Benchmarking Deep Learning Frameworks for Automated Diagnosis of Ocular Toxoplasmosis: A Comprehensive Approach to Classification and Segmentation
This work provides a benchmark for automated diagnosis of ocular toxoplasmosis, which could lead to cheaper and easier detection methods, but it is incremental as it evaluates existing models without introducing new ones.
The study benchmarked pre-trained deep learning models for classifying and segmenting ocular toxoplasmosis from fundus images, finding MobileNetV2 achieved the highest accuracy (0.7% above InceptionV3) in classification and MobileNetV2/U-Net with Jaccard loss outperformed ResNet34 by 0.5% in accuracy and 2.1% in Dice score for segmentation.
Ocular Toxoplasmosis (OT), is a common eye infection caused by T. gondii that can cause vision problems. Diagnosis is typically done through a clinical examination and imaging, but these methods can be complicated and costly, requiring trained personnel. To address this issue, we have created a benchmark study that evaluates the effectiveness of existing pre-trained networks using transfer learning techniques to detect OT from fundus images. Furthermore, we have also analysed the performance of transfer-learning based segmentation networks to segment lesions in the images. This research seeks to provide a guide for future researchers looking to utilise DL techniques and develop a cheap, automated, easy-to-use, and accurate diagnostic method. We have performed in-depth analysis of different feature extraction techniques in order to find the most optimal one for OT classification and segmentation of lesions. For classification tasks, we have evaluated pre-trained models such as VGG16, MobileNetV2, InceptionV3, ResNet50, and DenseNet121 models. Among them, MobileNetV2 outperformed all other models in terms of Accuracy (Acc), Recall, and F1 Score outperforming the second-best model, InceptionV3 by 0.7% higher Acc. However, DenseNet121 achieved the best result in terms of Precision, which was 0.1% higher than MobileNetv2. For the segmentation task, this work has exploited U-Net architecture. In order to utilize transfer learning the encoder block of the traditional U-Net was replaced by MobileNetV2, InceptionV3, ResNet34, and VGG16 to evaluate different architectures moreover two different two different loss functions (Dice loss and Jaccard loss) were exploited in order to find the most optimal one. The MobileNetV2/U-Net outperformed ResNet34 by 0.5% and 2.1% in terms of Acc and Dice Score, respectively when Jaccard loss function is employed during the training.