• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.344-353
• /
• 2021

Objective: The mitotic count of gastrointestinal stromal tumors (GIST) is closely associated with the risk of planting and metastasis. The purpose of this study was to develop a predictive model for the mitotic index of local primary GIST, based on deep learning algorithm. Materials and Methods: Abdominal contrast-enhanced CT images of 148 pathologically confirmed GIST cases were retrospectively collected for the development of a deep learning classification algorithm. The areas of GIST masses on the CT images were retrospectively labelled by an experienced radiologist. The postoperative pathological mitotic count was considered as the gold standard (high mitotic count, > 5/50 high-power fields [HPFs]; low mitotic count, ≤ 5/50 HPFs). A binary classification model was trained on the basis of the VGG16 convolutional neural network, using the CT images with the training set (n = 108), validation set (n = 20), and the test set (n = 20). The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated at both, the image level and the patient level. The receiver operating characteristic curves were generated on the basis of the model prediction results and the area under curves (AUCs) were calculated. The risk categories of the tumors were predicted according to the Armed Forces Institute of Pathology criteria. Results: At the image level, the classification prediction results of the mitotic counts in the test cohort were as follows: sensitivity 85.7% (95% confidence interval [CI]: 0.834-0.877), specificity 67.5% (95% CI: 0.636-0.712), PPV 82.1% (95% CI: 0.797-0.843), NPV 73.0% (95% CI: 0.691-0.766), and AUC 0.771 (95% CI: 0.750-0.791). At the patient level, the classification prediction results in the test cohort were as follows: sensitivity 90.0% (95% CI: 0.541-0.995), specificity 70.0% (95% CI: 0.354-0.919), PPV 75.0% (95% CI: 0.428-0.933), NPV 87.5% (95% CI: 0.467-0.993), and AUC 0.800 (95% CI: 0.563-0.943). Conclusion: We developed and preliminarily verified the GIST mitotic count binary prediction model, based on the VGG convolutional neural network. The model displayed a good predictive performance.

• Korean Journal of Radiology
• /
• v.22 no.5
• /
• pp.770-781
• /
• 2021

Objective: Chemical exchange-dependent saturation transfer (CEST) MRI is sensitive for detecting solid-like proteins and may detect changes in the levels of mobile proteins and peptides in tissues. The objective of this study was to evaluate the characteristics of chemical exchange proton pools using the CEST MRI technique in patients with dementia. Materials and Methods: Our institutional review board approved this cross-sectional prospective study and informed consent was obtained from all participants. This study included 41 subjects (19 with dementia and 22 without dementia). Complete CEST data of the brain were obtained using a three-dimensional gradient and spin-echo sequence to map CEST indices, such as amide, amine, hydroxyl, and magnetization transfer ratio asymmetry (MTR_asym) values, using six-pool Lorentzian fitting. Statistical analyses of CEST indices were performed to evaluate group comparisons, their correlations with gray matter volume (GMV) and Mini-Mental State Examination (MMSE) scores, and receiver operating characteristic (ROC) curves. Results: Amine signals (0.029 for non-dementia, 0.046 for dementia, p = 0.011 at hippocampus) and MTR_asym values at 3 ppm (0.748 for non-dementia, 1.138 for dementia, p = 0.022 at hippocampus), and 3.5 ppm (0.463 for non-dementia, 0.875 for dementia, p = 0.029 at hippocampus) were significantly higher in the dementia group than in the non-dementia group. Most CEST indices were not significantly correlated with GMV; however, except amide, most indices were significantly correlated with the MMSE scores. The classification power of most CEST indices was lower than that of GMV but adding one of the CEST indices in GMV improved the classification between the subject groups. The largest improvement was seen in the MTR_asym values at 2 ppm in the anterior cingulate (area under the ROC curve = 0.981), with a sensitivity of 100 and a specificity of 90.91. Conclusion: CEST MRI potentially allows noninvasive image alterations in the Alzheimer's disease brain without injecting isotopes for monitoring different disease states and may provide a new imaging biomarker in the future.

• Korean Journal of Radiology
• /
• v.22 no.1
• /
• pp.106-117
• /
• 2021

Objective: To explore the value of magnetic resonance imaging (MRI)-based whole tumor texture analysis in differentiating borderline epithelial ovarian tumors (BEOTs) from FIGO stage I/II malignant epithelial ovarian tumors (MEOTs). Materials and Methods: A total of 88 patients with histopathologically confirmed ovarian epithelial tumors after surgical resection, including 30 BEOT and 58 MEOT patients, were divided into a training group (n = 62) and a test group (n = 26). The clinical and conventional MRI features were retrospectively reviewed. The texture features of tumors, based on T2-weighted imaging, diffusion-weighted imaging, and contrast-enhanced T1-weighted imaging, were extracted using MaZda software and the three top weighted texture features were selected by using the Random Forest algorithm. A non-texture logistic regression model in the training group was built to include those clinical and conventional MRI variables with p value < 0.10. Subsequently, a combined model integrating non-texture information and texture features was built for the training group. The model, evaluated using patients in the training group, was then applied to patients in the test group. Finally, receiver operating characteristic (ROC) curves were used to assess the diagnostic performance of the models. Results: The combined model showed superior performance in categorizing BEOTs and MEOTs (sensitivity, 92.5%; specificity, 86.4%; accuracy, 90.3%; area under the ROC curve [AUC], 0.962) than the non-texture model (sensitivity, 78.3%; specificity, 84.6%; accuracy, 82.3%; AUC, 0.818). The AUCs were statistically different (p value = 0.038). In the test group, the AUCs, sensitivity, specificity, and accuracy were 0.840, 73.3%, 90.1%, and 80.8% when the non-texture model was used and 0.896, 75.0%, 94.0%, and 88.5% when the combined model was used. Conclusion: MRI-based texture features combined with clinical and conventional MRI features may assist in differentitating between BEOT and FIGO stage I/II MEOT patients.

• Korean Journal of Radiology
• /
• v.22 no.2
• /
• pp.213-224
• /
• 2021

Objective: Clinical outcomes of patients who undergo transarterial chemoembolization (TACE) for single small hepatocellular carcinoma (HCC) are not consistent, and may differ based on certain imaging findings. This retrospective study was aimed at determining the efficacy of pre-TACE CT or MR imaging findings in predicting survival outcomes in patients with small HCC upon being treated with TACE. Besides, the study proposed to build a risk prediction model for these patients. Materials and Methods: Altogether, 750 patients with functionally good hepatic reserve who received TACE as the first-line treatment for single small HCC between 2004 and 2014 were included in the study. These patients were randomly assigned into training (n = 525) and validation (n = 225) sets. Results: According to the results of a multivariable Cox analysis, three pre-TACE imaging findings (tumor margin, tumor location, enhancement pattern) and two clinical factors (age, serum albumin level) were selected and scored to create predictive models for overall, local tumor progression (LTP)-free, and progression-free survival in the training set. The median overall survival time in the validation set were 137.5 months, 76.1 months, and 44.0 months for low-, intermediate-, and high-risk groups, respectively (p < 0.001). Time-dependent receiver operating characteristic curves of the predictive models for overall, LTP-free, and progression-free survival applied to the validation cohort showed acceptable areas under the curve values (0.734, 0.802, and 0.775 for overall survival; 0.738, 0.789, and 0.791 for LTP-free survival; and 0.671, 0.733, and 0.694 for progression-free survival at 3, 5, and 10 years, respectively). Conclusion: Pre-TACE CT or MR imaging findings could predict survival outcomes in patients with small HCC upon treatment with TACE. Our predictive models including three imaging predictors could be helpful in prognostication, identification, and selection of suitable candidates for TACE in patients with single small HCC.

• Journal of Chest Surgery
• /
• v.57 no.1
• /
• pp.44-52
• /
• 2024

Background: Visceral pleural invasion (VPI) is a poor prognostic factor that contributes to the upstaging of early lung cancers. However, the preoperative assessment of VPI presents challenges. This study was conducted to examine intraoperative pleural carcinoembryonic antigen (pCEA) level and maximum standardized uptake value (SUVmax) as predictive markers of VPI in patients with clinical T1N0M0 lung adenocarcinoma. Methods: A retrospective review was conducted of the medical records of 613 patients who underwent intraoperative pCEA sampling and lung resection for non-small cell lung cancer. Of these, 390 individuals with clinical stage I adenocarcinoma and tumors ≤30 mm were included. Based on computed tomography findings, these patients were divided into pleural contact (n=186) and non-pleural contact (n=204) groups. A receiver operating characteristic (ROC) curve was constructed to analyze the association between pCEA and SUVmax in relation to VPI. Additionally, logistic regression analysis was performed to evaluate risk factors for VPI in each group. Results: ROC curve analysis revealed that pCEA level greater than 2.565 ng/mL (area under the curve [AUC]=0.751) and SUVmax above 4.25 (AUC=0.801) were highly predictive of VPI in patients exhibiting pleural contact. Based on multivariable analysis, pCEA (odds ratio [OR], 3.00; 95% confidence interval [CI], 1.14-7.87; p=0.026) and SUVmax (OR, 5.25; 95% CI, 1.90-14.50; p=0.001) were significant risk factors for VPI in the pleural contact group. Conclusion: In patients with clinical stage I lung adenocarcinoma exhibiting pleural contact, pCEA and SUVmax are potential predictive indicators of VPI. These markers may be helpful in planning for lung cancer surgery.

• Journal of Yeungnam Medical Science
• /
• v.40 no.4
• /
• pp.388-393
• /
• 2023

Background: Differentiating between bacterial and nonbacterial colitis remains a challenge. We aimed to evaluate the value of serum procalcitonin (PCT) and C-reactive protein (CRP) in differentiating between bacterial and nonbacterial colitis. Methods: Adult patients with three or more episodes of watery diarrhea and colitis symptoms within 14 days of a hospital visit were eligible for this study. The patients' stool pathogen polymerase chain reaction (PCR) testing results, serum PCT levels, and serum CRP levels were analyzed retrospectively. Patients were divided into bacterial and nonbacterial colitis groups according to their PCR. The laboratory data were compared between the two groups. The area under the receiver operating characteristic curve (AUC) was used to evaluate diagnostic accuracy. Results: In total, 636 patients were included; 186 in the bacterial colitis group and 450 in the nonbacterial colitis group. In the bacterial colitis group, Clostridium perfringens was the commonest pathogen (n=70), followed by Clostridium difficile toxin B (n=60). The AUC for PCT and CRP was 0.557 and 0.567, respectively, indicating poor discrimination. The sensitivity and specificity for diagnosing bacterial colitis were 54.8% and 52.6% for PCT, and 52.2% and 54.2% for CRP, respectively. Combining PCT and CRP measurements did not increase the discrimination performance (AUC, 0.522; 95% confidence interval, 0.474-0.571). Conclusion: Neither PCT nor CRP helped discriminate bacterial colitis from nonbacterial colitis.

• Journal of the Korean Society of Radiology
• /
• v.83 no.3
• /
• pp.620-631
• /
• 2022

Purpose This study aimed to investigate the diagnostic performance of features suggestive of nodal metastasis on preoperative MRI in patients with invasive breast cancer. Materials and Methods We retrospectively reviewed the preoperative breast MRI of 192 consecutive patients with surgically proven invasive breast cancer. We analyzed MRI findings of axillary lymph nodes with regard to the size, long/short ratio, cortical thickness, shape and margin of the cortex, loss of hilum, asymmetry, signal intensity (SI) on T2-weighted images (T2WI), degree of enhancement in the early phase, and enhancement kinetics. Receiver operating characteristic (ROC) analysis, chi-square test, t test, and McNemar's test were used for statistical analysis. Results Increased shorter diameter, uneven cortical shape, increased cortical thickness, loss of hilum, asymmetry, irregular cortical margin, and low SI on T2WI were significantly suggestive of metastasis. ROC analysis revealed the cutoff value for the shorter diameter and cortical thickness as 8.05 mm and 2.75 mm, respectively. Increased cortical thickness (> 2.75 mm) and uneven cortical shape showed significantly higher sensitivity than other findings in McNemar's test. Irregular cortical margins showed the highest specificity (100%). Conclusion Cortical thickness > 2.75 mm and uneven cortical shape are more sensitive parameters than other findings, and an irregular cortical margin is the most specific parameter for predicting axillary metastasis in patients with invasive breast cancer.

• Korean Journal of Radiology
• /
• v.25 no.4
• /
• pp.363-373
• /
• 2024

Objective: To develop and evaluate a deep learning model for automated segmentation and detection of bone metastasis on spinal MRI. Materials and Methods: We included whole spine MRI scans of adult patients with bone metastasis: 662 MRI series from 302 patients (63.5 ± 11.5 years; male:female, 151:151) from three study centers obtained between January 2015 and August 2021 for training and internal testing (random split into 536 and 126 series, respectively) and 49 MRI series from 20 patients (65.9 ± 11.5 years; male:female, 11:9) from another center obtained between January 2018 and August 2020 for external testing. Three sagittal MRI sequences, including non-contrast T1-weighted image (T1), contrast-enhanced T1-weighted Dixon fat-only image (FO), and contrast-enhanced fat-suppressed T1-weighted image (CE), were used. Seven models trained using the 2D and 3D U-Nets were developed with different combinations (T1, FO, CE, T1 + FO, T1 + CE, FO + CE, and T1 + FO + CE). The segmentation performance was evaluated using Dice coefficient, pixel-wise recall, and pixel-wise precision. The detection performance was analyzed using per-lesion sensitivity and a free-response receiver operating characteristic curve. The performance of the model was compared with that of five radiologists using the external test set. Results: The 2D U-Net T1 + CE model exhibited superior segmentation performance in the external test compared to the other models, with a Dice coefficient of 0.699 and pixel-wise recall of 0.653. The T1 + CE model achieved per-lesion sensitivities of 0.828 (497/600) and 0.857 (150/175) for metastases in the internal and external tests, respectively. The radiologists demonstrated a mean per-lesion sensitivity of 0.746 and a mean per-lesion positive predictive value of 0.701 in the external test. Conclusion: The deep learning models proposed for automated segmentation and detection of bone metastases on spinal MRI demonstrated high diagnostic performance.

• Korean Journal of Radiology
• /
• v.25 no.2
• /
• pp.189-198
• /
• 2024

Objective: To investigate the prognostic utility of radiomics features extracted from ¹⁸F-fluorodeoxyglucose (FDG) PET/CT combined with clinical factors and metabolic parameters in predicting progression-free survival (PFS) and overall survival (OS) in individuals diagnosed with extranodal nasal-type NK/T cell lymphoma (ENKTCL). Materials and Methods: A total of 126 adults with ENKTCL who underwent ¹⁸F-FDG PET/CT examination before treatment were retrospectively included and randomly divided into training (n = 88) and validation cohorts (n = 38) at a ratio of 7:3. Least absolute shrinkage and selection operation Cox regression analysis was used to select the best radiomics features and calculate each patient's radiomics scores (RadPFS and RadOS). Kaplan-Meier curve and Log-rank test were used to compare survival between patient groups risk-stratified by the radiomics scores. Various models to predict PFS and OS were constructed, including clinical, metabolic, clinical + metabolic, and clinical + metabolic + radiomics models. The discriminative ability of each model was evaluated using Harrell's C index. The performance of each model in predicting PFS and OS for 1-, 3-, and 5-years was evaluated using the time-dependent receiver operating characteristic (ROC) curve. Results: Kaplan-Meier curve analysis demonstrated that the radiomics scores effectively identified high- and low-risk patients (all P < 0.05). Multivariable Cox analysis showed that the Ann Arbor stage, maximum standardized uptake value (SUVmax), and RadPFS were independent risk factors associated with PFS. Further, β2-microglobulin, Eastern Cooperative Oncology Group performance status score, SUVmax, and RadOS were independent risk factors for OS. The clinical + metabolic + radiomics model exhibited the greatest discriminative ability for both PFS (Harrell's C-index: 0.805 in the validation cohort) and OS (Harrell's C-index: 0.833 in the validation cohort). The time-dependent ROC analysis indicated that the clinical + metabolic + radiomics model had the best predictive performance. Conclusion: The PET/CT-based clinical + metabolic + radiomics model can enhance prognostication among patients with ENKTCL and may be a non-invasive and efficient risk stratification tool for clinical practice.

• Journal of the Korean Society of Radiology
• /
• v.81 no.2
• /
• pp.379-394
• /
• 2020

Purpose To design a scoring system to predict malignancy of additional MRI-detected lesions in breast cancer patients. Materials and Methods Eighty-six lesions (64 benign and 22 malignant) detected on preoperative MRI of 68 breast cancer patients were retrospectively included. The clinico-radiologic features were correlated with the histopathologic results using the Student's t-test, Fisher's exact test, and logistic regression analysis. The scoring system was designed based on the significant predictive features of malignancy, and its diagnostic performance was compared with that of the Breast Imaging-Reporting and Data System (BI-RADS) category. Results Lesion size ≥ 8 mm (p < 0.001), location in the same quadrant as the primary cancer (p = 0.005), delayed plateau kinetics (p = 0.010), T2 isointense (p = 0.034) and hypointense (p = 0.024) signals, and irregular mass shape (p = 0.028) were associated with malignancy. In comparison with the BI-RADS category, the scoring system based on these features with suspicious non-mass internal enhancement increased the diagnostic performance (area under the receiver operating characteristic curve: 0.918 vs. 0.727) and detected three false-negative cases. With this scoring system, 22 second-look ultrasound examinations (22/66, 33.3%) could have been avoided. Conclusion The scoring system based on the lesion size, location relative to the primary cancer, delayed kinetic features, T2 signal intensity, mass shape, and non-mass internal enhancement can provide a more accurate approach to evaluate MRI-detected lesions in breast cancer patients.