• Korean Journal of Radiology
• /
• v.25 no.3
• /
• pp.243-256
• /
• 2024

Objective: We aimed to investigate whether 2-[¹⁸F]fluoro-2-deoxy-D-glucose positron emission tomography/computed tomography (2-[¹⁸F]FDG PET/CT) can aid in evaluating the risk of malignancy in ampullary tumors detected by endoscopy. Materials and Methods: This single-center retrospective cohort study analyzed 155 patients (79 male, 76 female; mean age, 65.7 ± 12.7 years) receiving 2-[¹⁸F]FDG PET/CT for endoscopy-detected ampullary tumors 5-87 days (median, 7 days) after the diagnostic endoscopy between June 2007 and December 2020. The final diagnosis was made based on histopathological findings. The PET imaging parameters were compared with clinical data and endoscopic features. A model to predict the risk of malignancy, based on PET, endoscopy, and clinical findings, was generated and validated using multivariable logistic regression analysis and an additional bootstrapping method. The final model was compared with standard endoscopy for the diagnosis of ampullary cancer using the DeLong test. Results: The mean tumor size was 17.1 ± 7.7 mm. Sixty-four (41.3%) tumors were benign, and 91 (58.7%) were malignant. Univariable analysis found that ampullary neoplasms with a blood-pool corrected peak standardized uptake value in earlyphase scan (SUVe) ≥ 1.7 were more likely to be malignant (odds ratio [OR], 16.06; 95% confidence interval [CI], 7.13-36.18; P < 0.001). Multivariable analysis identified the presence of jaundice (adjusted OR [aOR], 4.89; 95% CI, 1.80-13.33; P = 0.002), malignant traits in endoscopy (aOR, 6.80; 95% CI, 2.41-19.20; P < 0.001), SUVe ≥ 1.7 in PET (aOR, 5.43; 95% CI, 2.00-14.72; P < 0.001), and PET-detected nodal disease (aOR, 5.03; 95% CI, 1.16-21.86; P = 0.041) as independent predictors of malignancy. The model combining these four factors predicted ampullary cancers better than endoscopic diagnosis alone (area under the curve [AUC] and 95% CI: 0.925 [0.874-0.956] vs. 0.815 [0.732-0.873], P < 0.001). The model demonstrated an AUC of 0.921 (95% CI, 0.816-0.967) in candidates for endoscopic papillectomy. Conclusion: Adding 2-[¹⁸F]FDG PET/CT to endoscopy can improve the diagnosis of ampullary cancer and may help refine therapeutic decision-making, particularly when contemplating endoscopic papillectomy.

• Korean Journal of Radiology
• /
• v.24 no.1
• /
• pp.51-61
• /
• 2023

Objective: To develop and test a machine learning model for classifying human papillomavirus (HPV) status of patients with oropharyngeal squamous cell carcinoma (OPSCC) using ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) PET-derived parameters in derived parameters and an appropriate combination of machine learning methods in patients with OPSCC. Materials and Methods: This retrospective study enrolled 126 patients (118 male; mean age, 60 years) with newly diagnosed, pathologically confirmed OPSCC, that underwent ¹⁸F-FDG PET-computed tomography (CT) between January 2012 and February 2020. Patients were randomly assigned to training and internal validation sets in a 7:3 ratio. An external test set of 19 patients (16 male; mean age, 65.3 years) was recruited sequentially from two other tertiary hospitals. Model 1 used only PET parameters, Model 2 used only clinical features, and Model 3 used both PET and clinical parameters. Multiple feature transforms, feature selection, oversampling, and training models are all investigated. The external test set was used to test the three models that performed best in the internal validation set. The values for area under the receiver operating characteristic curve (AUC) were compared between models. Results: In the external test set, ExtraTrees-based Model 3, which uses two PET-derived parameters and three clinical features, with a combination of MinMaxScaler, mutual information selection, and adaptive synthetic sampling approach, showed the best performance (AUC = 0.78; 95% confidence interval, 0.46-1). Model 3 outperformed Model 1 using PET parameters alone (AUC = 0.48, p = 0.047) and Model 2 using clinical parameters alone (AUC = 0.52, p = 0.142) in predicting HPV status. Conclusion: Using oversampling and mutual information selection, an ExtraTree-based HPV status classifier was developed by combining metabolic parameters derived from ¹⁸F-FDG PET/CT and clinical parameters in OPSCC, which exhibited higher performance than the models using either PET or clinical parameters alone.

• Korean Journal of Radiology
• /
• v.24 no.6
• /
• pp.498-511
• /
• 2023

Objective: To evaluate the diagnostic performance of chest computed tomography (CT)-based qualitative and radiomics models for predicting residual axillary nodal metastasis after neoadjuvant chemotherapy (NAC) for patients with clinically node-positive breast cancer. Materials and Methods: This retrospective study included 226 women (mean age, 51.4 years) with clinically node-positive breast cancer treated with NAC followed by surgery between January 2015 and July 2021. Patients were randomly divided into the training and test sets (4:1 ratio). The following predictive models were built: a qualitative CT feature model using logistic regression based on qualitative imaging features of axillary nodes from the pooled data obtained using the visual interpretations of three radiologists; three radiomics models using radiomics features from three (intranodal, perinodal, and combined) different regions of interest (ROIs) delineated on pre-NAC CT and post-NAC CT using a gradient-boosting classifier; and fusion models integrating clinicopathologic factors with the qualitative CT feature model (referred to as clinical-qualitative CT feature models) or with the combined ROI radiomics model (referred to as clinical-radiomics models). The area under the curve (AUC) was used to assess and compare the model performance. Results: Clinical N stage, biological subtype, and primary tumor response indicated by imaging were associated with residual nodal metastasis during the multivariable analysis (all P < 0.05). The AUCs of the qualitative CT feature model and radiomics models (intranodal, perinodal, and combined ROI models) according to post-NAC CT were 0.642, 0.812, 0.762, and 0.832, respectively. The AUCs of the clinical-qualitative CT feature model and clinical-radiomics model according to post-NAC CT were 0.740 and 0.866, respectively. Conclusion: CT-based predictive models showed good diagnostic performance for predicting residual nodal metastasis after NAC. Quantitative radiomics analysis may provide a higher level of performance than qualitative CT features models. Larger multicenter studies should be conducted to confirm their performance.

• Korean Journal of Radiology
• /
• v.24 no.6
• /
• pp.541-552
• /
• 2023

Objective: Detection of pneumoperitoneum using abdominal radiography, particularly in the supine position, is often challenging. This study aimed to develop and externally validate a deep learning model for the detection of pneumoperitoneum using supine and erect abdominal radiography. Materials and Methods: A model that can utilize "pneumoperitoneum" and "non-pneumoperitoneum" classes was developed through knowledge distillation. To train the proposed model with limited training data and weak labels, it was trained using a recently proposed semi-supervised learning method called distillation for self-supervised and self-train learning (DISTL), which leverages the Vision Transformer. The proposed model was first pre-trained with chest radiographs to utilize common knowledge between modalities, fine-tuned, and self-trained on labeled and unlabeled abdominal radiographs. The proposed model was trained using data from supine and erect abdominal radiographs. In total, 191212 chest radiographs (CheXpert data) were used for pre-training, and 5518 labeled and 16671 unlabeled abdominal radiographs were used for fine-tuning and self-supervised learning, respectively. The proposed model was internally validated on 389 abdominal radiographs and externally validated on 475 and 798 abdominal radiographs from the two institutions. We evaluated the performance in diagnosing pneumoperitoneum using the area under the receiver operating characteristic curve (AUC) and compared it with that of radiologists. Results: In the internal validation, the proposed model had an AUC, sensitivity, and specificity of 0.881, 85.4%, and 73.3% and 0.968, 91.1, and 95.0 for supine and erect positions, respectively. In the external validation at the two institutions, the AUCs were 0.835 and 0.852 for the supine position and 0.909 and 0.944 for the erect position. In the reader study, the readers' performances improved with the assistance of the proposed model. Conclusion: The proposed model trained with the DISTL method can accurately detect pneumoperitoneum on abdominal radiography in both the supine and erect positions.

• Korean Journal of Radiology
• /
• v.24 no.5
• /
• pp.395-405
• /
• 2023

Objective: This study aimed to develop and validate models using radiomics features on a native T1 map from cardiac magnetic resonance (CMR) to predict left ventricular reverse remodeling (LVRR) in patients with nonischemic dilated cardiomyopathy (NIDCM). Materials and Methods: Data from 274 patients with NIDCM who underwent CMR imaging with T1 mapping at Severance Hospital between April 2012 and December 2018 were retrospectively reviewed. Radiomic features were extracted from the native T1 maps. LVRR was determined using echocardiography performed ≥ 180 days after the CMR. The radiomics score was generated using the least absolute shrinkage and selection operator logistic regression models. Clinical, clinical + late gadolinium enhancement (LGE), clinical + radiomics, and clinical + LGE + radiomics models were built using a logistic regression method to predict LVRR. For internal validation of the result, bootstrap validation with 1000 resampling iterations was performed, and the optimism-corrected area under the receiver operating characteristic curve (AUC) with 95% confidence interval (CI) was computed. Model performance was compared using AUC with the DeLong test and bootstrap. Results: Among 274 patients, 123 (44.9%) were classified as LVRR-positive and 151 (55.1%) as LVRR-negative. The optimism-corrected AUC of the radiomics model in internal validation with bootstrapping was 0.753 (95% CI, 0.698-0.813). The clinical + radiomics model revealed a higher optimism-corrected AUC than that of the clinical + LGE model (0.794 vs. 0.716; difference, 0.078 [99% CI, 0.003-0.151]). The clinical + LGE + radiomics model significantly improved the prediction of LVRR compared with the clinical + LGE model (optimism-corrected AUC of 0.811 vs. 0.716; difference, 0.095 [99% CI, 0.022-0.139]). Conclusion: The radiomic characteristics extracted from a non-enhanced T1 map may improve the prediction of LVRR and offer added value over traditional LGE in patients with NIDCM. Additional external validation research is required.

• Korean Journal of Radiology
• /
• v.24 no.2
• /
• pp.133-144
• /
• 2023

Objective: Cyclin-dependent kinase inhibitor (CDKN)2A/B homozygous deletion is a key molecular marker of isocitrate dehydrogenase (IDH)-mutant astrocytomas in the 2021 World Health Organization. We aimed to investigate whether qualitative and quantitative MRI parameters can predict CDKN2A/B homozygous deletion status in IDH-mutant astrocytomas. Materials and Methods: Preoperative MRI data of 88 patients (mean age ± standard deviation, 42.0 ± 11.9 years; 40 females and 48 males) with IDH-mutant astrocytomas (76 without and 12 with CDKN2A/B homozygous deletion) from two institutions were included. A qualitative imaging assessment was performed. Mean apparent diffusion coefficient (ADC), 5th percentile of ADC, mean normalized cerebral blood volume (nCBV), and 95th percentile of nCBV were assessed via automatic tumor segmentation. Logistic regression was performed to determine the factors associated with CDKN2A/B homozygous deletion in all 88 patients and a subgroup of 47 patients with histological grades 3 and 4. The discrimination performance of the logistic regression models was evaluated using the area under the receiver operating characteristic curve (AUC). Results: In multivariable analysis of all patients, infiltrative pattern (odds ratio [OR] = 4.25, p = 0.034), maximal diameter (OR = 1.07, p = 0.013), and 95th percentile of nCBV (OR = 1.34, p = 0.049) were independent predictors of CDKN2A/B homozygous deletion. The AUC, accuracy, sensitivity, and specificity of the corresponding model were 0.83 (95% confidence interval [CI], 0.72-0.91), 90.4%, 83.3%, and 75.0%, respectively. On multivariable analysis of the subgroup with histological grades 3 and 4, infiltrative pattern (OR = 10.39, p = 0.012) and 95th percentile of nCBV (OR = 1.24, p = 0.047) were independent predictors of CDKN2A/B homozygous deletion, with an AUC accuracy, sensitivity, and specificity of the corresponding model of 0.76 (95% CI, 0.60-0.88), 87.8%, 80.0%, and 58.1%, respectively. Conclusion: The presence of an infiltrative pattern, larger maximal diameter, and higher 95th percentile of the nCBV may be useful MRI biomarkers for CDKN2A/B homozygous deletion in IDH-mutant astrocytomas.

• Korean Journal of Radiology
• /
• v.23 no.10
• /
• pp.939-948
• /
• 2022

Objective: Evidence supports the efficacy of coronary computed tomography angiography (CCTA)-based risk scores in cardiovascular risk stratification of patients with suspected coronary artery disease (CAD). We aimed to compare two CCTA-based risk score algorithms, Leiden and Confirm scores, in patients with diabetes mellitus (DM) and suspected CAD. Materials and Methods: This single-center prospective cohort study consecutively included 1241 DM patients (54.1% male, 60.2 ± 10.4 years) referred for CCTA for suspected CAD in 2015-2017. Leiden and Confirm scores were calculated and stratified as < 5 (reference), 5-20, and > 20 for Leiden and < 14.3 (reference), 14.3-19.5, and > 19.5 for Confirm. Major adverse cardiovascular events (MACE) were defined as the composite outcomes of cardiovascular death, nonfatal myocardial infarction (MI), stroke, and unstable angina requiring hospitalization. The Cox model and Kaplan-Meier method were used to evaluate the effect size of the risk scores on MACE. The area under the curve (AUC) at the median follow-up time was also compared between score algorithms. Results: During a median follow-up of 31 months (interquartile range, 27.6-37.3 months), 131 of MACE were recorded, including 17 cardiovascular deaths, 28 nonfatal MIs, 64 unstable anginas requiring hospitalization, and 22 strokes. An incremental incidence of MACE was observed in both Leiden and Confirm scores, with an increase in the scores (log-rank p < 0.001). In the multivariable analysis, compared with Leiden score < 5, the hazard ratios for Leiden scores of 5-20 and > 20 were 2.37 (95% confidence interval [CI]: 1.53-3.69; p < 0.001) and 4.39 (95% CI: 2.40-8.01; p < 0.001), respectively, while the Confirm score did not demonstrate a statistically significant association with the risk of MACE. The Leiden score showed a greater AUC of 0.840 compared to 0.777 for the Confirm score (p < 0.001). Conclusion: CCTA-based risk score algorithms could be used as reliable cardiovascular risk predictors in patients with DM and suspected CAD, among which the Leiden score outperformed the Confirm score in predicting MACE.

• Korean Journal of Radiology
• /
• v.23 no.10
• /
• pp.949-958
• /
• 2022

Objective: To investigate the feasibility of using a deep learning-based analysis of auscultation data to predict significant stenosis of arteriovenous fistulas (AVF) in patients undergoing hemodialysis requiring percutaneous transluminal angioplasty (PTA). Materials and Methods: Forty patients (24 male and 16 female; median age, 62.5 years) with dysfunctional native AVF were prospectively recruited. Digital sounds from the AVF shunt were recorded using a wireless electronic stethoscope before (pre-PTA) and after PTA (post-PTA), and the audio files were subsequently converted to mel spectrograms, which were used to construct various deep convolutional neural network (DCNN) models (DenseNet201, EfficientNetB5, and ResNet50). The performance of these models for diagnosing ≥ 50% AVF stenosis was assessed and compared. The ground truth for the presence of ≥ 50% AVF stenosis was obtained using digital subtraction angiography. Gradient-weighted class activation mapping (Grad-CAM) was used to produce visual explanations for DCNN model decisions. Results: Eighty audio files were obtained from the 40 recruited patients and pooled for the study. Mel spectrograms of "pre-PTA" shunt sounds showed patterns corresponding to abnormal high-pitched bruits with systolic accentuation observed in patients with stenotic AVF. The ResNet50 and EfficientNetB5 models yielded an area under the receiver operating characteristic curve of 0.99 and 0.98, respectively, at optimized epochs for predicting ≥ 50% AVF stenosis. However, Grad-CAM heatmaps revealed that only ResNet50 highlighted areas relevant to AVF stenosis in the mel spectrogram. Conclusion: Mel spectrogram-based DCNN models, particularly ResNet50, successfully predicted the presence of significant AVF stenosis requiring PTA in this feasibility study and may potentially be used in AVF surveillance.

• Korean Journal of Radiology
• /
• v.23 no.10
• /
• pp.986-997
• /
• 2022

Objective: Whether metabolic redistribution occurs in patients with white matter hyperintensities (WMHs) on magnetic resonance imaging (MRI) is unknown. This study aimed 1) to propose a measure of the brain metabolic network for an individual patient and preliminarily apply it to identify impaired metabolic networks in patients with WMHs, and 2) to explore the clinical and imaging features of metabolic redistribution in patients with WMHs. Materials and Methods: This study included 50 patients with WMHs and 70 healthy controls (HCs) who underwent ¹⁸F-fluorodeoxyglucose-positron emission tomography/MRI. Various global property parameters according to graph theory and an individual parameter of brain metabolic network called "individual contribution index" were obtained. Parameter values were compared between the WMH and HC groups. The performance of the parameters in discriminating between the two groups was assessed using the area under the receiver operating characteristic curve (AUC). The correlation between the individual contribution index and Fazekas score was assessed, and the interaction between age and individual contribution index was determined. A generalized linear model was fitted with the individual contribution index as the dependent variable and the mean standardized uptake value (SUV_mean) of nodes in the whole-brain network or seven classic functional networks as independent variables to determine their association. Results: The means ± standard deviations of the individual contribution index were (0.697 ± 10.9) × 10^-3 and (0.0967 ± 0.0545) × 10^-3 in the WMH and HC groups, respectively (p < 0.001). The AUC of the individual contribution index was 0.864 (95% confidence interval, 0.785-0.943). A positive correlation was identified between the individual contribution index and the Fazekas scores in patients with WMHs (r = 0.57, p < 0.001). Age and individual contribution index demonstrated a significant interaction effect on the Fazekas score. A significant direct association was observed between the individual contribution index and the SUV_mean of the limbic network (p < 0.001). Conclusion: The individual contribution index may demonstrate the redistribution of the brain metabolic network in patients with WMHs.

• Korean Journal of Radiology
• /
• v.23 no.5
• /
• pp.505-516
• /
• 2022

Objective: To evaluate whether artificial intelligence (AI) for detecting breast cancer on mammography can improve the performance and time efficiency of radiologists reading mammograms. Materials and Methods: A commercial deep learning-based software for mammography was validated using external data collected from 200 patients, 100 each with and without breast cancer (40 with benign lesions and 60 without lesions) from one hospital. Ten readers, including five breast specialist radiologists (BSRs) and five general radiologists (GRs), assessed all mammography images using a seven-point scale to rate the likelihood of malignancy in two sessions, with and without the aid of the AI-based software, and the reading time was automatically recorded using a web-based reporting system. Two reading sessions were conducted with a two-month washout period in between. Differences in the area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, and reading time between reading with and without AI were analyzed, accounting for data clustering by readers when indicated. Results: The AUROC of the AI alone, BSR (average across five readers), and GR (average across five readers) groups was 0.915 (95% confidence interval, 0.876-0.954), 0.813 (0.756-0.870), and 0.684 (0.616-0.752), respectively. With AI assistance, the AUROC significantly increased to 0.884 (0.840-0.928) and 0.833 (0.779-0.887) in the BSR and GR groups, respectively (p = 0.007 and p < 0.001, respectively). Sensitivity was improved by AI assistance in both groups (74.6% vs. 88.6% in BSR, p < 0.001; 52.1% vs. 79.4% in GR, p < 0.001), but the specificity did not differ significantly (66.6% vs. 66.4% in BSR, p = 0.238; 70.8% vs. 70.0% in GR, p = 0.689). The average reading time pooled across readers was significantly decreased by AI assistance for BSRs (82.73 vs. 73.04 seconds, p < 0.001) but increased in GRs (35.44 vs. 42.52 seconds, p < 0.001). Conclusion: AI-based software improved the performance of radiologists regardless of their experience and affected the reading time.