Support vector machine and deep-learning object detection for localisation of hard exudates

Abstract

Hard exudates are one of the main clinical findings in the retinal images of patients with diabetic retinopathy. Detecting them early significantly impacts the treatment of underlying diseases; therefore, there is a need for automated systems with high reliability. We propose a novel method for identifying and localising hard exudates in retinal images. To achieve fast image pre-scanning, a support vector machine (SVM) classifier was combined with a faster region-based convolutional neural network (faster R-CNN) object detector for the localisation of exudates. Rapid pre-scanning filtered out exudate-free samples using a feature vector extracted from the pre-trained ResNet-50 network. Subsequently, the remaining samples were processed using a faster R-CNN detector for detailed analysis. When evaluating all the exudates as individual objects, the SVM classifier reduced the false positive rate by 29.7% and marginally increased the false negative rate by 16.2%. When evaluating all the images, we recorded a 50% reduction in the false positive rate, without any decrease in the number of false negatives. The interim results suggested that pre-scanning the samples using the SVM prior to implementing the deep-network object detector could simultaneously improve and speed up the current hard exudates detection method, especially when there is paucity of training data.

Diabetic Macular Edema Detection Using End-to-End Deep Fusion Model and Anatomical Landmark Visualization on an Edge Computing Device

“…Lam et al ( 39 ) used a sliding window to scan images and a CNN to detect whether HE lesions were present. In addition, Kurilová et al ( 40 ) used the object detector of Faster-RCNN to detect HE lesions in fundus images. In this study, the object detector of our fusion model was modified from EfficientDet-d1, in which the backbone was co-used with the classification module during both the training and inference phases.…”

Artificial Intelligence in Orthodontic Smart Application for Treatment Coaching and Its Impact on Clinical Performance of Patients Monitored with AI-TeleHealth System

“…Computer-based learning makes the use of the interactive elements of the computer applications and software and the ability to present any type of information to the users. Authors of this paper have published their experience in smart learning algorithms implementation [ 52 , 53 ], albeit any sophisticated A.I. upgrade requires simple computerized learning features first.…”

UAV Detection Using Reinforcement Learning

“…ML is proven to be incredibly effective in a variety of sectors when hand-coded solutions fail, and massive volumes of labeled data can be acquired [ 26 ]. In the case of UAV detection, ML algorithms were utilized through various detection methodologies including the analysis of RF signals [ 33 , 34 , 35 ], sound characteristics [ 27 , 36 , 37 , 38 ], and visual cues [ 39 , 40 , 41 ]. There is a great interest in applying RL techniques to help in the detection and identification of intruding UAVs.…”