Journal: Journal of Biomedical Physics & Engineering

Article Title: Advanced CNN Deep Learning Model for Diabetic Retinopathy Classification

doi: 10.31661/jbpe.v0i0.2406-1774

Figure Lengend Snippet: Dataset selection, preprocessing, and Deep Learning classification. It illustrates the main steps of the method, beginning with dataset selection followed by preprocessing, including image cropping, resizing, and contrast enhancement. Subsequently, three Deep Learning (DL) systems (Convolutional Neural Network (CNN), Decision Tree, and Logistic Regression) were chosen for the training and classification of DR. The results were then statistically analyzed using evaluation metrics such as accuracy, sensitivity, specificity, Area Under the Curve (AUC), and the confusion matrix.

Article Snippet: In another investigation, Adem [ ] used a CNN built on DL methods to classify retinal fundus images from the public Kaggle dataset; there was a 75% accuracy, 95% specificity, and 93% sensitivity in DR detection.

Techniques: Selection

Journal: Journal of Biomedical Physics & Engineering

Article Title: Advanced CNN Deep Learning Model for Diabetic Retinopathy Classification

doi: 10.31661/jbpe.v0i0.2406-1774

Figure Lengend Snippet: Schematic representation of Convolutional Neural Network (CNN) architecture shows the sequence of four filtration layers (convolutional layer, rectified linear unit layer, maxpooling layer, fully connected layer, and SoftMax layer).

Article Snippet: In another investigation, Adem [ ] used a CNN built on DL methods to classify retinal fundus images from the public Kaggle dataset; there was a 75% accuracy, 95% specificity, and 93% sensitivity in DR detection.

Techniques: Sequencing, Filtration

Journal: Journal of Biomedical Physics & Engineering

Article Title: Advanced CNN Deep Learning Model for Diabetic Retinopathy Classification

doi: 10.31661/jbpe.v0i0.2406-1774

Figure Lengend Snippet: Confusion matrixes of the Iraqi dataset. ( a ) using the decision tree model. ( b ) by Convolutional Neural Networks (CNN) model. ( c ) with Logistic Regression. True class data were collected based on the physician’s diagnosis. (PDR: Proliferative Diabetic Retinopathy)

Article Snippet: In another investigation, Adem [ ] used a CNN built on DL methods to classify retinal fundus images from the public Kaggle dataset; there was a 75% accuracy, 95% specificity, and 93% sensitivity in DR detection.

Techniques: Biomarker Discovery

Journal: Journal of Biomedical Physics & Engineering

Article Title: Advanced CNN Deep Learning Model for Diabetic Retinopathy Classification

doi: 10.31661/jbpe.v0i0.2406-1774

Figure Lengend Snippet: Confusion matrix of EyePACS ( a ) using decision tree model. ( b ) by logistic regression model. ( c ) with Convolutional Neural Network (CNN) model. (PDR: Proliferative Diabetic Retinopathy)

Article Snippet: In another investigation, Adem [ ] used a CNN built on DL methods to classify retinal fundus images from the public Kaggle dataset; there was a 75% accuracy, 95% specificity, and 93% sensitivity in DR detection.

Techniques:

Journal: Journal of Biomedical Physics & Engineering

Article Title: Advanced CNN Deep Learning Model for Diabetic Retinopathy Classification

doi: 10.31661/jbpe.v0i0.2406-1774

Figure Lengend Snippet: Confusion matrices of IDRiD, using ( a ) decision tree model, () logistic regression model. ( c ) Convolutional Neural Network (CNN) model. (PDR: Proliferative Diabetic Retinopathy)

Article Snippet: In another investigation, Adem [ ] used a CNN built on DL methods to classify retinal fundus images from the public Kaggle dataset; there was a 75% accuracy, 95% specificity, and 93% sensitivity in DR detection.

Techniques:

Journal: Frontiers in Physiology

Article Title: Grad-CAM based deep learning analytics for image-level colon disease classification based on graph neural networks and vision transformers

doi: 10.3389/fphys.2026.1734299

Figure Lengend Snippet: Architecture of the CNN-GNN pipeline for colon disease classification. The presentation of a detailed, step-by-step breakdown of the CNN-GNN pipeline, with each stage visually represented, highlighting the transition from raw medical images to classification outputs. Figure 5 illustrates the stages involved in analyzing a colonoscopy image using a hybrid approach combining Convolutional Neural Networks (CNN) and Graph Neural Networks (GNN). The diagram details the steps from input image processing to classification, including feature extraction, graph construction with K-NN, application of various GNN models, node-level embedding, global pooling, and linear classification with softmax.

Article Snippet: Alanazi et al ( ). showed that a simple CNN model, trained on the Kaggle H2E dataset, achieved 87% accuracy, outpacing several traditional classifiers.

Techniques: Extraction

Journal: Sensors (Basel, Switzerland)

Article Title: Multi-Chaotic HEOA for Hardware-Aware Neural Architecture Search: Brain Tumor Classification on FPGA

doi: 10.3390/s26092822

Figure Lengend Snippet: Vivado block design—CNN IP integration on the Zynq-7000 (Processing System + CNN accelerator via AXI Interconnect).

Article Snippet: The IP block generated by Vivado HLS was integrated into a complete system design on the Zynq-7000 platform using Vivado IP Integrator (Xilinx, San Jose, CA, USA). illustrates the system block design, comprising the Zynq-7000 Processing System (PS), the custom CNN IP ( brain_tumor_cnn_0 ), the AXI Interconnect, and the interrupt management module ensuring bidirectional communication between the ARM processor and the FPGA hardware accelerator.

Techniques: Blocking Assay