Related Experiment Video
Updated: Jan 10, 2026
Non-Invasive Visualization of Nailbed Microvascular Morphology in Mice Using Capillaroscopy
Published on: February 28, 2025
DGPCNet: anemia detection from multimodal palm, fingernails, and eye conjunctiva images using deep global pyramid
Trushna Deotale1, Seemanti Saha2
1Department of Electronics Engineering, GH Raisoni College of Engineering, Affiliated with Rashtrasant Tukadoji Maharaj Nagpur University, Nagpur, India.
Insights
This study introduces a noninvasive anemia detection method for children using the Deep Global Pyramid Convolutional Network (DGPCNet). The model achieves high accuracy by analyzing palm, fingernail, and eye conjunctiva images, offering a cost-effective diagnostic solution.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Healthcare
- Pediatric Hematology
Background:
- Anemia is a prevalent hematological disorder impacting children's development.
- Early anemia detection in children is crucial for timely intervention and improved outcomes.
- Noninvasive diagnostic techniques offer cost-effectiveness and ease of use, especially for pediatric patients.
Purpose of the Study:
- To develop and evaluate a novel noninvasive anemia detection model for children.
- To leverage deep learning for analyzing anatomical images for anemia diagnosis.
Main Methods:
- Proposed the Deep Global Pyramid Convolutional Network (DGPCNet) model for anemia detection.
- Utilized Grayscale-based Deep Statistical Structural Edge (GDSSE) features for enhanced representation.
- Analyzed images from three anatomical regions: palm, fingernails, and eye conjunctiva.
Main Results:
- The DGPCNet model achieved 97.66% accuracy with fused features.
- Demonstrated high sensitivity (97.19%) and specificity (98.14%).
- Reported a False Positive Rate (FPR) of 0.018 and False Negative Rate (FNR) of 0.028.
Conclusions:
- The proposed DGPCNet model with fused features significantly improves anemia detection accuracy and reliability in children.
- Hierarchy-based learning within the model enhances diagnostic performance.
- Noninvasive analysis of anatomical images provides a promising approach for pediatric anemia screening.
Background:
Anemia is one of the most common hematological disorders causing fatigue, increased vulnerability to infection, low birth weight, and threatening the physical and mental development of children. Hence, the early identification reduces the risk of patients and facilitates early intervention. On the other hand, the blood collection of the adults is simple, and the results will be precise, and directly show the cause of anemia in adults. Noninvasive techniques for anemia diagnosis are specific for young children and pediatric patients improving the cost-effectiveness.
Research Design And Methods:
Consequently, this research focus on anemia detection for children using the proposed Deep Global Pyramid Convolutional Network (DGPCNet) model. Specifically, the proposed approach involves anemia detection through three anatomical regions, such as palm, fingernails, and eye conjunctiva images. In the proposed method, the Grayscale-based Deep Statistical Structural Edge features (GDSSE) provide enriched feature representation by integrating multiple feature perspectives.
Results:
The experimental results report that the proposed method using fused features attains 97.66% accuracy, 97.19% sensitivity, 98.14% specificity, 97.90% precision, 0.018 FPR, and 0.028 FNR for 90% of training.
Conclusions:
Moreover, applying fused features in the proposed DGPCNet enables hierarchy-based learning thereby significantly boosting the accuracy and reliability of detection.
