Abstract

In recent years, the rapid development of deep neural networks has made great progress in automatic organ segmentation from abdominal CT scans. However, automatic segmentation for small organs (e.g., the pancreas) is still a challenging task. As an inconspicuous and small organ in the abdomen, the pancreas has a high degree of anatomical variability and is indistinguishable from the surrounding organs and tissues, which usually leads to a very vague boundary. Therefore, the accuracy of pancreatic segmentation is sometimes below satisfaction. In this paper, we propose a 2.5D U-net with an attention mechanism. The proposed network includes 2D convolutional layers and 3D convolutional layers, which means that it requires less computational resources than 3D segmentation models while it can capture more spatial information along the third dimension than 2D segmentation models. Then We use a cascaded framework to increase the accuracy of segmentation results. We evaluate our network on the NIH pancreas dataset and measure the segmentation accuracy by the Dice similarity coefficient (DSC). Experimental results demonstrate a better performance compared with state-of-the-art methods.

Highlights

  • Segmenting organs such as the spleen, liver, and pancreas from abdominal CT scans is a critical prerequisite of computer-aided diagnosis (CAD) [1, 2], quantitative and qualitative analysis

  • We are committed to automatic pancreas segmentation, which is an extensively useful CAD technique for the diagnosis and prognosis of pancreatic cancer

  • We evaluate our approach on the public NIH pancreas dataset [9], which is the largest and most authoritative Open Source Dataset in pancreas segmentation

Read more

Summary

Introduction

Segmenting organs such as the spleen, liver, and pancreas from abdominal CT scans is a critical prerequisite of computer-aided diagnosis (CAD) [1, 2], quantitative and qualitative analysis. We are committed to automatic pancreas segmentation, which is an extensively useful CAD technique for the diagnosis and prognosis of pancreatic cancer. Automatic segmentation for other organs (e.g., lung, kidney and liver) has reached relatively a high accuracy. With the fast development of deep learning, natural image semantic models are widely used to complete medical image segmentation tasks, such as full convolution network(FCN) [5] and U-net [6].

Objectives
Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call