Filters








118 Hits in 9.2 sec

Learn To Be Uncertain: Leveraging Uncertain Labels In Chest X-rays With Bayesian Neural Networks

Hao-Yu Yang, Junling Yang, Yue Pan, Kunlin Cao, Qi Song, Feng Gao, Youbing Yin
2019 Computer Vision and Pattern Recognition  
In this paper, we investigate the relationship between uncertainty in diagnostic chest x-ray radiology reports and uncertainty estimation of corresponding DNN models using Bayesian approaches.  ...  Communication of uncertainty is important for both radiology reports and deep neural networks (DNNs).  ...  Deep Bayesian Network In deep learning frameworks, a straightforward approach to performing sampling is multiplying the feature maps F with a sampling matrix M where each element is drawn from some distribution  ... 
dblp:conf/cvpr/YangYPCSGY19 fatcat:dkeujim3fvfcxlmxsik5a74gem

Uncertainty Quantification in Chest X-Ray Image Classification using Bayesian Deep Neural Networks

Yumin Liu, Claire Zhao, Jonathan Rubin
2020 European Conference on Artificial Intelligence  
In this paper, we quantify the uncertainty of DNNs for the task of Chest X-Ray (CXR) image classification.  ...  Deep neural networks (DNNs) have proven their effectiveness on numerous tasks.  ...  It is necessary to examine the uncertainty of neural network models in medical X-ray image processing.  ... 
dblp:conf/ecai/LiuZR20 fatcat:sadcjilwnzh5papxoozrd53ogq

Estimating Uncertainty and Interpretability in Deep Learning for Coronavirus (COVID-19) Detection [article]

Biraja Ghoshal, Allan Tucker
2020 arXiv   pre-print
In this paper, we investigate how drop-weights based Bayesian Convolutional Neural Networks (BCNN) can estimate uncertainty in Deep Learning solution to improve the diagnostic performance of the human-machine  ...  team using publicly available COVID-19 chest X-ray dataset and show that the uncertainty in prediction is highly correlates with accuracy of prediction.  ...  The most used approach to estimate uncertainty in deep learning try to place distributions over each of the network's weight parameters [3] Approximate Bayesian Convolutional Neural Networks (BCNN  ... 
arXiv:2003.10769v2 fatcat:7xuiad3rxbgjjcppzu3jhlinsa

On Calibrated Model Uncertainty in Deep Learning [article]

Biraja Ghoshal, Allan Tucker
2022 arXiv   pre-print
Estimated uncertainty by approximate posteriors in Bayesian neural networks are prone to miscalibration, which leads to overconfident predictions in critical tasks that have a clear asymmetric cost or  ...  We evaluated the effectiveness of our approach to detecting Covid-19 from X-Ray images.  ...  Following Gal [6] , Ghoshal et al [8] showed that Neural Networks with dropweights applied in the fully connected layer, is equivalent to variational Bayesian neural networks.  ... 
arXiv:2206.07795v1 fatcat:tmyodyo3mfgq7oybc6rnh6phyi

MMLN: Leveraging Domain Knowledge for Multimodal Diagnosis [article]

Haodi Zhang, Chenyu Xu, Peirou Liang, Ke Duan, Hao Ren, Weibin Cheng, Kaishun Wu
2022 arXiv   pre-print
Among the models, multimodality has been an emerging trend, integrating different forms of data such as chest X-ray (CXR) images and electronic medical records (EMRs).  ...  By incorporating domain knowledge, machine learning models can reduce the dependence on labeled data and improve interpretability.  ...  INTRODUCTION In recent years, advances in deep learning and the release of multiple, large, publicly available chest X-ray (CXR) datasets have led to a promising performance in many medical imaging analysis  ... 
arXiv:2202.04266v1 fatcat:6sbdv2gypfexpexgst3l4gn2xm

An Uncertainty-Aware Transfer Learning-Based Framework for COVID-19 Diagnosis

Afshar Shamsi, Hamzeh Asgharnezhad, Shirin Shamsi Jokandan, Abbas Khosravi, Parham M. Kebria, Darius Nahavandi, Saeid Nahavandi, Dipti Srinivasan
2021 IEEE Transactions on Neural Networks and Learning Systems  
Four popular convolutional neural networks (CNNs), including VGG16, ResNet50, DenseNet121, and InceptionResNetV2, are first applied to extract deep features from chest X-ray and computed tomography (CT  ...  Comprehensive simulation results for X-ray and CT image data sets indicate that linear support vector machine and neural network models achieve the best results as measured by accuracy, sensitivity, specificity  ...  chest X-ray and CT images.  ... 
doi:10.1109/tnnls.2021.3054306 fatcat:xuywwnjqdrcevhkg3o2f2z6zwq

An Uncertainty-aware Transfer Learning-based Framework for Covid-19 Diagnosis [article]

Afshar Shamsi Jokandan, Hamzeh Asgharnezhad, Shirin Shamsi Jokandan, Abbas Khosravi, Parham M.Kebria, Darius Nahavandi, Saeid Nahavandi, Dipti Srinivasan
2020 arXiv   pre-print
Four popular convolutional neural networks (CNNs) including VGG16, ResNet50, DenseNet121, and InceptionResNetV2 are first applied to extract deep features from chest X-ray and computed tomography (CT)  ...  Comprehensive simulation results for X-ray and CT image datasets indicate that linear support vector machine and neural network models achieve the best results as measured by accuracy, sensitivity, specificity  ...  The CheXNet is a 121 CNN which has been trained using 112,120 frontal-view chest X-ray images individually labeled [11] .  ... 
arXiv:2007.14846v1 fatcat:tsvx4hpgwfalfmtgnlh5qdybsi

Informative sample generation using class aware generative adversarial networks for classification of chest Xrays [article]

Behzad Bozorgtabar, Dwarikanath Mahapatra, Hendrik von Teng, Alexander Pollinger, Lukas Ebner, Jean-Phillipe Thiran, Mauricio Reyes
2019 arXiv   pre-print
We propose an active learning (AL) framework to select most informative samples for training our model using a Bayesian neural network.  ...  class label to another.  ...  In short, two types of uncertainty measures can be calculated from a Bayesian neural network -epistemic and aleotaric uncertainty.  ... 
arXiv:1904.10781v2 fatcat:6xuy37hwunaxhgrvg7joaufeza

Semi-Supervised Multi-Organ Segmentation through Quality Assurance Supervision [article]

Ho Hin Lee, Yucheng Tang, Olivia Tang, Yuchen Xu, Yunqiang Chen, Dashan Gao, Shizhong Han, Riqiang Gao, Michael R. Savona, Richard G. Abramson, Yuankai Huo, Bennett A. Landman
2019 arXiv   pre-print
Then, the ResNet-18 network was trained with 1623 montage images in equal distribution of all three code labels and achieved an accuracy 94% for classification predictions with 404 montage images withheld  ...  By performing QA on large-scale, previously unlabeled testing data, categorical QA scores can be generatedIn this paper, we propose a semi-supervised multi-organ segmentation deep neural network consisting  ...  We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan X Pascal GPU used for this research.  ... 
arXiv:1911.05113v1 fatcat:ykkp25w535esblx46bvmpmeqqa

Zero-Shot Learning and its Applications from Autonomous Vehicles to COVID-19 Diagnosis: A Review [article]

Mahdi Rezaei, Mahsa Shahidi
2020 arXiv   pre-print
Therefore, it makes it applicable in real-world scenarios, from developing autonomous vehicles to medical imaging and COVID-19 Chest X-Ray (CXR) based diagnosis.  ...  datasets, prepared by an expert human to train the network model.  ...  In the case of the few-shot learning, a handful of the chest CT scans or X-ray of the positive cases of the COVID-19 can also be beneficial as further support-set alongside the chest X-ray images of SARS  ... 
arXiv:2004.14143v2 fatcat:erh6xyog7bb5vofcebkk2zxumm

Trust It or Not: Confidence-Guided Automatic Radiology Report Generation [article]

Yixin Wang, Zihao Lin, Zhe Xu, Haoyu Dong, Jiang Tian, Jie Luo, Zhongchao Shi, Yang Zhang, Jianping Fan, Zhiqiang He
2022 arXiv   pre-print
Inspired by the significant progress in automatic image captioning, various deep learning (DL)-based methods have been proposed to generate radiology reports for medical images.  ...  Despite promising results, previous works overlook the uncertainties of their models and are thus unable to provide clinicians with the reliability/confidence of the generated radiology reports to assist  ...  IU X-Ray consists of 7, 470 chest X-ray images with 3, 955 reports. We implement the same way as [56] to randomly select 10% reports for testing.  ... 
arXiv:2106.10887v3 fatcat:mof3pehyxfcd3a6xgggsxh6uwe

Zero-Shot Learning and its Applications from Autonomous Vehicles to COVID-19 Diagnosis: A Review

Mahdi Rezaei, Mahsa Shahidi
2020 Social Science Research Network  
This makes the ZSL applicable in many real-world scenarios, from unknown object detection in autonomous vehicles to medical imaging and unforeseen diseases such as COVID-19 Chest X-Ray (CXR) based diagnosis  ...  advantages over each category to guide both clinicians and AI researchers to proceed with the best techniques and practices based on their applications.  ...  In the case of the few-shot learning, a handful of the chest CT scans or X-ray of the positive cases of the COVID-19 can also be beneficial as further support-set alongside the chest X-ray images of SARS  ... 
doi:10.2139/ssrn.3624379 fatcat:yifnxv46rjf6pgndowkxzmo5o4

Zero-Shot Learning and its Applications from Autonomous Vehicles to COVID-19 Diagnosis: A Review

Mahdi Rezaei, Mahsa Shahidi
2020 Intelligence-Based Medicine  
This makes the ZSL applicable in many real-world scenarios, from unknown object detection in autonomous vehicles to medical imaging and unforeseen diseases such as COVID-19 Chest X-Ray (CXR) based diagnosis  ...  advantages over each category to guide both clinicians and AI researchers to proceed with the best techniques and practices based on their applications.  ...  In the case of the few-shot learning, a handful of the chest CT scans or X-ray of the positive cases of the COVID-19 can also be beneficial as further support-set alongside the chest X-ray images of SARS  ... 
doi:10.1016/j.ibmed.2020.100005 pmid:33043311 pmcid:PMC7531283 fatcat:qzyaf7gpufhermyg5gvank5cja

Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation [article]

Nima Tajbakhsh, Laura Jeyaseelan, Qian Li, Jeffrey Chiang, Zhihao Wu, Xiaowei Ding
2020 arXiv   pre-print
The medical imaging literature has witnessed remarkable progress in high-performing segmentation models based on convolutional neural networks.  ...  However, rarely do we have a perfect training dataset, particularly in the field of medical imaging, where data and annotations are both expensive to acquire.  ...  This scheme was evaluated for the segmentation of the clavicles, lungs and heart on chest X-ray images.  ... 
arXiv:1908.10454v2 fatcat:mjvfbhx75bdkbheysq3r7wmhdi

A Survey of Deep Active Learning [article]

Pengzhen Ren, Yun Xiao, Xiaojun Chang, Po-Yao Huang, Zhihui Li, Brij B. Gupta, Xiaojiang Chen, Xin Wang
2021 arXiv   pre-print
A natural idea is whether AL can be used to reduce the cost of sample annotations, while retaining the powerful learning capabilities of DL. Therefore, deep active learning (DAL) has emerged.  ...  This is mainly because before the rise of DL, traditional machine learning requires relatively few labeled samples. Therefore, early AL is difficult to reflect the value it deserves.  ...  ∫ 𝑝 ( ŷ|x∗, 𝑋, 𝑌 ) = 𝑝 ( ŷ|x, 𝜃 ) 𝑝 (𝜃 |𝑋, 𝑌 )𝑑𝜃 = E𝜃 ∼𝑝 (𝜃 |𝑋 ,𝑌 ) [𝑓 (x; 𝜃 )]. (9) DBAL [72] combines BCNNs (Bayesian Convolutional Neural Networks) [  ... 
arXiv:2009.00236v2 fatcat:zuk2doushzhlfaufcyhoktxj7e
« Previous Showing results 1 — 15 out of 118 results