Densely Connected Recurrent Residual (Dense R2UNet) Convolutional Neural Network for Segmentation of Lung CT Images
This work addresses medical image segmentation for lung lesions, which is incremental as it builds on existing U-Net architectures with known components.
The paper tackled lung lesion segmentation in CT images by proposing Dense R2U CNN, a hybrid model combining recurrent, residual, and dense networks based on U-Net, which achieved better performance than equivalent models on a benchmark dataset.
Deep Learning networks have established themselves as providing state of art performance for semantic segmentation. These techniques are widely applied specifically to medical detection, segmentation and classification. The advent of the U-Net based architecture has become particularly popular for this application. In this paper we present the Dense Recurrent Residual Convolutional Neural Network(Dense R2U CNN) which is a synthesis of Recurrent CNN, Residual Network and Dense Convolutional Network based on the U-Net model architecture. The residual unit helps training deeper network, while the dense recurrent layers enhances feature propagation needed for segmentation. The proposed model tested on the benchmark Lung Lesion dataset showed better performance on segmentation tasks than its equivalent models.