Abstract
Quick and accurate detection of metastatic lymph nodules can significantly increase the probability of healing in patients with gastric cancer. In modern medical diagnosis, medical imaging specialists mainly observe the computed tomography (CT) images and make diagnostic decisions based on their own subjective experience. But this procedure is very laborious, inefficient, and error-prone. In this paper, as the deep convolutional neural networks (DCNNs) have achieved great success in the field of image recognition, we study the automatic detection of metastatic lymph nodules of the upper abdomen enhanced CT using DCNNs. We first adjust the Faster Region-based Convolutional Neural Network (Faster R-CNN) to adapt to the characteristics of the lymph nodules. Then, we train this network with images manually labeled by the medical imaging specialists. Finally, in order to improve the detection performance, we fine tune the trained network above based on the images labeled by doctors through reading and analyzing the patients’ pathology reports. Experimental results demonstrate the promising performance on nodules detection. The area under the receiver operating characteristic (ROC) curve is 0.9248, and the diagnosis time is 10-15s/case, which exhibit great potential in clinical applications.
Published Version
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
