23 papers
Preserving DEG Rankings for Gene Discovery in Histology-Based Spatial Gene Expression Prediction
Kaito Shiku, Kazuya Nishimura, Yasuhiro Kojima +1
Predicting spatial gene expression from histology images could scale spatial transcriptomics (ST) to image-only cohorts, but conventional histology-based ST prediction is trained a…
Weakly Supervised Instance-Level Gleason Pattern Estimation Using Primary and Secondary Labels
Nao Sugeta, Kaito Shiku, Shinnosuke Matsuo +1
In prostate cancer histopathology, the Gleason Score is determined by the most frequent (Primary) and second most frequent (Secondary) Gleason patterns within a whole-slide image.…
GC-MoE: Genomics-Guided Cell-Type-Specific Mixture of Experts for Histology-Based Single-Cell Spatial Transcriptomics
Kaito Shiku, Ahtisham Fazeel Abbasi, Ryoma Bise +4
Histology-based single-cell spatial transcriptomics (ST) estimation aims to predict gene expression for individual cells from histopathological images and cell locations, reducing…
Leveraging Vision-Language Models as Weak Annotators in Active Learning
Phuong Ngoc Nguyen, Kaito Shiku, Ryoma Bise +2
Active learning aims to reduce annotation cost by selectively querying informative samples for supervision under a limited labeling budget. In this work, we investigate how vision-…
Leveraging Cell-level Spatial Transcriptomics as Weak Supervision for Nuclei Classification
Kazuya Nishimura, Ryoma Bise, Haruka Hirose +1
Deep learning-based nuclei analysis in histopathology relies heavily on large-scale, expert-curated datasets that are costly and difficult to scale across organs. To address this,…
Cell Instance Segmentation via Multi-Task Image-to-Image Schrödinger Bridge
Hayato Inoue, Shota Harada, Shumpei Takezaki +1
Existing cell instance segmentation pipelines typically combine deterministic predictions with post-processing, which imposes limited explicit constraints on the global structure o…
Ranking-Guided Semi-Supervised Domain Adaptation for Severity Classification
Shota Harada, Ryoma Bise, Kiyohito Tanaka +1
Semi-supervised domain adaptation leverages a few labeled and many unlabeled target samples, making it promising for addressing domain shifts in medical image analysis. However, ex…
Cell-Type Prototype-Informed Neural Network for Gene Expression Estimation from Pathology Images
Kazuya Nishimura, Ryoma Bise, Shinnosuke Matsuo +2
Estimating slide- and patch-level gene expression profiles from pathology images enables rapid and low-cost molecular analysis with broad clinical impact. Despite strong results, e…
Leveraging Label Proportion Prior for Class-Imbalanced Semi-Supervised Learning
Kohki Akiba, Shinnosuke Matsuo, Shota Harada +1
Semi-supervised learning (SSL) often suffers under class imbalance, where pseudo-labeling amplifies majority bias and suppresses minority performance. We address this issue with a…
Hypernetwork-Based Adaptive Aggregation for Multimodal Multiple-Instance Learning in Predicting Coronary Calcium Debulking
Kaito Shiku, Ichika Seo, Tetsuya Matoba +3
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…
Learning Relative Gene Expression Trends from Pathology Images in Spatial Transcriptomics
Kazuya Nishimura, Haruka Hirose, Ryoma Bise +2
Gene expression estimation from pathology images has the potential to reduce the RNA sequencing cost. Point-wise loss functions have been widely used to minimize the discrepancy be…
Auxiliary Gene Learning: Spatial Gene Expression Estimation by Auxiliary Gene Selection
Kaito Shiku, Kazuya Nishimura, Shinnosuke Matsuo +2
Spatial transcriptomics (ST) is a novel technology that enables the observation of gene expression at the resolution of individual spots within pathological tissues. ST quantifies…
Learning from Majority Label: A Novel Problem in Multi-class Multiple-Instance Learning
Shiku Kaito, Shinnosuke Matsuo, Daiki Suehiro +1
The paper proposes a novel multi-class Multiple-Instance Learning (MIL) problem called Learning from Majority Label (LML). In LML, the majority class of instances in a bag is assig…
NoiseCutMix: A Novel Data Augmentation Approach by Mixing Estimated Noise in Diffusion Models
Shumpei Takezaki, Ryoma Bise, Shinnosuke Matsuo
In this study, we propose a novel data augmentation method that introduces the concept of CutMix into the generation process of diffusion models, thereby exploiting both the abilit…
Adaptive Pseudo Label Selection for Individual Unlabeled Data by Positive and Unlabeled Learning
Takehiro Yamane, Itaru Tsuge, Susumu Saito +1
This paper proposes a novel pseudo-labeling method for medical image segmentation that can perform learning on ``individual images'' to select effective pseudo-labels. We introduce…
Domain Generalization of Pathological Image Segmentation by Patch-Level and WSI-Level Contrastive Learning
Yuki Shigeyasu, Shota Harada, Akihiko Yoshizawa +6
In this paper, we address domain shifts in pathological images by focusing on shifts within whole slide images~(WSIs), such as patient characteristics and tissue thickness, rather…
Enhancing Reliability of Medical Image Diagnosis through Top-rank Learning with Rejection Module
Xiaotong Ji, Ryoma Bise, Seiichi Uchida
In medical image processing, accurate diagnosis is of paramount importance. Leveraging machine learning techniques, particularly top-rank learning, shows significant promise by foc…
Weakly-Supervised Domain Adaptation with Proportion-Constrained Pseudo-Labeling
Takumi Okuo, Shinnosuke Matsuo, Shota Harada +2
Domain shift is a significant challenge in machine learning, particularly in medical applications where data distributions differ across institutions due to variations in data coll…
Towards Spatial Transcriptomics-guided Pathological Image Recognition with Batch-Agnostic Encoder
Kazuya Nishimura, Ryoma Bise, Yasuhiro Kojima
Spatial transcriptomics (ST) is a novel technique that simultaneously captures pathological images and gene expression profiling with spatial coordinates. Since ST is closely relat…
Instance-wise Supervision-level Optimization in Active Learning
Shinnosuke Matsuo, Riku Togashi, Ryoma Bise +2
Active learning (AL) is a label-efficient machine learning paradigm that focuses on selectively annotating high-value instances to maximize learning efficiency. Its effectiveness c…
Deep Bayesian Active Learning-to-Rank with Relative Annotation for Estimation of Ulcerative Colitis Severity
Takeaki Kadota, Hideaki Hayashi, Ryoma Bise +2
Automatic image-based severity estimation is an important task in computer-aided diagnosis. Severity estimation by deep learning requires a large amount of training data to achieve…
Theoretical Proportion Label Perturbation for Learning from Label Proportions in Large Bags
Shunsuke Kubo, Shinnosuke Matsuo, Daiki Suehiro +4
Learning from label proportions (LLP) is a kind of weakly supervised learning that trains an instance-level classifier from label proportions of bags, which consist of sets of inst…
Learning from Partial Label Proportions for Whole Slide Image Segmentation
Shinnosuke Matsuo, Daiki Suehiro, Seiichi Uchida +4
In this paper, we address the segmentation of tumor subtypes in whole slide images (WSI) by utilizing incomplete label proportions. Specifically, we utilize `partial' label proport…