Classification and Disease Localization in Histopathology Using Only Global Labels: A Weakly-Supervised Approach
Explore this paper's citation graph
Summary
This work proposes a method for disease available during training that is able to demonstrate performance comparable with models trained with strong annotations on the Camelyon-16 lymph node metastases detection challenge, and achieves this through the use of pre-trained deep convolutional networks, feature embedding, as well as learning via top instances and negative evidence.
- Type
- preprint
- Published
- 2018-02-01
- Cited by
- 128
- References
- 36
- Access
- Open access
- OpenAlex
- https://openalex.org/W2786005418
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:3653978
Keywords
Artificial intelligence, Computer science, Digital pathology, Segmentation, Pattern recognition (psychology)
References
- Mitosis Detection in Breast Cancer Histology Images with Deep Neural Networks
- Multiple instance learning for soft bags via top instances
- Multiple instance classification: Review, taxonomy and comparative study
- Aggregating local descriptors into a compact image representation
- Digital imaging in pathology: the case for standardization
- Deep learning of feature representation with multiple instance learning for medical image analysis
- A Nonlinear Mapping Approach to Stain Normalization in Digital Histopathology Images Using Image-Specific Color Deconvolution
- Automatic detection of invasive ductal carcinoma in whole slide images with convolutional neural networks
- Pathology evaluation of sentinel lymph nodes in breast cancer: protocol recommendations and rationale
- Going deeper with convolutions
- Histopathological Image Analysis: A Review
- ImageNet: A large-scale hierarchical image database
- Solving the Multiple Instance Problem with Axis-Parallel Rectangles
- Validation of digital pathology imaging for primary histopathological diagnosis
- Applicability of White-Balancing Algorithms to Restoring Faded Colour Slides: An Empirical Evaluation
- A Threshold Selection Method from Gray-Level Histograms
- Deep Residual Learning for Image Recognition
- Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification
- A deep semantic mobile application for thyroid cytopathology
- Deep learning as a tool for increased accuracy and efficiency of histopathological diagnosis
Cited by
- Weakly Supervised Medical Diagnosis and Localization from Multiple Resolutions
- Brain age prediction of healthy subjects on anatomic MRI with deep learning : going beyond with an “explainable AI” mindset
- Deep Recurrent Attention Models for Histopathological Image Analysis
- A comparative analysis of sensitivity of convolutional neural networks for histopathology image classification in breast cancer
- High resolution whole prostate biopsy classification using streaming stochastic gradient descent
- Weakly supervised training of pixel resolution segmentation models on whole slide images
- Predicting Residual Cancer Burden In A Triple Negative Breast Cancer Cohort
- Weakly Supervised Deep Learning for Whole Slide Lung Cancer Image Analysis
- Transcriptomic learning for digital pathology
- Deep weakly-supervised learning methods for classification and localization in histology images: a survey
- Improved Prediction on Heart Transplant Rejection Using Convolutional Autoencoder and Multiple Instance Learning on Whole-Slide Imaging
- Deep learning-based classification of mesothelioma improves prediction of patient outcome
- Deep Learning for Whole Slide Image Analysis: An Overview
- Deep Learning-Based Classification of Liver Cancer Histopathology Images Using Only Global Labels
- Detection of Prostate Cancer in Whole-Slide Images Through End-to-End Training With Image-Level Labels
- Federated Survival Analysis with Discrete-Time Cox Models
- Deep learning in digital pathology image analysis: a survey
- A deep learning model to predict RNA-Seq expression of tumours from whole slide images
- Developing image analysis pipelines of whole-slide images: Pre- and post-processing
- A Weak Supervision-based Framework for Automatic Lung Cancer Classification on Whole Slide Image
Related papers
- Design of large zoom ratio long-wave infrared zoom system with compound zoom method
- UFO-Zoom: 화면으로부터의 수직 거리를 이용하여 Zoom을 수행하는 3차원 제스처 기반 화면 탐색 방식 제안
- UFO-Zoom: A new coupled map navigation technique using hand trajectories in the air
- An exact zooming method
- ОСОБЛИВОСТІ ПРОВЕДЕННЯ ОНЛАЙН-ЗАНЯТЬ З ІНОЗЕМНОЇ МОВИ ІЗ ЗАСТОСУВАННЯМ СЕРВЕРУ ZOOM В УМОВАХ ДИСТАНЦІЙНОГО НАВЧАННЯ
- Zoom systems: basic configurations