Related Experiment Video
Updated: Oct 16, 2025
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
Multi-Scale Convolutional Neural Network for Accurate Corneal Segmentation in Early Detection of Fungal Keratitis
Veena Mayya1,2, Sowmya Kamath Shevgoor1, Uma Kulkarni3
1Healthcare Analytics and Language Engineering (HALE) Lab, Department of Information Technology, National Institute of Technology Karnataka, Surathkal, Mangalore 575025, India.
Abstract:
Microbial keratitis is an infection of the cornea of the eye that is commonly caused by prolonged contact lens wear, corneal trauma, pre-existing systemic disorders and other ocular surface disorders. It can result in severe visual impairment if improperly managed. According to the latest World Vision Report, at least 4.2 million people worldwide suffer from corneal opacities caused by infectious agents such as fungi, bacteria, protozoa and viruses. In patients with fungal keratitis (FK), often overt symptoms are not evident, until an advanced stage. Furthermore, it has been reported that clear discrimination between bacterial keratitis and FK is a challenging process even for trained corneal experts and is often misdiagnosed in more than 30% of the cases. However, if diagnosed early, vision impairment can be prevented through early cost-effective interventions. In this work, we propose a multi-scale convolutional neural network (MS-CNN) for accurate segmentation of the corneal region to enable early FK diagnosis. The proposed approach consists of a deep neural pipeline for corneal region segmentation followed by a ResNeXt model to differentiate between FK and non-FK classes. The model trained on the segmented images in the region of interest, achieved a diagnostic accuracy of 88.96%. The features learnt by the model emphasize that it can correctly identify dominant corneal lesions for detecting FK.
Insights
Early diagnosis of fungal keratitis (FK) is crucial for preventing vision loss. A new multi-scale convolutional neural network (MS-CNN) accurately segments corneal regions, aiding in early FK detection and improving patient outcomes.
Area of Science:
- Ophthalmology
- Medical Imaging
- Artificial Intelligence
Background:
- Microbial keratitis, an eye infection, can cause severe vision impairment if not managed properly.
- Fungal keratitis (FK) often presents with subtle symptoms, leading to delayed diagnosis and misdiagnosis rates exceeding 30%.
- Accurate and early diagnosis of FK is essential for effective, cost-efficient interventions to prevent vision loss.
Purpose of the Study:
- To develop and evaluate a multi-scale convolutional neural network (MS-CNN) for accurate corneal region segmentation.
- To enable early diagnosis of fungal keratitis (FK) through improved image analysis.
- To differentiate between fungal keratitis and other conditions using a deep neural network approach.
Main Methods:
- A deep neural pipeline was employed for precise corneal region segmentation.
- A ResNeXt model was utilized to classify segmented images into FK and non-FK categories.
- The MS-CNN model was trained on segmented corneal images for diagnostic accuracy.
Main Results:
- The proposed MS-CNN achieved a diagnostic accuracy of 88.96% for FK detection.
- The model demonstrated the ability to identify key corneal lesions indicative of FK.
- Feature learning highlighted the model's effectiveness in distinguishing FK from other conditions.
Conclusions:
- The developed MS-CNN facilitates accurate corneal segmentation, crucial for early FK diagnosis.
- This AI-driven approach shows significant potential in improving the diagnostic accuracy of fungal keratitis.
- Early and accurate detection of FK using advanced computational methods can prevent irreversible vision impairment.
More Related Videos
11:29Corneal Confocal Microscopy: A Novel Non-invasive Technique to Quantify Small Fibre Pathology in Peripheral Neuropathies
Published on: January 3, 2011
07:51Full-Field Optical Coherence Microscopy for Histology-Like Analysis of Stromal Features in Corneal Grafts
Published on: October 21, 2022