Access the full text.
Sign up today, get DeepDyve free for 14 days.
Junshen Xu, Molin Zhang, E. Turk, Larry Zhang, P. Grant, K. Ying, P. Golland, E. Adalsteinsson (2019)
Fetal Pose Estimation in Volumetric MRI using a 3D Convolution Neural NetworkMedical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention, 11767
Jeffrey Zhang, Sravani Gajjala, Pulkit Agrawal, G. Tison, Laura Hallock, L. Beussink-Nelson, M. Lassen, Eugene Fan, M. Aras, ChaRandle Jordan, K. Fleischmann, M. Melisko, A. Qasim, Sanjiv Shah, R. Bajcsy, R. Deo (2018)
Fully Automated Echocardiogram Interpretation in Clinical PracticeCirculation, 138
Yiqiu Shen, Nan Wu, Jason Phang, Jungkyu Park, Kangning Liu, Sudarshini Tyagi, L. Heacock, S. Kim, L. Moy, Kyunghyun Cho, Krzysztof Geras (2020)
An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localizationMedical image analysis, 68
Ali Madani, R. Arnaout, M. Mofrad, R. Arnaout (2018)
Fast and accurate view classification of echocardiograms using deep learningNPJ Digital Medicine, 1
R. Arnaout, L. Curran, Yili Zhao, J. Levine, E. Chinn, A. Moon‐Grady (2021)
An ensemble of neural networks provides expert-level prenatal detection of complex congenital heart diseaseNature Medicine, 27
Varun Gulshan, L. Peng, Marc Coram, Martin Stumpe, Derek Wu, Arunachalam Narayanaswamy, Subhashini Venugopalan, Kasumi Widner, T. Madams, Jorge Cuadros, R. Kim, R. Raman, Philip Nelson, J. Mega, D. Webster (2016)
Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs.JAMA, 316 22
Kornblith (2022)
1915J Ultrasound Med, 41
Daniel Kermany, Daniel Kermany, M. Goldbaum, Wenjia Cai, C. Valentim, Huiying Liang, Sally Baxter, A. McKeown, Ge Yang, Xiaokang Wu, Fangbing Yan, J. Dong, Made Prasadha, Jacqueline Pei, Jacqueline Pei, M. Ting, Jie Zhu, Christina Li, Sierra Hewett, Sierra Hewett, Jason Dong, Ian Ziyar, Alexander Shi, Runze Zhang, Lianghong Zheng, Rui Hou, W. Shi, Xin Fu, Xin Fu, Yaou Duan, V. Huu, V. Huu, Cindy Wen, Edward Zhang, Edward Zhang, Charlotte Zhang, Charlotte Zhang, Oulan Li, Oulan Li, Xiaobo Wang, M. Singer, Xiaodong Sun, Jie Xu, A. Tafreshi, M. Lewis, H. Xia, Kang Zhang (2018)
Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep LearningCell, 172
Keze Wang, Dongyu Zhang, Ya Li, Ruimao Zhang, Liang Lin (2017)
Cost-Effective Active Learning for Deep Image ClassificationIEEE Transactions on Circuits and Systems for Video Technology, 27
E. Kaye, E. Aherne, C. Duzgol, I. Häggström, Erich Kobler, Y. Mazaheri, M. Fung, Zhigang Zhang, R. Otazo, H. Vargas, O. Akin (2020)
Accelerating Prostate Diffusion Weighted MRI using Guided Denoising Convolutional Neural Network: Retrospective Feasibility StudyRadiology. Artificial intelligence, 2 5
A. Esteva, Brett Kuprel, R. Novoa, J. Ko, S. Swetter, H. Blau, S. Thrun (2017)
Dermatologist-level classification of skin cancer with deep neural networksNature, 542
D. Cohn, L. Atlas, R. Ladner (1994)
Improving generalization with active learningMachine Learning, 15
J. Olvera-López, J. Carrasco-Ochoa, José Trinidad, J. Kittler (2010)
A review of instance selection methodsArtificial Intelligence Review, 34
Joseph Kaplinsky, R. Arnaout (2016)
Robust estimates of overall immune-repertoire diversity from high-throughput measurements on samplesNature Communications, 7
A. Rosenkrantz, D. Hughes, R. Duszak (2016)
The U.S. Radiologist Workforce: An Analysis of Temporal and Geographic Variation by Using Large National Datasets.Radiology, 279 1
Aaron Kornblith, N. Addo, Ruolei Dong, R. Rogers, J. Grupp‐Phelan, A. Butte, Pavan Gupta, R. Callcut, R. Arnaout (2021)
Development and Validation of a Deep Learning Strategy for Automated View Classification of Pediatric Focused Assessment With Sonography for TraumaJournal of Ultrasound in Medicine, 41
L. Gjesteby, Hongming Shan, Qingsong Yang, Yan Xi, Yannan Jin, D. Giantsoudi, H. Paganetti, B. Man, Ge Wang (2019)
A dual-stream deep convolutional network for reducing metal streak artifacts in CT imagesPhysics in Medicine & Biology, 64
D. Rhee, A. Jhingran, B. Rigaud, T. Netherton, C. Cardenas, L. Zhang, S. Vedam, S. Kry, K. Brock, W. Shaw, F. O'Reilly, J. Parkes, H. Burger, N. Fakie, C. Trauernicht, H. Simonds, L. Court (2020)
Automatic contouring system for cervical cancer using convolutional neural networksMedical Physics, 47
Wim Crusio, John Lambris, Gobert Lee, H. Fujita (2020)
Deep Learning in Medical Image Analysis: Challenges and ApplicationsDeep Learning in Medical Image Analysis
Hailong Li, Lili He, J. Dudley, T. Maloney, E. Somasundaram, S. Brady, N. Parikh, J. Dillman (2020)
DeepLiverNet: a deep transfer learning model for classifying liver stiffness using clinical and T2-weighted magnetic resonance imaging data in children and young adultsPediatric Radiology, 51
Muhan Shao, Shuo Han, A. Carass, Xiang Li, A. Blitz, Jerry Prince, L. Ellingsen (2018)
Shortcomings of Ventricle Segmentation Using Deep Convolutional NetworksUnderstanding and interpreting machine learning in medical image computing applications : first International Workshops, MLCN 2018, DLF 2018, and iMIMIC 2018, held in conjunction with MICCAI 2018, Granada, Spain, September 16-20, 2018 :..., 11038
M. Alam, L. Vidyaratne, Z. Shboul, K. Iftekharuddin (2018)
Deep learning and texture-based semantic label fusion for brain tumor segmentation, 10575
Lexiaozi Fan, Daming Shen, Hassan Haji-Valizadeh, N. Naresh, J. Carr, B. Freed, Daniel Lee, Daniel Kim (2020)
Rapid dealiasing of undersampled, non‐Cartesian cardiac perfusion images using U‐netNMR in Biomedicine, 33
Rohit Arora, R. Arnaout (2022)
Repertoire-scale measures of antigen bindingProceedings of the National Academy of Sciences of the United States of America, 119
L. Jost (2018)
What do we mean by diversity? The path towards quantificationMètode Revista de difusió de la investigació
Arnaout (2021)
882Nat Med, 27
B. Anderson, E. Lin, C. Cardenas, D. Gress, W. Erwin, B. Odisio, E. Koay, K. Brock (2020)
Automated Contouring of Contrast and Noncontrast Computed Tomography Liver Images With Fully Convolutional NetworksAdvances in Radiation Oncology, 6
ObjectiveDeep learning (DL) has been applied in proofs of concept across biomedical imaging, including across modalities and medical specialties. Labeled data are critical to training and testing DL models, but human expert labelers are limited. In addition, DL traditionally requires copious training data, which is computationally expensive to process and iterate over. Consequently, it is useful to prioritize using those images that are most likely to improve a model’s performance, a practice known as instance selection. The challenge is determining how best to prioritize. It is natural to prefer straightforward, robust, quantitative metrics as the basis for prioritization for instance selection. However, in current practice, such metrics are not tailored to, and almost never used for, image datasets.Materials and MethodsTo address this problem, we introduce ENRICH—Eliminate Noise and Redundancy for Imaging Challenges—a customizable method that prioritizes images based on how much diversity each image adds to the training set.ResultsFirst, we show that medical datasets are special in that in general each image adds less diversity than in nonmedical datasets. Next, we demonstrate that ENRICH achieves nearly maximal performance on classification and segmentation tasks on several medical image datasets using only a fraction of the available images and without up-front data labeling. ENRICH outperforms random image selection, the negative control. Finally, we show that ENRICH can also be used to identify errors and outliers in imaging datasets.ConclusionsENRICH is a simple, computationally efficient method for prioritizing images for expert labeling and use in DL.
Journal of the American Medical Informatics Association – Oxford University Press
Published: Apr 10, 2023
Keywords: deep learning; medical imaging; information theory; instance selection; data quality; data efficiency
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.