전산화단층촬영 영상에서 통계적 특징을 이용한 질감특징분석 알고리즘의 적용

유주은(Jueun Yoo),전태성(Taesung Jun),권진아(Jina Kwon),정주영(Juyoung Jeong),임인철(Inchul Im),이재승(Jaeseung Lee),박형후(Hyonghu Park),곽병준(Byungjoon Kwak),유윤식(Yunsik Yu) 한국방사선학회 2013 한국방사선학회 논문지 Vol.7 No.1

본 연구는 전산화단층촬영에서 간 질환의 자동 인식으로 질감특징분석(texture feature analysis. TFA) 알고리즘을 제안하고자 하였으며, 간세포암(Hepatocellular carcinoma. HCC)에 대한 컴퓨터보조진단(computer-aided diagnosis. CAD) 시스템을 설계하고, 제안하는 각 알고리즘의 성능을 평가하고자 하였다. HCC 영상에서 분석영역(40×40 픽셀)을 설정하고 각 부분영상에 통계적 특징을 이용한 6가지 TFA 파라메터(평균 밝기, 평균 대조도, 평탄도, 왜곡도, 균일도, 엔트로피)비교하여 간세포암 인식률(recognition rate)을 구하였다. 결과적으로 TFA는 간세포암 인식률을 나타내는 척도로 유의함을 알 수 있었으며 6가지 파라메터에서 균일도가 가장 인식률이 높았으며 평균 대조도, 평탄도, 왜곡도가 비교적 높았고 평균 밝기와 엔트로피는 상대적으로 낮은 인식률을 나타내었다. 이와 관련하여 높은 인식률을 보인 알고리즘(최대 97.14%, 최소 82.86%)을 간세포암 영상의 병변을 판별하여 임상의 조기 진단을 보조하여 치료를 시행한다면 진단의 효율성이 높아 질 것으로 판단되었으며, 향후 효율적이고 정량적인 분석을 추가함으로써 질병인식의 일반화에 대한 기준 연구가 필요 할 것으로 사료되었다. In this study, texture feature analysis (TFA) algorithm to automatic recognition of liver disease suggests by utilizing computed tomography (CT), by applying the algorithm computer-aided diagnosis (CAD) of hepatocellular carcinoma (HCC) design. Proposed the performance of each algorithm was to comparison and evaluation. In the HCC image, set up region of analysis (ROA, window size was 40×40 pixels) and by calculating the figures for TFA algorithm of the six parameters (average gray level, average contrast, measure of smoothness, skewness, measure of uniformity, entropy) HCC recognition rate were calculated. As a result, TFA was found to be significant as a measure of HCC recognition rate. Measure of uniformity was the most recognition. Average contrast, measure of smoothness, and skewness were relatively high, and average gray level, entropy showed a relatively low recognition rate of the parameters. In this regard, showed high recognition algorithms (a maximum of 97.14%, a minimum of 82.86%) use the determining HCC imaging lesions and assist early diagnosis of clinic. If this use to therapy, the diagnostic efficiency of clinical early diagnosis better than before. Later, after add the effective and quantitative analysis, criteria research for generalized of disease recognition is needed to be considered.

Automatic Extraction of Aortic Aneurysm from Thoracic CTA based on Fuzzy-based 3-D Region Growing Method

Tatsushi Tokuyasu,Takashi Shuto,Kenji Yufu,Shotaro Kanao,Akira Marui,Masashi Komeda 제어로봇시스템학회 2010 제어로봇시스템학회 국제학술대회 논문집 Vol.2010 No.10

Computer-Aided Diagnosis (CAD) system that helps medical staffs to diagnose patient"s disease conditions has been used in a variety fields of medicine. For cardiovascular surgery, radiologists manually construct 3-D volume model of patient organ and provide this information to cardiovascular surgeons, therefore automation technique for image processing of building patient 3-D volume model is highly requested from clinical site. The 3-D volume model is used in not only diagnosing patient disease condition, but also making a surgical plan before an operation. In the case of using CAD system for a cardiovascular disease patient, computed tomography angiography (CTA) has been used as the source data that clearly indicates the region of blood flow on the image due to contrast agent. However, sufficient information for the diagnosis is not obtained from CTA, because the regions of aneurysm and aortic wall tissue can not distinguished correctly even using the latest CAD system. Then, this study proposes Fuzzy-based region growing method that enables a computer to have the ability of reading radiogram. We focused on the skill of reading radiogram of experienced doctors, because they know the boundary line between aneurysm and aortic wall tissue on CTA image. Hence, Fuzzy inference has been employed to express doctor"s skill of reading radiogram and used as the growing criteria. The proposed method is applied to one patient CTA data and its result is shown and discussed in this paper.

Statistical-techniques-based Computer-aided Diagnosis (CAD) Using Texture Feature Analysis: Application in Computed Tomography (CT) Imaging to Fatty Liver Disease

정운관,박형후,임인철,이재승,구은회,동경래 한국물리학회 2012 THE JOURNAL OF THE KOREAN PHYSICAL SOCIETY Vol.61 No.5

This paper proposes a computer-aided diagnosis (CAD) system based on texture feature analysis and statistical wavelet transformation technology to diagnose fatty liver disease with computed tomography (CT) imaging. In the target image, a wavelet transformation was performed for each lesion area to set the region of analysis (ROA, window size: 50 × 50 pixels) and define the texture feature of a pixel. Based on the extracted texture feature values, six parameters (average gray level, average contrast, relative smoothness, skewness, uniformity, and entropy) were determined to calculate the recognition rate for a fatty liver. In addition, a multivariate analysis of the variance (MANOVA) method was used to perform a discriminant analysis to verify the significance of the extracted texture feature values and the recognition rate for a fatty liver. According to the results, each texture feature value was significant for a comparison of the recognition rate for a fatty liver (p < 0.05). Furthermore, the F-value, which was used as a scale for the difference in recognition rates, was highest in the average gray level, relatively high in the skewness and the entropy, and relatively low in the uniformity, the relative smoothness and the average contrast. The recognition rate for a fatty liver had the same scale as that for the F-value, showing 100% (average gray level) at the maximum and 80% (average contrast) at the minimum. Therefore, the recognition rate is believed to be a useful clinical value for the automatic detection and computer-aided diagnosis (CAD) using the texture feature value. Nevertheless, further study on various diseases and singular diseases will be needed in the future.

CT Image Analysis of Hepatic Lesions Using CAD ; Fractal Texture Analysis

( Kyung-hoon Hwang ),( Cheong Ji Wook ),( Jung-chul Lee ),( Hyung-ji Lee ),( Duckjoo Choi ),( Wonsick Choe ) 한국정보처리학회 2007 한국정보처리학회 학술대회논문집 Vol.14 No.1

We investigated whether the CT images of hepatic lesions could be analyzed by computer-aided diagnosis (CAD) tool. We retrospectively reanalyzed 14 liver CT images (10 hepatocellular cancers and 4 benign liver lesions; patients who presented with hepatic masses). The hepatic lesions on CT were segmented by rectangular ROI technique and the morphologic features were extracted and quantitated using fractal texture analysis. The contrast enhancement of hepatic lesions was also quantified and added to the differential diagnosis. The best discriminating function combining the textural features and the values of contrast enhancement of the lesions was created using linear discriminant analysis. Textural feature analysis showed moderate accuracy in the differential diagnosis of hepatic lesions, but statistically insignificant. Combining textural analysis and contrast enhancement value resulted in improved diagnostic accuracy, but further studies are needed.

Statistical Techniques based Computer-aided Diagnosis (CAD) using Texture Feature Analysis: Applied of Cerebral Infarction in Computed Tomography (CT) Images

Jaeseung Lee,Inchul Im,Yunsik Yu,Hyonghu Park,Byungjoon Kwak 대한의생명과학회 2012 Biomedical Science Letters Vol.18 No.4

The brain is the body"s most organized and controlled organ, and it governs various psychological and mental functions. A brain abnormality could greatly affect one"s physical and mental abilities, and consequently one"s social life. Brain disorders can be broadly categorized into three main afflictions: stroke, brain tumor, and dementia. Among these, stroke is a common disease that occurs owing to a disorder in blood flow, and it is accompanied by a sudden loss of consciousness and motor paralysis. The main types of strokes are infarction and hemorrhage. The exact diagnosis and early treatment of an infarction are very important for the patient"s prognosis and for the determination of the treatment direction. In this study, texture features were analyzed in order to develop a prototype auto-diagnostic system for infarction using computer auto-diagnostic software. The analysis results indicate that of the six parameters measured, the average brightness, average contrast, flatness, and uniformity show a high cognition rate whereas the degree of skewness and entropy show a low cognition rate. On the basis of these results, it was suggested that a digital CT image obtained using the computer auto-diagnostic software can be used to provide valuable information for general CT image auto-detection and diagnosis for pre-reading. This system is highly advantageous because it can achieve early diagnosis of the disease and it can be used as supplementary data in image reading. Further, it is expected to enable accurate medical image detection and reduced diagnostic time in final-reading.

유방 SPECT 및 초음파 컴퓨터진단시스템 결합의 유방암 진단성능

황경훈 ( Kyung Hoon Hwang ),이준구 ( Jun Gu Lee ),김종효 ( Jong Hyo Kim ),이형지 ( Hyung Ji Lee ),엄경식 ( Kyong Sik Om ),이병일 ( Byeong II Lee ),최덕주 ( Duck Joo Choi ),최원식 ( Won Sick Choe ) 대한핵의학회 2007 핵의학 분자영상 Vol.41 No.3

Kinetic Features of Invasive Breast Cancers on Computer-Aided Diagnosis Using 3T MRI Data: Correlation with Clinical and Pathologic Prognostic Factors

송성은,조규란,서보경,우옥희,정승필,성득제 대한영상의학회 2019 Korean Journal of Radiology Vol.20 No.3

Objective: To investigate the correlation of kinetic features of breast cancers on computer-aided diagnosis (CAD) of preoperative 3T magnetic resonance imaging (MRI) data and clinical-pathologic factors in breast cancer patients. Materials and Methods: Between July 2016 and March 2017, 85 patients (mean age, 54 years; age range, 35–81 years) with invasive breast cancers (mean, 1.8 cm; range, 0.8-4.8 cm) who had undergone MRI and surgery were retrospectively enrolled. All magnetic resonance images were processed using CAD, and kinetic features of tumors were acquired. The relationships between kinetic features and clinical-pathologic factors were assessed using Spearman correlation test and binary logistic regression analysis. Results: Peak enhancement and angio-volume were significantly correlated with histologic grade, Ki-67 index, and tumor size: r = 0.355 (p = 0.001), r = 0.330 (p = 0.002), and r = 0.231 (p = 0.033) for peak enhancement, r = 0.410 (p = 0.005), r = 0.341 (p < 0.001), and r = 0.505 (p < 0.001) for angio-volume. Delayed-plateau component was correlated with Ki-67 (r = 0.255 [p = 0.019]). In regression analysis, higher peak enhancement was associated with higher histologic grade (odds ratio [OR] = 1.004; 95% confidence interval [CI]: 1.001–1.008; p = 0.024), and higher delayed-plateau component and angio-volume were associated with higher Ki-67 (OR = 1.051; 95% CI: 1.011–1.094; p = 0.013 for delayed-plateau component, OR = 1.178; 95% CI: 1.023–1.356; p = 0.023 for angio-volume). Conclusion: Of the CAD-assessed kinetic features, higher peak enhancement may correlate with higher histologic grade, and higher delayed-plateau component and angio-volume correlate with higher Ki-67 index. These results support the clinical application of kinetic features in prognosis assessment.

Detection of Microcalcification Using the Wavelet Based Adaptive Sigmoid Function and Neural Network

( Sanjeev Kumar ),( Mahesh Chandra ) 한국정보처리학회 2017 Journal of information processing systems Vol.13 No.4

Mammogram images are sensitive in nature and even a minor change in the environment affects the quality of the images. Due to the lack of expert radiologists, it is difficult to interpret the mammogram images. In this paper an algorithm is proposed for a computer-aided diagnosis system, which is based on the wavelet based adaptive sigmoid function. The cascade feed-forward back propagation technique has been used for training and testing purposes. Due to the poor contrast in digital mammogram images it is difficult to process the images directly. Thus, the images were first processed using the wavelet based adaptive sigmoid function and then the suspicious regions were selected to extract the features. A combination of texture features and graylevel co-occurrence matrix features were extracted and used for training and testing purposes. The system was trained with 150 images, while a total 100 mammogram images were used for testing. A classification accuracy of more than 95% was obtained with our proposed method.

Detection of Microcalcification Using the Wavelet Based Adaptive Sigmoid Function and Neural Network

Kumar, Sanjeev,Chandra, Mahesh Korea Information Processing Society 2017 Journal of information processing systems Vol.13 No.4

Mammogram images are sensitive in nature and even a minor change in the environment affects the quality of the images. Due to the lack of expert radiologists, it is difficult to interpret the mammogram images. In this paper an algorithm is proposed for a computer-aided diagnosis system, which is based on the wavelet based adaptive sigmoid function. The cascade feed-forward back propagation technique has been used for training and testing purposes. Due to the poor contrast in digital mammogram images it is difficult to process the images directly. Thus, the images were first processed using the wavelet based adaptive sigmoid function and then the suspicious regions were selected to extract the features. A combination of texture features and gray-level co-occurrence matrix features were extracted and used for training and testing purposes. The system was trained with 150 images, while a total 100 mammogram images were used for testing. A classification accuracy of more than 95% was obtained with our proposed method.

유방 초음파 영상의 CAD 적용을 위한 Segmentation 알고리즘 제안

구락조,정인성,배재호,최성욱,박희붕,왕지남 대한산업공학회 2008 산업공학 Vol.21 No.4

The objective of this paper is to design segmentation algorithm for applying the breast ultrasound image to CAD(Computer Aided Diagnosis). This study is conducted after understanding limits, used algorithm and demands of CAD system by interviewing with a medical doctor and analyzing related works based on a general CAD framework that is consisted of five step-establishment of plan, analysis of needs, design, implementation and test & maintenance. Detection function of CAD is accomplished by Canny algorithm and arithmetic operations for segmentation. In addition to, long computing time is solved by extracting ROI (Region Of Interests) and applying segmentation technical methods based morphology algorithm. Overall course of study is conducted by verification of medical doctor. And validity and verification are satisfied by medical doctor's confirmation. Moreover, manual segmentation of related works, restrictions on the number of tumor and dependency of image resolution etc. was solved. This study is utilized as a support system aided doctors' subjective diagnosis even though a lot of future studies is needed for entire application of CAD system.