English
Related papers

Related papers: SAM-MIL: A Spatial Contextual Aware Multiple Insta…

200 papers

Vision language models (VLM) pre-trained on datasets of histopathological image-caption pairs enabled zero-shot slide-level classification. The ability of VLM image encoders to extract discriminative features also opens the door for…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Pablo Meseguer , Rocío del Amor , Valery Naranjo

Whole Slide Image (WSI) classification is often formulated as a Multiple Instance Learning (MIL) problem. Recently, Vision-Language Models (VLMs) have demonstrated remarkable performance in WSI classification. However, existing methods…

Computer Vision and Pattern Recognition · Computer Science 2024-04-08 Hao Li , Ying Chen , Yifei Chen , Wenxian Yang , Bowen Ding , Yuchen Han , Liansheng Wang , Rongshan Yu

Multi-class multi-instance segmentation is the task of identifying masks for multiple object classes and multiple instances of the same class within an image. The foundational Segment Anything Model (SAM) is designed for promptable…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Mariia Khan , Yue Qiu , Yuren Cong , Jumana Abu-Khalaf , David Suter , Bodo Rosenhahn

While the Segment Anything Model (SAM) excels in semantic segmentation for general-purpose images, its performance significantly deteriorates when applied to medical images, primarily attributable to insufficient representation of medical…

Computer Vision and Pattern Recognition · Computer Science 2023-11-07 Yiming Zhang , Tianang Leng , Kun Han , Xiaohui Xie

The Segment Anything Model (SAM) excels at generating precise object masks from input prompts but lacks semantic awareness, failing to associate its generated masks with specific object categories. To address this limitation, we propose…

Computer Vision and Pattern Recognition · Computer Science 2025-09-04 Rohit Kundu , Sudipta Paul , Arindam Dutta , Amit K. Roy-Chowdhury

Recent advancements in computational pathology and artificial intelligence have significantly improved whole slide image (WSI) classification. However, the gigapixel resolution of WSIs and the scarcity of manual annotations present…

Computer Vision and Pattern Recognition · Computer Science 2024-08-26 Mingxi Ouyang , Yuqiu Fu , Renao Yan , ShanShan Shi , Xitong Ling , Lianghui Zhu , Yonghong He , Tian Guan

Multiple Instance Learning (MIL) is a weakly-supervised problem in which one label is assigned to the whole bag of instances. An important class of MIL models is instance-based, where we first classify instances and then aggregate those…

Image and Video Processing · Electrical Eng. & Systems 2024-03-13 Łukasz Struski , Dawid Rymarczyk , Arkadiusz Lewicki , Robert Sabiniewicz , Jacek Tabor , Bartosz Zieliński

Recently, developing unified medical image segmentation models gains increasing attention, especially with the advent of the Segment Anything Model (SAM). SAM has shown promising binary segmentation performance in natural domains, however,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-18 Shuangping Huang , Hao Liang , Qingfeng Wang , Chulong Zhong , Zijian Zhou , Miaojing Shi

Although multi-instance learning (MIL) has succeeded in pathological image classification, it faces the challenge of high inference costs due to the need to process thousands of patches from each gigapixel whole slide image (WSI). To…

Computer Vision and Pattern Recognition · Computer Science 2025-08-08 Jiuyang Dong , Jiahan Li , Junjun Jiang , Kui Jiang , Yongbing Zhang

Whole Slide Imaging (WSI) has become a gold standard in cancer diagnosis, inspecting multi-scale information from cellular to tissue levels. Processing an entire WSI directly is infeasible due to GPU memory constraints; thus, Multiple…

Image and Video Processing · Electrical Eng. & Systems 2026-05-08 Tianyi Zhang , Sicheng Chen , Borui Kang , Dankai Liao , Qiaochu Xue , Bochong Zhang , Fei Xia , Zeyu Liu , Yueming Jin

In digital pathology, the multiple instance learning (MIL) strategy is widely used in the weakly supervised histopathology whole slide image (WSI) classification task where giga-pixel WSIs are only labeled at the slide level. However,…

Image and Video Processing · Electrical Eng. & Systems 2024-03-28 Zhan Shi , Jingwei Zhang , Jun Kong , Fusheng Wang

Annotating cancerous regions in whole-slide images (WSIs) of pathology samples plays a critical role in clinical diagnosis, biomedical research, and machine learning algorithms development. However, generating exhaustive and accurate…

Computer Vision and Pattern Recognition · Computer Science 2022-06-09 Zhenzhen Wang , Carla Saoud , Sintawat Wangsiricharoen , Aaron W. James , Aleksander S. Popel , Jeremias Sulam

Behavioral changes are the earliest signs of a mental disorder, but arguably, the dynamics of brain function gets affected even earlier. Subsequently, spatio-temporal structure of disorder-specific dynamics is crucial for early diagnosis…

Machine Learning · Computer Science 2021-06-22 Usman Mahmood , Md Mahfuzur Rahman , Alex Fedorov , Noah Lewis , Zening Fu , Vince D. Calhoun , Sergey M. Plis

The Segment Anything Model (SAM) exhibits a capability to segment a wide array of objects in natural images, serving as a versatile perceptual tool for various downstream image segmentation tasks. In contrast, medical image segmentation…

Computer Vision and Pattern Recognition · Computer Science 2023-08-29 Yizhe Zhang , Tao Zhou , Shuo Wang , Ye Wu , Pengfei Gu , Danny Z. Chen

Segmenting tumors in histological images is vital for cancer diagnosis. While fully supervised models excel with pixel-level annotations, creating such annotations is labor-intensive and costly. Accurate histopathology image segmentation…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Yinsheng He , Xingyu Li , Roger J. Zemp

In whole slide images (WSIs) analysis, attention-based multi-instance learning (MIL) models are susceptible to spurious correlations and degrade under domain shift. These methods may assign high attention weights to non-tumor regions, such…

Computer Vision and Pattern Recognition · Computer Science 2025-12-08 Xin Liu , Weijia Zhang , Wei Tang , Thuc Duy Le , Jiuyong Li , Lin Liu , Min-Ling Zhang

Multiple instance learning (MIL) is a supervised learning methodology that aims to allow models to learn instance class labels from bag class labels, where a bag is defined to contain multiple instances. MIL is gaining traction for learning…

Computer Vision and Pattern Recognition · Computer Science 2019-11-14 Samuel W. Remedios , Zihao Wu , Camilo Bermudez , Cailey I. Kerley , Snehashis Roy , Mayur B. Patel , John A. Butman , Bennett A. Landman , Dzung L. Pham

Multi-instance learning (MIL) is a form of weakly supervised learning where a single class label is assigned to a bag of instances while the instance-level labels are not available. Training classifiers to accurately determine the bag label…

Computer Vision and Pattern Recognition · Computer Science 2020-06-11 Bin Li , Kevin W. Eliceiri

Squamous cell carcinoma (SCC) is the most common cancer subtype, with an increasing incidence and a significant impact on cancer-related mortality. SCC grading using whole slide images is inherently challenging due to the lack of a reliable…

In computational pathology, random sampling of patches during training of Multiple Instance Learning (MIL) methods is computationally efficient and serves as a regularization strategy. Despite its promising benefits, questions concerning…

Computer Vision and Pattern Recognition · Computer Science 2024-03-11 H. Keshvarikhojasteh , J. P. W. Pluim , M. Veta