Mammogram 진단에 있어 이미지 강조기법과 Fractal Dimension을 이용한 미세석회 검출에 대한 평가

남상희,은충기 인제대학교 1998 仁濟論叢 Vol.14 No.2

Some researches related to the digital image processing and analysis of the mammograms have been conducted to solve some problems of interpreting the mammograms. In the mammography x-ray film-screen, the contrast between bengm and malignant cancer is not so distinct. This study was performed to help the clinicians interpreting the mammograms by providing fractal dimension of mass, mass and microcalcification, and microcalcification. Raw data of the 60 patients(30 for each group ; 'mass and microcalcifications' and ' microcalcifications' group) were obtained in the conditions of 0.1mm resolution, 12 bit gray scale images. The image enhancement was performed and the fractal dimensions were extracted to represent. The mass showed the smooth shape, however, microcalcification symptom has more rough figures. In conclusion, the calculation of the fractal dimension could improve the early detection of the breast cancer. The fractal dimension could be applied for the diagnosis of the breast cancer.

Is There a Correlation between the Presence of a Spiculated Mass on Mammogram and Luminal A Subtype Breast Cancer?

Song Liu,Xiao-Dong Wu,Wen-Jian Xu,Qing Lin,Xue-Jun Liu,Ying Li 대한영상의학회 2016 Korean Journal of Radiology Vol.17 No.6

Objective: To determine whether the appearance of a spiculated mass on a mammogram is associated with luminal A subtype breast cancer and the factors that may influence the presence or absence of the spiculated mass. Materials and Methods: Three hundred seventeen (317) patients who underwent image-guided or surgical biopsy between December 2014 and April 2015 were included in the study. Radiologists conducted retrospective assessments of the presence of spiculated masses according to the criteria of Breast Imaging Reporting and Data System. We used combinations of estrogen receptor (ER), progesterone receptor (PR), human epithelial growth factor receptor 2 (HER2), and Ki67 as surrogate markers to identify molecular subtypes of breast cancer. Pearson chi-square test was employed to measure statistical significance of correlations. Furthermore, we built a bi-variate logistic regression model to quantify the relative contribution of the factors that may influence the presence or absence of the spiculated mass. Results: Seventy-one percent (71%) of the spiculated masses were classified as luminal A. Masses classified as luminal A were 10.3 times more likely to be presented as spiculated mass on a mammogram than all other subtypes. Patients with low Ki67 index (< 14%) and HER2 negative were most likely to present with a spiculated mass on their mammograms (p < 0.001) than others. The hormone receptor status (ER and PR), pathology grade, overall breast composition, were all associated with the presence of a spiculated mass, but with less weight in contribution than Ki67 and HER2. Conclusion: We observed an association between the luminal A subtype of invasive breast cancer and the presence of a spiculated mass on a mammogram. It is hypothesized that lower Ki67 index and HER2 negativity may be the most significant factors in the presence of a spiculated mass.

토모신테시스의 유방촬영에서의 활용

이미화(Mi-Hwa Lee) 한국콘텐츠학회 2015 한국콘텐츠학회논문지 Vol.15 No.11

본 연구는 기존의 Mammogram와 Tomosynthesis를 비교하여 진단적 가치를 평가하고 피검자의 유선선량을 비교하여 Tomosynthesis의 활용에 대해서 고찰해 보고자 하였다. 2015년 1월 한 달 동안 본원을 내원한 환자 62명을 대상으로 선행 검사를 시행한 후 어떤 병변이 있을 때 추가적으로 Tomosynthesis를 시행하였는지 분석하였다. 유방촬영용 ACR phantom을 이용하였으며 자동 노출이 되도록 설정된 상태에서 촬영한 kVp와 mAs를 기준으로 하여 kVp는 고정하고 mAs를 단계적으로 변화를 주어 유선선량을 분석하였다. 그 결과 Tomosynthesis가 유방 병변 구별에 우수하였으며 2D Mammogram과 비교할 때 확연한 대조도 차이를 보였다. 또한 두 검사의 평균유선선량에서는 Mammogram(1.15 mGy)보다 Tomosynthesis(1.48 mGy)가 0.33 mGy정도 높았으나 추가검사의 불필요함으로 인해 장기적으로는 피폭선량이 감소하는 효과를 보였다. 그러므로 Tomosynthesis는 유방의 진단적 가치를 높임과 동시에 피폭선량을 줄일 수 있는 검사이며 향후 유방질환의 검사에 적합하게 적용되고 응용할 수 있을 것이다. This study evaluated the diagnostic value and compares the Mammogram Tomosynthesis, and as compared to the AGD, was studied with respect to utilization of Tomosynthesis. During January 2015 one month were enrolled patients admitted to 62 people present. The ACR phantom was used. AEC was set to be. kVp is fixed and given a step-by-step changing the mAs analyzed AGD. Tomosynthesis was superior to the distinction of breast lesions when compared with Mammogram showed a noticeable difference in contrast. AGD(Average Glandular Dose) was higher 0.33 mGy. However, in the long run, the dose was reduced. Tomosynthesis is therefore increase the diagnostic value of the breast, a examination that can reduce the dose.

MRT letter: Segmentation and texture‐based classification of breast mammogram images

Naveed, Nawazish,Jaffar, M. Arfan,Choi, Tae‐,Sun Wiley Subscription Services, Inc., A Wiley Company 2011 Microscopy research and technique Vol.74 No.11

<P><B>Abstract</B></P><P>Breast cancer is the most common cancer diagnosed among women. In this article, support vector machine is used to classify digital mammogram images into malignant and benign. Wiener filter is used to handle the possible quantum noise, which is more likely to occur in mammograms. Stack‐based connected component method is proposed for background removal, and the image is enhanced using retinax method. Seeded region growing algorithm is used to remove the pectoral muscle part of the mammogram. We have extracted 13 different multidomains' features for classification. Results show the superiority of the proposed algorithm in terms of sensitivity, specificity, and accuracy. We have used MIAS database of mammography for experimentation. Microsc. Res. Tech., 2011. © 2011 Wiley Periodicals, Inc.</P>

디지털 유방영상에서 멀티영상 기반의 컴퓨터 보조 진단에 관한 연구

최형식,조용호,조백환,문우경,임정기,김인영,김선일,Choi, Hyoung-Sik,Cho, Yong-Ho,Cho, Baek-Hwan,Moon, Woo-Kyoung,Im, Jung-Gi,Kim, In-Young,Kim, Sun-I. 대한의용생체공학회 2007 의공학회지 Vol.28 No.1

For the past decade, the full-field digital mammography has been widely used for early diagnosis of breast cancer, and computer aided diagnosis has been developed to assist physicians as a second opinion. In this study, we try to predict the breast cancer using both mediolateral oblique(MLO) view and craniocaudal(CC) view together. A skilled radiologist selected 35 pairs of ROIs from both MLO view and CC view of digital mammogram. We extracted textural features using Spatial Grey Level Dependence matrix from each mammogram and evaluated the generalization performance of the classifier using Support Vector Machine. We compared the multi-view based classifier to single-view based classifier that is built from each mammogram view. The results represent that the multi-view based computer aided diagnosis in digital mammogram could improve the diagnostic performance and have good possibility for clinical use to assist physicians as a second opinion.

디지털 맘모그램을 위한 비선형 영상 향상 방법

전금상,김상희,Jeon, Geum-Sang,Kim, Sang-Hee 한국융합신호처리학회 2013 융합신호처리학회 논문지 (JISPS) Vol.14 No.1

맘모그램은 유방암의 조기발견을 위해 가장 일반적으로 이용되고 있다 유방암의 정확한 진단과 효율적인 치료를 위하여 많은 영상향상 방법들이 개발되어왔다. 본 논문은 디지털 유방 촬영상의 영상향상을 위하여 새로운 비선형 영상향상 방법을 제안한다. 제안된 방법은 영상의 밝기 정보를 향상시키기 위한 비선형 함수와 경계와 디테일 정보를 개선하기 위한 비선형 필터로 구성된다. 비선형 함수는 영상의 어두운 영역의 밝기를 향상시키고 밝은 영역의 동적범위를 넓혀주며, 비선형 필터는 영상의 특정 영역이나 객체를 효과적으로 개선시킨다. 최종 향상된 영상은 비선형 함수로 처리한 영상과 비선형 필터로 필터된 영상을 더하여 얻어진다. 제안된 비선형 영상향상 방법은 실험에서 기존 방법과 영상향상 결과를 비교하여 우수한 성능을 확인하였다. Mammography is the most common technique for the early detection of breast cancer. To diagnose correctly and treat of breast cancer efficiently, many image enhancement methods have been developed. This paper presents a nonlinear image enhancement method for the enhancement of digital mammogram. The proposed method is composed of a nonlinear function for brightness improvement and a nonlinear filter for contrast enhancement. The nonlinear function improves the brightness of dark area and extends the dynamic range of bright area, and the nonlinear filter efficiently enhances the specific regions and objects of the mammogram. The final enhanced image was obtained by combining the processed image with the nonlinear function and the filtered image with the nonlinear filter. The proposed nonlinear image enhancement method was confirmed the enhanced performance comparing with other existing methods.

Computer-Aided Detection of Breast Masses on Mammograms Using Region-Based Feature Analysis

Jae Young Choi,Dae Hoe Kim,Yong Man Ro 한국멀티미디어학회 2011 한국멀티미디어학회 국제학술대회 Vol.2011 No.-

This paper proposes the effective approach to detecting the masses on mammograms. In particular, to considerably reduce False Positive (FP) detections, the new region-based stellate features are suggested. The experimental results show that our method achieves FP maker rate up to one per image at the sensitivity of 92%.

Diagnostic Yield of Primary Circulating Tumor Cells in Women Suspected of Breast Cancer: the BEST (Breast Early Screening Test) Study

Murray, Nigel P,Miranda, Roxana,Ruiz, Amparo,Droguett, Elsa Asian Pacific Journal of Cancer Prevention 2015 Asian Pacific journal of cancer prevention Vol.16 No.5

Purpose: To determine the diagnostic yield of primary circulating tumor cells in women with suspicion of breast cancer, detected as a result of an abnormal mammography. Materials and Methods: Consecutive women presenting for breast biopsy as a result of a mammogram BiRADs of 3 or more, had an 8ml blood sample taken for primary circulating tumor cell (CTC) detection. Mononuclear cells were obtained using differential gel centrifugation and CTCs identified using standard immunocytochemistry using anti-mammoglobin. A test was determined to be positive if 1 CTC was detected. Results: A total of 144 women with a mean age of $54.7{\pm}15.6$ years participated, 78/144 (53.0%) had breast cancer on biopsy, 65/140 (46.3%) benign pathologies and 1(0.7%) non-Hogkins lymphoma. Increasing BiRADs scores were associated with increased cancer detection (p=0.004, RR 1.00, 4.24, 8.50). CTC mammoglobin positive had a sensitivity of 81.1% and specificity of 90.9%, with positive and negative predictive values of 90.9% and 81.1% respectively. Mammoglobin positive CTCs detected 87% of invasive cancers, while poorly differentiated cancers were negative for mammoglobin. Only 50% of in situ cancers and none of the intraductal cancers had CTCs detected. Menopausal status did not affect the diagnostic yield of the CTC test, which was higher in women with BiRADS 4 mammograms. There was a significant trend (p<0.0001 Chi squared for trends) in CTC detection frequency from intraductal, in situ and invasive (OR 1.00, 8.00, 472.00). Conclusions: The use of primary CTC detection in women suspected of breast cancer has potential uses, especially with invasive cancer, but it failed to detect intra-ductal cancer and 50% of in situ cancer. There was no difference in the diagnostic yield between pre and post menopausal women. To confirm its use in reducing biopsies in women with BIRADs 4a mammagrams and in the detection of interval invasive breast cancer, larger studies are needed.

Mammogram에서 동질성과 지형적 높이정보 해석에 의한 종양의 추출

유승화(Seung-Wha Yoo),김선주(Seon-Joo Kim),김진환(Jin-Hwan Kim) 한국멀티미디어학회 2002 멀티미디어학회논문지 Vol.5 No.2

A Review on Advanced Methodologies to Identify the Breast Cancer Classification using the Deep Learning Techniques

Bandaru, Satish Babu,Babu, G. Rama Mohan International Journal of Computer ScienceNetwork S 2022 International journal of computer science and netw Vol.22 No.4

Breast cancer is among the cancers that may be healed as the disease diagnosed at early times before it is distributed through all the areas of the body. The Automatic Analysis of Diagnostic Tests (AAT) is an automated assistance for physicians that can deliver reliable findings to analyze the critically endangered diseases. Deep learning, a family of machine learning methods, has grown at an astonishing pace in recent years. It is used to search and render diagnoses in fields from banking to medicine to machine learning. We attempt to create a deep learning algorithm that can reliably diagnose the breast cancer in the mammogram. We want the algorithm to identify it as cancer, or this image is not cancer, allowing use of a full testing dataset of either strong clinical annotations in training data or the cancer status only, in which a few images of either cancers or noncancer were annotated. Even with this technique, the photographs would be annotated with the condition; an optional portion of the annotated image will then act as the mark. The final stage of the suggested system doesn't need any based labels to be accessible during model training. Furthermore, the results of the review process suggest that deep learning approaches have surpassed the extent of the level of state-of-of-the-the-the-art in tumor identification, feature extraction, and classification. in these three ways, the paper explains why learning algorithms were applied: train the network from scratch, transplanting certain deep learning concepts and constraints into a network, and (another way) reducing the amount of parameters in the trained nets, are two functions that help expand the scope of the networks. Researchers in economically developing countries have applied deep learning imaging devices to cancer detection; on the other hand, cancer chances have gone through the roof in Africa. Convolutional Neural Network (CNN) is a sort of deep learning that can aid you with a variety of other activities, such as speech recognition, image recognition, and classification. To accomplish this goal in this article, we will use CNN to categorize and identify breast cancer photographs from the available databases from the US Centers for Disease Control and Prevention.