Auto-Contouring with Deep Learning

HuraRT (DV.Target)

HuraRT (DV.Target) is a full-fledged software for auto-contouring organs-at-risk (OARs) on CT images. Empowered by innovative deep learning algorithms, our system can automatically segment all major OARs, significantly enhancing the accuracy and efficiency of radiation therapy planning.

Application
Support automatic delineation of about 50 major OARs in four body parts head-and-neck, thorax, abdomen, and pelvic, including OARs of virtual clinical value as well as hard and small OARs such as optic chiasm.

Integration
Interact with medical data acquisition flow and TPS system with ease. File Organization system and built-in delineation editor provide clean and powerful user experience.

Intelligence
Go beyond the traditional altas-based OARs contouring solution, which delivers rapid and accurate OARs segmentation predictions by the benefit of state-of-art AI technology and big data collected from global medical institutions.

Publications
Tang, H., Chen, X., Liu, Y., Lu, Z., You, J., Yang, M., ... & Xie, X. (2019). Clinically applicable deep learning framework for organs at risk delineation in CT images. Nature Machine Intelligence, 1(10), 480-491. Zhu, W., Huang, Y., Zeng, L., Chen, X., Liu, Y., Qian, Z., ... & Xie, X. (2019). AnatomyNet: deep learning for fast and fully automated whole‐volume segmentation of head and neck anatomy. Medical physics, 46(2), 576-589. Sun, S., Liu, Y., Bai, N., Tang, H., Chen, X., Huang, Q., ... & Xie, X. (2020, April). Attentionanatomy: A unified framework for whole-body organs at risk segmentation using multiple partially annotated datasets. In 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI) (pp. 1-5). IEEE. Shen, Z., Garsa, A., Sun, S., Bai, N., Zhang, C., Shiu, A., ... & Yang, W. (2020, June). Deep Learning-Based Auto-Segmentation of OARs in Head and Neck CT Images. In MEDICAL PHYSICS (Vol. 47, No. 6, pp. E598-E598). 111 RIVER ST, HOBOKEN 07030-5774, NJ USA: WILEY.

Research Partners