Hypernetwork-Based Adaptive Aggregation for Multimodal Multiple-Instance Learning in Predicting Coronary Calcium Debulking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shiku, Kaito, Seo, Ichika, Matoba, Tetsuya, Hino, Rissei, Nakano, Yasuhiro, Bise, Ryoma
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910004491059200
author Shiku, Kaito
Seo, Ichika
Matoba, Tetsuya
Hino, Rissei
Nakano, Yasuhiro
Bise, Ryoma
author_facet Shiku, Kaito
Seo, Ichika
Matoba, Tetsuya
Hino, Rissei
Nakano, Yasuhiro
Bise, Ryoma
contents In this paper, we present the first attempt to estimate the necessity of debulking coronary artery calcifications from computed tomography (CT) images. We formulate this task as a Multiple-instance Learning (MIL) problem. The difficulty of this task lies in that physicians adjust their focus and decision criteria for device usage according to tabular data representing each patient's condition. To address this issue, we propose a hypernetwork-based adaptive aggregation transformer (HyperAdAgFormer), which adaptively modifies the feature aggregation strategy for each patient based on tabular data through a hypernetwork. The experiments using the clinical dataset demonstrated the effectiveness of HyperAdAgFormer. The code is publicly available at https://github.com/Shiku-Kaito/HyperAdAgFormer.
format Preprint
id arxiv_https___arxiv_org_abs_2601_21479
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hypernetwork-Based Adaptive Aggregation for Multimodal Multiple-Instance Learning in Predicting Coronary Calcium Debulking
Shiku, Kaito
Seo, Ichika
Matoba, Tetsuya
Hino, Rissei
Nakano, Yasuhiro
Bise, Ryoma
Computer Vision and Pattern Recognition
In this paper, we present the first attempt to estimate the necessity of debulking coronary artery calcifications from computed tomography (CT) images. We formulate this task as a Multiple-instance Learning (MIL) problem. The difficulty of this task lies in that physicians adjust their focus and decision criteria for device usage according to tabular data representing each patient's condition. To address this issue, we propose a hypernetwork-based adaptive aggregation transformer (HyperAdAgFormer), which adaptively modifies the feature aggregation strategy for each patient based on tabular data through a hypernetwork. The experiments using the clinical dataset demonstrated the effectiveness of HyperAdAgFormer. The code is publicly available at https://github.com/Shiku-Kaito/HyperAdAgFormer.
title Hypernetwork-Based Adaptive Aggregation for Multimodal Multiple-Instance Learning in Predicting Coronary Calcium Debulking
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.21479