Jiazheng Shi

Pulmonary nodule registration in serial CT scans based on rib anatomy and nodule template matching.

An automated method is being developed in order to identify corresponding nodules in serial thoracic CT scans for interval change analysis. The method uses the rib centerlines as the reference for initial nodule registration. A spatially adaptive rib segmentation method first locates the regions where the ribs join the spine, which define the starting locations for rib tracking. Each rib is tracked and locally segmented by expectation-maximization. The ribs are automatically labeled, and the centerlines are estimated using skeletonization. For a given nodule in the source scan, the closest three ribs are identified. A three-dimensional (3D) rigid affine transformation guided by simplex optimization aligns the centerlines of each of the three rib pairs in the source and target CT volumes. Automatically defined control points along the centerlines of the three ribs in the source scan and the registered ribs in the target scan are used to guide an initial registration using a second 3D rigid affine transformation. A search volume of interest (VOI) is then located in the target scan. Nodule candidate locations within the search VOI are identified as regions with high Hessian responses. The initial registration is refined by searching for the maximum cross-correlation between the nodule template from the source scan and the candidate locations. The method was evaluated on 48 CT scans from 20 patients. Experienced radiologists identified 101 pairs of corresponding nodules. Three metrics were used for performance evaluation. The first metric was the Euclidean distance between the nodule centers identified by the radiologist and the computer registration, the second metric was a volume overlap measure between the nodule VOIs identified by the radiologist and the computer registration, and the third metric was the hit rate, which measures the fraction of nodules whose centroid computed by the computer registration in the target scan falls within the VOI identified by the radiologist. The average Euclidean distance error was 2.7 +/- 3.3 mm. Only two pairs had an error larger than 10 mm. The average volume overlap measure was 0.71 +/- 0.24. Eighty-three of the 101 pairs had ratios larger than 0.5, and only two pairs had no overlap. The final hit rate was 93/101.

The effect of nodule segmentation on the accuracy of computerized lung nodule detection on CT scans: comparison on a data set annotated by multiple radiologists

In computerized nodule detection systems on CT scans, many features that are useful for classifying whether a nodule candidate identified by prescreening is a true positive depend on the shape of the segmented object. We designed two segmentation algorithms for detailed delineation of the boundaries for nodule candidates. The first segmentation technique was a three-dimensional (3D) region-growing (RG) method which grew the object across multiple CT sections. The second technique was based on a 3D active contour (AC) model. A training set of 94 CT scans was used for algorithm design. An independent set of 62 scans, each read by multiple radiologists, was used for testing. Thirty-three scans were collected from patient files at the University of Michigan and 29 scans by the Lung Imaging Database Consortium (LIDC). In this study, we concentrated on the detection of internal lung nodules having a size ≥3 mm that were not pure ground-glass opacities. Of the lesions marked by one or multiple radiologists, 124 nodules satisfied these criteria and were considered true nodules. The performance of the detection system in the AC feature space, RG feature space, and the combined feature space were compared using free-response receiver operating curves (FROC). The FROC curve using the combined feature space was significantly higher than that using the RG feature space or the AC feature space alone (p=0.02 and 0.03, respectively). At a sensitivity of 70% for internal non-GGO nodules, the FP rates were 2.2, 2.2, and 1.5 per scan, respectively, for the RG, AC, and the combined methods. Our results indicate that the 3D AC algorithm can provide useful features to improve nodule detection on CT scans.

Treatment response assessment of breast masses on dynamic contrast-enhanced magnetic resonance scans using fuzzy c-means clustering and level set segmentation

The goal of this study was to develop an automated method to segment breast masses on dynamic contrast-enhanced (DCE) magnetic resonance (MR) scans and to evaluate its potential for estimating tumor volume on pre- and postchemotherapy images and tumor change in response to treatment. A radiologist experienced in interpreting breast MR scans defined a cuboid volume of interest (VOI) enclosing the mass in the MR volume at one time point within the sequence of DCE-MR scans. The corresponding VOIs over the entire time sequence were then automatically extracted. A new 3D VOI representing the local pharmacokinetic activities in the VOI was generated from the 4D VOI sequence by summarizing the temporal intensity enhancement curve of each voxel with its standard deviation. The method then used the fuzzy c-means (FCM) clustering algorithm followed by morphological filtering for initial mass segmentation. The initial segmentation was refined by the 3D level set (LS) method. The velocity field of the LS method was formulated in terms of the mean curvature which guaranteed the smoothness of the surface, the Sobel edge information which attracted the zero LS to the desired mass margin, and the FCM membership function which improved segmentation accuracy. The method was evaluated on 50 DCE-MR scans of 25 patients who underwent neoadjuvant chemotherapy. Each patient had pre- and postchemotherapy DCE-MR scans on a 1.5 T magnet. The in-plane pixel size ranged from 0.546 to 0.703 mm and the slice thickness ranged from 2.5 to 4.5 mm. The flip angle was 15 degrees, repetition time ranged from 5.98 to 6.7 ms, and echo time ranged from 1.2 to 1.3 ms. Computer segmentation was applied to the coronal T1-weighted images. For comparison, the same radiologist who marked the VOI also manually segmented the mass on each slice. The performance of the automated method was quantified using an overlap measure, defined as the ratio of the intersection of the computer and the manual segmentation volumes to the manual segmentation volume. Pre- and postchemotherapy masses had overlap measures of 0.81 +/- 0.13 (mean +/- s.d.) and 0.71 +/- 0.22, respectively. The percentage volume reduction (PVR) estimated by computer and the radiologist were 55.5 +/- 43.0% (mean +/- s.d.) and 57.8 +/- 51.3%, respectively. Paired Students t test indicated that the difference between the mean PVRs estimated by computer and the radiologist did not reach statistical significance (p = 0.641). The automated mass segmentation method may have the potential to assist physicians in monitoring volume change in breast masses in response to treatment.

Automated detection of breast vascular calcification on full-field digital mammograms

Breast vascular calcifications (BVCs) are calcifications that line the blood vessel walls in the breast and appear as parallel or tubular tracks on mammograms. BVC is one of the major causes of the false positive (FP) marks from computer-aided detection (CADe) systems for screening mammography. With the detection of BVCs and the calcified vessels identified, these FP clusters can be excluded. Moreover, recent studies reported the increasing interests in the correlation between mammographically visible BVCs and the risk of coronary artery diseases. In this study, we developed an automated BVC detection method based on microcalcification prescreening and a new k-segments clustering algorithm. The mammogram is first processed with a difference-image filtering technique designed to enhance calcifications. The calcification candidates are selected by an iterative process that combines global thresholding and local thresholding. A new k-segments clustering algorithm is then used to find a set of line segments that may be caused by the presence of calcified vessels. A linear discriminant analysis (LDA) classifier was designed to reduce false segments that are not associated with BVCs. Four features for each segment selected with stepwise feature selection were used for this LDA classification. Finally, the neighboring segments were linked and dilated with morphological dilation to cover the regions of calcified vessels. A data set of 16 FFDM cases with vascular calcifications was collected for this preliminary study. Our preliminary result demonstrated that breast vascular calcifications can be accurately detected and the calcified vessels identified. It was found that the automated method can achieve a detection sensitivity of 65%, 70%, and 75% at 6.1 mm, 8.4 mm, and 12.6mm FP segments/image, respectively, without any true clustered microcalcifications being falsely marked. Further work is underway to improve this method and to incorporate it into our FFDM CADe system.

Truncation artifact and boundary artifact reduction in breast tomosynthesis reconstruction

Digital Tomosynthesis Mammography (DTM) is an emerging technique that has the potential to improve breast cancer detection. DTM acquires low-dose mammograms at a number of projection angles over a limited angular range and reconstructs the 3D breast volume. Due to the limited number of projections within a limited angular range and the finite size of the detector, DTM reconstruction contains boundary and truncation artifacts that degrade the image quality of the tomosynthesized slices, especially that of the boundary and truncated regions. In this work, we developed artifact reduction methods that make use of both 2D and 3D breast boundary information and local intensity-equalization and tissue-compensation techniques. A breast phantom containing test objects and a selected DTM patient case were used to evaluate the effects of artifact reduction. The contrast-to-noise ratio (CNR), the normalized profiles of test objects, and a non-uniformity error index were used as performance measures. A GE prototype DTM system was used to acquire 21 PVs in 3° increments over a ±30° angular range. The Simultaneous Algebraic Reconstruction Technique (SART) was used for DTM reconstruction. Our results demonstrated that the proposed methods can improve the image quality both qualitatively and quantitatively, resulting in increased CNR value, background uniformity and an overall reconstruction quality comparable to that without truncation. For the selected DTM patient case, the obscured breast structural information near the truncated regions was essentially recovered. In addition, restricting SART reconstruction to be performed within the estimated 3D breast volume increased the computation efficiency.

A dynamic multiple thresholding method for automated breast boundary detection in digitized mammograms

We have previously developed a breast boundary detection method by using a gradient-based method to search for the breast boundary (GBB). In this study, we developed a new dynamic multiple thresholding based breast boundary detection system (MTBB). The initial breast boundary (MTBB-Initial) is obtained based on the analysis of multiple thresholds on the image. The final breast boundary (MTBB-Final) is obtained based on the initial breast boundary and the gradient information from horizontal and the vertical Sobel filtering. In this way, it is possible to accurately segment the breast area from the background region. The accuracy of the breast boundary detection algorithm was evaluated by comparison with an experienced radiologists manual segmentation using three performance metrics: the Hausdorff distance (HDist), the average minimum Euclidean distance (AMinDist), and the area overlap (AOM). It was found that 68%, 85%, and 90% of images have HDist errors less than 6 mm for GBB, MTBB-Initial, and MTBB-Final, respectively. Ninety-five percent, 96%, and 97% of the images have AMinDist errors less than 1.5 mm for GBB, MTBB-Initial, and MTBB-Final, respectively. Ninety-six percent, 97%, and 99% of the images have AOM values larger than 0.9 for GBB, MTBB-Initial, and MTBB-Final, respectively. It was found that the performance of the proposed method was improved in comparison to our previous method.

Breast mass segmentation on dynamic contrast-enhanced magnetic resonance scans using the level set method

The goal of this study was to develop an automated method to segment breast masses on dynamic contrast-enhanced (DCE) magnetic resonance (MR) scans that were performed to monitor breast cancer response to neoadjuvant chemotherapy. A radiologist experienced in interpreting breast MR scans defined the mass using a cuboid volume of interest (VOI). Our method then used the K-means clustering algorithm followed by morphological operations for initial mass segmentation on the VOI. The initial segmentation was then refined by a three-dimensional level set (LS) method. The velocity field of the LS method was formulated in terms of the mean curvature which guaranteed the smoothness of the surface and the Sobel edge information which attracted the zero LS to the desired mass margin. We also designed a method to reduce segmentation leak by adapting a region growing technique. Our method was evaluated on twenty DCE-MR scans of ten patients who underwent neoadjuvant chemotherapy. Each patient had pre- and post-chemotherapy DCE-MR scans on a 1.5 Tesla magnet. Computer segmentation was applied to coronal T1-weighted images. The in-plane pixel size ranged from 0.546 to 0.703 mm and the slice thickness ranged from 2.5 to 4.0 mm. The flip angle was 15 degrees, repetition time ranged from 5.98 to 6.7 ms, and echo time ranged from 1.2 to 1.3 ms. The computer segmentation results were compared to the radiologists manual segmentation in terms of the overlap measure defined as the ratio of the intersection of the computer and the radiologists segmentations to the radiologists segmentation. Pre- and post-chemotherapy masses had overlap measures of 0.81±0.11 (mean±s.d.) and 0.70±0.21, respectively.

Comparison of Mammographic Parenchymal Patterns of Normal Subjects and Breast Cancer Patients

In this study, we compared the texture features of mammographic parenchymal patterns (MPPs) of normal subjects and breast cancer patients and evaluated whether a texture classifier can differentiate their MPPs. The breast image was first segmented from the surrounding image background by boundary detection. Regions of interest (ROIs) were extracted from the segmented breast area in the retroareolar region on the cranio-caudal (CC) view mammograms. A mass set (MS) of ROIs was extracted from the mammograms with cancer, but ROIs overlapping with the mass were excluded. A contralateral set (CS) of ROIs was extracted from the contralateral mammograms. A normal set (NS) of ROIs was extracted from one CC view mammogram of the normal subjects. Each data set was randomly separated into two independent subsets for 2-fold cross-validation training and testing. Texture features from run-length statistics (RLS) and newly developed region-size statistics (RSS) were extracted to characterize the MPP of the breast. Linear discriminant analysis (LDA) was performed to compare the MPP difference in each of the three pairs: MS-vs-NS, CS-vs-NS, and MS-vs-CS. The Az values for the three pairs were 0.79, 0.73, and 0.56, respectively. These results indicate that the MPPs of the contralateral breast of breast cancer patients exhibit textures comparable to that of the affected breast and that the MPPs of cancer patients are different from those of normal subjects.

Breast Mass Classification on Full-Field Digital Mammography and Screen-Film Mammography

Studies have shown that full-field digital mammography (FFDM) has the potential to alleviate some of the limitations of screen-film mammography (SFM). It is therefore important to develop computer-aided diagnosis (CAD) systems for FFDM or adapt CAD systems developed for SFM to FFDM. The purpose of this study was to evaluate the performance of a CAD system, originally developed for characterization of breast masses on SFM, on a data set of masses acquired with FFDM. The performance on the FFDM set was compared to that on the corresponding masses on SFM of the same patients acquired within six months of the FFDM exam. The CAD system was trained on an SFM data set with 397 biopsy-proven masses (187 malignant and 210 benign) in 868 regions of interest (ROIs) (437 malignant and 431 benign). Four computer-extracted mammographic features and the patient age were selected as input predictor variables to two classification methods: linear discriminant analysis (LDA) and C5.0 decision tree (DT). The trained CAD systems were fixed and tested on an independent FFDM data set with 122 biopsy-proven masses (29 malignant and 93 benign) in 238 ROIs (60 malignant and 178 benign) and on the corresponding SFM data set. Receiver operating characteristic (ROC) analysis indicated that the CAD system using the LDA classifier achieved view-based test Az values of 0.81±0.03 and 0.82±0.03 for SFM and FFDM, respectively. The case-based test Az values with the same classifier were 0.82±0.04 for SFM and 0.88±0.03 for FFDM. The difference in the Az values between the two modalities did not achieve statistical significance (p=0.62 and p=0.13 for view-based and case-based evaluation, respectively). The use of the DT classifier resulted in a slight increase in performance for both modalities, with view-based Az values of 0.82±0.03 and 0.83±0.03 for SFM and FFDM, respectively.

Design and evaluation of a new automated method for the segmentation and characterization of masses on ultrasound images

Segmentation of masses is the first step in most computer-aided diagnosis (CAD) systems for characterization of breast masses as malignant or benign. In this study, we designed an automated method for segmentation of masses on ultrasound (US) images. The method automatically estimated an initial contour based on a manually-identified point approximately at the mass center. A two-stage active contour (AC) method iteratively refined the initial contour and performed self-examination and correction on the segmentation result. To evaluate our method, we compared it with manual segmentation by an experienced radiologists (R1) on a data set of 226 US images containing biopsy-proven masses from 121 patients (44 malignant and 77 benign). Four performance measures were used to evaluate the segmentation accuracy; two measures were related to the overlap between the computer and radiologist segmentation, and two were related to the area difference between the two segmentation results. To compare the difference between the segmentation results by the computer and R1 to inter-observer variation, a second radiologist (R2) also manually segmented all masses. The two overlap measures between the segmentation results by the computer and R1 were 0.87+ 0.16 and 0.73+ 0.17 respectively, indicating a high agreement. However, the segmentation results between two radiologists were more consistent. To evaluate the effect of the segmentation method on classification accuracy, three feature spaces were formed by extracting texture, width-to-height, and posterior shadowing features using the computer segmentation, R1s manual segmentation, and R2s manual segmentation. A linear discriminant analysis classifier using stepwise feature selection was tested and trained by a leave-one-case-out method to characterize the masses as malignant or benign. For case-based classification, the area Az under the test receiver operating characteristic (ROC) curve was 0.90±0.03, 0.87±0.03 and 0.87±0.03 for the feature sets based on computer segmentation, R1s manual segmentation, and R2s manual segmentation, respectively.