Related Experiment Video
Updated: Sep 15, 2025
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
Integrating vision transformer-based deep learning model with kernel extreme learning machine for non-invasive
M Eliazer1, Sibi Amaran1, K Sreekumar1
1Department of Computing Technologies, SRM Institute of Science and Technology, Kattankulathur, Chennai, 603203, India.
Insights
This study introduces an AI model for early neonatal jaundice detection using image analysis. The Early Diagnosis of Neonatal Jaundice Image Classification Using Kernel Extreme Learning Machine (EDNJIC-KELM) achieved 96.97% accuracy, improving diagnosis and treatment.
Area of Science:
- Medical Imaging and Artificial Intelligence
- Neonatal Healthcare Technology
- Machine Learning in Diagnostics
Background:
- Neonatal jaundice, indicated by elevated bilirubin, is a common and potentially severe condition in newborns.
- Early detection and accurate diagnosis are crucial for timely treatment and preventing complications.
- Current diagnostic methods can be limited by subjective assessment and potential misdiagnosis.
Purpose of the Study:
- To develop an automated system for the early and accurate classification of neonatal jaundice using medical images.
- To enhance the diagnostic capabilities in the healthcare sector through advanced machine learning techniques.
- To improve patient outcomes by enabling prompt identification of hyperbilirubinemia in newborns.
Main Methods:
- Proposed an Early Diagnosis of Neonatal Jaundice Image Classification Using Kernel Extreme Learning Machine (EDNJIC-KELM) approach.
- Utilized Wiener filtering (WF) for image pre-processing to reduce noise and improve image quality.
- Employed Vision Transformer (ViT) for feature extraction and Kernel Extreme Learning Machine (KELM) for classification, with Enhanced Coati Optimization Algorithm (ECOA) for hyperparameter tuning.
Main Results:
- The EDNJIC-KELM model demonstrated a high classification accuracy of 96.97% on the Jaundice Image dataset.
- The proposed method significantly outperformed existing models in diagnosing neonatal jaundice.
- Image processing and machine learning integration proved effective for objective jaundice assessment.
Conclusions:
- The EDNJIC-KELM approach offers a robust and accurate solution for the early diagnosis of neonatal jaundice.
- This AI-driven tool has the potential to revolutionize neonatal care by enabling faster and more reliable diagnoses.
- Further implementation of such technologies can lead to reduced morbidity and mortality associated with neonatal jaundice.
Abstract:
Birth complications, particularly jaundice, are one of the leading causes of adolescent death and disease all over the globe. The main severity of these illnesses may diminish if scholars study more about their sources and progress toward effective treatment. Assured developments were prepared, but they are inadequate. Newborns repeatedly have jaundice as their primary medical concern. A raised level of bilirubin is a symbol of jaundice. Generally, in newborns, hyperbilirubinemia peaks in the initial post-delivery week. The inability to perceive issues early is sufficient for quick treatment, and the resemblance of indications might lead to misdiagnosis. Therefore, appropriate technologies are instantly required. Nowadays, researchers have begun to implement an image-processing model for analyzing jaundice. Paediatricians can detect and classify neonatal jaundice with machine learning (ML) and deep learning (DL) techniques. This study proposes an Early Diagnosis of Neonatal Jaundice Image Classification Using Kernel Extreme Learning Machine (EDNJIC-KELM) approach in the Healthcare Sector. The main intention of the EDNJIC-KELM approach is to build an effective system for diagnosing neonatal jaundice based on advanced methods. Initially, the image pre-processing stage applies the Wiener filtering (WF) method to improve the quality of an image and make it more suitable for analysis by removing the noise. In addition, the vision transformer (ViT) method is employed for the feature extraction process. Furthermore, the EDNJIC-KELM method employs the kernel extreme learning machine (KELM) method for the jaundice image classification. Finally, the enhanced coati optimization algorithm (ECOA) method is implemented for the hyperparameter tuning of the KELM method, which results in a higher classification process. The experimental analysis of the EDNJIC-KELM technique is examined using the Jaundice Image data. The performance validation of the EDNJIC-KELM technique portrayed a superior accuracy value of 96.97% over existing models.
