Automated chest X-ray analysis has a great potential for diagnosing thorax diseases since errors in diagnosis have always been a concern among radiologists. Being a multi-label classification problem, achieving accurate classification still remains challenging. Several studies have focused on accurately segmenting the lung regions from the chest X-rays to deal with the challenges involved. The features extracted from the lung regions typically provide precise clues for diseases like nodules. However, such methods ignore the features outside the lung regions, which have been shown to be crucial for diagnosing conditions like cardiomegaly. Therefore, in this work, we explore a dual-branch a network-based framework that relies on features extracted from the lung regions as well as the entire chest x-rays. The proposed framework uses a novel network named R-I UNet for segmenting the lung regions. The dual-branch network in the proposed framework employs two fine-tuned AlexNet models to extract discriminative features, forming two feature vectors. Each of these feature vectors is fed into a recurrent neural network consisting of a stack of gated recurrent units with skip connections. Finally, the resulting feature vectors are concatenated for classification. The R-I UNet has been evaluated on the JSRT and Montgomery datasets, while the dual-branch classification network has been evaluated on the NIH ChestXray14 dataset. The proposed models achieve state of-the-art performance for both segmentation and classification tasks on the above benchmark datasets.

Segmentation of breast masses in digital mammograms is very challenging due to its complexity. The recent U-shaped encoder-decoder networks achieved remarkable performance in medical image segmentation. However, these networks have some limitations: a) The multi-scale context information is required to accurately segment mass but is not effectively extracted and utilized. b) The global context information is often ignored by the skip connection. To overcome these limitations and achieve better segmentation, we propose an Enhanced U-shaped Network (EU-Net). The proposed EU-Net comprises of 3 novel components: 1) dense block, which is employed in the encoder and the decoder in place of convolutional layers to achieve the multi-scale features. 2) Multi-Scale Feature Extraction and Fusion, which is used in the junction between the encoder and the decoder for further extracting and fusing the multi-scale context information. 3) Skip Connection Reconstruction, which is inserted between the encoder and the decoder at each stage, to redesign the skip connection and emphasize the global context information. Extensive experimental results under different settings show that the proposed EU-Net achieves superior performances than the previous state-of-the-art segmentation models, and other existing approaches on IN-Breast and CBIS-DDSM mammogram datasets. The generalization ability of the proposed EU-Net is evidenced through crossdataset and ternary dataset evaluation performance. In the ternary dataset evaluation, the model is trained and evaluated on the UDIAT breast ultrasound dataset without finetuning. The EU-Net achieves higher generalization performance in both evaluation experiments. These experiments collectively indicate the efficiency and high generalization ability of the proposed EU-Net.

Automatic segmentation of multi-modal Cardiac Magnetic Resonance Imaging (CMRI) scans is challenging due to the variant intensity distribution and unclear boundaries between the neighbouring tissues and other organs. The deep convolutional neural networks have shown great potential in medical image segmentation tasks. In this paper, we present a deep convolutional neural network model named Multi-Modal Cardiac Network (MMC-Net) for segmenting three cardiac structures namely right ventricle (RV), left ventricle (LV), and left ventricular myocardium (LVM) from multi-modal CMRI’s. The proposed MMC-Net is designed using a densely connected backbone enabling feature reuse, an atrous convolution module for fusing multi-scale features, and a pixel-classification module for generating the segmentation result. This model was evaluated on a publicly available MS-CMRSeg-2019 challenge dataset in segmentation of RV, LV, and LVM from CMRI scans. The segmentation results from extensive experiments demonstrate our MMC-Net can achieve better segmentation performance compared to other state-of-the-art models, and the existing approaches. Additionally, the generalization ability of the proposed MMC-Net is validated on another publicly available ACDC dataset without fine-tuning. The results demonstrate that the proposed MMC-Net shows a powerful generalisation ability of segmenting RV, LV, and LVM with higher performance.