Paper Info
Title
Hetero-Modal Learning and Expansive Consistency Constraints for Semi-supervised Detection from Multi-sequence Data.
Abstract
Lesion detection serves a critical role in early diagnosis and has been well explored in recent years due to methodological advancesand increased data availability. However, the high costs of annotations hinder the collection of large and completely labeled datasets, motivating semi-supervised detection approaches. In this paper, we introduce mean teacher hetero-modal detection (MTHD), which addresses two important gaps in current semi-supervised detection. First, it is not obvious how to enforce unlabeled consistency constraints across the very different outputs of various detectors, which has resulted in various compromises being used in the state of the art. Using an anchor-free framework, MTHD formulates a mean teacher approach without such compromises, enforcing consistency on the soft-output of object centers and size. Second, multi-sequence data is often critical, e.g., for abdominal lesion detection, but unlabeled data is often missing sequences. To deal with this, MTHD incorporates hetero-modal learning in its framework. Unlike prior art, MTHD is able to incorporate an expansive set of consistency constraints that include geometric transforms and random sequence combinations. We train and evaluate MTHD on liver lesion detection using the largest MR lesion dataset to date (1099 patients with >5000 volumes). MTHD surpasses the best fully-supervised and semi-supervised competitors by 10.1% and 3.5%, respectively, in average sensitivity.
Year
DOI
Venue
2021
10.1007/978-3-030-87589-3_31
MLMI@MICCAI
DocType
Citations 
PageRank 
Conference
0
0.34
References 
Authors
0
10
Name
Order
Citations
PageRank
Bolin Lai101.35
Yuhsuan Wu200.68
Xiao-Yun Zhou378.03
Peng Wang4385106.03
Le Lu5129786.78
Lingyun Huang603.04
Mei Han795257.87
Jing Xiao83112.96
Heping Hu900.68
Adam P. Harrison1010117.06