Poster

Sample efficient learning of image-based diagnostic classifiers via probabilistic labels

Roberto Vega · Pouneh Gorji · Zichen Zhang · Xuebin Qin · Abhilash Rakkunedeth · Jeevesh Kapur · Jacob Jaremko · Russell Greiner

Keywords: [ Models and Methods ] [ Supervised Learning ]

[ Abstract ]
Tue 13 Apr 6:30 p.m. PDT — 8:30 p.m. PDT

Abstract:

Deep learning approaches often require huge datasets to achieve good generalization. This complicates its use in tasks like image-based medical diagnosis, where the small training datasets are usually insufficient to learn appropriate data representations. For such sensitive tasks it is also important to provide the confidence in the predictions. Here, we propose a way to learn and use probabilistic labels to train accurate and calibrated deep networks from relatively small datasets. We observe gains of up to 22% in the accuracy of models trained with these labels, as compared with traditional approaches, in three classification tasks: diagnosis of hip dysplasia, fatty liver, and glaucoma. The outputs of models trained with probabilistic labels are calibrated, allowing the interpretation of its predictions as proper probabilities. We anticipate this approach will apply to other tasks where few training instances are available and expert knowledge can be encoded as probabilities.

Chat is not available.