担当区分：筆頭著者,　責任著者   出版者・発行元：Springer Nature Switzerland  

Malignant lymphoma subtype classification directly impacts treatment
strategies and patient outcomes, necessitating classification models that
achieve both high accuracy and sufficient explainability. This study proposes a
novel explainable Multi-Instance Learning (MIL) framework that identifies
subtype-specific Regions of Interest (ROIs) from Whole Slide Images (WSIs)
while integrating cell distribution characteristics and image information. Our
framework simultaneously addresses three objectives: (1) indicating appropriate
ROIs for each subtype, (2) explaining the frequency and spatial distribution of
characteristic cell types, and (3) achieving high-accuracy subtyping by
leveraging both image and cell-distribution modalities. The proposed method
fuses cell graph and image features extracted from each patch in the WSI using
a Mixture-of-Experts (MoE) approach and classifies subtypes within an MIL
framework. Experiments on a dataset of 1,233 WSIs demonstrate that our approach
achieves state-of-the-art accuracy among ten comparative methods and provides
region-level and cell-level explanations that align with a pathologist's
perspectives.

DOI： 10.1007/978-3-032-05162-2_31

arXiv

researchmap

担当区分：筆頭著者,　責任著者   掲載種別：研究論文（学術雑誌）   出版者・発行元：Institute of Electronics, Information and Communications Engineers (IEICE)  

DOI： 10.1587/transinf.2022edp7200

researchmap

担当区分：筆頭著者,　責任著者   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

DOI： 10.1109/ijcnn55064.2022.9892108

DOI： 10.48550/arXiv.2209.10920

researchmap

記述言語：日本語   掲載種別：研究発表ペーパー・要旨（全国大会，その他学術会議）  

researchmap

出版者・発行元：arXiv  

Deep learning models are susceptible to adversarial attacks, where slight
perturbations to input data lead to misclassification. Adversarial attacks
become increasingly effective with access to information about the targeted
classifier. In the context of multi-task learning, where a single model learns
multiple tasks simultaneously, attackers may aim to exploit vulnerabilities in
specific tasks with limited information. This paper investigates the
feasibility of attacking hidden tasks within multi-task classifiers, where
model access regarding the hidden target task and labeled data for the hidden
target task are not available, but model access regarding the non-target tasks
is available. We propose a novel adversarial attack method that leverages
knowledge from non-target tasks and the shared backbone network of the
multi-task model to force the model to forget knowledge related to the target
task. Experimental results on CelebA and DeepFashion datasets demonstrate the
effectiveness of our method in degrading the accuracy of hidden tasks while
preserving the performance of visible tasks, contributing to the understanding
of adversarial vulnerabilities in multi-task classifiers.

DOI： 10.48550/ARXIV.2405.15244

arXiv

researchmap

その他リンク： http://arxiv.org/pdf/2405.15244v2

記述言語：日本語   出版者・発行元：電子情報通信学会 情報セキュリティ研究専門委員会（ISEC研）  

researchmap

担当区分：筆頭著者  

DOI： 10.11517/pjsai.JSAI2023.0_3D1GS203

J-GLOBAL

researchmap

担当区分：筆頭著者  

In real-world applications of multi-class classification models,
misclassification in an important class (e.g., stop sign) can be significantly
more harmful than in other classes (e.g., speed limit). In this paper, we
propose a loss function that can improve the recall of an important class while
maintaining the same level of accuracy as the case using cross-entropy loss.
For our purpose, we need to make the separation of the important class better
than the other classes. However, existing methods that give a class-sensitive
penalty for cross-entropy loss do not improve the separation. On the other
hand, the method that gives a margin to the angle between the feature vectors
and the weight vectors of the last fully connected layer corresponding to each
feature can improve the separation. Therefore, we propose a loss function that
can improve the separation of the important class by setting the margin only
for the important class, called Class-sensitive Additive Angular Margin Loss
(CAMRI Loss). CAMRI loss is expected to reduce the variance of angles between
features and weights of the important class relative to other classes due to
the margin around the important class in the feature space by adding a penalty
to the angle. In addition, concentrating the penalty only on the important
classes hardly sacrifices the separation of the other classes. Experiments on
CIFAR-10, GTSRB, and AwA2 showed that the proposed method could improve up to
9% recall improvement on cross-entropy loss without sacrificing accuracy.

DOI： 10.1587/transinf.2022EDP7200

arXiv

researchmap

その他リンク： http://arxiv.org/pdf/2209.10920v1

記述言語：英語   会議種別：ポスター発表  

開催地：Brisbane   国名：オーストラリア連邦  

researchmap

開催年月日： 2025年9月

Malignant lymphoma subtype classification directly impacts treatment strategies and patient outcomes, necessitating classification models that achieve both high accuracy and sufficient explainability. This study proposes a novel explainable Multi-Instance Learning (MIL) framework that identifies subtype-specific Regions of Interest (ROIs) from Whole Slide Images (WSIs) while integrating cell distribution characteristics and image information. Our framework simultaneously addresses three objectives: (1) indicating appropriate ROIs for each subtype, (2) explaining the frequency and spatial distribution of characteristic cell types, and (3) achieving high-accuracy subtyping by leveraging both image and cell-distribution modalities. The proposed method fuses cell graph and image features extracted from each patch in the WSI using a Mixture-of-Experts (MoE) approach and classifies subtypes within an MIL framework. Experiments on a dataset of 1,233 WSIs demonstrate that our approach achieves state-of-the-art accuracy among ten comparative methods and provides region-level and cell-level explanations that align with a pathologist's perspectives.

researchmap

開催年月日： 2025年3月

記述言語：日本語  

researchmap

開催年月日： 2024年6月

会議種別：シンポジウム・ワークショップ パネル（指名）  

researchmap

開催年月日： 2024年1月

記述言語：日本語   会議種別：口頭発表（一般）  

researchmap

情報セキュリティ分野に関する国家資格「情報処理安全確保支援士」を取得。

researchmap

researchmap

researchmap

対象： 中学生,　教育関係者,　行政機関

種別：セミナー・ワークショップ

つくば市内の中学生を対象としたサーバー・ネットワーク教育イベント「インデペンデンス・サーバー・デイ」に、2019年度より継続して参画。参加者が1人1台のサーバーと固定グローバルIPアドレスを用いて、Linux、ネットワーク、Webサーバー、セキュリティ等を学ぶ講義・実習において、講師や企画運営および受講者支援を担当している。

researchmap

執筆者：本人以外 

AbemaTV配信番組『TDK presents 学生イノベーションバトル そのヒラメキで世界を変えろ』に、筑波大学チーム「Dr.B」として出演。外国人旅行者の医療費未払い問題の解決を目的として、暗号資産を活用した医療費決済サービスを開発した。約4か月間の研究開発・検証・発表の過程がドキュメンタリーとして特集され、全7チームによる開発コンテストで優勝した。

researchmap