☆ 3.8 Proceedings Paper

Differentiable Zooming for Multiple Instance Learning on Whole-Slide Images

COMPUTER VISION, ECCV 2022, PT XXI (2022)

Related references

Note: Only part of the references are listed.

Article Computer Science, Artificial Intelligence

Hierarchical graph representations in digital pathology

Pushpak Pati et al.

Summary: The accurate diagnosis, prognosis, and therapy response predictions for cancer patients rely heavily on the phenotype and distribution of histological entities in tissue specimens. Various methods have been developed to represent tissue structures using cell-graphs, leveraging graph theory and machine learning. This study proposes a novel hierarchical entity graph representation for tissue specimens and introduces a hierarchical graph neural network to map tissue structure to functionality. Through evaluation with the BRACS dataset, the proposed method demonstrates superior classification results compared to alternative methods and individual pathologists.

MEDICAL IMAGE ANALYSIS (2022)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Efficient Classification of Very Large Images with Tiny Objects

Fanjie Kong et al.

Summary: In computer vision, it is challenging to classify large images with small informative objects. Existing deep architectures and convolutional neural networks are not suitable for handling such images with memory constraints. The Zoom-In network is an end-to-end CNN model that combines hierarchical attention sampling to efficiently classify large images with tiny objects using a single GPU. Experimental results demonstrate higher accuracy and lower memory resource requirements compared to existing methods.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

Add to Collection

Article Mathematical & Computational Biology

BRACS: A Dataset for BReAst Carcinoma Subtyping in H&E Histology Images

Nadia Brancati et al.

Summary: Breast cancer is a common and deadly disease for women, and the use of Artificial Intelligence (AI) and digital workflows can improve diagnosis and patient care. This paper presents a large breast cancer subtyping dataset, consisting of annotated whole-slide images and regions of interest, which can be used to advance AI algorithms.

DATABASE-THE JOURNAL OF BIOLOGICAL DATABASES AND CURATION (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Neural Image Compression for Gigapixel Histopathology Image Analysis

David Tellez et al.

Summary: The proposed Neural Image Compression (NIC) method utilizes weak image-level labels to build convolutional neural networks in two steps: compressing image representations and training CNN on these compressed representations. Through contrasting training and evaluation, it is found that NIC successfully integrates visual cues associated with image-level labels.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

Add to Collection

Article Engineering, Biomedical

Deep Multi-Magnification Networks for multi-class breast cancer image segmentation

David Joon Ho et al.

Summary: In this paper, a Deep Multi-Magnification Network trained by partial annotation is proposed for automated multi-class tissue segmentation using a set of patches from multiple magnifications in digitized whole slide images. The proposed architecture outperforms other single and multi-magnification-based architectures by achieving the highest mean intersection-over-union, which can facilitate pathologists' assessments of breast cancer.

COMPUTERIZED MEDICAL IMAGING AND GRAPHICS (2021)

Add to Collection

Article Engineering, Biomedical

Data-efficient and weakly supervised computational pathology on whole-slide images

Ming Y. Lu et al.

Summary: The CLAM method utilizes attention-based learning to identify subregions with high diagnostic value for accurate classification of whole-slide images. It can localize well-known morphological features without the need for spatial labels, outperforming standard weakly supervised classification algorithms, and adapt to independent test cohorts, smartphone microscopy, and varying tissue content.

NATURE BIOMEDICAL ENGINEERING (2021)

Add to Collection

Article Biology

A multi-resolution model for histopathology image classification and localization with multiple instance learning

Jiayun Li et al.

Summary: This research introduces a multi-resolution multiple instance learning model that leverages saliency maps to detect suspicious regions in histopathological images for fine-grained grade prediction, eliminating the need for expensive region or pixel-level annotations. Trained on a large-scale prostate biopsy dataset, the model achieves high accuracy in predicting benign, low grade, and high grade pathology levels with slide-level labels only. The model also performs well in cancer detection on an external dataset, showcasing high AUROC and AP values.

COMPUTERS IN BIOLOGY AND MEDICINE (2021)

Add to Collection

Article Multidisciplinary Sciences

AI-based pathology predicts origins for cancers of unknown primary

Ming Y. Lu et al.

Summary: Cancer of unknown primary (CUP) is a difficult diagnosis as the primary site of tumor origin cannot be determined. The deep-learning-based algorithm TOAD provides a differential diagnosis for the origin of the primary tumor, achieving high accuracy on test sets and reducing the occurrence of CUP by assisting in assigning differential diagnoses for complicated cases.

NATURE (2021)

Add to Collection

Article Multidisciplinary Sciences

CAD systems for colorectal cancer from WSI are still not ready for clinical acceptance

Sara P. Oliveira et al.

Summary: Most oncological cases are detected through imaging techniques, but diagnosis relies on pathological assessment of tissue samples; the digital era of pathology has opened up research opportunities, particularly in the field of AI for CRC diagnosis on WSI; this study emphasizes the need for large datasets and appropriate learning methods in developing computer-aided diagnosis systems for CRC.

SCIENTIFIC REPORTS (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Learning Whole-Slide Segmentation from Inexact and Incomplete Labels Using Tissue Graphs

Valentin Anklin et al.

Summary: This paper introduces a weakly-supervised segmentation method, SegGini, which utilizes graphs to segment histology images using weak multiplex annotations. The method achieves state-of-the-art segmentation performance on public prostate cancer datasets and can be used in various annotation settings.

MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2021, PT II (2021)

Add to Collection

Proceedings Paper Acoustics

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

Andriy Myronenko et al.

Summary: The proposed deep learning based MIL method in this study explicitly considers dependencies between instances by embedding self-attention Transformer blocks and utilizing an instance-wise loss function based on pseudo-labels. This approach achieves state-of-the-art results in classifying WSI images on the PANDA challenge dataset.

MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2021, PT VIII (2021)

Add to Collection

Proceedings Paper Engineering, Biomedical

Graph Convolutional Networks for Region of Interest Classification in Breast Histopathology

Bulut Aygunes et al.

Summary: Current deep learning approaches for breast histopathology face limitations in multi-class categorization tasks, leading to the proposal of a solution that utilizes graph convolution networks to propagate local inter-patch context information.

MEDICAL IMAGING 2020: DIGITAL PATHOLOGY (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Context-Aware Convolutional Neural Network for Grading of Colorectal Cancer Histology Images

Muhammad Shaban et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Whole slide images based cancer survival prediction using attention guided deep multiple instance learning networks

Jiawen Yao et al.

MEDICAL IMAGE ANALYSIS (2020)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Multi-scale Domain-adversarial Multiple-instance CNN for Cancer Subtype Classification with Unannotated Histopathological Images

Noriaki Hashimoto et al.

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2020)

Add to Collection

Article Computer Science, Information Systems

Weakly Supervised Biomedical Image Segmentation by Reiterative Learning

Qiaokang Liang et al.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2019)

Add to Collection

Article Biochemistry & Molecular Biology

Clinical-grade computational pathology using weakly supervised deep learning on whole slide images

Gabriele Campanella et al.

NATURE MEDICINE (2019)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Learning Where to See: A Novel Attention Model for Automated Immunohistochemical Scoring

Talha Qaiser et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Adaptive Weighting Multi-Field-of-View CNN for Semantic Segmentation in Pathology

Hiroki Tokunaga et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Theory & Methods

Graph CNN for Survival Analysis on Whole Slide Pathological Images

Ruoyu Li et al.

MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2018, PT II (2018)

Add to Collection

Proceedings Paper Computer Science, Theory & Methods

Predicting Cancer with a Recurrent Visual Attention Model for Histopathology Images

Aicha BenTaieb et al.

MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2018, PT II (2018)

Add to Collection

Proceedings Paper Computer Science, Theory & Methods

Reinforced Auto-Zoom Net: Towards Accurate and Fast Breast Cancer Segmentation in Whole-Slide Images

Nanqing Dong et al.

DEEP LEARNING IN MEDICAL IMAGE ANALYSIS AND MULTIMODAL LEARNING FOR CLINICAL DECISION SUPPORT, DLMIA 2018 (2018)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Constrained Deep Weak Supervision for Histopathology Image Segmentation

Zhipeng Jia et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2017)

Add to Collection

Article Medicine, General & Internal

Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer

Babak Ehteshami Bejnordi et al.

JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION (2017)

Add to Collection

Article Radiology, Nuclear Medicine & Medical Imaging

Context-aware stacked convolutional neural networks for classification of breast carcinomas in whole-slide histopathology images

Babak Ehteshami Bejnordi et al.

JOURNAL OF MEDICAL IMAGING (2017)

Add to Collection

Proceedings Paper Optics

Multi-scale learning based segmentation of glands in digital colonrectal pathology images

Yi Gao et al.

MEDICAL IMAGING 2016: DIGITAL PATHOLOGY (2016)

Add to Collection

Correction Medicine, General & Internal

Diagnostic Concordance Among Pathologists Interpreting Breast Biopsy Specimens (vol 313, pg 1122, 2015)

Joann G. Elmore et al.

JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION (2015)

Add to Collection

Proceedings Paper Optics

A multi-scale superpixel classification approach to the detection of regions of interest in whole slide histopathology images

Babak Ehteshami Bejnordi et al.

MEDICAL IMAGING 2015: DIGITAL PATHOLOGY (2015)

Add to Collection

Article Medicine, General & Internal

Diagnostic Concordance Among Pathologists interpreting Breast Biopsy Specimens

Joann G. Elmore et al.

JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION (2015)

Add to Collection

Article Pathology

Inter-observer variability between general pathologists and a specialist in breast pathology in the diagnosis of lobular neoplasia, columnar cell lesions, atypical ductal hyperplasia and ductal carcinoma in situ of the breast

Douglas S. Gomes et al.

DIAGNOSTIC PATHOLOGY (2014)

Add to Collection

© Peeref 2019-2024. All rights reserved.