Multi-Scale Convolutional Neural Network for Accurate Corneal Segmentation in Early Detection of Fungal Keratitis

Article Engineering, Multidisciplinary

Deep Sequential Feature Learning in Clinical Image Classification of Infectious Keratitis

Yesheng Xu et al.

Summary: Infectious keratitis is a medical emergency that requires rapid and accurate diagnosis to prevent serious damage. A proposed deep learning model in this study effectively discriminates infectious corneal disease with an accuracy of 80%.

ENGINEERING (2021)

Add to Collection

Article Computer Science, Information Systems

Open-Source Automatic Segmentation of Ocular Structures and Biomarkers of Microbial Keratitis on Slit-Lamp Photography Images Using Deep Learning

Jessica Loo et al.

Summary: The study presents a fully-automatic algorithm for segmenting ocular structures and MK biomarkers on SLP images. The algorithm performed well on all 133 eyes, showing good performance compared to manual annotations by a second physician on 75 eyes, especially in segmenting hypopyons, WBCs, and edema.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2021)

Add to Collection

Article Engineering, Biomedical

ECNet: An evolutionary convolutional network for automated glaucoma detection using fundus images

Deepak Ranjan Nayak et al.

Summary: This paper proposes a novel non-handcrafted feature extraction method based on evolutionary convolutional network (ECNet) for automated detection of glaucoma. The method achieves high accuracy by optimizing weights and selecting optimal classifiers.

BIOMEDICAL SIGNAL PROCESSING AND CONTROL (2021)

Add to Collection

Article Infectious Diseases

Fungal keratitis at a tertiary eye care in Northern Thailand: Etiology and prognostic factors for treatment outcomes

Napaporn Tananuvat et al.

Summary: The study evaluated the etiology and prognostic factors for fungal keratitis (FK) and found that ocular trauma was the major predisposing factor in Northern Thailand, with Fusarium being the most common identified pathogen. Many cases were refractory to medications and required surgical intervention, with advanced age, delayed treatment, and large lesion size being predictors for poor outcomes.

JOURNAL OF INFECTION (2021)

Add to Collection

Article Medicine, General & Internal

Using Slit-Lamp Images for Deep Learning-Based Identification of Bacterial and Fungal Keratitis: Model Development and Validation with Different Convolutional Neural Networks

Ning Hung et al.

Summary: This study developed a deep learning model for identifying bacterial and fungal keratitis using slit-lamp images, achieving high diagnostic accuracy. The DenseNet161 CNN showed the best model performance with an AUC of 0.85 for both types of keratitis, demonstrating the model's ability to accurately identify corneal infiltrations.

DIAGNOSTICS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence