Kidney Tumor Detection using Attention based U-Net

Abstract

The advancement of deep learning techniques has provoked the potential of using Medical Image Analysis (MIA) for disease detection and prediction in numerous ways. This has been mostly useful in identifying tumours and abnormalities in many organs of the human body. Particularly in kidney diseases, the treatment options such as surgery have largely benefitted by the ability to detect tumours in early stages, thereby shifting towards more efficient methods including conservative nephron procedures. Therefore, to enable the early detection of kidney tumours, we propose a convolutional neural network based U-Net architecture which is able to detect tumours using an attention mechanism. The proposed architecture was evaluated using KiTS19 Challenge dataset that includes a collection of multi-phase CT imaging, segmentation masks, and comprehensive clinical outcomes for 300 patients who underwent nephrectomy for kidney tumours. The outcomes demonstrate the ability of the proposed architecture to distinguish images with tumours in the kidney and support early tumour detection.

Automated detection and segmentation of pleural effusion on ultrasound images using an Attention U‐net

“…Then, by using this weight graph, the feature graph of the next layer of the same layer of the under‐sampling layer is gated to obtain the weighted feature graph. This mechanism enables the network to pay more attention to and retain the encoder feature maps that are similar to the decoder feature maps, thus improving the accuracy of semantic segmentation 20,21 …”

“…This mechanism enables the network to pay more attention to and retain the encoder feature maps that are similar to the decoder feature maps, thus improving the accuracy of semantic segmentation. 20 , 21 …”