Up against the likes of Amazon, Google, Microsoft, Apple and Clarifai, the deep learning development platform developed by New Zealand’s oDocs, MedicMind, has been ranked as one of the top medical imaging classification platforms for ophthalmic diseases in the world.
The globally available, code-free cloud-based platform allows researchers and clinicians without coding experience to create deep learning algorithms, advancing clinical decision making, said proud oDocs’ founder and CEO Dr Sheng Chiong Hong. “Medic Mind performed well with low standard deviations demonstrating repeatability.”
The comparative study, published by Nature Machine Intelligence, analysed the performance and features of six platforms using four representative cross-sectional and en-face medical imaging datasets to create image classification models.
The mean F1 (test accuracy) scores across platforms for all model-dataset pairs were: Amazon, 93.9 (with 5.4 standard deviation); Apple, 72.0 (13.6); Clarifai, 74.2 (7.1); Google, 92.0 (5.4); MedicMind, 90.7 (9.6); and Microsoft, 88.6 (5.3). The findings showed all platforms demonstrated higher classification performance with optical coherence tomography modality.
