首页|Acquiring Weak Annotations for Tumor Localization in Temporal and Volumetric Data
Acquiring Weak Annotations for Tumor Localization in Temporal and Volumetric Data
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
万方数据
Creating large-scale and well-annotated datasets to train AI algorithms is crucial for automated tumor detection and local-ization.However,with limited resources,it is challenging to determine the best type of annotations when annotating massive amounts of unlabeled data.To address this issue,we focus on polyps in colonoscopy videos and pancreatic tumors in abdominal CT scans;Both ap-plications require significant effort and time for pixel-wise annotation due to the high dimensional nature of the data,involving either temporary or spatial dimensions.In this paper,we develop a new annotation strategy,termed Drag&Drop,which simplifies the annota-tion process to drag and drop.This annotation strategy is more efficient,particularly for temporal and volumetric imaging,than other types of weak annotations,such as per-pixel,bounding boxes,scribbles,ellipses and points.Furthermore,to exploit our Drag&Drop an-notations,we develop a novel weakly supervised learning method based on the watershed algorithm.Experimental results show that our method achieves better detection and localization performance than alternative weak annotations and,more importantly,achieves sim-ilar performance to that trained on detailed per-pixel annotations.Interestingly,we find that,with limited resources,allocating weak an-notations from a diverse patient population can foster models more robust to unseen images than allocating per-pixel annotations for a small set of images.In summary,this research proposes an efficient annotation strategy for tumor detection and localization that is less accurate than per-pixel annotations but useful for creating large-scale datasets for screening tumors in various medical modalities.Project Page:https://github.com/johnson111788/Drag-Drop.
NETL
NSTL
万方数据
