Deep learning-based auto-segmentation of clinical target volumes for radiotherapy treatment of cervical cancer.

OBJECTIVES: Because radiotherapy is indispensible for treating cervical cancer, it is critical to accurately and efficiently delineate the radiation targets. We evaluated a deep learning (DL)-based auto-segmentation algorithm for automatic contouring of clinical target volumes (CTVs) in cervical cancers. METHODS: Computed tomography (CT) datasets from 535 cervical cancers treated with definitive or postoperative radiotherapy were collected. A DL tool based on VB-Net was developed to delineate CTVs of the pelvic lymph drainage area (dCTV1) and parametrial area (dCTV2) in the definitive radiotherapy group. The training/validation/test number is 157/20/23. CTV of the pelvic lymph drainage area (pCTV1) was delineated in the postoperative radiotherapy group. The training/validation/test number is 272/30/33. Dice similarity coefficient (DSC), mean surface distance (MSD), and Hausdorff distance (HD) were used to evaluate the contouring accuracy. Contouring times were recorded for efficiency comparison. RESULTS: The mean DSC, MSD, and HD values for our DL-based tool were 0.88/1.32 mm/21.60 mm for dCTV1, 0.70/2.42 mm/22.44 mm for dCTV2, and 0.86/1.15 mm/20.78 mm for pCTV1. Only minor modifications were needed for 63.5% of auto-segmentations to meet the clinical requirements. The contouring accuracy of the DL-based tool was comparable to that of senior radiation oncologists and was superior to that of junior/intermediate radiation oncologists. Additionally, DL assistance improved the performance of junior radiation oncologists for dCTV2 and pCTV1 contouring (mean DSC increases: 0.20 for dCTV2, 0.03 for pCTV1; mean contouring time decrease: 9.8 min for dCTV2, 28.9 min for pCTV1). CONCLUSIONS: DL-based auto-segmentation improves CTV contouring accuracy, reduces contouring time, and improves clinical efficiency for treating cervical cancer.

PACS and Web-based image distribution and display.

Picture archiving and communication system (PACS) delivers images to the display workstations mostly through digital image communication in medicine (DICOM) protocols in radiology departments, and there are lots of medical applications in healthcare community needing to access PACS images for different application purposes. In this paper, we first reviewed a hospital-integrated PACS image data flow and typical diagnostic display software architecture, and discussed some Web technologies and Web-based image application server architectures, as well as image accessing and viewing methods in these architectures. Then, we present one approach to develop component-based image display architecture and use image processing and display component to build a diagnostic display workstation, and also, give a method to integrate this component into Web-based image distribution server to enable users using Web browsers to access, view and manipulate PACS DICOM images as easy as with PACS display workstations. Finally, we test and evaluate the performance of image loading and displaying by using the diagnostic display workstation and the component-based Web display system, the experimental results show that the image distribution and display performance from the Web server to browser clients is similar with that of the image loading and displaying procedure of the diagnostic workstation as more browser clients accessing the Web server at same time. We also discuss the advantages and disadvantages of the Web-based image distribution and display in different medical applications.