Dual attention multiple instance learning with unsupervised complementary loss for COVID-19 screening

Chikontwe, Philip; Luna, Miguel; Kang, Myeongkyun; Hong, Kyung Soo; Ahn, Jae‐Jun; Park, Sang Hyun

doi:10.1016/j.media.2021.102105

Cited by 29 publications

(11 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, U-Net (13,14), V-Net (15), and nnU-Net (16) exhibit accurate segmentation performance; affine models (i.e., FLIRT, A-SIFT) (17) and deformable models [i.e., FNIRT, ANTS, VoxelMorph (18), Dual-PRNet (19), LDDMM (20)] assist to image registration; ResNet (21), DenseNet (22) and their variants have attracted much attention in classification tasks. Also, varied attention mechanisms and loss functions have been utilized to optimize the deep learning network and improve its robustness (23)(24)(25)(26). The accurate analysis of medical images accelerates the development and upgrading of intelligent algorithms that can be integrated into the software to enable easy-to-use clinical research.…”

Section: Introductionmentioning

confidence: 99%

uRP: An integrated research platform for one-stop analysis of medical images

Xia

Wang

et al. 2023

Front. Radiol.

View full text Add to dashboard Cite

IntroductionMedical image analysis is of tremendous importance in serving clinical diagnosis, treatment planning, as well as prognosis assessment. However, the image analysis process usually involves multiple modality-specific software and relies on rigorous manual operations, which is time-consuming and potentially low reproducible.MethodsWe present an integrated platform - uAI Research Portal (uRP), to achieve one-stop analyses of multimodal images such as CT, MRI, and PET for clinical research applications. The proposed uRP adopts a modularized architecture to be multifunctional, extensible, and customizable.Results and DiscussionThe uRP shows 3 advantages, as it 1) spans a wealth of algorithms for image processing including semi-automatic delineation, automatic segmentation, registration, classification, quantitative analysis, and image visualization, to realize a one-stop analytic pipeline, 2) integrates a variety of functional modules, which can be directly applied, combined, or customized for specific application domains, such as brain, pneumonia, and knee joint analyses, 3) enables full-stack analysis of one disease, including diagnosis, treatment planning, and prognosis assessment, as well as full-spectrum coverage for multiple disease applications. With the continuous development and inclusion of advanced algorithms, we expect this platform to largely simplify the clinical scientific research process and promote more and better discoveries.

show abstract

Section: Introductionmentioning

confidence: 99%

uRP: An integrated research platform for one-stop analysis of medical images

Xia

Wang

et al. 2023

Front. Radiol.

View full text Add to dashboard Cite

show abstract

“…From 2012, deep learning methods, such as convolutional neural network (CNN), have greatly promoted the development of computer vision (CV) [5] field. Recently, deep learning has become an emerging field that can play an important role in the detection of COVID-19 [6] , [7] , [8] . Some deep learning methods used X-rays or CT images to complete COVID-19 recognition.…”

Section: Introductionmentioning

confidence: 99%

DCML: Deep contrastive mutual learning for COVID-19 recognition

Zhang

Liang

et al. 2022

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

“…Existing deep learning models for weakly supervised medical segmentation class the images with features extracted with convolutions ( 9 – 12 ). The pixel-level and image-level predictions are unified with algorithms based on Multiple-instance learning (MIL) ( 9 , 10 , 13 ) or class activation map (CAM) ( 11 , 12 , 14 ). Moreover, the attention mechanism is adopted to promote their performances ( 9 – 12 ).…”

Section: Introductionmentioning

confidence: 99%

Chest L-Transformer: Local Features With Position Attention for Weakly Supervised Chest Radiograph Segmentation and Classification

Wang

Qin

et al. 2022

Front. Med.

View full text Add to dashboard Cite

We consider the problem of weakly supervised segmentation on chest radiographs. The chest radiograph is the most common means of screening and diagnosing thoracic diseases. Weakly supervised deep learning models have gained increasing popularity in medical image segmentation. However, these models are not suitable for the critical characteristics presented in chest radiographs: the global symmetry of chest radiographs and dependencies between lesions and their positions. These models extract global features from the whole image to make the image-level decision. The global symmetry can lead these models to misclassification of symmetrical positions of the lesions. Thoracic diseases often have special disease prone areas in chest radiographs. There is a relationship between the lesions and their positions. In this study, we propose a weakly supervised model, called Chest L-Transformer, to take these characteristics into account. Chest L-Transformer classifies an image based on local features to avoid the misclassification caused by the global symmetry. Moreover, associated with Transformer attention mechanism, Chest L-Transformer models the dependencies between the lesions and their positions and pays more attention to the disease prone areas. Chest L-Transformer is only trained with image-level annotations for lesion segmentation. Thus, Log-Sum-Exp voting and its variant are proposed to unify the pixel-level prediction with the image-level prediction. We demonstrate a significant segmentation performance improvement over the current state-of-the-art while achieving competitive classification performance.

show abstract

Dual attention multiple instance learning with unsupervised complementary loss for COVID-19 screening

Abstract: Graphical abstract

Cited by 29 publications

References 42 publications

uRP: An integrated research platform for one-stop analysis of medical images

uRP: An integrated research platform for one-stop analysis of medical images

DCML: Deep contrastive mutual learning for COVID-19 recognition

Chest L-Transformer: Local Features With Position Attention for Weakly Supervised Chest Radiograph Segmentation and Classification

Contact Info

Product

Resources

About