No abstract

AimsTo investigate the efficacy of a bi-modality deep convolutional neural network (DCNN) framework to categorise age-related macular degeneration (AMD) and polypoidal choroidal vasculopathy (PCV) from colour fundus images and optical coherence tomography (OCT) images.MethodsA retrospective cross-sectional study was proposed of patients with AMD or PCV who came to Peking Union Medical College Hospital. Diagnoses of all patients were confirmed by two retinal experts based on diagnostic gold standard for AMD and PCV. Patients with concurrent retinal vascular diseases were excluded. Colour fundus images and spectral domain OCT images were taken from dilated eyes of patients and healthy controls, and anonymised. All images were pre-labelled into normal, dry or wet AMD or PCV. ResNet-50 models were used as the backbone and alternate machine learning models including random forest classifiers were constructed for further comparison. For human-machine comparison, the same testing data set was diagnosed by three retinal experts independently. All images from the same participant were presented only within a single partition subset.ResultsOn a test set of 143 fundus and OCT image pairs from 80 eyes (20 eyes per-group), the bi-modal DCNN demonstrated the best performance, with accuracy 87.4%, sensitivity 88.8% and specificity 95.6%, and a perfect agreement with diagnostic gold standard (Cohen’s κ 0.828), exceeds slightly over the best expert (Human1, Cohen’s κ 0.810). For recognising PCV, the model outperformed the best expert as well.ConclusionA bi-modal DCNN for automated classification of AMD and PCV is accurate and promising in the realm of public health.

No abstract

This paper studies automated categorization of age-related macular degeneration (AMD) given a multi-modal input, which consists of a color fundus image and an optical coherence tomography (OCT) image from a specific eye. Previous work uses a traditional method, comprised of feature extraction and classifier training that cannot be optimized jointly. By contrast, we propose a two-stream convolutional neural network (CNN) that is end-to-end. The CNN's fusion layer is tailored to the need of fusing information from the fundus and OCT streams. For generating more multi-modal training instances, we introduce Loose Pair training, where a fundus image and an OCT image are paired based on class labels rather than eyes. Moreover, for a visual interpretation of how the individual modalities make contributions, we extend the class activation mapping technique to the multi-modal scenario. Experiments on a real-world dataset collected from an outpatient clinic justify the viability of our proposal for multi-modal AMD categorization.

Air tamponade is a safe and effective treatment for chronic and severe macular holes, with several spectral-domain optical coherence tomography parameters highly predictive of postoperative visual acuity.

No abstract

This prospective clinical study was to compare the effect of panretinal photocoagulation (PRP) associated with intravitreal conbercept injections versus PRP alone in the treatment of proliferative diabetic retinopathy (PDR). For each of 15 patients included, one eye was randomly assigned to receive treatment with PRP, and the other eye received conbercept combined PRP. Ophthalmic examinations, optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA) were performed at baseline and at each monthly visit until 6 months. Fluorescein angiography (FA) was acquired at baseline, 3 months and 6 months. Between group and within group analysis was done by using generalized estimating equations (GEE). The combination group had a significant decrease of neovascularization (NV) leakage area than the PRP group at month 3 and month 6 after treatment, and a better best-corrected visual acuity (BCVA) during the first three months. Within-group analysis indicated a significant decrease in NV leakage at month 3 and month 6 in both groups, and a significant increase in BCVA at 1 month in the combination group. In summary, the combination of intravitreal injection of conbercept and PRP can significantly reduce the NV of PDR patients and achieve better BCVA during the drug's lifespan compared with PRP alone.

Human activity recognition (HAR) has been a very popular field in both real practice and theoretical research. Over the years, a number of many-vs-one Long Short-Term Memory (LSTM) models have been proposed for the sensor-based HAR problem. However, how to utilize sequence outputs of them to improve the HAR performance has not been studied seriously. To solve this problem, we present a novel loss function named harmonic loss, which is utilized to improve the overall classification performance of HAR based on baseline LSTM networks. First, label replication method is presented to duplicate true labels at each sequence step in many-vs-one LSTM networks, thus each sequence step can generate a local error and a local output. Then, considering the importance of different local errors and inspired by the Ebbinghaus memory curve, the harmonic loss is proposed to give unequal weights to different local errors based on harmonic series equation. Additionally, to improve the overall classification performance of HAR, integrated methods are utilized to exploit the sequence outputs of LSTM models based on harmonic loss and ensemble learning strategy. Finally, based on the LSTM model construction and hyper-parameter setting, extensive experiments are conducted. A series of experimental results demonstrate that our harmonic loss significantly achieves higher macro-F1 and accuracy than strong baselines on two public HAR benchmarks. Compared with previous state-of-art methods, our proposed methods can achieve competitive classification performance.