• Proceedings of the IEEK Conference
• /
• 2002.06d
• /
• pp.335-338
• /
• 2002

This paper proposes some technical approaches for automatic detection of pulmonary nodules in chest X-ray images. We applied threshold technique for the lung field segmentation and extended the lung field by using morphological methods. A template matching technique was employed for automatic detecting nodules in lung area. Genetic algorithm(GA) was used in template matching(TM) to select a matched image from various reference patterns(simulated typical nodules). We eliminated the false-positive candidates by using histograms and contrasts. We used standard databases published by Japanese Society of Radiological Technology (JSRT) for correct results. Also we employ two-dimensional Gaussian distribution for some reference images because the shadow of lung nodules in radiogram generally shows the distributions. Nodules of about 89% were correctly detected by our scheme. The simulation results show that it is an effective method to indicate lesions on chest radiograms.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.8
• /
• pp.225-231
• /
• 2013

Medical image segmentation is an image processing technology prior to performing various medical image processing. Therefore, a variety of methods have been researched for fast and accurate medical image segmentation. Accurate judgment of segmentation region is needed to segment the interest region in which patient requested in medical image that various organs exist. However, an case that scanned a part of organs is small occurs. In this case, information to determine the segmentation region is lack. consequently, a removal of segmentation region occurs during the segmentation process. In this paper, we improved segmentation results in a small region using volume data and linear equation. In order to verify the performance of the proposed method, we segmented the lung region of chest CT images. As a result of experiments, we confirmed that image segmentation accuracy rose from 0.978 to 0.981 and standard deviation also improved from 0.281 to 0.187.

• Journal of KIISE:Software and Applications
• /
• v.32 no.7
• /
• pp.625-635
• /
• 2005

In this paper, we propose a hybrid approach for segmenting the lungs efficiently and automatically in chest CT images. The proposed method consists of the following three steps. first, lungs and airways are extracted by two- and three-dimensional automatic seeded region growing and connected component labeling in low-resolution. Second, trachea and large airways are delineated from the lungs by two-dimensional morphological operations, and the left and right lungs are identified by connected component labeling in low-resolution. Third, smooth and accurate lung region borders are obtained by refinement based on image subtraction. In experiments, we evaluate our method in aspects of accuracy and efficiency using 10 chest CT images obtained from 5 patients. To evaluate the accuracy, we Present results comparing our automatic method to manually traced borders from radiologists. Experimental results show that proposed method which use connected component labeling in low-resolution reduce processing time by 31.4 seconds and maximum memory usage by 196.75 MB on average. Our method extracts lung surfaces efficiently and automatically without additional processing like hole-filling.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.16 no.2
• /
• pp.18-24
• /
• 2012

Purpose : Although lung ventilation SPECT (LV-SPECT) has a good sensitivity in detection of deep lung lesions, it is difficult to apply the LV-SPECT to patients having breathing problems due to limited examination time. In this study, we evaluated the usefulness of LEAP collimator, which provides high detection sensitivity and tolerable resolution, for the LV-SPECT in terms of diagnostic accuracy and examination time. Materials and Methods : Four volunteers inhaled Technegas (370 MBq) and the lung ventilation planar scan (LVPS, 300 counts/view (cpv)) with LEHR collimator was performed using Siemens E.cam scanner as a reference test. LV-SPECT scans were performed with three collimators, LEHR, LEUHR, and LEAP, in low (7 kcpv) and high (70 kcpv) counting modes. The count ratios of left (LT) and right (RT) lung segments were calculated on the geometric mean view of anterior and posterior images for LVPS and on the summed coronal images of LV-SPECT, respectively. Comparing to LVPS, the usefulness of three different collimators for LV-SPECT was evaluated through statistical analysis (paired t-test), on count ratios of lung segments. Results : The average LT:RT ratio in LVPS was 47:53. For LV-SPECT, there were negligible difference of the LT:RT ratios (48:52 on average) among three different collimators in low and high counting modes. Comparing to standard LVPS with LEHR, all LV-SPECTs with different collimators resulted in similar diagnostic accuracy through paired t-test (p>0.05). The scan time in LVPS (6 views) was 17.3 min. For LV-SPECT (128 views) in low counting mode, it took 18.7 (LEUHR), 15.0 (LEHR), and 12.3 min (LEAP), respectively. Conclusion : Comparing to standard LVPS, the LV-SPECT with LEAP in low counting mode provided the comparable diagnostic accuracy in addition to shortened scan time.

• 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 Korea Multimedia Society
• /
• v.16 no.6
• /
• pp.700-707
• /
• 2013

In this paper, we propose a non-rigid registration method of lung parenchyma in temporal chest CT scans using region binarization modeling and locally deformable model. To cope with intensity differences between CT scans, we segment the lung vessel and parenchyma in each scan and perform binarization modeling. Then, we match them without referring any intensity information. We globally align two lung surfaces. Then, locally deformable transformation model is developed for the subsequent non-rigid registration. Subtracted quantification results after non-rigid registration are visualized by pre-defined color map. Experimental results showed that proposed registration method correctly aligned lung parenchyma in the full inspiration and expiration CT images for ten patients. Our non-rigid lung registration method may be useful for the assessment of various lung diseases by providing intuitive color-coded information of quantification results about lung parenchyma.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.10b
• /
• pp.895-898
• /
• 2000

의료 영상에서 폐 영역의 정확한 추출과 폐엽의 분할은 폐 기능의 측정 및 폐 질환의 진단을 위하여 매우 중요하다. 본 논문에서는 EBT 흉부 영상에서 자동으로 폐 영역을 추출하고 폐 영역을 폐엽 단위로 분할하는 방법을 제안한다. 본 논문에서는 히스토그램 분석과 형태학적 연산자를 이용하여 폐 영역을 추출하고 adaptive filter를 이용한 에지 연산과 폐엽 경계(pulmonary fissure)에 대한 의학적 지식을 바탕으로 폐엽을 분할하였다. 본 방법을 여러 종류의 EBT 폐 영상에 적용하여 실험한 결과 95%이상의 정확도를 보였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.763-765
• /
• 2004

현재 의료 영상을 이용한 신속하고 정확한 진단과 치료를 위하여 각 기관별로 영상을 분할하는 방식이 기본적으로 사용되고 있다. 본 논문에서는 워터쉐드(Watershed) 알고리즘을 이용하여 해부학적 기관 중 폐 영역을 분할하는 방식을 제안한다. 초기에 소벨 에지 마스크(Sobel Edge Mask)를 이용하여 윤곽선을 강조하여 워터쉐드 알고리즘을 적용하였을 경우 과다 분할되는 문제점이 발생한다. 이를 해결하기 위하여 제거(Opening) 연산과 채움(Closing) 연산을 이용하여 마커(Marker) 정보를 추출하여 워터쉐드 알고리즘을 재적용하여 폐 영역 이미지를 분할하였다. 본 논문에서 제안한 마커 정보를 이용한 워터쉐드 재적용 방식은 폐 영역 효율적이고 정확하게 추출한다.

• Journal of KIISE:Software and Applications
• /
• v.33 no.11
• /
• pp.942-952
• /
• 2006

We propose an automatic segmentation method for identifying pulmonary structures using gray-level information of chest CT images. Our method consists of following five steps. First, to segment pulmonary structures based on the difference of gray-level value, we select the threshold using optimal thresholding. Second, we separate the thorax from the background air and then the lungs and airways from the thorax by applying the inverse operation of 2D region growing in chest CT images. To eliminate non-pulmonary structures which has similar intensities with the lungs, we use 3D connected component labeling. Third, we segment the trachea and left and right mainstem bronchi using 3D branch-based region growing in chest CT images. Fourth, we can obtain accurate lung boundaries by subtracting the result of third step from the result of second step. Finally, we select the threshold in accordance with histogram analysis and then segment radio-dense pulmonary vessels by applying gray-level thresholding to the result of the second step. To evaluate the accuracy of proposed method, we make a visual inspection of segmentation result of lungs, airways and pulmonary vessels. We compare the result of the conventional region growing with the result of proposed 3D branch-based region growing. Experimental results show that our proposed method extracts lung boundaries, airways, and pulmonary vessels automatically and accurately.

• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.464-475
• /
• 2021

Objective: This study aimed to evaluate the tumor doubling time of invasive lung adenocarcinoma according to the International Association of the Study for Lung Cancer (IASLC)/American Thoracic Society (ATS)/European Respiratory Society (ERS) histologic classification. Materials and Methods: Among the 2905 patients with surgically resected lung adenocarcinoma, we retrospectively included 172 patients (mean age, 65.6 ± 9.0 years) who had paired thin-section non-contrast chest computed tomography (CT) scans at least 84 days apart with the same CT parameters, along with 10 patients with squamous cell carcinoma (mean age, 70.9 ± 7.4 years) for comparison. Three-dimensional semiautomatic segmentation of nodules was performed to calculate the volume doubling time (VDT), mass doubling time (MDT), and specific growth rate (SGR) of volume and mass. Multivariate linear regression, one-way analysis of variance, and receiver operating characteristic curve analyses were performed. Results: The median VDT and MDT of lung cancers were as follows: acinar, 603.2 and 639.5 days; lepidic, 1140.6 and 970.1 days; solid/micropapillary, 232.7 and 221.8 days; papillary, 599.0 and 624.3 days; invasive mucinous, 440.7 and 438.2 days; and squamous cell carcinoma, 149.1 and 146.1 days, respectively. The adjusted SGR of volume and mass of the solid-/micropapillary-predominant subtypes were significantly shorter than those of the acinar-, lepidic-, and papillary-predominant subtypes. The histologic subtype was independently associated with tumor doubling time. A VDT of 465.2 days and an MDT of 437.5 days yielded areas under the curve of 0.791 and 0.795, respectively, for distinguishing solid-/micropapillary-predominant subtypes from other subtypes of lung adenocarcinoma. Conclusion: The tumor doubling time of invasive lung adenocarcinoma differed according to the IASCL/ATS/ERS histologic classification.