A novel adaptive momentum method for medical image classification using convolutional neural network
Künye
Aytaç, U. C., Güneş, A., & Ajlouni, N. (16.03.2022). A novel adaptive momentum method for medical image classification using convolutional neural network. BMC Medical Imaging, 22(1). https://doi.org/10.1186/s12880-022-00755-z Özet
Background: AI for medical diagnosis has made a tremendous impact by applying convolutional neural networks
(CNNs) to medical image classifcation and momentum plays an essential role in stochastic gradient optimization
algorithms for accelerating or improving training convolutional neural networks. In traditional optimizers in CNNs, the
momentum is usually weighted by a constant. However, tuning hyperparameters for momentum can be computationally complex. In this paper, we propose a novel adaptive momentum for fast and stable convergence.
Method: Applying adaptive momentum rate proposes increasing or decreasing based on every epoch’s error
changes, and it eliminates the need for momentum hyperparameter optimization. We tested the proposed method
with 3 diferent datasets: REMBRANDT Brain Cancer, NIH Chest X-ray, COVID-19 CT scan. We compared the performance of a novel adaptive momentum optimizer with Stochastic gradient descent (SGD) and other adaptive optimizers such as Adam and RMSprop.
Results: Proposed method improves SGD performance by reducing classifcation error from 6.12 to 5.44%, and it
achieved the lowest error and highest accuracy compared with other optimizers. To strengthen the outcomes of this
study, we investigated the performance comparison for the state-of-the-art CNN architectures with adaptive momentum. The results shows that the proposed method achieved the highest with 95% compared to state-of-the-art CNN
architectures while using the same dataset. The proposed method improves convergence performance by reducing
classifcation error and achieves high accuracy compared with other optimizers.