Code-free deep learning for multi-modality medical image classification

Abstract 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 featureset six platforms, using four representative cross-sectional en-face medical imaging datasets image classification models. The mean (s.d.) F1 scores across 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 MedicMind, 90.7 (9.6); Microsoft, 88.6 (5.3). demonstrated uniformly higher with optical coherence tomography modality. Potential use cases given proper validation include research dataset curation, mobile ‘edge models’ regions internet access, baseline models against which compare iterate bespoke approaches.