Search Results for author:
Found 7 papers, 3 papers with code
Distributionally Robust Safe Screening
In this study, we propose a method Distributionally Robust Safe Screening (DRSS), for identifying unnecessary samples and features within a DR covariate shift setting.
Mixing Histopathology Prototypes into Robust Slide-Level Representations for Cancer Subtyping
Whole-slide image analysis via the means of computational pathology often relies on processing tessellated gigapixel images with only slide-level labels available.
Generalized Low-Rank Update: Model Parameter Bounds for Low-Rank Training Data Modifications
Among the class of ML methods known as linear estimators, there exists an efficient model update framework called the low-rank update that can effectively handle changes in a small number of rows and columns within the data matrix.
Transformer-based Personalized Attention Mechanism for Medical Images with Clinical Records
In medical image diagnosis, identifying the attention region, i. e., the region of interest for which the diagnosis is made, is an important task.
Case-based Similar Image Retrieval for Weakly Annotated Large Histopathological Images of Malignant Lymphoma Using Deep Metric Learning
To address this problem, we employ attention-based multiple instance learning, which enables us to focus on tumor-specific regions when the similarity between cases is computed.
Multi-scale Domain-adversarial Multiple-instance CNN for Cancer Subtype Classification with Unannotated Histopathological Images
We propose a new method for cancer subtype classification from histopathological images, which can automatically detect tumor-specific features in a given whole slide image (WSI).
Computing Valid p-values for Image Segmentation by Selective Inference
To overcome this difficulty, we introduce a statistical approach called selective inference, and develop a framework to compute valid p-values in which the segmentation bias is properly accounted for.
