On Evaluating CNN Representations for Low Resource Medical Image Classification
| Autor: | Taruna Agrawal, Rahul Gupta, Shrikanth S. Narayanan |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science Feature extraction Machine Learning (stat.ML) 010501 environmental sciences 01 natural sciences Convolutional neural network Machine Learning (cs.LG) 030218 nuclear medicine & medical imaging 03 medical and health sciences 0302 clinical medicine Statistics - Machine Learning FOS: Electrical engineering electronic engineering information engineering 0105 earth and related environmental sciences Training set Contextual image classification business.industry Image and Video Processing (eess.IV) Pattern recognition Electrical Engineering and Systems Science - Image and Video Processing Keyword spotting Test set Video tracking Artificial intelligence Transfer of learning business Classifier (UML) |
| Zdroj: | ICASSP |
| Popis: | Convolutional Neural Networks (CNNs) have revolutionized performances in several machine learning tasks such as image classification, object tracking, and keyword spotting. However, given that they contain a large number of parameters, their direct applicability into low resource tasks is not straightforward. In this work, we experiment with an application of CNN models to gastrointestinal landmark classification with only a few thousands of training samples through transfer learning. As in a standard transfer learning approach, we train CNNs on a large external corpus, followed by representation extraction for the medical images. Finally, a classifier is trained on these CNN representations. However, given that several variants of CNNs exist, the choice of CNN is not obvious. To address this, we develop a novel metric that can be used to predict test performances, given CNN representations on the training set. Not only we demonstrate the superiority of the CNN based transfer learning approach against an assembly of knowledge driven features, but the proposed metric also carries an 87% correlation with the test set performances as obtained using various CNN representations. Accepted to ICASSP 2019 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|