Jihye Yun, PhD

Department of Radiology, Asan Medical Center, Seoul, South Korea

Deep Learning for Automated Triaging of Stable Chest Radiographs in a Follow-up Setting

Jihye Yun, Yura Ahn, Kyungjin Cho, Sang Young Oh, Sang Min Lee, Namkug Kim, and Joon Beom Seo

Background: Most artificial intelligence algorithms that interpret chest radiographs are restricted to an image from a single time point. However, in clinical practice, multiple radiographs are used for longitudinal follow-up, especially in intensive care units (ICUs).

Purpose: To develop and validate a deep learning algorithm using thoracic cage registration and subtraction to triage pairs of chest radiographs showing no change by using longitudinal follow-up data.

Materials and Methods: A deep learning algorithm was retrospectively developed using baseline and follow-up chest radiographs in adults from January 2011 to December 2018 at a tertiary referral hospital. Two thoracic radiologists reviewed randomly selected pairs of “change” and “no change” images to establish the ground truth, including normal or abnormal status. Algorithm performance was evaluated using area under the receiver operating characteristic curve (AUC) analysis in a validation set and temporally separated internal test sets (January 2019 to August 2021) from the emergency department (ED) and ICU. Threshold calibration for the test sets was conducted, and performance with 40% and 60% triage thresholds was assessed.

Results: This study included 3 304 996 chest radiographs in 329 036 patients (mean age, 59 years ± 14 [SD]; 170 433 male patients). The training set included 550 779 pairs of radiographs. The validation set included 1620 pairs (810 no change, 810 change). The test sets included 533 pairs (ED; 265 no change, 268 change) and 600 pairs (ICU; 310 no change, 290 change). The algorithm had AUCs of 0.77 (validation), 0.80 (ED), and 0.80 (ICU). With a 40% triage threshold, specificity was 88.4% (237 of 268 pairs) and 90.0% (261 of 290 pairs) in the ED and ICU, respectively. With a 60% triage threshold, specificity was 79.9% (214 of 268 pairs) and 79.3% (230 of 290 pairs) in the ED and ICU, respectively. For urgent findings (consolidation, pleural effusion, pneumothorax), specificity was 78.6%–100% (ED) and 85.5%–93.9% (ICU) with a 40% triage threshold.

Conclusion: The deep learning algorithm could triage pairs of chest radiographs showing no change while detecting urgent interval changes during longitudinal follow-up.

Technical Feasibility of Quantitative Measurement of Various Degrees of Small Bowel Motility
Using Cine Magnetic Resonance Imaging

Ji Young Choi, Jihye Yun, Subin Heo, Dong Wook Kim, Sang Hyun Choi, Jiyoung Yoon, Kyuwon Kim, Kee Wook Jung, and Seung-Jae Myung

Objective: Cine magnetic resonance imaging (MRI) has emerged as a noninvasive method to quantitatively assess bowel motility. However, its accuracy in measuring various degrees of small bowel motility has not been extensively evaluated. We aimed to draw a quantitative small bowel motility score from cine MRI and evaluate its performance in a population with varying degrees of small bowel motility.

Materials and Methods: A total of 174 participants (28.5 ± 7.6 years; 135 males) underwent a 22-second-long cine MRI sequence (2-dimensional balanced turbo-field echo; 0.5 seconds per image) approximately 5 minutes after being intravenously administered 10 mg of scopolamine-N-butyl bromide to deliberately create diverse degrees of small bowel motility. In a manually segmented area of the small bowel, motility was automatically quantified using a nonrigid registration and calculated as a quantitative motility score. The mean value (MV) of motility grades visually assessed by two radiologists was used as a reference standard. The quantitative motility score’s correlation (Spearman’s ρ) with the reference standard and performance (area under the receiver operating characteristics curve [AUROC], sensitivity, and specificity) for diagnosing adynamic small bowel (MV of 1) were evaluated.

Results: For the MV of the quantitative motility scores at grades 1, 1.5, 2, 2.5, and 3, the mean ± standard deviation values were 0.019 ± 0.003, 0.027 ± 0.010, 0.033 ± 0.008, 0.032 ± 0.009, and 0.043 ± 0.013, respectively. There was a significant positive correlation between the quantitative motility score and the MV (ρ = 0.531, P < 0.001). The AUROC value for diagnosing a MV of 1 (i.e., adynamic small bowel) was 0.953 (95% confidence interval, 0.923–0.984). Moreover, the optimal cutoff for the quantitative motility score was 0.024, with a sensitivity of 100% (15/15) and specificity of 89.9% (143/159).

Conclusion: The quantitative motility score calculated from a cine MRI enables diagnosis of an adynamic small bowel, and potentially discerns various degrees of bowel motility.

Keywords: Cine imaging; Magnetic resonance imaging; Gastrointestinal motility; Small intestine; Bowel

Generative adversarial network-based image conversion among different computed tomography protocols and vendors: Effects on accuracy and variability in quantifying regional disease patterns of interstitial lung disease

Hye Jeon Hwang, Hyunjong Kim, Joon Beom Seo, Jong Chul Ye, Gyutaek Oh, Sang Min Lee, Ryoungwoo Jang, Jihye Yun, Namkug Kim, Hee Jun Park, Ho Yun Lee, Soon Ho Yoon, Kyung Eun Shin, Jae Wook Lee, Woocheol Kwon, Joo Sung Sun, Seulgi You, Myung Hee Chung, Bo Mi Gil, Jae-Kwang Lim, Youkyung Lee, Su Jin Hong, Yo Won Choi, Korean Journal of Radiology, August 2023.

Automated detection of intracranial aneurysms using skeleton-based 3D patches, semantic segmentation, and auxiliary classification for overcoming data imbalance in brain TOF-MRA

Sungwon Ham, Jiyeon Seo, Jihye Yun, Yun Jung Bae, Tackeun Kim, Leonard Sunwoo, Sooyoung Yoo, Seung Chai Jung, Jeong-Whun Kim, Namkug Kim, Scientific Reports, July 2023.

MuSiC-ViT: Multi-task Siamese convolutional vision transformer for differentiating change or no-change in follow-up chest X-rays

Kyungjin Cho, Jeeyoung Kim, Ki Duk Kim, Seungju Park, Junsik Kim, Jihye Yun, Yura Ahn, Sangyoung Oh, Sang Min Lee, Joon Beom Seo, and Namkug Kim, Medical Image Analysis, July 2023.

Deep learning of time-signal intensity curves from dynamic susceptibility contrast imaging enables tissue labeling and prediction of survival in glioblastoma

Jihye Yun, Su Young Yun, Ji Eun Park, E-Nae Cheong, Seo Young Park, Namkug Kim, Ho Sung Kim, American Journal of Neuroradiology, April 2023.

Deep learning–based approach to predict pulmonary function at chest CT

Hyunjung Park, Jihye Yun, Sang Min Lee, Hye Jeon Hwang, Joon Beom Seo, Young Ju Jung, Jeongeun Hwang, Se Hee Lee, Sei Won Lee, Namkug Kim, Radiology, February 2023.

Federated learning enables big data for rare cancer boundary detection

Sarthak Pati et al., Nature communications, December 2022.

Interstitial lung abnormalities (ILA) on routine chest CT: Comparison of radiologists’ visual evaluation and automated quantification

Min Seon Kim, Jooae Choe, Hye Jeon Hwang, Sang Min Lee, Jihye Yun, Namkug Kim, Myung-Su Ko, Jaeyoun Yi, Donghoon Yu, Joon Beom Seo, European Journal of Radiology, December 2022.

Development and validation of a model using radiomics features from an apparent diffusion coefficient map to diagnose local tumor recurrence in patients treated for head and neck squamous cell carcinoma

Minjae Kim, Jeong Hyun Lee, Leehi Joo, Boryeong Jeong, Seonok Kim, Sungwon Ham, Jihye Yun, NamKug Kim, Sae Rom Chung, Young Jun Choi, Jung Hwan Baek, Ji Ye Lee, Ji-hoon Kim, Korean Journal of Radiology, November 2022.

Multi-domain CT translation by a routable translation network

Hyunjong Kim, Gyutaek Oh, Joon Beom Seo, Hye Jeon Hwang, Sang Min Lee, Jihye Yun, Jong Chul Ye, Physics in Medicine & Biology, October 2022.

Content-based image retrieval by using deep learning for interstitial lung disease diagnosis with chest CT

Jooae Choe, Hye Jeon Hwang , Joon Beom Seo, Sang Min Lee, Jihye Yun, Min-Ju Kim, Jewon Jeong, Youngsoo Lee, Kiok Jin, Rohee Park, Jihoon Kim, Howook Jeon, Namkug Kim, Jaeyoun Yi, Donghoon Yu, Byeongsoo Kim, Radiology, January 2022.

An open medical platform to share source code and various pre-trained weights for models to use in deep learning research

Sungchul Kim, Sungman Cho, Kyungjin Cho, Jiyeon Seo, Yujin Nam, Jooyoung Park, Kyuri Kim, Daeun Kim, Jeongeun Hwang, Jihye Yun, Miso Jang, Hyunna Lee, and Namkug Kim, Korean Journal of Radiology, December 2021.

Deep radiomics-based survival prediction in patients with chronic obstructive plumonary disease

Jihye Yun, Young Hoon Cho, Sang Min Lee, Jeongeun Hwang, Jae Seung Lee, Yeon-Mok Oh, Sang-Do Lee, Li-Cher Loh, Choo-Khoon Ong, Joon Beom Seo, Namkug Kim, Scientific Reports, July 2021

Diffusion and perfusion MRI radiomics obtained from deep learning segmentation provides reproducible and comparable diagnostic model to human in post-treatment glioblastoma

Ji Eun Park, Sungwon Ham, Ho Sung Kim, Seo Young Park, Jihye Yun, Hyunna Lee, Seung Hong Choi, Namkug Kim, European Radiology, May 2021.

Radiomics approach for survival prediction in chronic obstructive pulmonary disease

Young Hoon Cho, Joon Beom Seo, Sang Min Lee, Namkug Kim, Jihye Yun, Jeong Eun Hwang, Jae Seung Lee, Yeon-Mok Oh, Sang Do Lee, Li-Cher Loh, Choo-Khoom Ong, European Radiology, April 2021.

Realistic high-resolution body computed tomography image synthesis by using progressive growing generative adversarial network: visual Turing test

Ho Young Park, Hyun-Jin Bae, Gil-Sun Hong, Minjee Kim, Jihye Yun, Sungwon Park, Won Jung Chung, NamKug Kim, JMIR Medical Informatics, March 2021.

Machine learning approach for differentiating cytomegalovirus esophagitis from herpes simplex virus esophagitis

Jung Su Lee, Jihye Yun, Sungwon Ham, Hyunjung Park, Hyunsu Lee, Jeongseok Kim, Jeong-Sik Byeon, Hwoon-Yong Jung, Namkug Kim, Do Hoon Kim, Scientific Reports, February 2021

Value of bone suppression software in chest radiographs for improving image quality and reducing radiation dose

Gil-Sun Hong, Kyung-Hyun Do, A-Yeon Son, Kyung-Wook Jo, Kwang Pyo Kim, Jihye Yun, Choong Wook Lee, European Radiology, January 2021.

Oropharyngeal squamous cell carcinoma: radiomics machine-learning classifiers from multiparametric MR images for determination of HPV infection status

Chong Hyun Suh, Kyung Hwa Lee, Young Jun Choi, Sae Rom Chung, Jung Hwan Baek, Jeong Hyun Lee, Jihye Yun, Sungwon Ham, Namkug Kim, Scientific Reports, October 2020.

Development of machine learning-based clinical decision support system for hepatocellular carcinoma

Gwang Hyeon Choi, Jihye Yun, Jonggi Choi, Danbi Lee, Ju Hyun Shim, Han Chu Lee, Young-Hwa Chung, Yung Sang Lee, Beomhee Park, Namkug Kim, Kang Mo Kim, Scientific Reports, September 2020.

Fully automated lung lobe segmentation in volumetric chest CT with 3D U-Net: validation with intra- and extra-datasets

Jongha Park, Jihye Yun, Namkug Kim, Beomhee Park, Yongwon Cho, Hee Jun Park, Mijeong Song, Minho Lee, Joon Beom Seo, Journal of Digital Imaging, February 2020.

Deep learning in medical imaging

Mingyu Kim, Jihye Yun, Yongwon Cho, Keewon Shin, Ryoungwoo Jang, Hyun-jin Bae, Namkug Kim, Neurospine, December 2019.

Radiomics features and multilayer perceptron network classifier: a robust MRI classification strategy for distinguishing glioblastoma from primary central nervous system lymphoma

Jihye Yun, Ji Eun Park, Hyunna Lee, Sungwon Ham, Namkug Kim, Ho Sung Kim, Scientific Reports, April 2019.

Deep learning applications in chest radiography and computed tomography

Sang Min Lee, Joon Beom Seo, Jihye Yun, Young-Hoon Cho, Jens Vogel-Claussen, Mark L Schiebler, Warren B Gefter, Edwin JR Van Beek, Jin Mo Goo, Kyung Soo Lee, Hiroto Hatabu, James Gee, Namkug Kim, Journal of thoracic imaging, March 2019.

Improvement of fully automated airway segmentation on volumetric computed tomographic images using a 2.5 dimensional convolutional neural net

Jihye Yun, Jinkon Park, Donghoon Yu, Jaeyoun Yi, Minho Lee, Hee Jun Park, June-Goo Lee, Joon Beom Seo, Namkug Kim, Medical Image Analysis, January 2019.