1
|
Chen X, Zhang K, Abdoli N, Gilley PW, Wang X, Liu H, Zheng B, Qiu Y. Transformers Improve Breast Cancer Diagnosis from Unregistered Multi-View Mammograms. Diagnostics (Basel) 2022; 12:diagnostics12071549. [PMID: 35885455 PMCID: PMC9320758 DOI: 10.3390/diagnostics12071549] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/31/2022] [Revised: 06/21/2022] [Accepted: 06/24/2022] [Indexed: 11/16/2022] Open
Abstract
Deep convolutional neural networks (CNNs) have been widely used in various medical imaging tasks. However, due to the intrinsic locality of convolution operations, CNNs generally cannot model long-range dependencies well, which are important for accurately identifying or mapping corresponding breast lesion features computed from unregistered multiple mammograms. This motivated us to leverage the architecture of Multi-view Vision Transformers to capture long-range relationships of multiple mammograms from the same patient in one examination. For this purpose, we employed local transformer blocks to separately learn patch relationships within four mammograms acquired from two-view (CC/MLO) of two-side (right/left) breasts. The outputs from different views and sides were concatenated and fed into global transformer blocks, to jointly learn patch relationships between four images representing two different views of the left and right breasts. To evaluate the proposed model, we retrospectively assembled a dataset involving 949 sets of mammograms, which included 470 malignant cases and 479 normal or benign cases. We trained and evaluated the model using a five-fold cross-validation method. Without any arduous preprocessing steps (e.g., optimal window cropping, chest wall or pectoral muscle removal, two-view image registration, etc.), our four-image (two-view-two-side) transformer-based model achieves case classification performance with an area under ROC curve (AUC = 0.818 ± 0.039), which significantly outperforms AUC = 0.784 ± 0.016 achieved by the state-of-the-art multi-view CNNs (p = 0.009). It also outperforms two one-view-two-side models that achieve AUC of 0.724 ± 0.013 (CC view) and 0.769 ± 0.036 (MLO view), respectively. The study demonstrates the potential of using transformers to develop high-performing computer-aided diagnosis schemes that combine four mammograms.
Collapse
Affiliation(s)
- Xuxin Chen
- School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK 73019, USA; (K.Z.); (N.A.); (P.W.G.); (H.L.); (B.Z.)
- Correspondence: (X.C.); (Y.Q.)
| | - Ke Zhang
- School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK 73019, USA; (K.Z.); (N.A.); (P.W.G.); (H.L.); (B.Z.)
- Stephenson School of Biomedical Engineering, University of Oklahoma, Norman, OK 73019, USA
| | - Neman Abdoli
- School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK 73019, USA; (K.Z.); (N.A.); (P.W.G.); (H.L.); (B.Z.)
| | - Patrik W. Gilley
- School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK 73019, USA; (K.Z.); (N.A.); (P.W.G.); (H.L.); (B.Z.)
| | | | - Hong Liu
- School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK 73019, USA; (K.Z.); (N.A.); (P.W.G.); (H.L.); (B.Z.)
| | - Bin Zheng
- School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK 73019, USA; (K.Z.); (N.A.); (P.W.G.); (H.L.); (B.Z.)
| | - Yuchen Qiu
- School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK 73019, USA; (K.Z.); (N.A.); (P.W.G.); (H.L.); (B.Z.)
- Correspondence: (X.C.); (Y.Q.)
| |
Collapse
|
2
|
Prediction of Short-Term Breast Cancer Risk with Fusion of CC- and MLO-Based Risk Models in Four-View Mammograms. J Digit Imaging 2022; 35:910-922. [PMID: 35262841 PMCID: PMC9485387 DOI: 10.1007/s10278-019-00266-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022] Open
Abstract
This study performed and assessed a novel program to improve the accuracy of short-term breast cancer risk prediction by using information from craniocaudal (CC) and mediolateral-oblique (MLO) views of two breasts. An age-matched dataset of 556 patients with at least two sequential full-field digital mammography examinations was applied. In the second examination, 278 cases were diagnosed and pathologically verified as cancer, and 278 were negative, while all cases in the first examination were negative (not recalled). Two generalized linear-model-based risk prediction models were established with global- and local-based bilateral asymmetry features for CC and MLO views first. Then, a new fusion risk model was developed by fusing prediction results of the CC- and MLO-based risk models with an adaptive alpha-integration-based fusion method. The AUC of the fusion risk model was 0.72 ± 0.02, which was significantly higher than the AUC of CC- or MLO-based risk model (P < 0.05). The maximum odds ratio for CC- and MLO-based risk models were 8.09 and 5.25, respectively, and increased to 11.99 for the fusion risk model. For subgroups of patients aged 37-49 years, 50-65 years, and 66-87 years, the AUCs of 0.73, 0.71, and 0.75 for the fusion risk model were higher than AUC for CC- and MLO-based risk models. For the BIRADS 2 and 3 subgroups, the AUC values were 0.72 and 0.71 respectively for the fusion risk model which were higher than the AUC for the CC- and MLO-based risk models. This study demonstrated that the fusion risk model we established could effectively derive and integrate supplementary and useful information extracted from both CC and MLO view images and adaptively fuse them to increase the predictive power of the short-term breast cancer risk assessment model.
Collapse
|
3
|
Yan S, Wang Y, Aghaei F, Qiu Y, Zheng B. Improving Performance of Breast Cancer Risk Prediction by Incorporating Optical Density Image Feature Analysis: An Assessment. Acad Radiol 2022; 29 Suppl 1:S199-S210. [PMID: 28985925 PMCID: PMC5882616 DOI: 10.1016/j.acra.2017.08.007] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2017] [Revised: 07/22/2017] [Accepted: 08/07/2017] [Indexed: 01/03/2023]
Abstract
RATIONALE AND OBJECTIVES The purpose of this study is to improve accuracy of near-term breast cancer risk prediction by applying a new mammographic image conversion method combined with a two-stage artificial neural network (ANN)-based classification scheme. MATERIALS AND METHODS The dataset included 168 negative mammography screening cases. In developing and testing our new risk model, we first converted the original grayscale value (GV)-based mammographic images into optical density (OD)-based images. For each case, our computer-aided scheme then computed two types of image features representing bilateral asymmetry and the maximum of the image features computed from GV and OD images, respectively. A two-stage classification scheme consisting of three ANNs was developed. The first stage included two ANNs trained using features computed separately from GV and OD images of 138 cases. The second stage included another ANN to fuse the prediction scores produced by two ANNs in the first stage. The risk prediction performance was tested using the rest 30 cases. RESULTS With the two-stage classification scheme, the computed area under the receiver operating characteristic curve (AUC) was 0.816 ± 0.071, which was significantly higher than the AUC values of 0.669 ± 0.099 and 0.646 ± 0.099 achieved using two ANNs trained using GV features and OD features, respectively (P < .05). CONCLUSION This study demonstrated that applying an OD image conversion method can acquire new complimentary information to those acquired from the original images. As a result, fusion image features computed from these two types of images yielded significantly higher performance in near-term breast cancer risk prediction.
Collapse
Affiliation(s)
- Shiju Yan
- School of Medical Instrument and Food Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China,School of Electrical and Computer Engineering, University of Oklahoma, Norman, Oklahoma 73019, USA
| | - Yunzhi Wang
- School of Electrical and Computer Engineering, University of Oklahoma, Norman, Oklahoma 73019, USA
| | - Faranak Aghaei
- School of Electrical and Computer Engineering, University of Oklahoma, Norman, Oklahoma 73019, USA
| | - Yuchen Qiu
- School of Electrical and Computer Engineering, University of Oklahoma, Norman, Oklahoma 73019, USA
| | - Bin Zheng
- School of Electrical and Computer Engineering, University of Oklahoma, Norman, Oklahoma 73019, USA
| |
Collapse
|
4
|
Tan PS, Ali MA, Eriksson M, Hall P, Humphreys K, Czene K. Mammography features for early markers of aggressive breast cancer subtypes and tumor characteristics: A population-based cohort study. Int J Cancer 2020; 148:1351-1359. [PMID: 32976625 PMCID: PMC7891615 DOI: 10.1002/ijc.33309] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2020] [Revised: 09/05/2020] [Accepted: 09/15/2020] [Indexed: 12/14/2022]
Abstract
Current breast cancer risk models identify mostly less aggressive tumors, although only women developing fatal breast cancer will greatly benefit from early identification. Here, we evaluated the use of mammography features (microcalcification clusters, computer-generated Breast Imaging Reporting and Data System [cBIRADS] density and lack of breast density reduction) as early markers of aggressive subtypes and tumor characteristics. Mammograms were retrieved from a population-based cohort of women that were diagnosed with breast cancer from 2001 to 2008 in Stockholm-Gotland County, Sweden. Tumor and patient characteristics were obtained from Stockholm Breast Cancer Quality Register and the Swedish Cancer Registry. Multinomial logistic regression was used to individually model each mammographic feature as a function of molecular subtypes, tumor characteristics and detection mode. A total of 4546 women with invasive breast cancer were included in the study. Women with microcalcification clusters in the affected breast were more likely to have human epidermal growth factor receptor 2 subtype (odds ratio [OR] 1.78; 95% confidence interval [CI] 1.24-2.54) and potentially less likely to have basal subtype (OR 0.54; 0.30-0.96) compared to Luminal A subtype. High mammographic cBIRADS showed association with larger tumor size and interval vs screen-detected cancers. Lack of density reduction was associated with interval vs screen-detected cancers (OR 1.43; 1.11-1.83) and potentially of Luminal B subtype vs Luminal A subtype (OR 1.76; 1.04-2.99). In conclusion, microcalcification clusters, cBIRADS density and lack of breast density reduction could serve as early markers of particular subtypes and tumor characteristics of breast cancer. This information has the potential to be integrated into risk models to identify women at risk for developing aggressive breast cancer in need of supplemental screening.
Collapse
Affiliation(s)
- Pui San Tan
- Department of Medical Epidemiology and Biostatistics, Karolinska Institute, Solna, Sweden
| | - Maya Alsheh Ali
- Department of Medical Epidemiology and Biostatistics, Karolinska Institute, Solna, Sweden.,Swedish eScience Research Centre (SeRC), Karolinska Institute, Stockholm, Sweden
| | - Mikael Eriksson
- Department of Medical Epidemiology and Biostatistics, Karolinska Institute, Solna, Sweden
| | - Per Hall
- Department of Medical Epidemiology and Biostatistics, Karolinska Institute, Solna, Sweden.,Department of Oncology, Södersjukhuset, Stockholm, Sweden
| | - Keith Humphreys
- Department of Medical Epidemiology and Biostatistics, Karolinska Institute, Solna, Sweden.,Swedish eScience Research Centre (SeRC), Karolinska Institute, Stockholm, Sweden
| | - Kamila Czene
- Department of Medical Epidemiology and Biostatistics, Karolinska Institute, Solna, Sweden
| |
Collapse
|
5
|
Hudson SM, Wilkinson LS, De Stavola BL, Dos-Santos-Silva I. Left-right breast asymmetry and risk of screen-detected and interval cancers in a large population-based screening population. Br J Radiol 2020; 93:20200154. [PMID: 32525693 DOI: 10.1259/bjr.20200154] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/22/2023] Open
Abstract
OBJECTIVES To assess the associations between automated volumetric estimates of mammographic asymmetry and breast cancers detected at the same ("contemporaneous") screen, at subsequent screens, or in between (interval cancers). METHODS Automated measurements from mammographic images (N = 79,731) were used to estimate absolute asymmetry in breast volume (BV) and dense volume (DV) in a large ethnically diverse population of attendees of a UK breast screening programme. Logistic regression models were fitted to assess asymmetry associations with the odds of a breast cancer detected at contemporaneous screen (767 cases), adjusted for relevant confounders.Nested case-control investigations were designed to examine associations between asymmetry and the odds of: (a) interval cancer (numbers of cases/age-matched controls: 153/646) and (b) subsequent screen-detected cancer (345/1438), via conditional logistic regression. RESULTS DV, but not BV, asymmetry was positively associated with the odds of contemporaneous breast cancer (P-for-linear-trend (Pt) = 0.018). This association was stronger for first (prevalent) screens (Pt = 0.012). Both DV and BV asymmetry were positively associated with the odds of an interval cancer diagnosis (Pt = 0.060 and 0.030, respectively). Neither BV nor DV asymmetry were associated with the odds of having a subsequent screen-detected cancer. CONCLUSIONS Increased DV asymmetry was associated with the risk of a breast cancer diagnosis at a contemporaneous screen or as an interval cancer. BV asymmetry was positively associated with the risk of an interval cancer diagnosis. ADVANCES IN KNOWLEDGE The findings suggest that DV and BV asymmetry may provide additional signals for detecting contemporaneous cancers and assessing the likelihood of interval cancers in population-based screening programmes.
Collapse
Affiliation(s)
- Sue M Hudson
- Department of Non-Communicable Disease Epidemiology, London School of Hygiene and Tropical Medicine, Keppel Street, London WC1E 7HT, UK
| | - Louise S Wilkinson
- Oxford Breast Imaging Centre, Oxford University Hospitals NHS Foundation Trust, Oxford, UK
| | - Bianca L De Stavola
- Faculty of Pop Health Sciences, Institute of Child Health, University College London, London, UK
| | - Isabel Dos-Santos-Silva
- Department of Non-Communicable Disease Epidemiology, London School of Hygiene and Tropical Medicine, Keppel Street, London WC1E 7HT, UK
| |
Collapse
|
6
|
Hudson SM, Wilkinson LS, Denholm R, De Stavola BL, Dos-Santos-Silva I. Ethnic and age differences in right-left breast asymmetry in a large population-based screening population. Br J Radiol 2019; 93:20190328. [PMID: 31661305 DOI: 10.1259/bjr.20190328] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/13/2022] Open
Abstract
OBJECTIVE Exposure to sex hormones is important in the pathogenesis of breast cancer and inability to tolerate such exposure may be reflected in increased asymmetrical growth of the breasts. This study aims to characterize, for the first time, asymmetry in breast volume (BV) and radiodense volume (DV) in a large ethnically diverse population. METHODS Automated measurements from digital raw mammographic images of 54,591 cancer-free participants (aged 47-73) in a UK breast screening programme were used to calculate absolute (cm3) and relative asymmetry in BV and DV. Logistic regression models were fitted to assess asymmetry associations with age and ethnicity. RESULTS BV and DV absolute asymmetry were positively correlated with the corresponding volumetric dimension (BV or DV). BV absolute asymmetry increased, whilst DV absolute asymmetry decreased, with increasing age (P-for-linear-trend <0.001 for both). Relative to Whites, Blacks had statistically significantly higher, and Chinese lower, BV and DV absolute asymmetries. However, after adjustment for the corresponding underlying volumetric dimension the age and ethnic differences were greatly attenuated. Median relative (fluctuating) BV and DV asymmetry were 2.34 and 3.28% respectively. CONCLUSION After adjusting for the relevant volumetric dimension (BV or DV), age and ethnic differences in absolute breast asymmetry were largely resolved. ADVANCES IN KNOWLEDGE Previous small studies have reported breast asymmetry-breast cancer associations. Automated measurements of asymmetry allow the conduct of large-scale studies to further investigate these associations.
Collapse
Affiliation(s)
- Sue M Hudson
- Department of Non-Communicable Disease Epidemiology, London School of Hygiene and Tropical Medicine, London, UK
| | - Louise S Wilkinson
- Oxford Breast Imaging Centre, University of Oxford Hospitals NHS Foundation Trust, Oxford, UK
| | - Rachel Denholm
- Centre for Academic Primary Care, Bristol Medical School, University of Bristol, Bristol, UK
| | - Bianca L De Stavola
- Population, Policy and Practice Programme, Great Ormond Street Institute of Child Health, University College London, UK
| | - Isabel Dos-Santos-Silva
- Department of Non-Communicable Disease Epidemiology, London School of Hygiene and Tropical Medicine, London, UK
| |
Collapse
|
7
|
Brandt KR, Scott CG, Miglioretti DL, Jensen MR, Mahmoudzadeh AP, Hruska C, Ma L, Wu FF, Cummings SR, Norman AD, Engmann NJ, Shepherd JA, Winham SJ, Kerlikowske K, Vachon CM. Automated volumetric breast density measures: differential change between breasts in women with and without breast cancer. Breast Cancer Res 2019; 21:118. [PMID: 31660981 PMCID: PMC6819393 DOI: 10.1186/s13058-019-1198-9] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/22/2019] [Accepted: 09/13/2019] [Indexed: 12/22/2022] Open
Abstract
BACKGROUND Given that breast cancer and normal dense fibroglandular tissue have similar radiographic attenuation, we examine whether automated volumetric density measures identify a differential change between breasts in women with cancer and compare to healthy controls. METHODS Eligible cases (n = 1160) had unilateral invasive breast cancer and bilateral full-field digital mammograms (FFDMs) at two time points: within 2 months and 1-5 years before diagnosis. Controls (n = 2360) were matched to cases on age and date of FFDMs. Dense volume (DV) and volumetric percent density (VPD) for each breast were assessed using Volpara™. Differences in DV and VPD between mammograms (median 3 years apart) were calculated per breast separately for cases and controls and their difference evaluated by using the Wilcoxon signed-rank test. To simulate clinical practice where cancer laterality is unknown, we examined whether the absolute difference between breasts can discriminate cases from controls using area under the ROC curve (AUC) analysis, adjusting for age, BMI, and time. RESULTS Among cases, the VPD and DV between mammograms of the cancerous breast decreased to a lesser degree (- 0.26% and - 2.10 cm3) than the normal breast (- 0.39% and - 2.74 cm3) for a difference of 0.13% (p value < 0.001) and 0.63 cm3 (p = 0.002), respectively. Among controls, the differences between breasts were nearly identical for VPD (- 0.02 [p = 0.92]) and DV (0.05 [p = 0.77]). The AUC for discriminating cases from controls using absolute difference between breasts was 0.54 (95% CI 0.52, 0.56) for VPD and 0.56 (95% CI, 0.54, 0.58) for DV. CONCLUSION There is a small relative increase in volumetric density measures over time in the breast with cancer which is not found in the normal breast. However, the magnitude of this difference is small, and this measure alone does not appear to be a good discriminator between women with and without breast cancer.
Collapse
Affiliation(s)
- Kathleen R Brandt
- Department of Radiology, Mayo Clinic, 200 First Street SW, Rochester, MN, 55905, USA.
| | - Christopher G Scott
- Department of Health Sciences Research, Mayo Clinic, 200 First Street SW, Rochester, MN, 55905, USA
| | - Diana L Miglioretti
- Kaiser Permanente Washington Health Research Institute, 1730 Minor Avenue, Seattle, WA, 98101, USA
| | - Matthew R Jensen
- Department of Health Sciences Research, Mayo Clinic, 200 First Street SW, Rochester, MN, 55905, USA
| | - Amir P Mahmoudzadeh
- Department of Radiology and Biomedical Imaging, University of California, 505 Parnassus Avenue, San Francisco, CA, 94143, USA
| | - Carrie Hruska
- Department of Radiology, Mayo Clinic, 200 First Street SW, Rochester, MN, 55905, USA
| | - Lin Ma
- Division of Research, Kaiser Permanente, 2000 Broadway, Oakland, CA, 94612, USA
| | - Fang Fang Wu
- Department of Health Sciences Research, Mayo Clinic, 200 First Street SW, Rochester, MN, 55905, USA
| | - Steven R Cummings
- California Pacific Medical Center Research Institute, 475 Brannan Street #220, San Francisco, CA, 94107, USA
| | - Aaron D Norman
- Department of Health Sciences Research, Mayo Clinic, 200 First Street SW, Rochester, MN, 55905, USA
| | - Natalie J Engmann
- Department of Epidemiology and Biostatistics, University of California, 550 16th Street, Second Floor, San Francisco, CA, 94158, USA
| | - John A Shepherd
- University of Hawaii Cancer Center, 701 Ilalo Street, Honolulu, HI, 96813, USA
| | - Stacey J Winham
- Department of Health Sciences Research, Mayo Clinic, 200 First Street SW, Rochester, MN, 55905, USA
| | - Karla Kerlikowske
- Department of Epidemiology and Biostatistics, University of California, 550 16th Street, Second Floor, San Francisco, CA, 94158, USA
| | - Celine M Vachon
- Department of Health Sciences Research, Mayo Clinic, 200 First Street SW, Rochester, MN, 55905, USA
| |
Collapse
|
8
|
Wang Z, Huang Y, Li M, Zhang H, Li C, Xin J, Qian W. Breast mass detection and diagnosis using fused features with density. JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY 2019; 27:321-342. [PMID: 30856154 DOI: 10.3233/xst-180461] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/09/2023]
Abstract
BACKGROUND The morbidity of breast cancer has been increased in these years and ranked the first of all female diseases. Computer-aided diagnosis techniques for mammograms can help radiologists find early breast lesions. In mammograms, the degree of malignancy of the tumor is not only related to its morphology and texture features, but also closely related to the density of the tumor. However, in the current research on breast masses detection and diagnosis, people usually use the fusion feature of morphology and texture but neglect density, or only the density feature is considered. Therefore, this paper proposes a method to detect and diagnose the breast mass using fused features with density. METHODS In this paper, we first propose a method based on sub-region clustering to detect the breast mass. The breast region is divided into sub-regions of equal size, and each sub-region is extracted based on local density feature, after that, an Unsupervised ELM (US-ELM) is used for clustering to complete the mass detection. Second, the feature model is constructed based on the mass. This model is composed of the mass region density feature, morphology feature and texture feature. And Genetic Algorithm is used for feature selection, and the optimized feature model is formed. Finally, ELM is used to diagnose benign or malignant mass. RESULTS An experiment on the real dataset of 480 mammograms in Northeast China shows that our proposed method can effectively improve the detection and diagnosis accuracy of breast masses, where we obtained 0.9184 precision in detection of breast masses and 0.911 accuracy in diagnosis of breast masses. CONCLUSIONS We have proposed a mass detection system, which achieves better detection accuracy performance than the existing state-of-art algorithm. We also propose a mass diagnosis system based on the fused features with density, which is more efficient than other feature model and classifier on the same dataset.
Collapse
Affiliation(s)
- Zhiqiong Wang
- Sino-Dutch Biomedical and Information Engineering School, Northeastern University, China
- Neusoft Research of Intelligent Healthcare Technology, Co. Ltd., China
- Acoustics Science and Technology Laboratory, Harbin Engineering University, China
| | - Yukun Huang
- College of Information Science and Engineering, Northeastern University, China
| | - Mo Li
- School of Computer Science and Engineering, Key Laboratory of Big Data Management and Analytics (Liaoning), Northeastern University, China
| | - Hao Zhang
- Department of Breast Surgery, Shengjing Hospital of China Medical University, China
| | - Chen Li
- Sino-Dutch Biomedical and Information Engineering School, Northeastern University, China
| | - Junchang Xin
- School of Computer Science and Engineering, Key Laboratory of Big Data Management and Analytics (Liaoning), Northeastern University, China
| | - Wei Qian
- College of Engineering, University of Texas at El Paso, USA
| |
Collapse
|
9
|
Kim SJ, Kim WG. Imaging and Clinical Features of an Unusual Unilateral Breast Enlargement Diagnosed as Fibrocystic Change: A Case Report. AMERICAN JOURNAL OF CASE REPORTS 2018; 19:1550-1555. [PMID: 30595602 PMCID: PMC6324867 DOI: 10.12659/ajcr.913456] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
Abstract
Patient: Female, 38 Final Diagnosis: Fibrocystic change Symptoms: Breast swelling Medication: — Clinical Procedure: Breast biopsy Specialty: Radiology
Collapse
Affiliation(s)
- Suk Jung Kim
- Department of Radiology, Haeundae Paik Hospital, Inje University College of Medicine, Busan, South Korea
| | - Woo Gyeong Kim
- Department of Pathology, Haeundae Paik Hospital, Inje University College of Medicine, Busan, South Korea
| |
Collapse
|
10
|
Yan S, Zhang L, Song C. Applying a new maximum local asymmetry feature analysis method to improve near-term breast cancer risk prediction. Phys Med Biol 2018; 63:205010. [PMID: 30255850 DOI: 10.1088/1361-6560/aae452] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
Abstract
Quantitative assessment of mammographic asymmetry has been investigated for breast cancer risk prediction. A new asymmetry feature extraction method was proposed in this study to enhance the risk prediction accuracy of near-term breast cancer. Breast areas in each pair of bilateral mammographic images were divided into several pairs of matched local annular regions and the maximum local asymmetry features (MLAF) were extracted from these regions. Radial basis function network (RBFN) was used to merge these features for breast cancer risk prediction. The dataset included 560 negative subjects. The risk prediction performance was tested using a leave-one-case-out (LOCO) cross-validation method. Area under the receiver operating characteristic curve (AUC) was used as the risk prediction performance evaluation index. AUC = 0.898 ± 0.013 was obtained by using the MLAFs extracted from the annular regions, which was significantly higher than the AUC value of 0.505 ± 0.025 achieved by using global asymmetry features computed from the whole breast regions (p < 0.05, DeLong's test) and much higher than the AUC values of 0.825 ± 0.017 and 0.717 ± 0.021 achieved by using MLAFs extracted from horizontal strip regions and vertical strip regions. The study demonstrated that near-term breast cancer risk prediction could be improved by using the proposed feature extraction method.
Collapse
Affiliation(s)
- Shiju Yan
- School of Medical Instrument and Food Engineering, University of Shanghai for Science and Technology, 516 Jungong Road, Shanghai 200093, People's Republic of China. Author to whom any correspondence should be addressed
| | | | | |
Collapse
|
11
|
Heidari M, Khuzani AZ, Hollingsworth AB, Danala G, Mirniaharikandehei S, Qiu Y, Liu H, Zheng B. Prediction of breast cancer risk using a machine learning approach embedded with a locality preserving projection algorithm. Phys Med Biol 2018; 63:035020. [PMID: 29239858 DOI: 10.1088/1361-6560/aaa1ca] [Citation(s) in RCA: 38] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
Abstract
In order to automatically identify a set of effective mammographic image features and build an optimal breast cancer risk stratification model, this study aims to investigate advantages of applying a machine learning approach embedded with a locally preserving projection (LPP) based feature combination and regeneration algorithm to predict short-term breast cancer risk. A dataset involving negative mammograms acquired from 500 women was assembled. This dataset was divided into two age-matched classes of 250 high risk cases in which cancer was detected in the next subsequent mammography screening and 250 low risk cases, which remained negative. First, a computer-aided image processing scheme was applied to segment fibro-glandular tissue depicted on mammograms and initially compute 44 features related to the bilateral asymmetry of mammographic tissue density distribution between left and right breasts. Next, a multi-feature fusion based machine learning classifier was built to predict the risk of cancer detection in the next mammography screening. A leave-one-case-out (LOCO) cross-validation method was applied to train and test the machine learning classifier embedded with a LLP algorithm, which generated a new operational vector with 4 features using a maximal variance approach in each LOCO process. Results showed a 9.7% increase in risk prediction accuracy when using this LPP-embedded machine learning approach. An increased trend of adjusted odds ratios was also detected in which odds ratios increased from 1.0 to 11.2. This study demonstrated that applying the LPP algorithm effectively reduced feature dimensionality, and yielded higher and potentially more robust performance in predicting short-term breast cancer risk.
Collapse
Affiliation(s)
- Morteza Heidari
- School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK 73019, United States of America. Author to whom any correspondence should be addressed
| | | | | | | | | | | | | | | |
Collapse
|
12
|
Li Y, Fan M, Cheng H, Zhang P, Zheng B, Li L. Assessment of global and local region-based bilateral mammographic feature asymmetry to predict short-term breast cancer risk. Phys Med Biol 2018; 63:025004. [PMID: 29226849 DOI: 10.1088/1361-6560/aaa096] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/10/2023]
Abstract
This study aims to develop and test a new imaging marker-based short-term breast cancer risk prediction model. An age-matched dataset of 566 screening mammography cases was used. All 'prior' images acquired in the two screening series were negative, while in the 'current' screening images, 283 cases were positive for cancer and 283 cases remained negative. For each case, two bilateral cranio-caudal view mammograms acquired from the 'prior' negative screenings were selected and processed by a computer-aided image processing scheme, which segmented the entire breast area into nine strip-based local regions, extracted the element regions using difference of Gaussian filters, and computed both global- and local-based bilateral asymmetrical image features. An initial feature pool included 190 features related to the spatial distribution and structural similarity of grayscale values, as well as of the magnitude and phase responses of multidirectional Gabor filters. Next, a short-term breast cancer risk prediction model based on a generalized linear model was built using an embedded stepwise regression analysis method to select features and a leave-one-case-out cross-validation method to predict the likelihood of each woman having image-detectable cancer in the next sequential mammography screening. The area under the receiver operating characteristic curve (AUC) values significantly increased from 0.5863 ± 0.0237 to 0.6870 ± 0.0220 when the model trained by the image features extracted from the global regions and by the features extracted from both the global and the matched local regions (p = 0.0001). The odds ratio values monotonically increased from 1.00-8.11 with a significantly increasing trend in slope (p = 0.0028) as the model-generated risk score increased. In addition, the AUC values were 0.6555 ± 0.0437, 0.6958 ± 0.0290, and 0.7054 ± 0.0529 for the three age groups of 37-49, 50-65, and 66-87 years old, respectively. AUC values of 0.6529 ± 0.1100, 0.6820 ± 0.0353, 0.6836 ± 0.0302 and 0.8043 ± 0.1067 were yielded for the four mammography density sub-groups (BIRADS from 1-4), respectively. This study demonstrated that bilateral asymmetry features extracted from local regions combined with the global region in bilateral negative mammograms could be used as a new imaging marker to assist in the prediction of short-term breast cancer risk.
Collapse
Affiliation(s)
- Yane Li
- College of Life Information Science and Instrument Engineering, Hangzhou Dianzi University, Hangzhou 310018, People's Republic of China
| | | | | | | | | | | |
Collapse
|
13
|
Robichaux JP, Fuseler JW, Patel SS, Kubalak SW, Hartstone-Rose A, Ramsdell AF. Left-right analysis of mammary gland development in retinoid X receptor-α+/- mice. Philos Trans R Soc Lond B Biol Sci 2017; 371:rstb.2015.0416. [PMID: 27821527 DOI: 10.1098/rstb.2015.0416] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 06/01/2016] [Indexed: 12/31/2022] Open
Abstract
Left-right (L-R) differences in mammographic parenchymal patterns are an early predictor of breast cancer risk; however, the basis for this asymmetry is unknown. Here, we use retinoid X receptor alpha heterozygous null (RXRα+/-) mice to propose a developmental origin: perturbation of coordinated anterior-posterior (A-P) and L-R axial body patterning. We hypothesized that by analogy to somitogenesis-in which retinoic acid (RA) attenuation causes anterior somite pairs to develop L-R asynchronously-that RA pathway perturbation would likewise result in asymmetric mammary development. To test this, mammary glands of RXRα+/- mice were quantitatively assessed to compare left- versus right-side ductal epithelial networks. Unlike wild-type controls, half of the RXRα+/- thoracic mammary gland (TMG) pairs exhibited significant L-R asymmetry, with left-side reduction in network size. In RXRα+/- TMGs in which symmetry was maintained, networks had bilaterally increased size, with left networks showing greater variability in area and pattern. Reminiscent of posterior somites, whose bilateral symmetry is refractory to RA attenuation, inguinal mammary glands (IMGs) also had bilaterally increased network size, but no loss of symmetry. Together, these results demonstrate that mammary glands exhibit differential A-P sensitivity to RXRα heterozygosity, with ductal network symmetry markedly compromised in anterior but not posterior glands. As TMGs more closely model human breast development than IMGs, these findings raise the possibility that for some women, breast cancer risk may initiate with subtle axial patterning defects that result in L-R asymmetric growth and pattern of the mammary ductal epithelium.This article is part of the themed issue 'Provocative questions in left-right asymmetry'.
Collapse
Affiliation(s)
- Jacqulyne P Robichaux
- Department of Regenerative Medicine and Cell Biology, Medical University of South Carolina, Charleston, SC 29425, USA
| | - John W Fuseler
- Department of Cell Biology and Anatomy, School of Medicine, University of South Carolina, Columbia, SC 29208, USA
| | - Shrusti S Patel
- Department of Cell Biology and Anatomy, School of Medicine, University of South Carolina, Columbia, SC 29208, USA
| | - Steven W Kubalak
- Department of Regenerative Medicine and Cell Biology, Medical University of South Carolina, Charleston, SC 29425, USA
| | - Adam Hartstone-Rose
- Department of Cell Biology and Anatomy, School of Medicine, University of South Carolina, Columbia, SC 29208, USA
| | - Ann F Ramsdell
- Department of Regenerative Medicine and Cell Biology, Medical University of South Carolina, Charleston, SC 29425, USA .,Hollings Cancer Center, Medical University of South Carolina, Charleston, SC 29425, USA.,Department of Cell Biology and Anatomy, School of Medicine, University of South Carolina, Columbia, SC 29208, USA.,Program in Women's and Gender Studies, College of Arts and Sciences, University of South Carolina, Columbia, SC 29208, USA
| |
Collapse
|
14
|
Applying a new bilateral mammographic density segmentation method to improve accuracy of breast cancer risk prediction. Int J Comput Assist Radiol Surg 2017; 12:1819-1828. [PMID: 28726117 DOI: 10.1007/s11548-017-1648-8] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2017] [Accepted: 07/12/2017] [Indexed: 10/19/2022]
Abstract
PURPOSE How to optimally detect bilateral mammographic asymmetry and improve risk prediction accuracy remains a difficult and unsolved issue. Our aim was to find an effective mammographic density segmentation method to improve accuracy of breast cancer risk prediction. METHODS A dataset including 168 negative mammography screening cases was used. We applied a mutual threshold to bilateral mammograms of left and right breasts to segment the dense breast regions. The mutual threshold was determined by the median grayscale value of all pixels in both left and right breast regions. For each case, we then computed three types of image features representing asymmetry, mean and the maximum of the image features, respectively. A two-stage classification scheme was developed to fuse the three types of features. The risk prediction performance was tested using a leave-one-case-out cross-validation method. RESULTS By using the new density segmentation method, the computed area under the receiver operating characteristic curve was 0.830 ± 0.033 and overall prediction accuracy was 81.0%, significantly higher than those of 0.633 ± 0.043 and 57.1% achieved by using the previous density segmentation method ([Formula: see text], t-test). CONCLUSIONS A new mammographic density segmentation method based on a bilateral mutual threshold can be used to more effectively detect bilateral mammographic density asymmetry and help significantly improve accuracy of near-term breast cancer risk prediction.
Collapse
|
15
|
Tan M, Zheng B, Leader JK, Gur D. Association Between Changes in Mammographic Image Features and Risk for Near-Term Breast Cancer Development. IEEE TRANSACTIONS ON MEDICAL IMAGING 2016; 35:1719-28. [PMID: 26886970 PMCID: PMC4938728 DOI: 10.1109/tmi.2016.2527619] [Citation(s) in RCA: 33] [Impact Index Per Article: 4.1] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/19/2023]
Abstract
The purpose of this study is to develop and test a new computerized model for predicting near-term breast cancer risk based on quantitative assessment of bilateral mammographic image feature variations in a series of negative full-field digital mammography (FFDM) images. The retrospective dataset included series of four sequential FFDM examinations of 335 women. The last examination in each series ("current") and the three most recent "prior" examinations were obtained. All "prior" examinations were interpreted as negative during the original clinical image reading, while in the "current" examinations 159 cancers were detected and pathologically verified and 176 cases remained cancer-free. From each image, we initially computed 158 mammographic density, structural similarity, and texture based image features. The absolute subtraction value between the left and right breasts was selected to represent each feature. We then built three support vector machine (SVM) based risk models, which were trained and tested using a leave-one-case-out based cross-validation method. The actual features used in each SVM model were selected using a nested stepwise regression analysis method. The computed areas under receiver operating characteristic curves monotonically increased from 0.666±0.029 to 0.730±0.027 as the time-lag between the "prior" (3 to 1) and "current" examinations decreases. The maximum adjusted odds ratios were 5.63, 7.43, and 11.1 for the three "prior" (3 to 1) sets of examinations, respectively. This study demonstrated a positive association between the risk scores generated by a bilateral mammographic feature difference based risk model and an increasing trend of the near-term risk for having mammography-detected breast cancer.
Collapse
Affiliation(s)
- Maxine Tan
- School of Electrical and Computer Engineering, University of
Oklahoma, Norman, OK 73019 USA
| | - Bin Zheng
- School of Electrical and Computer Engineering, University of
Oklahoma, Norman, OK 73019 USA
| | - Joseph K. Leader
- Department of Radiology, University of Pittsburgh, Pittsburgh, PA
15213 USA
| | - David Gur
- Department of Radiology, University of Pittsburgh, Pittsburgh, PA
15213 USA
| |
Collapse
|
16
|
Identification of mammography anomalies for breast cancer detection by an ensemble of classification models based on artificial immune system. Knowl Based Syst 2016. [DOI: 10.1016/j.knosys.2016.02.019] [Citation(s) in RCA: 24] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
|