Journal: Frontiers in Medicine

Article Title: An interpretable deep concatenated architecture for osteoporosis detection using enhanced knee radiographs

doi: 10.3389/fmed.2026.1849727

Figure Lengend Snippet: Output of Normal and osteoporosis images after applying RG filter.

Article Snippet: The data collected in this paper is found in the publicly accessible Kaggle dataset called Osteoporosis Image Dataset.

Techniques:

Journal: Frontiers in Medicine

Article Title: An interpretable deep concatenated architecture for osteoporosis detection using enhanced knee radiographs

doi: 10.3389/fmed.2026.1849727

Figure Lengend Snippet: Grad-CAM visualization showing regions influencing model predictions for Normal and Osteoporosis classes. Warmer colors indicate higher importance.

Article Snippet: The data collected in this paper is found in the publicly accessible Kaggle dataset called Osteoporosis Image Dataset.

Techniques:

Journal: Healthcare Technology Letters

Article Title: Internet of Medical Things Enabled Multimodal Framework: Deep Machine Learning for Chronic Cardiac Disease Prediction in Healthcare 5.0

doi: 10.1049/htl2.70063

Figure Lengend Snippet: ECG Images from Dataset 1 labelled by category.

Article Snippet: As two publicly accessible ECG image datasets were obtained from Kaggle and Mendeley, where Institutional Review Board (IRB) approval was not necessary because both datasets were pre‐anonymised and all patient‐identifiable information had already been eliminated, both of these were utilised in this study, and all the images from both of the datasets were resized to 128 × 128 pixels to make them uniform, and then these all were normalised to ensure consistent input scales for the convolutional neural networks (CNNs).

Techniques:

Journal: Healthcare Technology Letters

Article Title: Internet of Medical Things Enabled Multimodal Framework: Deep Machine Learning for Chronic Cardiac Disease Prediction in Healthcare 5.0

doi: 10.1049/htl2.70063

Figure Lengend Snippet: ECG images from dataset 2 labelled by category.

Article Snippet: As two publicly accessible ECG image datasets were obtained from Kaggle and Mendeley, where Institutional Review Board (IRB) approval was not necessary because both datasets were pre‐anonymised and all patient‐identifiable information had already been eliminated, both of these were utilised in this study, and all the images from both of the datasets were resized to 128 × 128 pixels to make them uniform, and then these all were normalised to ensure consistent input scales for the convolutional neural networks (CNNs).

Techniques:

Journal: Healthcare Technology Letters

Article Title: Internet of Medical Things Enabled Multimodal Framework: Deep Machine Learning for Chronic Cardiac Disease Prediction in Healthcare 5.0

doi: 10.1049/htl2.70063

Figure Lengend Snippet: ECG analysis workflow.

Article Snippet: As two publicly accessible ECG image datasets were obtained from Kaggle and Mendeley, where Institutional Review Board (IRB) approval was not necessary because both datasets were pre‐anonymised and all patient‐identifiable information had already been eliminated, both of these were utilised in this study, and all the images from both of the datasets were resized to 128 × 128 pixels to make them uniform, and then these all were normalised to ensure consistent input scales for the convolutional neural networks (CNNs).

Techniques:

Journal: Bioinformation

Article Title: Identification of Hub genes in melasma using integrated transcriptomic analysis

doi: 10.6026/973206300220001

Figure Lengend Snippet: Volcano plots illustrating the distribution of upregulated and downregulated DEGs for GSE207744 dataset comparing lesional vs non-lesional. Red and green dots represent statistically significant upregulated and downregulated genes, respectively.

Article Snippet: After conducting a comprehensive search, the Gene Expression Omnibus (GEO) dataset accession numbers GSE207744 , GSE227015 , and GSE185308 were chosen from the National Center for Biotechnology Information (NCBI) [ ].

Techniques: