Proportion Estimation by Masked Learning from Label Proportion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Okuo, Takumi, Nishimura, Kazuya, Ito, Hiroaki, Terada, Kazuhiro, Yoshizawa, Akihiko, Bise, Ryoma
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916239105851392
author Okuo, Takumi
Nishimura, Kazuya
Ito, Hiroaki
Terada, Kazuhiro
Yoshizawa, Akihiko
Bise, Ryoma
author_facet Okuo, Takumi
Nishimura, Kazuya
Ito, Hiroaki
Terada, Kazuhiro
Yoshizawa, Akihiko
Bise, Ryoma
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_04815
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Proportion Estimation by Masked Learning from Label Proportion
Okuo, Takumi
Nishimura, Kazuya
Ito, Hiroaki
Terada, Kazuhiro
Yoshizawa, Akihiko
Bise, Ryoma
Computer Vision and Pattern Recognition
Machine Learning
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.
title Proportion Estimation by Masked Learning from Label Proportion
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2405.04815