Abstract
A common problem found in real-word medical image classification is the inherent imbalance of the positive and negative patterns in the dataset where positive patterns are usually rare. Moreover, in the classification of multiple classes with neural network, a training pattern is treated as a positive pattern in one output node and negative in all the remaining output nodes. In this paper, the weights of a training pattern in the loss function are designed based not only on the number of the training patterns in the class but also on the different nodes where one of them treats this training pattern as positive and the others treat it as negative. We propose a combined approach of weights calculation algorithm for deep network training and the training optimization from the state-of-the-art deep network architecture for thorax diseases classification problem. Experimental results on the Chest X-Ray image dataset demonstrate that this new weighting scheme improves classification performances, also the training optimization from the EfficientNet improves the performance furthermore. We compare the aggregate method with several performances from the previous study of thorax diseases classifications to provide the fair comparisons against the proposed method.
Highlights
A common problem found in real-word medical image classification is the inherent imbalance of the positive and negative patterns in the dataset where positive patterns are usually rare
The better features chosen during the feature engineering will produce more accurate classification performance
Cui et al.’s a pproach[2] treats the contributions of training patterns to the loss function for all the output nodes, this is contrary to the Wang and Gundel et al.’s m ethods[3,4] which use the distinct weights from positive and negative classes as the multipliers in the loss-function
Summary
A common problem found in real-word medical image classification is the inherent imbalance of the positive and negative patterns in the dataset where positive patterns are usually rare. Better classification performance can potentially be achieved by Cui et al.[2], the approach only addresses effective s amples[2] and the imbalances of positive-negative classes have not been tackled. A novel weights function for focal-loss is proposed to address the imbalance of positive-negative classes,which tackles the classification correctness in both positive and negative samples when training the neural networks. We tackle the imbalance problem within Chest X-Ray dataset and propose the advancement of the use of state-of-the-art neural net architecture for the final classification performance;The EfficientNet with two-stage training. Our contribution is to propose an approach which can combine weights calculation algorithm for deep-network and the optimization of training strategy from the state-of-the-art architecture. The “Discussion” section give a more in-depth discussion about the outcome, The “Conclusion” section explains the conclusion from the research
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
