What is it about?
•A new method of training a deep convolutional neural network with layer truncation, transfer learning, partial layer freezing, and feature fusion was proposed. •Achieved a competitive performance with significantly lesser parameters than other state-of-the-art models that diagnosed chest x-rays with COVID-19. •The proposed method and model can scale less effortlessly and does not consume massive amounts of disk capacities even with an increased amount of data.
Photo by Fusion Medical Animation on Unsplash
Why is it important?
This work proposed the Fused-DenseNet-Tiny, a lightweight DCNN model based on a densely connected neural network (DenseNet) truncated and concatenated. The model trained to learn CXR features based on transfer learning, partial layer freezing, and feature fusion. Upon evaluation, the proposed model achieved a remarkable 97.99 % accuracy, with only 1.2 million parameters and a shorter end-to-end structure. It has also shown better performance than some existing studies and other massive state-of-the-art models that diagnosed COVID-19 from CXRs.
Read the Original
This page is a summary of: Diagnosing Covid-19 chest x-rays with a lightweight truncated DenseNet with partial layer freezing and feature fusion, Biomedical Signal Processing and Control, July 2021, Elsevier, DOI: 10.1016/j.bspc.2021.102583.
You can read the full text:
The following have contributed to this page