Timezone: »

Synthetic Tumors Make AI Segment Tumors Better
Qixin Hu · Junfei Xiao · Alan Yuille · Zongwei Zhou

We develop a novel strategy to generate synthetic tumors. Unlike existing works, the tumors generated by our strategy have two intriguing advantages: (1) realistic in shape and texture, which even medical professionals can confuse with real tumors; (2) effective for training AI models, which can perform liver tumor segmentation similarly to the model trained on real tumors—this result is unprecedented because no existing work, using synthetic tumors only, has thus far reached a similar or even close performance to the model trained on real tumors. This result also implies that manual efforts for developing per-voxel annotation of tumors (which took years to create) can be considerably reduced for training AI models in the future. Moreover, our synthetic tumors have the potential to improve the success rate of small tumor detection by automatically generating enormous examples of small (or tiny) synthetic tumors.

Author Information

Qixin Hu (Huazhong University of Science and Technology)
Junfei Xiao (Johns Hopkins University)
Alan Yuille (JHU)
Zongwei Zhou (Johns Hopkins University)

More from the Same Authors