1
|
Automated Segmentation of Mass Regions in DBT Images Using a Dilated DCNN Approach. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2022; 2022:9082694. [PMID: 35154309 PMCID: PMC8828338 DOI: 10.1155/2022/9082694] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/06/2021] [Revised: 01/02/2022] [Accepted: 01/15/2022] [Indexed: 11/25/2022]
Abstract
To overcome the limitations of conventional breast screening methods based on digital mammography, a quasi-3D imaging technique, digital breast tomosynthesis (DBT) has been developed in the field of breast cancer screening in recent years. In this work, a computer-aided architecture for mass regions segmentation in DBT images using a dilated deep convolutional neural network (DCNN) is developed. First, to improve the low contrast of breast tumour candidate regions and depress the background tissue noise in the DBT image effectively, the constraint matrix is established after top-hat transformation and multiplied with the DBT image. Second, input image patches are generated, and the data augmentation technique is performed to create the training data set for training a dilated DCNN architecture. Then the mass regions in DBT images are preliminarily segmented; each pixel is divided into two different kinds of labels. Finally, the postprocessing procedure removes all false-positives regions with less than 50 voxels. The final segmentation results are obtained by smoothing the boundaries of the mass regions with a median filter. The testing accuracy (ACC), sensitivity (SEN), and the area under the receiver operating curve (AUC) are adopted as the evaluation metrics, and the ACC, SEN, as well as AUC are 86.3%, 85.6%, and 0.852 for segmenting the mass regions in DBT images on the entire data set, respectively. The experimental results indicate that our proposed approach achieves promising results compared with other classical CAD-based frameworks.
Collapse
|
2
|
Lai X, Yang W, Li R. DBT Masses Automatic Segmentation Using U-Net Neural Networks. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2020; 2020:7156165. [PMID: 32411285 PMCID: PMC7204342 DOI: 10.1155/2020/7156165] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/12/2019] [Revised: 12/17/2019] [Accepted: 12/18/2019] [Indexed: 12/02/2022]
Abstract
To improve the automatic segmentation accuracy of breast masses in digital breast tomosynthesis (DBT) images, we propose a DBT mass automatic segmentation algorithm by using a U-Net architecture. Firstly, to suppress the background tissue noise and enhance the contrast of the mass candidate regions, after the top-hat transform of DBT images, a constraint matrix is constructed and multiplied with the DBT image. Secondly, an efficient U-Net neural network is built and image patches are extracted before data augmentation to establish the training dataset to train the U-Net model. And then the presegmentation of the DBT tumors is implemented, which initially classifies per pixel into two different types of labels. Finally, all regions smaller than 50 voxels considered as false positives are removed, and the median filter smoothes the mass boundaries to obtain the final segmentation results. The proposed method can effectively improve the performance in the automatic segmentation of the masses in DBT images. Using the detection Accuracy (Acc), Sensitivity (Sen), Specificity (Spe), and area under the curve (AUC) as evaluation indexes, the Acc, Sen, Spe, and AUC for DBT mass segmentation in the entire experimental dataset is 0.871, 0.869, 0.882, and 0.859, respectively. Our proposed U-Net-based DBT mass automatic segmentation system obtains promising results, which is superior to some classical architectures, and may be expected to have clinical application prospects.
Collapse
Affiliation(s)
- Xiaobo Lai
- College of Medical Technology, Zhejiang Chinese Medical University, Hangzhou 310053, China
| | - Weiji Yang
- College of Life Science, Zhejiang Chinese Medical University, Hangzhou 310053, China
| | - Ruipeng Li
- Hangzhou Third People's Hospital, Hangzhou 310009, China
| |
Collapse
|
3
|
Models of breast lesions based on three-dimensional X-ray breast images. Phys Med 2019; 57:80-87. [DOI: 10.1016/j.ejmp.2018.12.012] [Citation(s) in RCA: 15] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/11/2018] [Revised: 11/30/2018] [Accepted: 12/17/2018] [Indexed: 02/08/2023] Open
|
4
|
Lee J, Nishikawa RM, Reiser I, Boone JM. Neutrosophic segmentation of breast lesions for dedicated breast computed tomography. J Med Imaging (Bellingham) 2018; 5:014505. [PMID: 29541650 PMCID: PMC5839418 DOI: 10.1117/1.jmi.5.1.014505] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2017] [Accepted: 02/12/2018] [Indexed: 11/14/2022] Open
Abstract
We proposed the neutrosophic approach for segmenting breast lesions in breast computed tomography (bCT) images. The neutrosophic set considers the nature and properties of neutrality (or indeterminacy). We considered the image noise as an indeterminate component while treating the breast lesion and other breast areas as true and false components. We iteratively smoothed and contrast-enhanced the image to reduce the noise level of the true set. We then applied one existing algorithm for bCT images, the RGI segmentation, on the resulting noise-reduced image to segment the breast lesions. We compared the segmentation performance of the proposed method (named as NS-RGI) to that of the regular RGI segmentation. We used 122 breast lesions (44 benign and 78 malignant) of 111 noncontrast enhanced bCT cases. We measured the segmentation performances of the NS-RGI and the RGI using the Dice coefficient. The average Dice values of the NS-RGI and RGI were 0.82 and 0.80, respectively, and their difference was statistically significant ([Formula: see text]). We conducted a subsequent feature analysis on the resulting segmentations. The classifier performance for the NS-RGI ([Formula: see text]) improved over that of the RGI ([Formula: see text], [Formula: see text]).
Collapse
Affiliation(s)
- Juhun Lee
- University of Pittsburgh, Department of Radiology, Pittsburgh, Pennsylvania, United States
| | - Robert M. Nishikawa
- University of Pittsburgh, Department of Radiology, Pittsburgh, Pennsylvania, United States
| | - Ingrid Reiser
- University of Chicago, Department of Radiology, Chicago, Illinois, United States
| | - John M. Boone
- University of California Davis Medical Center, Department of Radiology, Sacramento, California, United States
| |
Collapse
|
5
|
Janaki SD, Geetha K. Automatic segmentation of lesion from breast DCE-MR image using artificial fish swarm optimization algorithm. POLISH JOURNAL OF MEDICAL PHYSICS AND ENGINEERING 2017. [DOI: 10.1515/pjmpe-2017-0006] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
Abstract
Interpreting Dynamic Contrast-Enhanced (DCE) MR images for signs of breast cancer is time consuming and complex, since the amount of data that needs to be examined by a radiologist in breast DCE-MRI to locate suspicious lesions is huge. Misclassifications can arise from either overlooking a suspicious region or from incorrectly interpreting a suspicious region. The segmentation of breast DCE-MRI for suspicious lesions in detection is thus attractive, because it drastically decreases the amount of data that needs to be examined. The new segmentation method for detection of suspicious lesions in DCE-MRI of the breast tissues is based on artificial fishes swarm clustering algorithm is presented in this paper. Artificial fish swarm optimization algorithm is a swarm intelligence algorithm, which performs a search based on population and neighborhood search combined with random search. The major criteria for segmentation are based on the image voxel values and the parameters of an empirical parametric model of segmentation algorithms. The experimental results show considerable impact on the performance of the segmentation algorithm, which can assist the physician with the task of locating suspicious regions at minimal time.
Collapse
Affiliation(s)
- Sathya D. Janaki
- Department of Electrical & Electronics Engineering, PSG College of Technology, Coimbatore , India
| | - K. Geetha
- Department of Electrical & Electronics Engineering, Karpagam Institute of Technology, Coimbatore , India
| |
Collapse
|
6
|
Lee J, Nishikawa RM, Reiser I, Boone JM. Optimal reconstruction and quantitative image features for computer-aided diagnosis tools for breast CT. Med Phys 2017; 44:1846-1856. [PMID: 28295405 DOI: 10.1002/mp.12214] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2016] [Revised: 03/03/2017] [Accepted: 03/07/2017] [Indexed: 01/19/2023] Open
Abstract
PURPOSE The purpose of this study is to determine the optimal representative reconstruction and quantitative image feature set for a computer-aided diagnosis (CADx) scheme for dedicated breast computer tomography (bCT). METHOD We used 93 bCT scans that contain 102 breast lesions (62 malignant, 40 benign). Using an iterative image reconstruction (IIR) algorithm, we created 37 reconstructions with different image appearances for each case. In addition, we added a clinical reconstruction for comparison purposes. We used image sharpness, determined by the gradient of gray value in a parenchymal portion of the reconstructed breast, as a surrogate measure of the image qualities/appearances for the 38 reconstructions. After segmentation of the breast lesion, we extracted 23 quantitative image features. Using leave-one-out-cross-validation (LOOCV), we conducted the feature selection, classifier training, and testing. For this study, we used the linear discriminant analysis classifier. Then, we selected the representative reconstruction and feature set for the classifier with the best diagnostic performance among all reconstructions and feature sets. Then, we conducted an observer study with six radiologists using a subset of breast lesions (N = 50). Using 1000 bootstrap samples, we compared the diagnostic performance of the trained classifier to those of the radiologists. RESULT The diagnostic performance of the trained classifier increased as the image sharpness of a given reconstruction increased. Among combinations of reconstructions and quantitative image feature sets, we selected one of the sharp reconstructions and three quantitative image feature sets with the first three highest diagnostic performances under LOOCV as the representative reconstruction and feature set for the classifier. The classifier on the representative reconstruction and feature set achieved better diagnostic performance with an area under the ROC curve (AUC) of 0.94 (95% CI = [0.81, 0.98]) than those of the radiologists, where their maximum AUC was 0.78 (95% CI = [0.63, 0.90]). Moreover, the partial AUC, at 90% sensitivity or higher, of the classifier (pAUC = 0.085 with 95% CI = [0.063, 0.094]) was statistically better (P-value < 0.0001) than those of the radiologists (maximum pAUC = 0.009 with 95% CI = [0.003, 0.024]). CONCLUSION We found that image sharpness measure can be a good candidate to estimate the diagnostic performance of a given CADx algorithm. In addition, we found that there exists a reconstruction (i.e., sharp reconstruction) and a feature set that maximizes the diagnostic performance of a CADx algorithm. On this optimal representative reconstruction and feature set, the CADx algorithm outperformed radiologists.
Collapse
Affiliation(s)
- Juhun Lee
- Department of Radiology, University of Pittsburgh, Pittsburgh, PA, 15213, USA
| | - Robert M Nishikawa
- Department of Radiology, University of Pittsburgh, Pittsburgh, PA, 15213, USA
| | - Ingrid Reiser
- Department of Radiology, The University of Chicago, Chicago, IL, 60637, USA
| | - John M Boone
- Department of Radiology, University of California Davis Medical Center, Sacramento, CA, 95817, USA
| |
Collapse
|
7
|
Three-Dimensional Computer-Aided Detection of Microcalcification Clusters in Digital Breast Tomosynthesis. BIOMED RESEARCH INTERNATIONAL 2016; 2016:8651573. [PMID: 27274993 PMCID: PMC4870350 DOI: 10.1155/2016/8651573] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/10/2015] [Revised: 02/12/2016] [Accepted: 02/17/2016] [Indexed: 11/17/2022]
Abstract
We propose computer-aided detection (CADe) algorithm for microcalcification (MC) clusters in reconstructed digital breast tomosynthesis (DBT) images. The algorithm consists of prescreening, MC detection, clustering, and false-positive (FP) reduction steps. The DBT images containing the MC-like objects were enhanced by a multiscale Hessian-based three-dimensional (3D) objectness response function and a connected-component segmentation method was applied to extract the cluster seed objects as potential clustering centers of MCs. Secondly, a signal-to-noise ratio (SNR) enhanced image was also generated to detect the individual MC candidates and prescreen the MC-like objects. Each cluster seed candidate was prescreened by counting neighboring individual MC candidates nearby the cluster seed object according to several microcalcification clustering criteria. As a second step, we introduced bounding boxes for the accepted seed candidate, clustered all the overlapping cubes, and examined. After the FP reduction step, the average number of FPs per case was estimated to be 2.47 per DBT volume with a sensitivity of 83.3%.
Collapse
|
8
|
Vedantham S, Karellas A, Vijayaraghavan GR, Kopans DB. Digital Breast Tomosynthesis: State of the Art. Radiology 2016; 277:663-84. [PMID: 26599926 DOI: 10.1148/radiol.2015141303] [Citation(s) in RCA: 126] [Impact Index Per Article: 15.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/30/2022]
Abstract
This topical review on digital breast tomosynthesis (DBT) is provided with the intent of describing the state of the art in terms of technology, results from recent clinical studies, advanced applications, and ongoing efforts to develop multimodality imaging systems that include DBT. Particular emphasis is placed on clinical studies. The observations of increase in cancer detection rates, particularly for invasive cancers, and the reduction in false-positive rates with DBT in prospective trials indicate its benefit for breast cancer screening. Retrospective multireader multicase studies show either noninferiority or superiority of DBT compared with mammography. Methods to curtail radiation dose are of importance. (©) RSNA, 2015.
Collapse
Affiliation(s)
- Srinivasan Vedantham
- From the Department of Radiology, University of Massachusetts Medical School, 55 Lake Ave North, Worcester, MA 01655 (S.V., A.K., G.R.V.); and Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Mass (D.B.K.)
| | - Andrew Karellas
- From the Department of Radiology, University of Massachusetts Medical School, 55 Lake Ave North, Worcester, MA 01655 (S.V., A.K., G.R.V.); and Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Mass (D.B.K.)
| | - Gopal R Vijayaraghavan
- From the Department of Radiology, University of Massachusetts Medical School, 55 Lake Ave North, Worcester, MA 01655 (S.V., A.K., G.R.V.); and Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Mass (D.B.K.)
| | - Daniel B Kopans
- From the Department of Radiology, University of Massachusetts Medical School, 55 Lake Ave North, Worcester, MA 01655 (S.V., A.K., G.R.V.); and Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Mass (D.B.K.)
| |
Collapse
|
9
|
Wavelet-based 3D reconstruction of microcalcification clusters from two mammographic views: new evidence that fractal tumors are malignant and Euclidean tumors are benign. PLoS One 2014; 9:e107580. [PMID: 25222610 PMCID: PMC4164655 DOI: 10.1371/journal.pone.0107580] [Citation(s) in RCA: 26] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2014] [Accepted: 08/20/2014] [Indexed: 12/14/2022] Open
Abstract
The 2D Wavelet-Transform Modulus Maxima (WTMM) method was used to detect microcalcifications (MC) in human breast tissue seen in mammograms and to characterize the fractal geometry of benign and malignant MC clusters. This was done in the context of a preliminary analysis of a small dataset, via a novel way to partition the wavelet-transform space-scale skeleton. For the first time, the estimated 3D fractal structure of a breast lesion was inferred by pairing the information from two separate 2D projected mammographic views of the same breast, i.e. the cranial-caudal (CC) and mediolateral-oblique (MLO) views. As a novelty, we define the “CC-MLO fractal dimension plot”, where a “fractal zone” and “Euclidean zones” (non-fractal) are defined. 118 images (59 cases, 25 malignant and 34 benign) obtained from a digital databank of mammograms with known radiologist diagnostics were analyzed to determine which cases would be plotted in the fractal zone and which cases would fall in the Euclidean zones. 92% of malignant breast lesions studied (23 out of 25 cases) were in the fractal zone while 88% of the benign lesions were in the Euclidean zones (30 out of 34 cases). Furthermore, a Bayesian statistical analysis shows that, with 95% credibility, the probability that fractal breast lesions are malignant is between 74% and 98%. Alternatively, with 95% credibility, the probability that Euclidean breast lesions are benign is between 76% and 96%. These results support the notion that the fractal structure of malignant tumors is more likely to be associated with an invasive behavior into the surrounding tissue compared to the less invasive, Euclidean structure of benign tumors. Finally, based on indirect 3D reconstructions from the 2D views, we conjecture that all breast tumors considered in this study, benign and malignant, fractal or Euclidean, restrict their growth to 2-dimensional manifolds within the breast tissue.
Collapse
|
10
|
Qin X, Lu G, Sechopoulos I, Fei B. Breast Tissue Classification in Digital Tomosynthesis Images Based on Global Gradient Minimization and Texture Features. PROCEEDINGS OF SPIE--THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING 2014; 9034:90341V. [PMID: 25426271 PMCID: PMC4241347 DOI: 10.1117/12.2043828] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/27/2023]
Abstract
Digital breast tomosynthesis (DBT) is a pseudo-three-dimensional x-ray imaging modality proposed to decrease the effect of tissue superposition present in mammography, potentially resulting in an increase in clinical performance for the detection and diagnosis of breast cancer. Tissue classification in DBT images can be useful in risk assessment, computer-aided detection and radiation dosimetry, among other aspects. However, classifying breast tissue in DBT is a challenging problem because DBT images include complicated structures, image noise, and out-of-plane artifacts due to limited angular tomographic sampling. In this project, we propose an automatic method to classify fatty and glandular tissue in DBT images. First, the DBT images are pre-processed to enhance the tissue structures and to decrease image noise and artifacts. Second, a global smooth filter based on L0 gradient minimization is applied to eliminate detailed structures and enhance large-scale ones. Third, the similar structure regions are extracted and labeled by fuzzy C-means (FCM) classification. At the same time, the texture features are also calculated. Finally, each region is classified into different tissue types based on both intensity and texture features. The proposed method is validated using five patient DBT images using manual segmentation as the gold standard. The Dice scores and the confusion matrix are utilized to evaluate the classified results. The evaluation results demonstrated the feasibility of the proposed method for classifying breast glandular and fat tissue on DBT images.
Collapse
Affiliation(s)
- Xulei Qin
- Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA
| | - Guolan Lu
- Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA
| | - Ioannis Sechopoulos
- Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA
- Winship Cancer Institute, Emory University, Atlanta, GA
| | - Baowei Fei
- Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA
- Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA
- Department of Mathematics & Computer Science, Emory University, Atlanta, GA
- Winship Cancer Institute, Emory University, Atlanta, GA
| |
Collapse
|
11
|
Sechopoulos I. A review of breast tomosynthesis. Part II. Image reconstruction, processing and analysis, and advanced applications. Med Phys 2013; 40:014302. [PMID: 23298127 PMCID: PMC3548896 DOI: 10.1118/1.4770281] [Citation(s) in RCA: 113] [Impact Index Per Article: 10.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/13/2012] [Revised: 11/16/2012] [Accepted: 11/16/2012] [Indexed: 02/03/2023] Open
Abstract
Many important post-acquisition aspects of breast tomosynthesis imaging can impact its clinical performance. Chief among them is the reconstruction algorithm that generates the representation of the three-dimensional breast volume from the acquired projections. But even after reconstruction, additional processes, such as artifact reduction algorithms, computer aided detection and diagnosis, among others, can also impact the performance of breast tomosynthesis in the clinical realm. In this two part paper, a review of breast tomosynthesis research is performed, with an emphasis on its medical physics aspects. In the companion paper, the first part of this review, the research performed relevant to the image acquisition process is examined. This second part will review the research on the post-acquisition aspects, including reconstruction, image processing, and analysis, as well as the advanced applications being investigated for breast tomosynthesis.
Collapse
Affiliation(s)
- Ioannis Sechopoulos
- Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA, USA
| |
Collapse
|
12
|
Sahiner B, Chan HP, Hadjiiski LM, Helvie MA, Wei J, Zhou C, Lu Y. Computer-aided detection of clustered microcalcifications in digital breast tomosynthesis: a 3D approach. Med Phys 2012; 39:28-39. [PMID: 22225272 DOI: 10.1118/1.3662072] [Citation(s) in RCA: 44] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/26/2022] Open
Abstract
PURPOSE To design a computer-aided detection (CADe) system for clustered microcalcifications in reconstructed digital breast tomosynthesis (DBT) volumes and to perform a preliminary evaluation of the CADe system. METHODS IRB approval and informed consent were obtained in this study. A data set of two-view DBT of 72 breasts containing microcalcification clusters was collected from 72 subjects who were scheduled to undergo breast biopsy. Based on tissue sampling results, 17 cases had breast cancer and 55 were benign. A separate data set of two-view DBT of 38 breasts free of clustered microcalcifications from 38 subjects was collected to independently estimate the number of false-positives (FPs) generated by the CADe system. A radiologist experienced in breast imaging marked the biopsied cluster of microcalcifications with a 3D bounding box using all available clinical and imaging information. A CADe system was designed to detect microcalcification clusters in the reconstructed volume. The system consisted of prescreening, clustering, and false-positive reduction stages. In the prescreening stage, the conspicuity of microcalcification-like objects was increased by an enhancement-modulated 3D calcification response function. An iterative thresholding and 3D object growing method was used to detect cluster seed objects, which were used as potential centers of microcalcification clusters. In the cluster detection stage, microcalcification candidates were identified using a second iterative thresholding procedure, which was applied to the signal-to-noise ratio (SNR) enhanced image voxels with a positive calcification response. Starting with each cluster seed object as the initial cluster center, a dynamic clustering algorithm formed a cluster candidate by including microcalcification candidates within a 3D neighborhood of the cluster seed object that satisfied the clustering criteria. The number, size, and SNR of the microcalcifications in a cluster candidate and the cluster shape were used to reduce the number of FPs. RESULTS The prescreening stage detected a cluster seed object in 94% of the biopsied microcalcification clusters at a threshold of 100 cluster seed objects per DBT volume. After clustering, the detection sensitivity was 90% at 15 marks per DBT volume. After FP reduction, at 85% sensitivity, the average number of FPs estimated using the data set containing microcalcification clusters was 3.8 per DBT volume, and that estimated using the data set free of microcalcification clusters was 3.4. The detection performance for malignant microcalcification clusters was superior to that for benign clusters. CONCLUSIONS Our study indicates the feasibility of the 3D approach to the detection of clustered microcalcifications in DBT and that the newly designed enhancement-modulated 3D calcification response function is promising for prescreening. Further work is needed to assess the generalizability of our approach and to improve its performance.
Collapse
Affiliation(s)
- Berkman Sahiner
- Department of Radiology, University of Michigan, Ann Arbor, Michigan 48109, USA.
| | | | | | | | | | | | | |
Collapse
|
13
|
Chan HP, Wu YT, Sahiner B, Wei J, Helvie MA, Zhang Y, Moore RH, Kopans DB, Hadjiiski L, Way T. Characterization of masses in digital breast tomosynthesis: comparison of machine learning in projection views and reconstructed slices. Med Phys 2010; 37:3576-86. [PMID: 20831065 DOI: 10.1118/1.3432570] [Citation(s) in RCA: 24] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022] Open
Abstract
PURPOSE In digital breast tomosynthesis (DBT), quasi-three-dimensional (3D) structural information is reconstructed from a small number of 2D projection view (PV) mammograms acquired over a limited angular range. The authors developed preliminary computer-aided diagnosis (CADx) methods for classification of malignant and benign masses and compared the effectiveness of analyzing lesion characteristics in the reconstructed DBT slices and in the PVs. METHODS A data set of MLO view DBT of 99 patients containing 107 masses (56 malignant and 51 benign) was collected at the Massachusetts General Hospital with IRB approval. The DBTs were obtained with a GE prototype system which acquired 11 PVs over a 50 degree arc. The authors reconstructed the DBTs at 1 mm slice interval using a simultaneous algebraic reconstruction technique. The region of interest (ROI) containing the mass was marked by a radiologist in the DBT volume and the corresponding ROIs on the PVs were derived based on the imaging geometry. The subsequent processes were fully automated. For classification of masses using the DBT-slice approach, the mass on each slice was segmented by an active contour model initialized with adaptive k-means clustering. A spiculation likelihood map was generated by analysis of the gradient directions around the mass margin and spiculation features were extracted from the map. The rubber band straightening transform (RBST) was applied to a band of pixels around the segmented mass boundary. The RBST image was enhanced by Sobel filtering in the horizontal and vertical directions, from which run-length statistics texture features were extracted. Morphological features including those from the normalized radial length were designed to describe the mass shape. A feature space composed of the spiculation features, texture features, and morphological features extracted from the central slice alone and seven feature spaces obtained by averaging the corresponding features from three to 19 slices centered at the central slice were compared. For classification of masses using the PV approach, a feature extraction process similar to that described above for the DBT approach was performed on the ROIs from the individual PVs. Six feature spaces obtained from the central PV alone and by averaging the corresponding features from three to 11 PVs were formed. In each feature space for either the DBT-slice or the PV approach, a linear discriminant analysis classifier with stepwise feature selection was trained and tested using a two-loop leave-one-case-out resampling procedure. Simplex optimization was used to guide feature selection automatically within the training set in each leave-one-case-out cycle. The performance of the classifiers was evaluated by the area (Az) under the receiver operating characteristic curve. RESULTS The test Az values from the DBT-slice approach ranged from 0.87 +/- 0.03 to 0.93 +/- 0.02, while those from the PV approach ranged from 0.78 +/- 0.04 to 0.84 +/- 0.04. The highest test Az of 0.93 +/- 0.02 from the nine-DBT-slice feature space was significantly (p = 0.006) better than the highest test Az of 0.84 +/- 0.04 from the nine-PV feature space. CONCLUSION The features of breast lesions extracted from the DBT slices consistently provided higher classification accuracy than those extracted from the PV images.
Collapse
Affiliation(s)
- Heang-Ping Chan
- Department of Radiology, University of Michigan, Ann Arbor, Michigan 48109, USA.
| | | | | | | | | | | | | | | | | | | |
Collapse
|
14
|
Zuley ML, Bandos AI, Abrams GS, Cohen C, Hakim CM, Sumkin JH, Drescher J, Rockette HE, Gur D. Time to diagnosis and performance levels during repeat interpretations of digital breast tomosynthesis: preliminary observations. Acad Radiol 2010; 17:450-5. [PMID: 20036584 DOI: 10.1016/j.acra.2009.11.011] [Citation(s) in RCA: 38] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2009] [Revised: 11/06/2009] [Accepted: 11/08/2009] [Indexed: 10/20/2022]
Abstract
RATIONALE AND OBJECTIVES To compare time to interpretation and diagnostic performance levels during repeat readings of full-field digital mammography (FFDM) and digital breast tomosynthesis (DBT) in a retrospective study. MATERIALS AND METHODS Three experienced radiologists twice interpreted 125 selected examinations, 35 with verified cancers and 90 negative for cancer during a period of 22 months using FFDM alone followed by a combined FFDM + DBT mode. Changes in time to "review and rate" these examinations as well as in diagnostic performance levels where assessed. A fixed-effect analysis accounting for cross-correlation due to the review of the same examinations by the same readers was performed. RESULTS The total (combined) time to review and rate an examination increased on average by 33% between the first and second readings of the same examinations (P < .001). Radiologists reduced their time to review FFDM before making the DBT available for viewing. However, they spent more time reviewing the combined FFDM + DBT mode. The recall rates for examinations depicting cancer remained largely unchanged. Among the groups of examinations with concordant and discordant recall recommendations during the two readings only the group examinations that were "newly recalled" during repeat reading, took significantly longer (P < .01). CONCLUSION DBT-based breast imaging may ultimately result in a substantial increase in performance; however, without efficiency improvements DBT may take longer to interpret. Addition of "false-positive recalls" was most strongly associated with increase in interpretation time while elimination of "false-positive recalls" did not require longer interpretation time.
Collapse
|
15
|
Abstract
OBJECTIVE The purpose of this study was to compare in a retrospective observer study the diagnostic performance of full-field digital mammography (FFDM) with that of digital breast tomosynthesis. MATERIALS AND METHODS Eight experienced radiologists interpreted images from 125 selected examinations, 35 with verified findings of cancer and 90 with no finding of cancer. The four display conditions included FFDM alone, 11 low-dose projections, reconstructed digital breast tomosynthesis images, and a combined display mode of FFDM and digital breast tomosynthesis images. Observers rated examinations using the screening BI-RADS rating scale and the free-response receiver operating characteristic paradigm. Observer performance levels were measured as the proportion of examinations prompting recall of patients for further diagnostic evaluation. The results were presented in terms of true-positive fraction and false-positive fraction. Performance levels were compared among the acquisitions and reading modes. Time to view and interpret an examination also was evaluated. RESULTS Use of the combination of digital breast tomosynthesis and FFDM was associated with 30% reduction in recall rate for cancer-free examinations that would have led to recall if FFDM had been used alone (p < 0.0001 for the participating radiologists, p = 0.047 in the context of a generalized population of radiologists). Use of digital breast tomosynthesis alone also tended to reduce recall rates, an average of 10%, although the observed decrease was not statistically significant (p = 0.09 for the participating radiologists). There was no convincing evidence that use of digital breast tomosynthesis alone or in combination with FFDM results in a substantial improvement in sensitivity. CONCLUSION Use of digital breast tomosynthesis for breast imaging may result in a substantial decrease in recall rate.
Collapse
|
16
|
Abstract
Computer-aided diagnosis (CAD), in the general sense, includes computer-aided detection and characterization of abnormalities on medical images. The usefulness of CAD for assisting radiologists in detection of breast cancer in screening mammography has been demonstrated by a number of prospective clinical trials in recent years. The development of CAD in other areas is also being actively pursued by researchers. In this talk, the recent work in two areas of CAD, digital breast tomosynthesis (DBT) and chest computed tomography (CT), in the CAD Research Laboratory at the University of Michigan will be reviewed. DBT is a new modality under development for breast imaging. The quasi-3D information in DBT alleviates the problem of overlapping tissue in mammography and holds the promise to improve the sensitivity for cancer detection. DBT image analysis can be performed in the 3D reconstructed volume of the 2D projection view (PV) images. DBT image quality depend on the image acquisition parameters, reconstruction method and parameters. The flexibility in image processing approaches makes CAD development for DBT interesting and challenging. out early experiences in the development of image segmentation and features extraction technique for mass detection and characterization in DBT will be discussed. The performances of the CAD systems using the 2D, 3D, and combined 2D and 3D approaches will be compared. CT has been shown to be superior to chest x-ray in detection of small lung nodules and thus lung cancer screening with CT is still being debated, many research groups are developing CAD methods for detection and characterization of lung nodules in chest CT scans. The specific prescreening, segmentation, and feature extraction techniques designed for our lung nodule detection and characterization systems will be discussed. The effects of CAD on radiologists' accuracy in nodules detection and characterization in CT scans will be demonstrated by results of observer ROC studies. There are similarities in the approaches to developing CAD methods in 3D image volumes such as DBT and CT, these experiences will facilitate the development of CAD systems for other diseases in 3D modalities.
Collapse
|
17
|
Chan HP, Wei J, Zhang Y, Helvie MA, Moore RH, Sahiner B, Hadjiiski L, Kopans DB. Computer-aided detection of masses in digital tomosynthesis mammography: comparison of three approaches. Med Phys 2008; 35:4087-95. [PMID: 18841861 DOI: 10.1118/1.2968098] [Citation(s) in RCA: 74] [Impact Index Per Article: 4.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022] Open
Abstract
The authors are developing a computer-aided detection (CAD) system for masses on digital breast tomosynthesis mammograms (DBT). Three approaches were evaluated in this study. In the first approach, mass candidate identification and feature analysis are performed in the reconstructed three-dimensional (3D) DBT volume. A mass likelihood score is estimated for each mass candidate using a linear discriminant analysis (LDA) classifier. Mass detection is determined by a decision threshold applied to the mass likelihood score. A free response receiver operating characteristic (FROC) curve that describes the detection sensitivity as a function of the number of false positives (FPs) per breast is generated by varying the decision threshold over a range. In the second approach, prescreening of mass candidate and feature analysis are first performed on the individual two-dimensional (2D) projection view (PV) images. A mass likelihood score is estimated for each mass candidate using an LDA classifier trained for the 2D features. The mass likelihood images derived from the PVs are backprojected to the breast volume to estimate the 3D spatial distribution of the mass likelihood scores. The FROC curve for mass detection can again be generated by varying the decision threshold on the 3D mass likelihood scores merged by backprojection. In the third approach, the mass likelihood scores estimated by the 3D and 2D approaches, described above, at the corresponding 3D location are combined and evaluated using FROC analysis. A data set of 100 DBT cases acquired with a GE prototype system at the Breast Imaging Laboratory in the Massachusetts General Hospital was used for comparison of the three approaches. The LDA classifiers with stepwise feature selection were designed with leave-one-case-out resampling. In FROC analysis, the CAD system for detection in the DBT volume alone achieved test sensitivities of 80% and 90% at average FP rates of 1.94 and 3.40 per breast, respectively. With the 2D detection approach, the FP rates were 2.86 and 4.05 per breast, respectively, at the corresponding sensitivities. In comparison, the average FP rates of the system combining the 3D and 2D information were 1.23 and 2.04 per breast, respectively, at 80% and 90% sensitivities. The difference in the detection performances between the 2D and the 3D approach, and that between the 3D and the combined approach were both statistically significant (p = 0.02 and 0.01, respectively) as estimated by alternative FROC analysis. The combined system is a promising approach to improving automated mass detection on DBTs.
Collapse
Affiliation(s)
- Heang-Ping Chan
- Department of Radiology, University of Michigan, Ann Arbor, Michigan 48109-5842, USA.
| | | | | | | | | | | | | | | |
Collapse
|
18
|
Abstract
PURPOSE OF REVIEW Computer-aided diagnosis (CAD) is a technology used for the detection and characterization of cancer. Although CAD is not limited to a single type of cancer, a large number of CAD systems to date have been designed and used for breast cancer. The aim of this review is to discuss the current state of the CAD systems for breast-cancer diagnosis, their application as a second reader in clinical practice, and studies that have evaluated the effect of CAD on radiologists' performance. RECENT FINDINGS A large number of CAD applications are being developed for different imaging modalities. Owing to commercially available Food and Drug Administration (FDA) approved systems, the main clinical use of CAD to date is for screen-film mammography. Many studies have shown that CAD improves radiologists' performance. A large number of academic institutions have devoted a substantial research effort to developing CAD methods. SUMMARY CAD systems will play an increasingly important role in the clinic as a second reader. Clinical trials have shown that CAD can improve the accuracy of breast-cancer detection. Preclinical studies have demonstrated the potential of CAD to improve the classification of malignant and benign lesions. An increased number of CAD systems are being developed for different breast-imaging modalities.
Collapse
Affiliation(s)
- Lubomir Hadjiiski
- Department of Radiology, University of Michigan, Ann Arbor, Michigan 48109-0904, USA.
| | | | | |
Collapse
|
19
|
Abstract
OBJECTIVE The objective of our study was to assess ergonomic and diagnostic performance-related issues associated with the interpretation of digital breast tomosynthesis-generated examinations. MATERIALS AND METHODS Thirty selected cases were read under three different display conditions by nine experienced radiologists in a fully crossed, mode-balanced observer performance study. The reading modes included full-field digital mammography (FFDM) alone, the 11 low-dose projections acquired for the reconstruction of tomosynthesis images, and the reconstructed digital breast tomosynthesis examination. Observers rated cases under the free-response receiver operating characteristic, as well as a screening paradigm, and provided subjective assessments of the relative diagnostic value of the two digital breast tomosynthesis-based image sets as compared with FFDM. The time to review and diagnose each case was also evaluated. RESULTS Observer performance measures were not statistically significant (p > 0.05) primarily because of the small sample size in this pilot study, suggesting that showing significant improvements in diagnosis, if any, will require a larger study. Several radiologists did perceive the digital breast tomosynthesis image set and the projection series to be better than FFDM (p < 0.05) for diagnosing this specific case set. The time to review, interpret, and rate the examinations was significantly different for the techniques in question (p < 0.05). CONCLUSION Tomosynthesis-based breast imaging may have great potential, but much work is needed before its optimal role in the clinical environment is known.
Collapse
|
20
|
Park JM, Franken EA, Garg M, Fajardo LL, Niklason LT. Breast tomosynthesis: present considerations and future applications. Radiographics 2008; 27 Suppl 1:S231-40. [PMID: 18180229 DOI: 10.1148/rg.27si075511] [Citation(s) in RCA: 134] [Impact Index Per Article: 8.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
Abstract
Mammography is an effective imaging tool for detecting breast cancer at an early stage and is the only screening modality proved to reduce mortality from breast cancer. However, the overlap of tissues depicted on mammograms may create significant obstacles to the detection and diagnosis of abnormalities. Diagnostic testing initiated because of a questionable result at screening mammography frequently causes patients unnecessary anxiety and incurs increased medical costs. Breast tomosynthesis, a new tool that is based on the acquisition of three-dimensional digital image data, could help solve the problem of interpreting mammographic features produced by tissue overlap. Although the technology has not yet been approved by the Food and Drug Administration, breast tomosynthesis has the potential to help reduce recall rates, improve the selection of patients for biopsy, and increase cancer detection rates, especially in patients with dense breasts. Supplemental material available at radiographics.rsnajnls.org/cgi/content/full/27/S231/DC1.
Collapse
Affiliation(s)
- Jeong Mi Park
- Division of Breast Imaging and Intervention, Department of Radiology, University of Iowa Hospitals and Clinics, Carver College of Medicine, 200 Hawkins Dr, Iowa City, IA 52242-1082, USA.
| | | | | | | | | |
Collapse
|
21
|
Singletary SE. Multidisciplinary frontiers in breast cancer management: a surgeon's perspective. Cancer 2007; 109:1019-29. [PMID: 17295294 DOI: 10.1002/cncr.22519] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
Abstract
The current paradigm of breast cancer management may be altered significantly over the coming years by the adoption of new treatment schema and devices outside of the surgical arena. New advances in breast cancer imaging will improve our ability to detect early-stage disease but also will assist in monitoring treatment outcomes and support the development of nonsurgical ablation techniques. These advances, some already in use, include a 3-dimensional adaptation of digital mammography, color Doppler ultrasonography that can visualize neovascularization in growing tumors, contrast-enhanced magnetic resonance imaging with improved accuracy for the detection of occult cancers, a specialized approach to positron emission tomography designed for use on the breast, and the development of nanoparticle contrast agents that can be visualized with near-infrared light. Systemic therapy, which revolutionized breast cancer management in the last half of the 20th century, is being reconceptualized, with attention turning to adjusting the timing of chemotherapy. Dose-dense regimens are being tested, and there also is interest in so-called metronomic chemotherapy in which very low doses are given on a very frequent schedule, resulting in reduced toxicity and treatment outcomes that reflect an antiangiogenic mode of action. Finally, the possibility of a breast cancer vaccine continues to intrigue and excite physicians and patients alike, with the promise of enlisting the body's own immune system to seek out and destroy cancer cells and/or prevent the development of future disease. It will be important for surgeons to stay aware of all developments that may improve the care of their patients and to be true surgical oncologists rather than merely surgical technicians.
Collapse
Affiliation(s)
- S Eva Singletary
- Department of Surgical Oncology, The University of Texas M. D. Anderson Cancer Center, Houston, Texas 77030-4095, USA.
| |
Collapse
|
22
|
Roy AS, Armato SG, Wilson A, Drukker K. Automated detection of lung nodules in CT scans: false-positive reduction with the radial-gradient index. Med Phys 2006; 33:1133-40. [PMID: 16696491 DOI: 10.1118/1.2178450] [Citation(s) in RCA: 20] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/15/2023] Open
Abstract
We present a number of approaches based on the radial gradient index (RGI) to achieve false-positive reduction in automated CT lung nodule detection. A database of 38 cases was used that contained a total of 82 lung nodules. For each CT section, a complementary image known as an "RGI map" was constructed to enhance regions of high circularity and thus improve the contrast between nodules and normal anatomy. Thresholds on three RGI parameters were varied to construct RGI filters that sensitively eliminated false-positive structures. In a consistency approach, RGI filtering eliminated 36% of the false-positive structures detected by the automated method without the loss of any true positives. Use of an RGI filter prior to a linear discriminant classifier yielded notable improvements in performance, with the false-positive rate at a sensitivity of 70% being reduced from 0.5 to 0.28 per section. Finally, the performance of the linear discriminant classifier was evaluated with RGI-based features. RGI-based features achieved a substantial improvement in overall performance, with a 94.8% reduction in the false-positive rate at a fixed sensitivity of 70%. These results demonstrate the potential role of RGI analysis in an automated lung nodule detection method.
Collapse
Affiliation(s)
- Arunabha S Roy
- Department of Radiology, The University of Chicago, Chicago, Illinois 60637, USA
| | | | | | | |
Collapse
|
23
|
Reiser I, Nishikawa RM, Giger ML, Wu T, Rafferty EA, Moore R, Kopans DB. Computerized mass detection for digital breast tomosynthesis directly from the projection images. Med Phys 2006; 33:482-91. [PMID: 16532956 DOI: 10.1118/1.2163390] [Citation(s) in RCA: 60] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022] Open
Abstract
Digital breast tomosynthesis (DBT) has recently emerged as a new and promising three-dimensional modality in breast imaging. In DBT, the breast volume is reconstructed from 11 projection images, taken at source angles equally spaced over an arc of 50 degrees. Reconstruction algorithms for this modality are not fully optimized yet. Because computerized lesion detection in the reconstructed breast volume will be affected by the reconstruction technique, we are developing a novel mass detection algorithm that operates instead on the set of raw projection images. Mass detection is done in three stages. First, lesion candidates are obtained for each projection image separately, using a mass detection algorithm that was initially developed for screen-film mammography. Second, the locations of a lesion candidate are backprojected into the breast volume. In this feature volume, voxel intensities are a combined measure of detection frequency (e.g., the number of projections in which a given lesion candidate was detected), and a measure of the angular range over which a given lesion was detected. Third, features are extracted after reprojecting the three-dimensional (3-D) locations of lesion candidates into projection images. Features are combined using linear discriminant analysis. The database used to test the algorithm consisted of 21 mass cases (13 malignant, 8 benign) and 15 cases without mass lesions. Based on this database, the algorithm yielded a sensitivity of 90% at 1.5 false positives per breast volume. Algorithm performance is positively biased because this dataset was used for development, training, and testing, and because the number of algorithm parameters was approximately the same as the number.of patient cases. Our results indicate that computerized mass detection in the sequence of projection images for DBT may be effective despite the higher noise level in those images.
Collapse
Affiliation(s)
- I Reiser
- Department of Radiology, The University of Chicago, Chicago, Illinois 60637, USA
| | | | | | | | | | | | | |
Collapse
|
24
|
Boone JM, Kwan ALC, Yang K, Burkett GW, Lindfors KK, Nelson TR. Computed tomography for imaging the breast. J Mammary Gland Biol Neoplasia 2006; 11:103-11. [PMID: 17053979 DOI: 10.1007/s10911-006-9017-1] [Citation(s) in RCA: 92] [Impact Index Per Article: 5.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 10/24/2022] Open
Abstract
Despite the success of screening mammography contributing to the reduction of cancer mortality, a number of other imaging techniques are being studied for breast cancer screening. In our laboratory, a dedicated breast computed tomography (CT) system has been developed and is currently undergoing patient testing. The breast CT system is capable of scanning the breast with the woman lying prone on a tabletop, with the breast in the pendant position. A 360 degrees scan currently requires 16.6 s, and a second scanner with a 9-second scan time is nearly operational. Extensive effort was placed on computing the radiation dose to the breast under CT geometry, and the scan parameters are selected to utilize the same radiation dose levels as two-view mammography. A total of 55 women have been scanned, ten healthy volunteers in a Phase I trial, and 45 women with a high likelihood of having breast cancer in a Phase II trial. The breast CT process leads to the production of approximately three hundred 512 x 512 images for each breast. Subjective evaluation of the breast CT images reveals excellent anatomical detail, good depiction of microcalcifications, and exquisite visualization of the soft tissue components of the tumor when contrasted against adipose tissues. The use of iodine contrast injection dramatically enhances the visualization of tumors. While a thorough scientific investigation based upon observer performance studies is in progress, initial breast CT images do appear promising and it is likely that breast CT will play some role in breast cancer imaging.
Collapse
Affiliation(s)
- John M Boone
- Department of Radiology, UC Davis Medical Center, University of California, Davis, 4860 Y Street, Suite 3100, Sacramento, CA 95817, USA.
| | | | | | | | | | | |
Collapse
|
25
|
Reiser I, Nishikawa R, Giger M, Kopans D, Rafferty E, Wu T, Moore R. A multi-scale 3D radial gradient filter for computerized mass detection in digital tomosynthesis breast images. ACTA ACUST UNITED AC 2005. [DOI: 10.1016/j.ics.2005.03.171] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|