A number of large technology companies have created code-free cloud-based platforms that allow researchers and clinicians without coding experience to create deep learning algorithms. In this study, we comprehensively analyse the performance and featureset of six platforms, using four representative cross-sectional and en-face medical imaging datasets to create image classification models. The mean (s.d.) F1 scores across platforms for all model–dataset pairs were as follows: Amazon, 93.9 (5.4); Apple, 72.0 (13.6); Clarifai, 74.2 (7.1); Google, 92.0 (5.4); MedicMind, 90.7 (9.6); Microsoft, 88.6 (5.3). The platforms demonstrated uniformly higher classification performance with the optical coherence tomography modality. Potential use cases given proper validation include research dataset curation, mobile ‘edge models’ for regions without internet access, and baseline models against which to compare and iterate bespoke deep learning approaches.
2 September 2020 in Science Translational Medicine
Agrin heals joint surfaces by recruiting joint stem cells and inducing the formation of cartilage and bone with correct architecture in mice and sheep.
1 January 2022 in Arquivos Brasileiros de Oftalmologia
Purpose: To evaluate contrast sensitivity in non-high-risk, treatment-naïve proliferative diabetic retinopathy patients treated with panretinal photocoagulation and intravitreal injections of ranibizumab) versus panretinal photocoagulation alone. Methods: Sixty eyes of 30 patients with bilateral proliferative diabetic retinopathy were randomized into two groups: one received panretinal photocoagulation and ranibizumab injections (study group), while the other received panretinal photocoagulation alone (control group). All eyes were treated with panretinal photocoagulation in three sessions according to the Early Treatment Diabetic Retinopathy Study guidelines. Contrast sensitivity measurements were performed under photopic conditions (85 cd/m2) with the Visual Contrast Test Sensitivity 6500 chart, allowing for the evaluation of five spatial frequencies with sine wave grating charts: 1.5, 3.0, 6.0, 12.0, and 18.0 cycles per degree (cpd). Outcomes were measured in contrast sensitivity threshold scores among and within groups, from baseline to 1, 3, and 6 months. Results: Fifty-eight eyes (28 in the study group and 30 in the control group) reached the study endpoint. A comparative analysis of changes in contrast sensitivity between the groups showed significant differences mainly in low frequencies as follows: at month 1 in 1.5 cpd (p=0.001) and 3.0 cpd (p=0.04); at month 3 in 1.5 cpd (p=0.016), and at month 6 in 1.5 cpd (p=0.001) and 3.0 cpd (p=0.026) in favor of the study group. Conclusions: In eyes of patients with non-high-risk proliferative diabetic retinopathy, panretinal photocoagulation treatment with ranibizumab appears to cause less damage to contrast sensitivity compared with panretinal photocoagulation treatment alone. Thus, our evaluation of contrast sensitivity may support the use of ranabizumab as an adjuvant to panretinal photocoagulation for the treatment of proliferative diabetic retinopathy.