OVS+Tumor: a tool for enhanced lung tumor annotation in VR for machine learning training and analysis

Creators: Lombeyda, Santiago; Mahabal, Ashish; Crichton, Daniel; Kincaid, Heather; Djorgovski, S. G.; Patriotis, Christos; Srivastava, Sudhir

Abstract

OVS+Tumor creates a seamless VR environment designed for intuitive interaction aiding in the complex task of parsing through 3D CT-scans and annotating candidate tumors. Through interactive subsetting and on-the-fly iso-cloud generation, a wider range of users beyond just domain experts (radiologists/surgeons) can generate a viable machine-learning training dataset.

Additional Information

© 2019. Copyright is held by the owner/author(s). We would like to thank the guidance and aid from Jim Barry, Mathieu Desbrun, and Matt Thomson; as well as acknowledge funding from the Interagency Agreement between National Institutes of Health (NIH)/National Cancer Institute (NCI) and NASA, the Chan-Zuckerberg Institute, and Caltech's Student Affairs, and hardware donations from HTC/Vive, Microsoft, NVIDIA, and Logitech which made of this work possible. OVS+Tumor was developed using free/personal versions of Unity, alongside SteamVR, as well as Zen Fulcrum's VR Browser for Unity. Voicework by Ashwini Nayak.

Attached Files

Supplemental Material - a26-crichton.pdf

Files

a26-crichton.pdf

Files (852.0 kB)

Name	Size	Download all
a26-crichton.pdf md5:1db9bf60ee490294dd43ac5d1d4edb81	852.0 kB	Preview Download

Additional details

	All versions	This version
Views	0	0
Downloads	0	0
Data volume	0 Bytes	0 Bytes