• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.6
• /
• pp.35-43
• /
• 2009

In the Computer Aided Diagnosis(CAD) System, the efficient way of classifying nodules from chest CT images of a patient is to perform the classification of the remaining part after the pulmonary vessel extraction. During the pulmonary vessel extraction, due to the small difference between the vessel and nodule features in imaging studies such as CT scans after having an injection of contrast, nodule maybe extracted along with the pulmonary vessel. Therefore, the pulmonary vessel extraction method plays an important role in the nodule classification process. In this paper, we propose a nodule reclassification method based on vessel thickness analysis. The proposed method consist of four steps, lung region searching step, vessel extraction and thinning step, vessel topology formation and correction step and the reclassification of nodule in the vessel candidate step. The radiologists helped us to compare the accuracy of the CAD system using the proposed method and the accuracy of general one. Experimental results show that the proposed method can extract pulmonary vessels and reclassify false-positive nodules accurately.

• Korean Journal of Radiology
• /
• v.25 no.7
• /
• pp.673-683
• /
• 2024

Objective: To evaluate the role of visual and quantitative chest CT parameters in assessing treatment response in patients with severe asthma. Materials and Methods: Korean participants enrolled in a prospective multicenter study, named the Precision Medicine Intervention in Severe Asthma study, from May 2020 to August 2021, underwent baseline and follow-up chest CT scans (inspiration/expiration) 10-12 months apart, before and after biologic treatment. Two radiologists scored bronchiectasis severity and mucus plugging extent. Quantitative parameters were obtained from each CT scan as follows: normal lung area (normal), air trapping without emphysema (AT without emph), air trapping with emphysema (AT with emph), and airway (total branch count, Pi10). Clinical parameters, including pulmonary function tests (forced expiratory volume in 1 s [FEV1] and FEV1/forced vital capacity [FVC]), sputum and blood eosinophil count, were assessed at initial and follow-up stages. Changes in CT parameters were correlated with changes in clinical parameters using Pearson or Spearman correlation. Results: Thirty-four participants (female:male, 20:14; median age, 50.5 years) diagnosed with severe asthma from three centers were included. Changes in the bronchiectasis and mucus plugging extent scores were negatively correlated with changes in FEV1 and FEV1/FVC (ρ = from -0.544 to -0.368, all P < 0.05). Changes in quantitative CT parameters were correlated with changes in FEV1 (normal, r = 0.373 [P = 0.030], AT without emph, r = -0.351 [P = 0.042]), FEV1/FVC (normal, r = 0.390 [P = 0.022], AT without emph, r = -0.370 [P = 0.031]). Changes in total branch count were positively correlated with changes in FEV1 (r = 0.349 [P = 0.043]). There was no correlation between changes in Pi10 and the clinical parameters (P > 0.05). Conclusion: Visual and quantitative CT parameters of normal, AT without emph, and total branch count may be effective for evaluating treatment response in patients with severe asthma.

• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.476-488
• /
• 2021

Objective: We aimed to develop a deep neural network for segmenting lung parenchyma with extensive pathological conditions on non-contrast chest computed tomography (CT) images. Materials and Methods: Thin-section non-contrast chest CT images from 203 patients (115 males, 88 females; age range, 31-89 years) between January 2017 and May 2017 were included in the study, of which 150 cases had extensive lung parenchymal disease involving more than 40% of the parenchymal area. Parenchymal diseases included interstitial lung disease (ILD), emphysema, nontuberculous mycobacterial lung disease, tuberculous destroyed lung, pneumonia, lung cancer, and other diseases. Five experienced radiologists manually drew the margin of the lungs, slice by slice, on CT images. The dataset used to develop the network consisted of 157 cases for training, 20 cases for development, and 26 cases for internal validation. Two-dimensional (2D) U-Net and three-dimensional (3D) U-Net models were used for the task. The network was trained to segment the lung parenchyma as a whole and segment the right and left lung separately. The University Hospitals of Geneva ILD dataset, which contained high-resolution CT images of ILD, was used for external validation. Results: The Dice similarity coefficients for internal validation were 99.6 ± 0.3% (2D U-Net whole lung model), 99.5 ± 0.3% (2D U-Net separate lung model), 99.4 ± 0.5% (3D U-Net whole lung model), and 99.4 ± 0.5% (3D U-Net separate lung model). The Dice similarity coefficients for the external validation dataset were 98.4 ± 1.0% (2D U-Net whole lung model) and 98.4 ± 1.0% (2D U-Net separate lung model). In 31 cases, where the extent of ILD was larger than 75% of the lung parenchymal area, the Dice similarity coefficients were 97.9 ± 1.3% (2D U-Net whole lung model) and 98.0 ± 1.2% (2D U-Net separate lung model). Conclusion: The deep neural network achieved excellent performance in automatically delineating the boundaries of lung parenchyma with extensive pathological conditions on non-contrast chest CT images.

• Journal of Chest Surgery
• /
• v.41 no.6
• /
• pp.795-798
• /
• 2008

A 50 year old male patient was admitted due to fever and left upper-quadrant abdominal pain. He had a history of previous treatment for pulmonary TB and splenectomy due to plastic anemia. A large peritoneal abscess with connection to a chronic left side tuberculous empyema thoracis was diagnosed on admission. Chest CT also revealed a soft issue lesion on the left anterior chest wall. Staged drainage of the peritoneal lesion followed by left side pleuropneumonectomy with chest wall resection was performed. The pathologic studies showed a high grade sarcoma of the chest wall.

• Journal of the Korean Society of Radiology
• /
• v.82 no.1
• /
• pp.212-218
• /
• 2021

Ewing sarcomas constitute a group of small, round, blue cell tumors of the bone and soft tissue. Extraskeletal Ewing sarcoma (EES) is a rare malignant neoplasm that arises from soft tissues, and it usually affects children and young adults. EES of the thoracopulmonary region commonly presents with a palpable mass or pain. Although rarely reported, EES affecting the anterior chest wall may present as a breast mass. We report a case of EES arising from the chest wall and manifesting as a palpable breast mass in a 22-year-old woman. The large mass was initially misdiagnosed as a breast origin mass on ultrasonography, but subsequent CT and MRI showed that the mass originated from the chest wall. Radiologists should be aware of the imaging findings of EES, and they should understand that chest wall lesions may be clinically confused as breast lesions.

• 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.

• Journal of Chest Surgery
• /
• v.30 no.8
• /
• pp.780-785
• /
• 1997

Mediastinal tumor had been fascinated by its location on heart, great vessels, esophagus, and nervous tissue, its convenience of surgical treatment and superiority of its operative result. Between January 1989 and June 1995, eighty-seven patients with mediastinal tumor which were treated surgically in the Department of Thoracic and Cardiovascular Surgery, Asan Medical Center, School of Medicine, University of Ulsan. To provide the appropriate surgical management of mediastinal tumor, the demographic data, diagnostic evaluation, clinical presentation, location, size, operative finding and histopathologic distribution were reviewed and we analyzed relativity between invasiveness in chest computed tomographic finding or invasiveness on operative finding and histopathologic invasiveness. The anterosuperior mediastinum was the most commonly involved site of a mediastinal tumor(57%), followed by the posterior mediastinum(35%) and middle mediastinum(8%). The most frequently encountered tumors were thymic neoplasia(31%), followed by primary cyst(22%), neurogenic tumor(22%) and teratoma(10%) in decreasing order of frequency. Histopathologically invasive tumors were present in 17 patients(20%) and its site included anterosuperior mediastinum(16%) and posterior mediastinum(4%). All patients in this study underwent chest CT. In chest CT's finding, 15 patients(17%) showed invasiveness. A total excision of the tumor was performed 80 patients(92%), subtotal excision 6 patients(7%) and biopsy only 1 patient(2%). In operative finding, 14 patients(16%) were suspected invasiveness. The mean size of the tumor was 6.0$\pm$ 3.2cm. In anterosuperior mediastinum, the mean size was 6.2$\pm$3.1cm, in middle mediastinum, it was 3.9$\pm$1.1cm, in posterior mediastinum, it was 5.8$\pm$2.6cm. In malignant tumors, the mean size was 7.3$\pm$4.6cm, in benign tumor, it was 5.5$\pm$2.6cm(P<0.05). Relativity between histopathological invasiveness(17 patients) and invasiveness in chest CT's finding(15 patients) included sensitivity 35%, specificity 87% and predictability 35%, relativity between histopathological invasiveness(17 patients) and invasiveness on operative finding included sensitivity 52%, specificity 93% and predictability 64%. In conclusion, since it was proved that the compatibility of preoperative chest CT findings or operative findings and histopathological invasiveness is quite low, it is considered that wide excision of the mediastinal tumor except cystic lesion including adjacent tissues would yield better postoperative results.

• Journal of Chest Surgery
• /
• v.29 no.1
• /
• pp.120-124
• /
• 1996

We report three cases of posterior mediastinal tumor in Von Recklinghausen's disease on 12-yearsy old boy, 8-years-old girl and 6-years-old boy. Especially the last case was combinded with "Dumbbell" neurilemmoma of cervical spine. In the first case, preoperative CT scan showed a homogeneous large mass In the posterior mediastinum. But the mass did not show intraspinal invasion on the chest MRI scan. In the last case, cervical spine CT with thecal enhancement shows dumbbell shaped neurofibroma, compressed spinal cord and thecal sac In three cases we removed all the masses successfully and the patients were discharged safely without significant problem.t problem.

• Journal of Yeungnam Medical Science
• /
• v.37 no.1
• /
• pp.54-58
• /
• 2020

Achromobacter xylosoxidans is a gram-negative bacterium that can oxidize xylose. It is commonly found in contaminated soil and water but does not normally infect immunocompetent humans. We report a case of a cavitary lung lesion associated with community-acquired A. xylosoxidans infection, which mimicked pulmonary tuberculosis or lung cancer in an immunocompetent man. The patient was hospitalized due to hemoptysis, and chest computed tomography (CT) revealed a cavitary lesion in the superior segment of the left lower lobe. We performed bronchoscopy and bronchial washing, and subsequent bacterial cultures excluded pulmonary tuberculosis and identified A. xylosoxidans. We performed antibiotic sensitivity testing and treated the patient with a 6-week course of amoxicillin/clavulanate. After 2 months, follow-up chest CT revealed complete resolution of the cavitary lesion.

• Nuclear Medicine and Molecular Imaging
• /
• v.42 no.sup1
• /
• pp.32-38
• /
• 2008

This review focuses on the clinical use of $^{18}F-FDG$ PET in esophageal cancer. For initial staging of esophageal cancer, $^{18}F-FDG$ PET is better than chest CT and is complementary to endoscopic ultrasound. Due to its good results for detecting distant metastasis, $^{18}F-FDG$ PET evades unnecessary curative surgery. Also, PET findings are associated with prognosis in esophageal cancer. $^{18}F-FDG$ PET seems to be useful for detecting recurrence and restaging in esophageal cancer. For therapy response assessment, $^{18}F-FDG$ PET is effective after chemotherapy or radiation therapy. $^{18}F-FDG$ PET is useful to predict pathological response after neoadjuvant therapy in esophageal cancer, which is better than chest CT and endoscopic ultrasound. For radiation therapy planning, $^{18}F-FDG$ PET may be helpful, but requires further investigations.