Authors:
Takeshi Yoshida
1
;
Kazuki Uehara
2
;
Hidenori Sakanashi
1
;
2
;
Hirokazu Nosato
2
and
Masahiro Murakawa
1
;
2
Affiliations:
1
University of Tsukuba, 1-1-1, Tennoudai, Tsukuba, Ibaraki, Japan
;
2
National Institute of Advanced Industrial Science and Technology (AIST), 1-1-1, Umezono, Tsukuba, Ibaraki, Japan
Keyword(s):
Attention Mechanism, Multi-Scale Whole Slide Image, Multiple Instance Learning, Pathological Diagnosis Support Technology.
Abstract:
This study proposes a multi-scale attention assembler network (MSAA-Net) for multi-scale pathological image classification. The proposed method discovers crucial features by observing each scale and finding essential scales used for classification. To realize this characteristic, we introduce a two-stage feature aggregation mechanism, which first assigns the attention weights to useful local regions for each scale and then assigns the attention weights to the scale. The mechanism observes a pathological image from each scale perspective and adaptively determines the essential scale to classify from the observation results. To train the MSAA-Net, we adopt multiple instance learning (MIL), a learning approach for predicting a label corresponding to multiple images. The labeling effort reduces because the MIL trains the classification model using diagnoses for whole slide-level images obtained by daily diagnoses of pathologists instead of detailed annotations of the images. We conducted
classification using two pathological image datasets to evaluate the proposed method. The results indicate that the proposed method outperforms state-of-the-art multi-scale-based methods.
(More)