Jungkyu Park
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jungkyu Park has a total of 90 co-authors. Here are the top co-authors by number of shared publications:
- Krzysztof J. Geras
Center for Data Science, New York University, New York, New York, United States of America
5 shared publications Linda Moy
Department of Radiology, NYU Langone Health, New York, NY, USA
5 shared publicationsKyunghyun Cho
Center for Data Science, New York University, 60 5th Ave, New York, NY 10011, USA; Department of Computer Science, Courant Institute of Mathematical Sciences, New York University, 251 Mercer St, New York, NY 10012, USA
4 shared publicationsAlana Lewin
Department of Radiology, NYU Langone Health, New York, NY, USA
3 shared publicationsAlexandra Millet
Department of Radiology, NYU Langone Health, New York, NY, USA
3 shared publications- Beatriu Reig
Department of Radiology, New York University Grossman School of Medicine , New York, NY
3 shared publications
Latest Publications
- Open Access
- 17 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 43 (1) , 351-365
An Efficient Deep Neural Network to Classify Large 3D Images With Small Objects
3D imaging enables accurate diagnosis by providing spatial information about organ anatomy. However, using 3D images to train AI models is computationally challenging because they consist of 10x or 100x more pixels than their 2D counterparts. To be trained with high-resolution 3D images, convolutional neural networks resort to downsampling them or projecting them to 2D. We propose an effective alternative, a neural network that enables efficient classification of full-resolution 3D medical images. Compared to off-the-shelf convolutional neural networks, our network, 3D Globally-Aware Multiple Instance Classifier (3D-GMIC), uses 77.98%-90.05% less GPU memory and 91.23%-96.02% less computation. While it is trained only with image-level labels, without segmentation labels, it explains its predictions by providing pixel-level saliency maps. On a dataset collected at NYU Langone Health, including 85,526 patients with full-field 2D mammography (FFDM), synthetic 2D mammography, and 3D mammography, 3D-GMIC achieves an AUC of 0.831 (95% CI: 0.769-0.887) in classifying breasts with malignant findings using 3D mammography. This is comparable to the performance of GMIC on FFDM (0.816, 95% CI: 0.737-0.878) and synthetic 2D (0.826, 95% CI: 0.754-0.884), which demonstrates that 3D-GMIC successfully classified large 3D images despite focusing computation on a smaller percentage of its input compared to GMIC. Therefore, 3D-GMIC identifies and utilizes extremely small regions of interest from 3D images consisting of hundreds of millions of pixels, dramatically reducing associated computational challenges. 3D-GMIC generalizes well to BCS-DBT, an external dataset from Duke University Hospital, achieving an AUC of 0.848 (95% CI: 0.798-0.896).
- 17 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 43 (1) , 351-365
Open AccessAn Efficient Deep Neural Network to Classify Large 3D Images With Small Objects
3D imaging enables accurate diagnosis by providing spatial information about organ anatomy. However, using 3D images to train AI models is computationally challenging because they consist of 10x or 100x more pixels than their 2D counterparts. To be trained with high-resolution 3D images, convolutional neural networks resort to downsampling them or projecting them to 2D. We propose an effective alternative, a neural network that enables efficient classification of full-resolution 3D medical images. Compared to off-the-shelf convolutional neural networks, our network, 3D Globally-Aware Multiple Instance Classifier (3D-GMIC), uses 77.98%-90.05% less GPU memory and 91.23%-96.02% less computation. While it is trained only with image-level labels, without segmentation labels, it explains its predictions by providing pixel-level saliency maps. On a dataset collected at NYU Langone Health, including 85,526 patients with full-field 2D mammography (FFDM), synthetic 2D mammography, and 3D mammography, 3D-GMIC achieves an AUC of 0.831 (95% CI: 0.769-0.887) in classifying breasts with malignant findings using 3D mammography. This is comparable to the performance of GMIC on FFDM (0.816, 95% CI: 0.737-0.878) and synthetic 2D (0.826, 95% CI: 0.754-0.884), which demonstrates that 3D-GMIC successfully classified large 3D images despite focusing computation on a smaller percentage of its input compared to GMIC. Therefore, 3D-GMIC identifies and utilizes extremely small regions of interest from 3D images consisting of hundreds of millions of pixels, dramatically reducing associated computational challenges. 3D-GMIC generalizes well to BCS-DBT, an external dataset from Duke University Hospital, achieving an AUC of 0.848 (95% CI: 0.798-0.896).
- Top Cited PapersOpen Access
- 24 September 2021
- Published by Springer Nature in Nature Communications
- Vol. 12 (1) , 1-13
Artificial intelligence system reduces false-positive findings in the interpretation of breast ultrasound exams
Though consistently shown to detect mammographically occult cancers, breast ultrasound has been noted to have high false-positive rates. In this work, we present an AI system that achieves radiologist-level accuracy in identifying breast cancer in ultrasound images. Developed on 288,767 exams, consisting of 5,442,907 B-mode and Color Doppler images, the AI achieves an area under the receiver operating characteristic curve (AUROC) of 0.976 on a test set consisting of 44,755 exams. In a retrospective reader study, the AI achieves a higher AUROC than the average of ten board-certified breast radiologists (AUROC: 0.962 AI, 0.924 ± 0.02 radiologists). With the help of the AI, radiologists decrease their false positive rates by 37.3% and reduce requested biopsies by 27.8%, while maintaining the same level of sensitivity. This highlights the potential of AI in improving the accuracy, consistency, and efficiency of breast ultrasound diagnosis.
- 24 September 2021
- Published by Springer Nature in Nature Communications
- Vol. 12 (1) , 1-13
Top Cited PapersOpen AccessArtificial intelligence system reduces false-positive findings in the interpretation of breast ultrasound exams
Though consistently shown to detect mammographically occult cancers, breast ultrasound has been noted to have high false-positive rates. In this work, we present an AI system that achieves radiologist-level accuracy in identifying breast cancer in ultrasound images. Developed on 288,767 exams, consisting of 5,442,907 B-mode and Color Doppler images, the AI achieves an area under the receiver operating characteristic curve (AUROC) of 0.976 on a test set consisting of 44,755 exams. In a retrospective reader study, the AI achieves a higher AUROC than the average of ten board-certified breast radiologists (AUROC: 0.962 AI, 0.924 ± 0.02 radiologists). With the help of the AI, radiologists decrease their false positive rates by 37.3% and reduce requested biopsies by 27.8%, while maintaining the same level of sensitivity. This highlights the potential of AI in improving the accuracy, consistency, and efficiency of breast ultrasound diagnosis.
- 19 July 2021
- Published by Springer Nature in Nature Machine Intelligence
- Vol. 3 (8) , 735-736
Lessons from the first DBTex Challenge
- 19 July 2021
- Published by Springer Nature in Nature Machine Intelligence
- Vol. 3 (8) , 735-736
Lessons from the first DBTex Challenge
- Top Cited PapersOpen Access
- 1 February 2021
- Published by Elsevier in Medical Image Analysis
- Vol. 68, 101908
An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization
- 1 February 2021
- Published by Elsevier in Medical Image Analysis
- Vol. 68, 101908
Top Cited PapersOpen AccessAn interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization
- 1 July 2020
- Vol. 121, 827-842
Improving the Ability of Deep Neural Networks to Use Information from Multiple Views in Breast Cancer Screening.
In breast cancer screening, radiologists make the diagnosis based on images that are taken from two angles. Inspired by this, we seek to improve the performance of deep neural networks applied to this task by encouraging the model to use information from both views of the breast. First, we took a closer look at the training process and observed an imbalance between learning from the two views. In particular, we observed that layers processing one of the views have parameters with larger gradients in magnitude, and contribute more to the overall loss reduction. Next, we tested several methods targeted at utilizing both views more equally in training. We found that using the same weights to process both views, or using modality dropout, leads to a boost in performance. Looking forward, our results indicate improving learning dynamics as a promising avenue for improving utilization of multiple views in deep neural networks for medical diagnosis.
- 1 July 2020
- Vol. 121, 827-842
Improving the Ability of Deep Neural Networks to Use Information from Multiple Views in Breast Cancer Screening.
In breast cancer screening, radiologists make the diagnosis based on images that are taken from two angles. Inspired by this, we seek to improve the performance of deep neural networks applied to this task by encouraging the model to use information from both views of the breast. First, we took a closer look at the training process and observed an imbalance between learning from the two views. In particular, we observed that layers processing one of the views have parameters with larger gradients in magnitude, and contribute more to the overall loss reduction. Next, we tested several methods targeted at utilizing both views more equally in training. We found that using the same weights to process both views, or using modality dropout, leads to a boost in performance. Looking forward, our results indicate improving learning dynamics as a promising avenue for improving utilization of multiple views in deep neural networks for medical diagnosis.
- 10 October 2019
- Published by Springer Nature
- Vol. 11861, 18-26
Globally-Aware Multiple Instance Classifier for Breast Cancer Screening
Deep learning models designed for visual classification tasks on natural images have become prevalent in medical image analysis. However, medical images differ from typical natural images in many ways, such as significantly higher resolutions and smaller regions of interest. Moreover, both the global structure and local details play important roles in medical image analysis tasks. To address these unique properties of medical images, we propose a neural network that is able to classify breast cancer lesions utilizing information from both a global saliency map and multiple local patches. The proposed model outperforms the ResNet-based baseline and achieves radiologist-level performance in the interpretation of screening mammography. Although our model is trained only with image-level labels, it is able to generate pixel-level saliency maps that provide localization of possible malignant findings.
- 10 October 2019
- Published by Springer Nature
- Vol. 11861, 18-26
Globally-Aware Multiple Instance Classifier for Breast Cancer Screening
Deep learning models designed for visual classification tasks on natural images have become prevalent in medical image analysis. However, medical images differ from typical natural images in many ways, such as significantly higher resolutions and smaller regions of interest. Moreover, both the global structure and local details play important roles in medical image analysis tasks. To address these unique properties of medical images, we propose a neural network that is able to classify breast cancer lesions utilizing information from both a global saliency map and multiple local patches. The proposed model outperforms the ResNet-based baseline and achieves radiologist-level performance in the interpretation of screening mammography. Although our model is trained only with image-level labels, it is able to generate pixel-level saliency maps that provide localization of possible malignant findings.
- Top Cited PapersOpen Access
- 7 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 39 (4) , 1184-1194
Deep Neural Networks Improve Radiologists’ Performance in Breast Cancer Screening
We present a deep convolutional neural network for breast cancer screening exam classification, trained, and evaluated on over 200000 exams (over 1000000 images). Our network achieves an AUC of 0.895 in predicting the presence of cancer in the breast, when tested on the screening population. We attribute the high accuracy to a few technical advances. 1) Our network's novel two-stage architecture and training procedure, which allows us to use a high-capacity patch-level network to learn from pixel-level labels alongside a network learning from macroscopic breast-level labels. 2) A custom ResNet-based network used as a building block of our model, whose balance of depth and width is optimized for high-resolution medical images. 3) Pretraining the network on screening BI-RADS classification, a related task with more noisy labels. 4) Combining multiple input views in an optimal way among a number of possible choices. To validate our model, we conducted a reader study with 14 readers, each reading 720 screening mammogram exams, and show that our model is as accurate as experienced radiologists when presented with the same data. We also show that a hybrid model, averaging the probability of malignancy predicted by a radiologist with a prediction of our neural network, is more accurate than either of the two separately. To further understand our results, we conduct a thorough analysis of our network's performance on different subpopulations of the screening population, the model's design, training procedure, errors, and properties of its internal representations. Our best models are publicly available at https://github.com/nyukat/breast_cancer_classifier.
- 7 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 39 (4) , 1184-1194
Top Cited PapersOpen AccessDeep Neural Networks Improve Radiologists’ Performance in Breast Cancer Screening
We present a deep convolutional neural network for breast cancer screening exam classification, trained, and evaluated on over 200000 exams (over 1000000 images). Our network achieves an AUC of 0.895 in predicting the presence of cancer in the breast, when tested on the screening population. We attribute the high accuracy to a few technical advances. 1) Our network's novel two-stage architecture and training procedure, which allows us to use a high-capacity patch-level network to learn from pixel-level labels alongside a network learning from macroscopic breast-level labels. 2) A custom ResNet-based network used as a building block of our model, whose balance of depth and width is optimized for high-resolution medical images. 3) Pretraining the network on screening BI-RADS classification, a related task with more noisy labels. 4) Combining multiple input views in an optimal way among a number of possible choices. To validate our model, we conducted a reader study with 14 readers, each reading 720 screening mammogram exams, and show that our model is as accurate as experienced radiologists when presented with the same data. We also show that a hybrid model, averaging the probability of malignancy predicted by a radiologist with a prediction of our neural network, is more accurate than either of the two separately. To further understand our results, we conduct a thorough analysis of our network's performance on different subpopulations of the screening population, the model's design, training procedure, errors, and properties of its internal representations. Our best models are publicly available at https://github.com/nyukat/breast_cancer_classifier.
- 22 November 2018
- Published by Springer Nature in Review of Philosophy and Psychology
- Vol. 10 (3) , 479-498
The Evolution of Shared Concepts in Changing Populations
- 22 November 2018
- Published by Springer Nature in Review of Philosophy and Psychology
- Vol. 10 (3) , 479-498
The Evolution of Shared Concepts in Changing Populations