A Weakly-supervised Guided Soft Attention Network for Classification of Intracranial Hemorrhage

2022 ◽  
pp. 1-1
Author(s):  
Long Zhang ◽  
Wenlong Miao ◽  
Chuang Zhu ◽  
Yuanyuan Wang ◽  
Yihao Luo ◽  
...  
Keyword(s):  
Intracranial Hemorrhage ◽  
Attention Network ◽  
Weakly Supervised

scholarly journals Classification of Financial Tickets Using Weakly Supervised Fine-Grained Networks

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 129469-129477
Author(s):  
Hanning Zhang ◽  
Bo Dong ◽  
Boqin Feng ◽  
Fang Yang ◽  
Bo Xu
Keyword(s):  
Fine Grained ◽  
Weakly Supervised

Automatic Classification of Radiological Report for Intracranial Hemorrhage

2019 ◽  
Author(s):  
Kamal Jnawali ◽  
Mohammad R. Arbabshirani ◽  
Alvaro E. Ulloa ◽  
Navalgund Rao ◽  
Aalpen A. Patel
Keyword(s):  
Intracranial Hemorrhage ◽  
Automatic Classification ◽  
Radiological Report

scholarly journals Multiple Feature Integration for Classification of Thoracic Disease in Chest Radiography

2019 ◽  
Vol 9 (19) ◽  
pp. 4130 ◽  
Author(s):  
Thi Kieu Ho ◽  
Jeonghwan Gwak
Keyword(s):  
Treatment Strategies ◽  
Classification Model ◽  
Thoracic Diseases ◽  
Accurate Localization ◽  
Multiple Feature ◽  
Lung Abnormalities ◽  
Radiological Images ◽  
Weakly Supervised ◽  
Localization Approach

The accurate localization and classification of lung abnormalities from radiological images are important for clinical diagnosis and treatment strategies. However, multilabel classification, wherein medical images are interpreted to point out multiple existing or suspected pathologies, presents practical constraints. Building a highly precise classification model typically requires a huge number of images manually annotated with labels and finding masks that are expensive to acquire in practice. To address this intrinsically weakly supervised learning problem, we present the integration of different features extracted from shallow handcrafted techniques and a pretrained deep CNN model. The model consists of two main approaches: a localization approach that concentrates adaptively on the pathologically abnormal regions utilizing pretrained DenseNet-121 and a classification approach that integrates four types of local and deep features extracted respectively from SIFT, GIST, LBP, and HOG, and convolutional CNN features. We demonstrate that our approaches efficiently leverage interdependencies among target annotations and establish the state of the art classification results of 14 thoracic diseases in comparison with current reference baselines on the publicly available ChestX-ray14 dataset.

scholarly journals Weakly supervised learning for classification of lung cytological images using attention-based multiple instance learning

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Atsushi Teramoto ◽  
Yuka Kiriyama ◽  
Tetsuya Tsukamoto ◽  
Eiko Sakurai ◽  
Ayano Michiba ◽  
...  
Keyword(s):  
Supervised Learning ◽  
Classification Performance ◽  
Multiple Instance Learning ◽  
Cancer Type ◽  
Malignant Cells ◽  
Cytological Examination ◽  
Automated Method ◽  
Weakly Supervised ◽  
Better Than

AbstractIn cytological examination, suspicious cells are evaluated regarding malignancy and cancer type. To assist this, we previously proposed an automated method based on supervised learning that classifies cells in lung cytological images as benign or malignant. However, it is often difficult to label all cells. In this study, we developed a weakly supervised method for the classification of benign and malignant lung cells in cytological images using attention-based deep multiple instance learning (AD MIL). Images of lung cytological specimens were divided into small patch images and stored in bags. Each bag was then labeled as benign or malignant, and classification was conducted using AD MIL. The distribution of attention weights was also calculated as a color map to confirm the presence of malignant cells in the image. AD MIL using the AlexNet-like convolutional neural network model showed the best classification performance, with an accuracy of 0.916, which was better than that of supervised learning. In addition, an attention map of the entire image based on the attention weight allowed AD MIL to focus on most malignant cells. Our weakly supervised method automatically classifies cytological images with acceptable accuracy based on supervised learning without complex annotations.

Sign in / Sign up

Export Citation Format

Share Document