paper-with-me

홈 › Papers

Multi-level Multiple Instance Learning with Transformer for Whole Slide Image Classification

2023-06-08 · Ruijie Zhang, Qiaozhe Zhang, Yingzhuang Liu, Hao Xin, Yan Liu, Xinggang Wang

Whole slide image (WSI) refers to a type of high-resolution scanned tissue image, which is extensively employed in computer-assisted diagnosis (CAD). The extremely high resolution and limited availability of region-level annotations make employing deep learning methods for WSI-based digital diagnosis challenging. Recently integrating multiple instance learning (MIL) and Transformer for WSI analysis shows very promising results. However, designing effective Transformers for this weakly-supervised high-resolution image analysis is an underexplored yet important problem. In this paper, we propose a Multi-level MIL (MMIL) scheme by introducing a hierarchical structure to MIL, which enables efficient handling of MIL tasks involving a large number of instances. Based on MMIL, we instantiated MMIL-Transformer, an efficient Transformer model with windowed exact self-attention for large-scale MIL tasks. To validate its effectiveness, we conducted a set of experiments on WSI classification tasks, where MMIL-Transformer demonstrate superior performance compared to existing state-of-the-art methods, i.e., 96.80% test AUC and 97.67% test accuracy on the CAMELYON16 dataset, 99.04% test AUC and 94.37% test accuracy on the TCGA-NSCLC dataset, respectively. All code and pre-trained models are available at: https://github.com/hustvl/MMIL-Transformer

📄 PDF Abstract BibTeX arXiv:2306.05029

Code (1)

hustvl/mmil-transformer 공식 구현 pytorch

Tasks

image-classificationImage ClassificationMultiple Instance Learning

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

BEL: A Bag Embedding Loss for Transformer enhances Multiple Instance Whole Slide Image Classification

2023-03-02 · Daniel Sens, Ario Sadafi, Francesco Paolo Casale, Nassir Navab 외

Multiple Instance Learning (MIL) has become the predominant approach for classification tasks on gigapixel histopathology whole slide images (WSIs). Within the MIL framework, single WSIs (bags) are decomposed into patche…

image-classificationImage ClassificationMultiple Instance Learningwhole slide images

Diagnose Like a Pathologist: Transformer-Enabled Hierarchical Attention-Guided Multiple Instance Learning for Whole Slide Image Classification

2023-01-19 · Conghao Xiong, Hao Chen, Joseph J. Y. Sung, Irwin King

Multiple Instance Learning (MIL) and transformers are increasingly popular in histopathology Whole Slide Image (WSI) classification. However, unlike human pathologists who selectively observe specific regions of histopat…

image-classificationImage ClassificationMultiple Instance Learning

LNPL-MIL: Learning from Noisy Pseudo Labels for Promoting Multiple Instance Learning in Whole Slide Image

2023-01-01 · ICCV 2023 1 · Zhuchen Shao, Yifeng Wang, Yang Chen, Hao Bian 외

Gigapixel Whole Slide Images (WSIs) aided patient diagnosis and prognosis analysis are promising directions in computational pathology. However, limited by expensive and time-consuming annotation costs, WSIs usually …

Multiple Instance LearningPrognosisSurvival Predictionwhole slide images

Accounting for Dependencies in Deep Learning Based Multiple Instance Learning for Whole Slide Imaging

2021-11-01 · Andriy Myronenko, Ziyue Xu, Dong Yang, Holger Roth 외

Multiple instance learning (MIL) is a key algorithm for classification of whole slide images (WSI). Histology WSIs can have billions of pixels, which create enormous computational and annotation challenges. Typically, su…

Multiple Instance Learningwhole slide images

Multiple Instance Learning with Mixed Supervision in Gleason Grading

2022-06-26 · Hao Bian, Zhuchen Shao, Yang Chen, Yifeng Wang 외

With the development of computational pathology, deep learning methods for Gleason grading through whole slide images (WSIs) have excellent prospects. Since the size of WSIs is extremely large, the image label usually co…

Multiple Instance Learningwhole slide images