Proportion Estimation by Masked Learning from Label Proportion

Autor:	Okuo, Takumi, Nishimura, Kazuya, Ito, Hiroaki, Terada, Kazuhiro, Yoshizawa, Akihiko, Bise, Ryoma
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	The PD-L1 rate, the number of PD-L1 positive tumor cells over the total number of all tumor cells, is an important metric for immunotherapy. This metric is recorded as diagnostic information with pathological images. In this paper, we propose a proportion estimation method with a small amount of cell-level annotation and proportion annotation, which can be easily collected. Since the PD-L1 rate is calculated from only `tumor cells' and not using `non-tumor cells', we first detect tumor cells with a detection model. Then, we estimate the PD-L1 proportion by introducing a masking technique to `learning from label proportion.' In addition, we propose a weighted focal proportion loss to address data imbalance problems. Experiments using clinical data demonstrate the effectiveness of our method. Our method achieved the best performance in comparisons. Comment: Accepted at The 3rd MICCAI workshop on Data Augmentation, Labeling, and Imperfections
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2405.04815 Zobrazit plný text záznamu View this record from Arxiv