20 Hits in 7.2 sec

Chest X-Rays Image Classification from beta-Variational Autoencoders Latent Features [article]

Leonardo Crespi, Daniele Loiacono, Arturo Chiti
2021 arXiv   pre-print
models, latent features have been extracted and used to train other Machine Learning models, able to classify the original images from the features extracted by the beta-VAE.  ...  To move in this direction, we trained several beta-Variational Autoencoder (beta-VAE) models on the CheXpert dataset, one of the largest publicly available collection of labeled CXR images; from these  ...  features from the images.  ... 
arXiv:2109.14760v1 fatcat:yytuaewagbea7l63ertd6lzppy

A survey on generative adversarial networks for imbalance problems in computer vision tasks

Vignesh Sampath, Iñaki Maurtua, Juan José Aguilar Martín, Aitor Gutierrez
2021 Journal of Big Data  
Image level imbalances in classification, 2. object level imbalances in object detection and 3. pixel level imbalances in segmentation tasks.  ...  Unfortunately, the occurrence of imbalance problems in acquired image datasets in certain complex real-world problems such as anomaly detection, emotion recognition, medical image analysis, fraud detection  ...  On chest X-ray dataset [193] , a mean classification accuracy improved from 70.87 to 92.10%. Frid-Adar et al.  ... 
doi:10.1186/s40537-021-00414-0 pmid:33552840 pmcid:PMC7845583 fatcat:g3p6hbjuj5c5vbe23ms4g6ed6q

Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencoder [article]

Clément Chadebec, Elina Thibeau-Sutre, Ninon Burgos, Stéphanie Allassonnière
2021 arXiv   pre-print
In this paper, we propose a new method to perform data augmentation in a reliable way in the High Dimensional Low Sample Size (HDLSS) setting using a geometry-based variational autoencoder.  ...  It is also validated on a medical imaging classification task on the challenging ADNI database where a small number of 3D brain MRIs are considered and augmented using the proposed VAE framework.  ...  Pai, “Lung segmentation from chest x-rays generative adversarial networks,” in International Workshop on using variational data imputation,” arXiv:2005.10052 [cs, eess, Simulation  ... 
arXiv:2105.00026v1 fatcat:x2bpaga45zazfj3vcsidsfgphe

Feature Concentration for Supervised and Semi-supervised Learning with Unbalanced Datasets in Visual Inspection

Jiyong Jang, Sungroh Yoon
2020 IEEE transactions on industrial electronics (1982. Print)  
We address this by introducing feature concentration, in which features from annotated images of defective and normal components are separated in feature space by moving them towards cluster centers.  ...  We also apply feature concentration to consistency regularization in semi-supervised classification, in which only a small proportion of the data is annotated.  ...  Other approaches [31] , [32] using a variational autoencoder [33] . Schlegl et al.  ... 
doi:10.1109/tie.2020.3003622 fatcat:7qkugdzfffgfhlnaaxji4drcty

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.  ...  data is available for training, and weak annotations where the training data has only sparse annotations, noisy annotations, or image-level annotations.  ...  This scheme was evaluated for the segmentation of the clavicles, lungs and heart on chest X-ray images.  ... 
arXiv:1908.10454v2 fatcat:mjvfbhx75bdkbheysq3r7wmhdi

Machine Learning Research Towards Combating COVID-19: Virus Detection, Spread Prevention, and Medical Assistance [article]

Osama Shahid, Mohammad Nasajpour, Seyedamin Pouriyeh, Reza M. Parizi, Meng Han, Maria Valero, Fangyu Li, Mohammed Aledhari, Quan Z. Sheng
2020 arXiv   pre-print
The virus is deadly, and people who are suffering from prior illnesses or are older than the age of 60 are at a higher risk of mortality.  ...  In this paper, we present a journey of what role ML has played so far in combating the virus, mainly looking at it from a screening, forecasting, and vaccine perspectives.  ...  Fig. 1 . 1 Chest X-Ray (CXR) images of COVID-19 infected people versus uninfected people [52] . Fig. 2 . 2 CT-Scan images of COVID-19 infected people versus uninfected people [52] .  ... 
arXiv:2010.07036v1 fatcat:r55zllnsmjg5hle2rr2wxixmgq

Generalizing to Unseen Domains: A Survey on Domain Generalization [article]

Jindong Wang, Cuiling Lan, Chang Liu, Yidong Ouyang, Tao Qin, Wang Lu, Yiqiang Chen, Wenjun Zeng, Philip S. Yu
2021 arXiv   pre-print
segmentation e.g. [140] Parkinson's disease e.g. [27] Chest X-ray recognition e.g. [81, 79] EEG-based seizure detection e.g. [76] Other applications Human activity recognition e.g. [127] Fault diagnosis  ...  error in classifying images coming from natural images or photos, which are clearly having distinguished distributions from the images in training set.  ... 
arXiv:2103.03097v5 fatcat:nvwnepfeb5adjfghuvuqx5hopy

2020 Index IEEE Transactions on Biomedical Engineering Vol. 67

2020 IEEE Transactions on Biomedical Engineering  
Synthesis With Deep Convolutional Adversarial Networks" [Mar 18 2720-2730]; TBME Sept. 2020 2706 Nie, Q., see Zheng, X., 1418-1428 Nieberler, M., see Gorpas, D., TBME Jan. 2020 185-192 Niederer, S.A  ...  ., Facilitating Calibration in High-Speed BCI Spellers via Leveraging Cross-Device Shared Latent Responses; TBME April 2020 1105-1113 Narayanan, A.M., and Bertrand, A., Analysis of Miniaturization Effects  ...  Ye, C., +, TBME Feb. 2020 482-494 Classification of Aortic Stenosis Using Time-Frequency Features From Chest Cardio-Mechanical Signals.  ... 
doi:10.1109/tbme.2020.3048339 fatcat:y7zxxew27fgerapsnrhh54tm7y

2021 Index IEEE Transactions on Image Processing Vol. 30

2021 IEEE Transactions on Image Processing  
-that appeared in this periodical during 2021, and items from previous years that were commented upon or corrected in 2021.  ...  ., +, TIP 2021 1261-1274 Discriminative Feature Learning for Thorax Disease Classification in Chest X-ray Images.  ...  ., +, TIP 2021 7074-7089 Diseases Discriminative Feature Learning for Thorax Disease Classification in Chest X-ray Images.  ... 
doi:10.1109/tip.2022.3142569 fatcat:z26yhwuecbgrnb2czhwjlf73qu

COVID-19 Modeling: A Review [article]

Longbing Cao, Qing Liu
2021 arXiv   pre-print
Machine learning for COVID-19 diagnosis on medical imaging. A very intensive application of classic machine learning methods is to screen COVID-19 infections on CT, chest X-ray (CXR) or PET images.  ...  utf8=%E2%9C%93&q=covid&scope=all&lang=us;;;  ... 
arXiv:2104.12556v3 fatcat:pj2bketcrveafbjf2m7tx3odxy

ROAM: Random Layer Mixup for Semi-Supervised Learning in Medical Imaging [article]

Tariq Bdair, Benedikt Wiestler, Nassir Navab, Shadi Albarqouni
2020 arXiv   pre-print
Medical image segmentation is one of the major challenges addressed by machine learning methods.  ...  We conduct extensive experiments to validate our method on three publicly available datasets on whole-brain image segmentation.  ...  Similar approach was utilized by [7] for Chest X-ray images segmentation.  ... 
arXiv:2003.09439v4 fatcat:is6zyhxvabgotmqt4a6gyondh4

Artificial Intellgence – Application in Life Sciences and Beyond. The Upper Rhine Artificial Intelligence Symposium UR-AI 2021 [article]

Karl-Herbert Schäfer
2021 arXiv   pre-print
Khan, A.I., Shah, J.L., Bhat, M.M.: CoroNet: A deep neural network for detection and diagnosis of COVID-19 from chest x-ray images.  ...  Chest X-ray images with lungs marked in red. (Left) COVID-19 positive image, typical Ground-glass opacication marked in blue. (Right) COVID-19 negative image.  ...  It extracts several features from an input image. The features are stored in a so-called feature map whose resolution is 1/8 of the resolution of the input image.  ... 
arXiv:2112.05657v1 fatcat:wdjgymicyrfybg5zth2dc2i3ni

Millimeter Wave Sensing: A Review of Application Pipelines and Building Blocks

Bram van Berlo, Amany Elkelany, Tanir Ozcelebi, Nirvana Meratnia
2021 IEEE Sensors Journal  
The millimeter wave spectrum is part of 5G and covers frequencies between 30 and 300 GHz that correspond to wavelengths ranging from 10 to 1 mm.  ...  methodology and reviewing 165 papers, we not only extend previous investigations focused only on communication aspects of the millimeter wave technology and using millimeter wave technology for active imaging  ...  extracted feature sequence [76] , and alpha-beta filtered trajectory [128] .  ... 
doi:10.1109/jsen.2021.3057450 fatcat:utlcmfq55raqpkhv7ad34nhfh4

Recent Advances in Electrochemical Biosensors: Applications, Challenges, and Future Scope

Anoop Singh, Asha Sharma, Aamir Ahmed, Ashok K. Sundramoorthy, Hidemitsu Furukawa, Sandeep Arya, Ajit Khosla
2021 Biosensors  
In the case of biosensors, the presence of impurity affects the performance of the sensor and machine learning helps in removing signals obtained from the contaminants to obtain a high sensitivity.  ...  Convolutional Neural Network (CNN) Analyzing images like computed tomography (CT) images, X-ray images, and magnetic resonance images is done by a very efficient deep learning type known as CNN [153]  ...  With the enhanced performance in the classification of the images, CNN is very famous.  ... 
doi:10.3390/bios11090336 pmid:34562926 fatcat:hqo6kyzsyneujne5qmmaorc47a

Well-calibrated predictive uncertainty in medical imaging with Bayesian Deep Learning [article]

Max-Heinrich Viktor Laves, University, My
We show that the uncertainty from variational Bayesian inference is miscalibrated and does not represent the predictive error well.  ...  The approach achieves state-of-the-art performance on both medical and non-medical classification data sets. Many medic [...]  ...  The third test image x xray shows a chest x-ray for pneumonia assessment.  ... 
doi:10.15488/11588 fatcat:hkyyhvzumrecxeuar2m6mjyosi
« Previous Showing results 1 — 15 out of 20 results