Luan Jiang

Automated detection of breast mass spiculation levels and evaluation of scheme performance.

RATIONALE AND OBJECTIVES Although the spiculation levels of breast mass boundaries are a primary sign of malignancy for masses detected on mammography, developing an automated computerized method to detect spiculation levels and quantitatively evaluating the performance of such a method is a difficult task. The objectives of this study were to (1) develop and test a new method to improve mass segmentation and detect mass boundary spiculation levels and (2) assess the performance of this method using a relatively large imaging data set. MATERIALS AND METHODS The fully automated method developed for this study includes three image-processing steps. In the first step, the principle of maximum entropy is applied in the selected region of interest (ROI) after correcting the background trend to enhance the initial outlines of a mass. In the second step, an active-contour model is used to refine the initial outlines. In the third step, spiculated lines connected to the mass boundary are detected and identified using a special line detector. A quantitative spiculation index is computed to assess the degree of spiculation. To develop and evaluate this automated method, 211 ROIs depicting masses were extracted from a publicly available image database. Among these ROIs, 106 depicted circumscribed mass regions and 105 involved spiculated mass regions. The performance of the method was evaluated using receiver-operating characteristic (ROC) analysis. RESULTS The computed area under the ROC curve, when applying the method to the data set, was 0.701 +/- 0.027. By setting up a threshold at a spiculation index of 5.0, the method achieved an overall classification accuracy of 66.4%, with 54.3% sensitivity and 78.3% specificity. CONCLUSIONS In this study, a new computerized method with a number of unique characteristics was developed to detect spiculated mass regions, and a simple spiculation index was applied to quantify mass spiculation levels. Although this quantitative index can be used to distinguish between spiculated and circumscribed masses, the results also suggest that the automated detection of mass spiculation levels remains a technical challenge.

Quantitative assessment of background parenchymal enhancement in breast magnetic resonance images predicts the risk of breast cancer

The objective of this study was to evaluate the association betweenthe quantitative assessment of background parenchymal enhancement rate (BPER) and breast cancer. From 14,033 consecutive patients who underwent breast MRI in our center, we randomly selected 101 normal controls. Then, we selected 101 women with benign breast lesions and 101 women with breast cancer who were matched for age and menstruation status. We evaluated BPER at early (2 minutes), medium (4 minutes) and late (6 minutes) enhanced time phases of breast MRI for quantitative assessment. Odds ratios (ORs) for risk of breast cancer were calculated using the receiver operating curve. The BPER increased in a time-dependent manner after enhancement in both premenopausal and postmenopausal women. Premenopausal women had higher BPER than postmenopausal women at early, medium and late enhanced phases. In the normal population, the OR for probability of breast cancer for premenopausal women with high BPER was 4.1 (95% CI: 1.7–9.7) and 4.6 (95% CI: 1.7–12.0) for postmenopausal women. The OR of breast cancer morbidity in premenopausal women with high BPER was 2.6 (95% CI: 1.1–6.4) and 2.8 (95% CI: 1.2–6.1) for postmenopausal women. The BPER was found to be a predictive factor of breast cancer morbidity. Different time phases should be used to assess BPER in premenopausal and postmenopausal women.

Computer-aided detection of mammographic masses based on content-based image retrieval

A method for computer-aided detection (CAD) of mammographic masses is proposed and a prototype CAD system is presented. The method is based on content-based image retrieval (CBIR). A mammogram database containing 2000 mammographic regions is built in our prototype CBIR-CAD system. Every region of interested (ROI) in the database has known pathology. Specifically, there are 583 ROIs depicting biopsy-proven masses, and the rest 1417 ROIs are normal. Whenever a suspicious ROI is detected in a mammogram by a radiologist, it can be submitted as a query to this CBIRCAD system. As the query results, a series of similar ROI images together with their known pathology knowledge will be retrieved from the database and displayed in the screen in descending order of their similarities to the query ROI to help the radiologist to make the diagnosis decision. Furthermore, our CBIR-CAD system will output a decision index (DI) to quantitatively indicate the probability that the query ROI contains a mass. The DI is calculated by the query matches. In the querying process, 24 features are extracted from each ROI to form a 24-dimensional vector. Euclidean distance in the 24-dimensional feature vector space is applied to measure the similarities between ROIs. The prototype CBIR-CAD system is evaluated based on the leave-one-out sampling scheme. The experiment results showed that the system can achieve a receiver operating characteristic (ROC) area index AZ =0.84 for detection of mammographic masses, which is better than the best results achieved by the other known mass CAD systems.

Fully automated segmentation of whole breast using dynamic programming in dynamic contrast enhanced MR images

Purpose Amount of fibroglandular tissue (FGT) and level of background parenchymal enhancement (BPE) in breast dynamic contrast enhanced magnetic resonance images (DCE‐MRI) are suggested as strong indices for assessing breast cancer risk. Whole breast segmentation is the first important task for quantitative analysis of FGT and BPE in three‐dimensional (3‐D) DCE‐MRI. The purpose of this study is to develop and evaluate a fully automated technique for accurate segmentation of the whole breast in 3‐D fat‐suppressed DCE‐MRI. Methods The whole breast segmentation consisted of two major steps, i.e., the delineation of chest wall line and breast skin line. First, a sectional dynamic programming method was employed to trace the upper and/or lower boundaries of the chest wall by use of the positive and/or negative gradient within a band along the chest wall in each 2‐D slice. Second, another dynamic programming was applied to delineate the skin‐air boundary slice‐by‐slice based on the saturated gradient of the enhanced image obtained with the prior statistical distribution of gray levels of the breast skin line. Starting from the central slice, these two steps employed a Gaussian function to limit the search range of boundaries in adjacent slices based on the continuity of chest wall line and breast skin line. Finally, local breast skin line detection was applied around armpit to complete the whole breast segmentation. The method was validated with a representative dataset of 100 3‐D breast DCE‐MRI scans through objective quantification and subjective evaluation. The MR scans in the dataset were acquired with four MR scanners in five spatial resolutions. The cases were assessed with four breast density ratings by radiologists based on Breast Imaging Reporting and Data System (BI‐RADS) of American College of Radiology. Results Our segmentation algorithm achieved a Dice volume overlap measure of 95.8 ± 1.2% and volume difference measure of 8.4 ± 2.4% between the automatically and manually segmented breast regions. Moreover, the root‐mean‐square distances between the automatically and manually segmented boundaries for the chest wall line and the breast skin line were 0.40 ± 0.15 mm and 0.89 ± 0.21 mm respectively. The segmentation algorithm took approximately 1.0 min to segment the breasts in a MR scan of 160 slices. Conclusions Our fully automated method could robustly achieve high segmentation accuracy and efficiency. It would be useful for developing CAD systems for quantitative analysis of FGT and BPE in 3‐D DCE‐MRI.

Fully automated segmentation of left ventricle using dual dynamic programming in cardiac cine MR images

Cardiovascular diseases are becoming a leading cause of death all over the world. The cardiac function could be evaluated by global and regional parameters of left ventricle (LV) of the heart. The purpose of this study is to develop and evaluate a fully automated scheme for segmentation of LV in short axis cardiac cine MR images. Our fully automated method consists of three major steps, i.e., LV localization, LV segmentation at end-diastolic phase, and LV segmentation propagation to the other phases. First, the maximum intensity projection image along the time phases of the midventricular slice, located at the center of the image, was calculated to locate the region of interest of LV. Based on the mean intensity of the roughly segmented blood pool in the midventricular slice at each phase, end-diastolic (ED) and end-systolic (ES) phases were determined. Second, the endocardial and epicardial boundaries of LV of each slice at ED phase were synchronously delineated by use of a dual dynamic programming technique. The external costs of the endocardial and epicardial boundaries were defined with the gradient values obtained from the original and enhanced images, respectively. Finally, with the advantages of the continuity of the boundaries of LV across adjacent phases, we propagated the LV segmentation from the ED phase to the other phases by use of dual dynamic programming technique. The preliminary results on 9 clinical cardiac cine MR cases show that the proposed method can obtain accurate segmentation of LV based on subjective evaluation.

Fully automated segmentation of whole breast in MR images by use of dynamic programming

Breast segmentation is an important and challenging task for computerized analysis of background parenchymal enhancement (BPE) in dynamic contrast enhanced magnetic resonance images (DCE-MRI). The purpose of this study is to develop and evaluate a fully automated technique for accurate segmentation of whole breast in three-dimensional (3-D) DCE-MRI. The whole breast segmentation consists of two steps, i.e., the delineation of the chest wall and breast skin line. A sectional dynamic programming method was first designed in each 2-D slice to trace the upper and/or lower boundaries of the chest wall. The statistical distribution of gray levels of the breast skin line was employed as weighting factor to enhance the skin line, and dynamic programming was then applied to delineate breast skin line slice-by-slice within the automatically extracted volume of interest (VOI). Our method also took advantages of the continuity of chest wall and skin line across adjacent slices. Finally, the segmented breast skin line and the detected chest wall were connected to create the whole breast segmentation. The preliminary results on 70 cases show that the proposed method can obtain accurate segmentation of whole breast based on subjective observation. With the manually delineated region of 16 breasts in 8 cases, our method achieved Dice overlap measure of 92.1% ± 1.9% (mean ± SD) and volume agreement of 91.6% ± 4.7% for whole breast segmentation. It took approximately 4 minutes and 2.5 minutes for our method to segment the breast in an MR scan of 160 slices and 108 slices, respectively.

Mass edge detection in mammography based on plane fitting and dynamic programming

In this paper an automatic and effective method was proposed for mass segmentation in mammography. Based on the facts that mass edges are continuous and closed curves consisted of points which have larger gradient transformation, a plane fitting method and a dynamic programming technique were applied. The regions of interest (ROIs) used in this study were extracted from DDSM. The preliminary experimental results show that the segmentation algorithm performs well for various types of masses.

Association Between Background Parenchymal Enhancement and Pathologic Complete Remission Throughout the Neoadjuvant Chemotherapy in Breast Cancer Patients

PURPOSE: To retrospectively investigate the quantitative background parenchymal enhancement (BPE) of the contralateral normal breast in patients with unilateral invasive breast cancer throughout multiple monitoring points of neoadjuvant chemotherapy (NAC) and to further determine whether BPE is associated with tumor response, especially at the early stage of NAC. MATERIALS AND METHODS: A total of 90 patients with unilateral breast cancer who then received six or eight cycles of NAC before surgery were analyzed retrospectively. BPE was measured in dynamic contrast-enhanced MRI at baseline and after 2nd, 4th, and 6th NAC, respectively. Correlation between BPE and tumor size was analyzed, and the association between pathologic complete remission (pCR) and BPE was also analyzed. RESULTS: The BPE of contralateral normal breast showed a constant reduction throughout NAC therapy regardless of the menopausal status (P < .001 in all). Both the BPEs and the changes of BPE in each of the three monitoring points were significantly correlated with those in tumor size (P < .05 in all), and the reduction of BPE after 2nd NAC had the largest diagnostic value for pCR (AUC = 0.726, P < .001), particularly in hormonal receptor (HR)-negative patients (OR = 0.243, 95%CI = 0.083 to 0.706, P = .009). CONCLUSION: The BPE of contralateral normal breast had a constant decreased tendency similar to the change of tumor size in NAC. Reduction of BPE at the early stage of NAC was positively associated with pCR, especially in HR-negative status.

Fully automated quantitative analysis of breast cancer risk in DCE-MR images

Amount of fibroglandular tissue (FGT) and background parenchymal enhancement (BPE) in dynamic contrast enhanced magnetic resonance (DCE-MR) images are two important indices for breast cancer risk assessment in the clinical practice. The purpose of this study is to develop and evaluate a fully automated scheme for quantitative analysis of FGT and BPE in DCE-MR images. Our fully automated method consists of three steps, i.e., segmentation of whole breast, fibroglandular tissues, and enhanced fibroglandular tissues. Based on the volume of interest extracted automatically, dynamic programming method was applied in each 2-D slice of a 3-D MR scan to delineate the chest wall and breast skin line for segmenting the whole breast. This step took advantages of the continuity of chest wall and breast skin line across adjacent slices. We then further used fuzzy c-means clustering method with automatic selection of cluster number for segmenting the fibroglandular tissues within the segmented whole breast area. Finally, a statistical method was used to set a threshold based on the estimated noise level for segmenting the enhanced fibroglandular tissues in the subtraction images of pre- and post-contrast MR scans. Based on the segmented whole breast, fibroglandular tissues, and enhanced fibroglandular tissues, FGT and BPE were automatically computed. Preliminary results of technical evaluation and clinical validation showed that our fully automated scheme could obtain good segmentation of the whole breast, fibroglandular tissues, and enhanced fibroglandular tissues to achieve accurate assessment of FGT and BPE for quantitative analysis of breast cancer risk.

Breast segmentation in MR images using three-dimensional spiral scanning and dynamic programming

Magnetic resonance (MR) imaging has been widely used for risk assessment and diagnosis of breast cancer in clinic. To develop a computer-aided diagnosis (CAD) system, breast segmentation is the first important and challenging task. The accuracy of subsequent quantitative measurement of breast density and abnormalities depends on accurate definition of the breast area in the images. The purpose of this study is to develop and evaluate a fully automated method for accurate segmentation of breast in three-dimensional (3-D) MR images. A fast method was developed to identify bounding box, i.e., the volume of interest (VOI), for breasts. A 3-D spiral scanning method was used to transform the VOI of each breast into a single two-dimensional (2-D) generalized polar-coordinate image. Dynamic programming technique was applied to the transformed 2-D image for delineating the “optimal” contour of the breast. The contour of the breast in the transformed 2-D image was utilized to reconstruct the segmentation results in the 3-D MR images using interpolation and lookup table. The preliminary results on 17 cases show that the proposed method can obtain accurate segmentation of the breast based on subjective observation. By comparing with the manually delineated region of 16 breasts in 8 cases, an overlap index of 87.6% ± 3.8% (mean ± SD), and a volume agreement of 93.4% ± 4.5% (mean ± SD) were achieved, respectively. It took approximately 3 minutes for our method to segment the breast in an MR scan of 256 slices.