

confidence: 99%

Improving the Concrete Crack Detection Process via a Hybrid Visual Transformer Algorithm

Shahin,

Chen,

Maghanaki

et al. 2024

Sensors

Self Cite

View full text Add to dashboard Cite

Inspections of concrete bridges across the United States represent a significant commitment of resources, given their biannual mandate for many structures. With a notable number of aging bridges, there is an imperative need to enhance the efficiency of these inspections. This study harnessed the power of computer vision to streamline the inspection process. Our experiment examined the efficacy of a state-of-the-art Visual Transformer (ViT) model combined with distinct image enhancement detector algorithms. We benchmarked against a deep learning Convolutional Neural Network (CNN) model. These models were applied to over 20,000 high-quality images from the Concrete Images for Classification dataset. Traditional crack detection methods often fall short due to their heavy reliance on time and resources. This research pioneers bridge inspection by integrating ViT with diverse image enhancement detectors, significantly improving concrete crack detection accuracy. Notably, a custom-built CNN achieves over 99% accuracy with substantially lower training time than ViT, making it an efficient solution for enhancing safety and resource conservation in infrastructure management. These advancements enhance safety by enabling reliable detection and timely maintenance, but they also align with Industry 4.0 objectives, automating manual inspections, reducing costs, and advancing technological integration in public infrastructure management.

show abstract

“…The HAM10000 dataset, which consists of high-quality pictures of seven different types of skin disorders, was analyzed by Shahin et al ( 6 ) using a combination of 16 different convolutional neural network simulations constructed using deep learning. Utilizing images of lesions as input, these algorithms were successful in correctly diagnosing and categorizing skin conditions.…”

Section: Literature Reviewmentioning

confidence: 99%

An integration of hybrid MCDA framework to the statistical analysis of computer-based health monitoring applications

Hongxia,

Juanjuan,

Han

et al. 2024

Front. Public Health

View full text Add to dashboard Cite

The surge in computer-based health surveillance applications, leveraging technologies like big data analytics, artificial intelligence, and the Internet of Things, aims to provide personalized and streamlined medical services. These applications encompass diverse functionalities, from portable health trackers to remote patient monitoring systems, covering aspects such as heart rate tracking, task monitoring, glucose level checking, medication reminders, and sleep pattern assessment. Despite the anticipated benefits, concerns about performance, security, and alignment with healthcare professionals’ needs arise with their widespread deployment. This study introduces a Hybrid Multi-Criteria Decision Analysis (MCDA) paradigm, combining the strengths of Additive Ratio Assessment (ARAS) and Analytic Hierarchy Process (AHP), to address the intricate nature of decision-making processes. The method involves selecting and structuring criteria hierarchically, providing a detailed evaluation of application efficacy. Professional stakeholders quantify the relative importance of each criterion through pairwise comparisons, generating criteria weights using AHP. The ARAS methodology then ranks applications based on their performance concerning the weighted criteria. This approach delivers a comprehensive assessment, considering factors like real-time capabilities, surgical services, and other crucial aspects. The research results provide valuable insights for healthcare practitioners, legislators, and technologists, aiding in deciding the adoption and integration of computer-based health monitoring applications, ultimately enhancing medical services and healthcare outcomes.

show abstract

A smartphone-based application for an early skin disease prognosis: Towards a lean healthcare system via computer-based vision

Cited by 27 publications

References 199 publications

Integration of Multimodal Data Sources for Enhanced Skin Disease Classification and Cancer Prediction: A Study Leveraging Pre-Trained Models on HAM_10000 Metadata and Squamous Cell Carcinoma (SCC) Images.

Integration of Multimodal Data Sources for Enhanced Skin Disease Classification and Cancer Prediction: A Study Leveraging Pre-Trained Models on HAM_10000 Metadata and Squamous Cell Carcinoma (SCC) Images.

Improving the Concrete Crack Detection Process via a Hybrid Visual Transformer Algorithm

An integration of hybrid MCDA framework to the statistical analysis of computer-based health monitoring applications

Contact Info

Product

Resources

About