1
|
Farahmand M, Mirinejad H, Scully CG. Model-based approach to investigate equipment-induced error in pressure-waveform derived hemodynamic measurements. Physiol Meas 2021; 42:10.1088/1361-6579/ac38be. [PMID: 34763325 PMCID: PMC8757537 DOI: 10.1088/1361-6579/ac38be] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/29/2021] [Accepted: 11/11/2021] [Indexed: 12/30/2022]
Abstract
Objective.Advanced hemodynamic monitoring systems have provided less invasive methods for estimating pressure-derived measurements such as pressure-derived cardiac output (CO) measurements. These devices apply algorithms to arterial pressure waveforms recorded via pressure recording components that transmit the pressure signal to a pressure monitor. While standards have been developed for pressure monitoring equipment, it is unclear how the equipment-induced error can affect secondary measurements from pressure waveforms. We propose an approach for modelling different components of a pressure monitoring system and use this model-based approach to investigate the effect of different pressure recording configurations on pressure-derived hemodynamic measurements.Approach.The proposed model-based approach is a three step process. (1) Modelling the response of pressure recording components using bench tests; (2) verifying the identified models through nonparametric equivalence tests; and (3) assessing the effects of pressure recording components on pressure-derived measurements. To delineate the application of this approach, we performed a series of model-based analyses to quantify the combined effect of a wide range of tubing configurations with various damping ratios and natural frequencies and monitors with different bandwidths on pressure waveforms and CO measurements by six pulse contour algorithms.Results.Model-based results show the error in pressure-derived CO measurements because of tubing configurations with different natural frequencies and damping ratios. Tubing configurations with low natural frequencies (<23 Hz) altered characteristics of pressure waveforms in a way that affected the CO measurement, some by as much as 20%.Significance.Our method can serve as a tool to quantify the performance of pressure recording systems with different dynamic properties. This approach can be applied to investigate the effects of physiologic signal recording configurations on various pressure-derived hemodynamic measurements.
Collapse
Affiliation(s)
- Masoud Farahmand
- Division of Biomedical Physics, Office of Science and Engineering Laboratories, Center for Devices and Radiological Health, Food and Drug Administration, Silver Spring, MD 20993, United States of America
| | - Hossein Mirinejad
- College of Aeronautics and Engineering, Kent State University, Kent, OH 44242, United States of America
| | - Christopher G Scully
- Division of Biomedical Physics, Office of Science and Engineering Laboratories, Center for Devices and Radiological Health, Food and Drug Administration, Silver Spring, MD 20993, United States of America
| |
Collapse
|
2
|
Acciavatti RJ, Cohen EA, Maghsoudi OH, Gastounioti A, Pantalone L, Hsieh MK, Conant EF, Scott CG, Winham SJ, Kerlikowske K, Vachon C, Maidment ADA, Kontos D. Incorporating Robustness to Imaging Physics into Radiomic Feature Selection for Breast Cancer Risk Estimation. Cancers (Basel) 2021; 13:5497. [PMID: 34771660 PMCID: PMC8582675 DOI: 10.3390/cancers13215497] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/21/2021] [Revised: 10/16/2021] [Accepted: 10/27/2021] [Indexed: 11/17/2022] Open
Abstract
Digital mammography has seen an explosion in the number of radiomic features used for risk-assessment modeling. However, having more features is not necessarily beneficial, as some features may be overly sensitive to imaging physics (contrast, noise, and image sharpness). To measure the effects of imaging physics, we analyzed the feature variation across imaging acquisition settings (kV, mAs) using an anthropomorphic phantom. We also analyzed the intra-woman variation (IWV), a measure of how much a feature varies between breasts with similar parenchymal patterns-a woman's left and right breasts. From 341 features, we identified "robust" features that minimized the effects of imaging physics and IWV. We also investigated whether robust features offered better case-control classification in an independent data set of 575 images, all with an overall BI-RADS® assessment of 1 (negative) or 2 (benign); 115 images (cases) were of women who developed cancer at least one year after that screening image, matched to 460 controls. We modeled cancer occurrence via logistic regression, using cross-validated area under the receiver-operating-characteristic curve (AUC) to measure model performance. Models using features from the most-robust quartile of features yielded an AUC = 0.59, versus 0.54 for the least-robust, with p < 0.005 for the difference among the quartiles.
Collapse
Affiliation(s)
- Raymond J. Acciavatti
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA; (E.A.C.); (O.H.M.); (A.G.); (L.P.); (M.-K.H.); (E.F.C.); (A.D.A.M.); (D.K.)
| | - Eric A. Cohen
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA; (E.A.C.); (O.H.M.); (A.G.); (L.P.); (M.-K.H.); (E.F.C.); (A.D.A.M.); (D.K.)
| | - Omid Haji Maghsoudi
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA; (E.A.C.); (O.H.M.); (A.G.); (L.P.); (M.-K.H.); (E.F.C.); (A.D.A.M.); (D.K.)
| | - Aimilia Gastounioti
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA; (E.A.C.); (O.H.M.); (A.G.); (L.P.); (M.-K.H.); (E.F.C.); (A.D.A.M.); (D.K.)
| | - Lauren Pantalone
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA; (E.A.C.); (O.H.M.); (A.G.); (L.P.); (M.-K.H.); (E.F.C.); (A.D.A.M.); (D.K.)
| | - Meng-Kang Hsieh
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA; (E.A.C.); (O.H.M.); (A.G.); (L.P.); (M.-K.H.); (E.F.C.); (A.D.A.M.); (D.K.)
| | - Emily F. Conant
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA; (E.A.C.); (O.H.M.); (A.G.); (L.P.); (M.-K.H.); (E.F.C.); (A.D.A.M.); (D.K.)
| | - Christopher G. Scott
- Division of Epidemiology, Department of Health Sciences Research, Mayo Clinic, Rochester, MN 55905, USA; (C.G.S.); (S.J.W.); (C.V.)
| | - Stacey J. Winham
- Division of Epidemiology, Department of Health Sciences Research, Mayo Clinic, Rochester, MN 55905, USA; (C.G.S.); (S.J.W.); (C.V.)
| | - Karla Kerlikowske
- Departments of Medicine and Epidemiology/Biostatistics, Women’s Health Clinical Research Center, UCSF, San Francisco, CA 94143, USA;
| | - Celine Vachon
- Division of Epidemiology, Department of Health Sciences Research, Mayo Clinic, Rochester, MN 55905, USA; (C.G.S.); (S.J.W.); (C.V.)
| | - Andrew D. A. Maidment
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA; (E.A.C.); (O.H.M.); (A.G.); (L.P.); (M.-K.H.); (E.F.C.); (A.D.A.M.); (D.K.)
| | - Despina Kontos
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA; (E.A.C.); (O.H.M.); (A.G.); (L.P.); (M.-K.H.); (E.F.C.); (A.D.A.M.); (D.K.)
| |
Collapse
|
3
|
Nisbett WH, Kavuri A, Das M. On the correlation between second order texture features and human observer detection performance in digital images. Sci Rep 2020; 10:13510. [PMID: 32782415 PMCID: PMC7419558 DOI: 10.1038/s41598-020-69816-z] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/10/2019] [Accepted: 07/14/2020] [Indexed: 11/15/2022] Open
Abstract
Image texture, the relative spatial arrangement of intensity values in an image, encodes valuable information about the scene. As it stands, much of this potential information remains untapped. Understanding how to decipher textural details would afford another method of extracting knowledge of the physical world from images. In this work, we attempt to bridge the gap in research between quantitative texture analysis and the visual perception of textures. The impact of changes in image texture on human observer's ability to perform signal detection and localization tasks in complex digital images is not understood. We examine this critical question by studying task-based human observer performance in detecting and localizing signals in tomographic breast images. We have also investigated how these changes impact the formation of second-order image texture. We used digital breast tomosynthesis (DBT) an FDA approved tomographic X-ray breast imaging method as the modality of choice to show our preliminary results. Our human observer studies involve localization ROC (LROC) studies for low contrast mass detection in DBT. Simulated images are used as they offer the benefit of known ground truth. Our results prove that changes in system geometry or processing leads to changes in image texture magnitudes. We show that the variations in several well-known texture features estimated in digital images correlate with human observer detection-localization performance for signals embedded in them. This insight can allow efficient and practical techniques to identify the best imaging system design and algorithms or filtering tools by examining the changes in these texture features. This concept linking texture feature estimates and task based image quality assessment can be extended to several other imaging modalities and applications as well. It can also offer feedback in system and algorithm designs with a goal to improve perceptual benefits. Broader impact can be in wide array of areas including imaging system design, image processing, data science, machine learning, computer vision, perceptual and vision science. Our results also point to the caution that must be exercised in using these texture features as image-based radiomic features or as predictive markers for risk assessment as they are sensitive to system or image processing changes.
Collapse
Affiliation(s)
- William H Nisbett
- Department of Physics, University of Houston, Houston, TX, 77004, USA
| | - Amar Kavuri
- Department of Biomedical Engineering, University of Houston, Houston, TX, 77004, USA
| | - Mini Das
- Department of Physics, University of Houston, Houston, TX, 77004, USA.
- Department of Biomedical Engineering, University of Houston, Houston, TX, 77004, USA.
| |
Collapse
|
4
|
Acciavatti RJ, Cohen EA, Maghsoudi OH, Gastounioti A, Pantalone L, Hsieh MK, Conant EF, Scott CG, Winham SJ, Kerlikowske K, Vachon C, Maidment ADA, Kontos D. Robust Radiomic Feature Selection in Digital Mammography: Understanding the Effect of Imaging Acquisition Physics Using Phantom and Clinical Data Analysis. PROCEEDINGS OF SPIE--THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING 2020; 11314:113140W. [PMID: 37982014 PMCID: PMC10655898 DOI: 10.1117/12.2549163] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/21/2023]
Abstract
Studies have shown that combining calculations of radiomic features with estimates of mammographic density results in an even better assessment of breast cancer risk than density alone. However, to ensure that risk assessment calculations are consistent across different imaging acquisition settings, it is important to identify features that are not overly sensitive to changes in these settings. In this study, digital mammography (DM) images of an anthropomorphic phantom ("Rachel", Gammex 169, Madison, WI) were acquired at various technique settings. We varied kV and mAs, which control contrast and noise, respectively. DM images in women with negative screening exams were also analyzed. Radiomic features were calculated in the raw ("FOR PROCESSING") DM images; i.e., grey-level histogram, co-occurrence, run length, fractal dimension, Gabor Wavelet, local binary pattern, Laws, and co-occurrence Laws features. For each feature, the range of variation across technique settings in phantom images was calculated. This range was scaled against the range of variation in the clinical distribution (specifically, the range corresponding to the middle 90% of the distribution). In order for a radiomic feature to be considered robust, this metric of imaging acquisition variation (IAV) should be as small as possible (approaching zero). An IAV threshold of 0.25 was proposed for the purpose of this study. Out of 341 features, 284 features (83%) met the threshold IAV ≤ 0.25. In conclusion, we have developed a method to identify robust radiomic features in DM.
Collapse
Affiliation(s)
- Raymond J Acciavatti
- University of Pennsylvania, Department of Radiology, 3400 Spruce Street, Philadelphia PA 19104
| | - Eric A Cohen
- University of Pennsylvania, Department of Radiology, 3400 Spruce Street, Philadelphia PA 19104
| | - Omid Haji Maghsoudi
- University of Pennsylvania, Department of Radiology, 3400 Spruce Street, Philadelphia PA 19104
| | - Aimilia Gastounioti
- University of Pennsylvania, Department of Radiology, 3400 Spruce Street, Philadelphia PA 19104
| | - Lauren Pantalone
- University of Pennsylvania, Department of Radiology, 3400 Spruce Street, Philadelphia PA 19104
| | - Meng-Kang Hsieh
- University of Pennsylvania, Department of Radiology, 3400 Spruce Street, Philadelphia PA 19104
| | - Emily F Conant
- University of Pennsylvania, Department of Radiology, 3400 Spruce Street, Philadelphia PA 19104
| | | | | | - Karla Kerlikowske
- UCSF Women's Health Clinical Research Center, 550 16 Street, San Francisco CA 94143
| | - Celine Vachon
- Mayo Clinic, 200 First Street SW, Rochester MN 55905
| | - Andrew D A Maidment
- University of Pennsylvania, Department of Radiology, 3400 Spruce Street, Philadelphia PA 19104
| | - Despina Kontos
- University of Pennsylvania, Department of Radiology, 3400 Spruce Street, Philadelphia PA 19104
| |
Collapse
|
5
|
Evans KK, Culpan AM, Wolfe JM. Detecting the "gist" of breast cancer in mammograms three years before localized signs of cancer are visible. Br J Radiol 2019; 92:20190136. [PMID: 31166769 DOI: 10.1259/bjr.20190136] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/13/2023] Open
Abstract
OBJECTIVES After a 500 ms presentation, experts can distinguish abnormal mammograms at above chance levels even when only the breast contralateral to the lesion is shown. Here, we show that this signal of abnormality is detectable 3 years before localized signs of cancer become visible. METHODS In 4 prospective studies, 59 expert observers from 3 groups viewed 116-200 bilateral mammograms for 500 ms each. Half of the images were prior exams acquired 3 years prior to onset of visible, actionable cancer and half were normal. Exp. 1D included cases having visible abnormalities. Observers rated likelihood of abnormality on a 0-100 scale and categorized breast density. Performance was measured using receiver operating characteristic analysis. RESULTS In all three groups, observers could detect abnormal images at above chance levels 3 years prior to visible signs of breast cancer (p < 0.001). The results were not due to specific salient cases nor to breast density. Performance was correlated with expertise quantified by the number of mammographic cases read within a year. In Exp. 1D, with cases having visible actionable pathology included, the full group of readers failed to reliably detect abnormal priors; with the exception of a subgroup of the six most experienced observers. CONCLUSIONS Imaging specialists can detect signals of abnormality in mammograms acquired years before lesions become visible. Detection may depend on expertise acquired by reading large numbers of cases. ADVANCES IN KNOWLEDGE Global gist signal can serve as imaging risk factor with the potential to identify patients with elevated risk for developing cancer, resulting in improved early cancer diagnosis rates and improved prognosis for females with breast cancer.
Collapse
Affiliation(s)
- Karla K Evans
- 1 Psychology Department, University of York , York , United Kingdom
| | | | - Jeremy M Wolfe
- 3 Harvard Medical School and Brigham and Women's Hospital , Boston , MA, USA
| |
Collapse
|
6
|
Incorporating Breast Anatomy in Computational Phenotyping of Mammographic Parenchymal Patterns for Breast Cancer Risk Estimation. Sci Rep 2018; 8:17489. [PMID: 30504841 PMCID: PMC6269457 DOI: 10.1038/s41598-018-35929-9] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2018] [Accepted: 11/08/2018] [Indexed: 12/17/2022] Open
Abstract
We retrospectively analyzed negative screening digital mammograms from 115 women who developed unilateral breast cancer at least one year later and 460 matched controls. Texture features were estimated in multiple breast regions defined by an anatomically-oriented polar grid, and were weighted by their position and underlying dense versus fatty tissue composition. Elastic net regression with cross-validation was performed and area under the curve (AUC) of the receiver operating characteristic (ROC) was used to evaluate ability to predict breast cancer. We also compared our anatomy-augmented features to current state-of-the-art in which parenchymal texture was assessed without considering breast anatomy and evaluated the added value of the extracted features to breast density, body-mass-index (BMI) and age as baseline predictors. Our anatomy-augmented texture features resulted in higher discriminatory capacity (AUC = 0.63 vs. AUC = 0.59) when breast anatomy was not considered (p = 0.021), with dense tissue regions and the central breast quadrant being more heavily weighted. Texture also improved baseline models (from AUC = 0.62 to AUC = 0.67, p = 0.029). Our findings suggest that incorporating breast anatomy information could augment imaging markers of breast cancer risk with the potential to improve personalized breast cancer risk assessment.
Collapse
|
7
|
Kontos D, Winham SJ, Oustimov A, Pantalone L, Hsieh MK, Gastounioti A, Whaley DH, Hruska CB, Kerlikowske K, Brandt K, Conant EF, Vachon CM. Radiomic Phenotypes of Mammographic Parenchymal Complexity: Toward Augmenting Breast Density in Breast Cancer Risk Assessment. Radiology 2018; 290:41-49. [PMID: 30375931 DOI: 10.1148/radiol.2018180179] [Citation(s) in RCA: 53] [Impact Index Per Article: 8.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
Abstract
Purpose To identify phenotypes of mammographic parenchymal complexity by using radiomic features and to evaluate their associations with breast density and other breast cancer risk factors. Materials and Methods Computerized image analysis was used to quantify breast density and extract parenchymal texture features in a cross-sectional sample of women screened with digital mammography from September 1, 2012, to February 28, 2013 (n = 2029; age range, 35-75 years; mean age, 55.9 years). Unsupervised clustering was applied to identify and reproduce phenotypes of parenchymal complexity in separate training (n = 1339) and test sets (n = 690). Differences across phenotypes by age, body mass index, breast density, and estimated breast cancer risk were assessed by using Fisher exact, χ2, and Kruskal-Wallis tests. Conditional logistic regression was used to evaluate preliminary associations between the detected phenotypes and breast cancer in an independent case-control sample (76 women diagnosed with breast cancer and 158 control participants) matched on age. Results Unsupervised clustering in the screening sample identified four phenotypes with increasing parenchymal complexity that were reproducible between training and test sets (P = .001). Breast density was not strongly correlated with phenotype category (R2 = 0.24 for linear trend). The low- to intermediate-complexity phenotype (prevalence, 390 of 2029 [19%]) had the lowest proportion of dense breasts (eight of 390 [2.1%]), whereas similar proportions were observed across other phenotypes (from 140 of 291 [48.1%] in the high-complexity phenotype to 275 of 511 [53.8%] in the low-complexity phenotype). In the independent case-control sample, phenotypes showed a significant association with breast cancer (P = .001), resulting in higher discriminatory capacity when added to a model with breast density and body mass index (area under the curve, 0.84 vs 0.80; P = .03 for comparison). Conclusion Radiomic phenotypes capture mammographic parenchymal complexity beyond conventional breast density measures and established breast cancer risk factors. © RSNA, 2018 Online supplemental material is available for this article. See also the editorial by Pinker in this issue.
Collapse
Affiliation(s)
- Despina Kontos
- From the Department of Radiology, University of Pennsylvania, Perelman School of Medicine & Hospital of the University of Pennsylvania, 3400 Spruce St, Philadelphia, PA 19104 (D.K., A.O., L.P., M.K.H., A.G., E.F.C.); Department of Health Sciences Research (S.J.W., C.M.V.) and Department of Radiology (D.H.W., C.B.H., K.B.), Mayo Clinic, Rochester, Minn (S.J.W., D.H.W., C.B.H., K.B., C.M.V.); and Departments of Medicine and Epidemiology and Biostatistics, University of California at San Francisco, San Francisco, Calif (K.K.)
| | - Stacey J Winham
- From the Department of Radiology, University of Pennsylvania, Perelman School of Medicine & Hospital of the University of Pennsylvania, 3400 Spruce St, Philadelphia, PA 19104 (D.K., A.O., L.P., M.K.H., A.G., E.F.C.); Department of Health Sciences Research (S.J.W., C.M.V.) and Department of Radiology (D.H.W., C.B.H., K.B.), Mayo Clinic, Rochester, Minn (S.J.W., D.H.W., C.B.H., K.B., C.M.V.); and Departments of Medicine and Epidemiology and Biostatistics, University of California at San Francisco, San Francisco, Calif (K.K.)
| | - Andrew Oustimov
- From the Department of Radiology, University of Pennsylvania, Perelman School of Medicine & Hospital of the University of Pennsylvania, 3400 Spruce St, Philadelphia, PA 19104 (D.K., A.O., L.P., M.K.H., A.G., E.F.C.); Department of Health Sciences Research (S.J.W., C.M.V.) and Department of Radiology (D.H.W., C.B.H., K.B.), Mayo Clinic, Rochester, Minn (S.J.W., D.H.W., C.B.H., K.B., C.M.V.); and Departments of Medicine and Epidemiology and Biostatistics, University of California at San Francisco, San Francisco, Calif (K.K.)
| | - Lauren Pantalone
- From the Department of Radiology, University of Pennsylvania, Perelman School of Medicine & Hospital of the University of Pennsylvania, 3400 Spruce St, Philadelphia, PA 19104 (D.K., A.O., L.P., M.K.H., A.G., E.F.C.); Department of Health Sciences Research (S.J.W., C.M.V.) and Department of Radiology (D.H.W., C.B.H., K.B.), Mayo Clinic, Rochester, Minn (S.J.W., D.H.W., C.B.H., K.B., C.M.V.); and Departments of Medicine and Epidemiology and Biostatistics, University of California at San Francisco, San Francisco, Calif (K.K.)
| | - Meng-Kang Hsieh
- From the Department of Radiology, University of Pennsylvania, Perelman School of Medicine & Hospital of the University of Pennsylvania, 3400 Spruce St, Philadelphia, PA 19104 (D.K., A.O., L.P., M.K.H., A.G., E.F.C.); Department of Health Sciences Research (S.J.W., C.M.V.) and Department of Radiology (D.H.W., C.B.H., K.B.), Mayo Clinic, Rochester, Minn (S.J.W., D.H.W., C.B.H., K.B., C.M.V.); and Departments of Medicine and Epidemiology and Biostatistics, University of California at San Francisco, San Francisco, Calif (K.K.)
| | - Aimilia Gastounioti
- From the Department of Radiology, University of Pennsylvania, Perelman School of Medicine & Hospital of the University of Pennsylvania, 3400 Spruce St, Philadelphia, PA 19104 (D.K., A.O., L.P., M.K.H., A.G., E.F.C.); Department of Health Sciences Research (S.J.W., C.M.V.) and Department of Radiology (D.H.W., C.B.H., K.B.), Mayo Clinic, Rochester, Minn (S.J.W., D.H.W., C.B.H., K.B., C.M.V.); and Departments of Medicine and Epidemiology and Biostatistics, University of California at San Francisco, San Francisco, Calif (K.K.)
| | - Dana H Whaley
- From the Department of Radiology, University of Pennsylvania, Perelman School of Medicine & Hospital of the University of Pennsylvania, 3400 Spruce St, Philadelphia, PA 19104 (D.K., A.O., L.P., M.K.H., A.G., E.F.C.); Department of Health Sciences Research (S.J.W., C.M.V.) and Department of Radiology (D.H.W., C.B.H., K.B.), Mayo Clinic, Rochester, Minn (S.J.W., D.H.W., C.B.H., K.B., C.M.V.); and Departments of Medicine and Epidemiology and Biostatistics, University of California at San Francisco, San Francisco, Calif (K.K.)
| | - Carrie B Hruska
- From the Department of Radiology, University of Pennsylvania, Perelman School of Medicine & Hospital of the University of Pennsylvania, 3400 Spruce St, Philadelphia, PA 19104 (D.K., A.O., L.P., M.K.H., A.G., E.F.C.); Department of Health Sciences Research (S.J.W., C.M.V.) and Department of Radiology (D.H.W., C.B.H., K.B.), Mayo Clinic, Rochester, Minn (S.J.W., D.H.W., C.B.H., K.B., C.M.V.); and Departments of Medicine and Epidemiology and Biostatistics, University of California at San Francisco, San Francisco, Calif (K.K.)
| | - Karla Kerlikowske
- From the Department of Radiology, University of Pennsylvania, Perelman School of Medicine & Hospital of the University of Pennsylvania, 3400 Spruce St, Philadelphia, PA 19104 (D.K., A.O., L.P., M.K.H., A.G., E.F.C.); Department of Health Sciences Research (S.J.W., C.M.V.) and Department of Radiology (D.H.W., C.B.H., K.B.), Mayo Clinic, Rochester, Minn (S.J.W., D.H.W., C.B.H., K.B., C.M.V.); and Departments of Medicine and Epidemiology and Biostatistics, University of California at San Francisco, San Francisco, Calif (K.K.)
| | - Kathleen Brandt
- From the Department of Radiology, University of Pennsylvania, Perelman School of Medicine & Hospital of the University of Pennsylvania, 3400 Spruce St, Philadelphia, PA 19104 (D.K., A.O., L.P., M.K.H., A.G., E.F.C.); Department of Health Sciences Research (S.J.W., C.M.V.) and Department of Radiology (D.H.W., C.B.H., K.B.), Mayo Clinic, Rochester, Minn (S.J.W., D.H.W., C.B.H., K.B., C.M.V.); and Departments of Medicine and Epidemiology and Biostatistics, University of California at San Francisco, San Francisco, Calif (K.K.)
| | - Emily F Conant
- From the Department of Radiology, University of Pennsylvania, Perelman School of Medicine & Hospital of the University of Pennsylvania, 3400 Spruce St, Philadelphia, PA 19104 (D.K., A.O., L.P., M.K.H., A.G., E.F.C.); Department of Health Sciences Research (S.J.W., C.M.V.) and Department of Radiology (D.H.W., C.B.H., K.B.), Mayo Clinic, Rochester, Minn (S.J.W., D.H.W., C.B.H., K.B., C.M.V.); and Departments of Medicine and Epidemiology and Biostatistics, University of California at San Francisco, San Francisco, Calif (K.K.)
| | - Celine M Vachon
- From the Department of Radiology, University of Pennsylvania, Perelman School of Medicine & Hospital of the University of Pennsylvania, 3400 Spruce St, Philadelphia, PA 19104 (D.K., A.O., L.P., M.K.H., A.G., E.F.C.); Department of Health Sciences Research (S.J.W., C.M.V.) and Department of Radiology (D.H.W., C.B.H., K.B.), Mayo Clinic, Rochester, Minn (S.J.W., D.H.W., C.B.H., K.B., C.M.V.); and Departments of Medicine and Epidemiology and Biostatistics, University of California at San Francisco, San Francisco, Calif (K.K.)
| |
Collapse
|
8
|
Zhang L, Feldman AG, Levin MF. Vestibular and corticospinal control of human body orientation in the gravitational field. J Neurophysiol 2018; 120:3026-3041. [PMID: 30207862 DOI: 10.1152/jn.00483.2018] [Citation(s) in RCA: 21] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/21/2022] Open
Abstract
Body orientation with respect to the direction of gravity changes when we lean forward from upright standing. We tested the hypothesis that during upright standing, the nervous system specifies the referent body orientation that defines spatial thresholds for activation of multiple muscles across the body. To intentionally lean the body forward, the system is postulated to transfer balance and stability to the leaned position by monotonically tilting the referent orientation, thus increasing the activation thresholds of ankle extensors and decreasing their activity. Consequently, the unbalanced gravitational torque would start to lean the body forward. With restretching, ankle extensors would be reactivated and generate increasing electromyographic (EMG) activity until the enhanced gravitational torque would be balanced at a new posture. As predicted, vestibular influences on motoneurons of ankle extensors evaluated by galvanic vestibular stimulation were smaller in the leaned compared with the upright position, despite higher tonic EMG activity. Defacilitation of vestibular influences was also observed during forward leaning when the EMG levels in the upright and leaned position were equalized by compensating the gravitational torque with a load. The vestibular system is involved in the active control of body orientation without directly specifying the motor outcome. Corticospinal influences originating from the primary motor cortex evaluated by transcranial magnetic stimulation remained similar at the two body postures. Thus, in contrast to the vestibular system, the corticospinal system maintains a similar descending facilitation of motoneurons of leg muscles at different body orientations. The study advances the understanding of how body orientation is controlled. NEW & NOTEWORTHY The brain changes the referent body orientation with respect to gravity to lean the body forward. Physiologically, this is achieved by shifts in spatial thresholds for activation of ankle muscles, which involves the vestibular system. Results advance the understanding of how the brain controls body orientation in the gravitational field. The study also extends previous evidence of empirical control of motor function, i.e., without the reliance on model-based computations and direct specification of motor outcome.
Collapse
Affiliation(s)
- Lei Zhang
- Department of Neuroscience, University of Montreal , Montreal, Quebec , Canada.,Institut de Réadaptation Gingras-Lindsay de Montréal, Centre for Interdisciplinary Research in Rehabilitation of Greater Montreal (CRIR) , Montreal, Quebec , Canada.,Jewish Rehabilitation Hospital, CRIR, Laval, Quebec , Canada
| | - Anatol G Feldman
- Department of Neuroscience, University of Montreal , Montreal, Quebec , Canada.,Institut de Réadaptation Gingras-Lindsay de Montréal, Centre for Interdisciplinary Research in Rehabilitation of Greater Montreal (CRIR) , Montreal, Quebec , Canada.,Jewish Rehabilitation Hospital, CRIR, Laval, Quebec , Canada
| | - Mindy F Levin
- Jewish Rehabilitation Hospital, CRIR, Laval, Quebec , Canada.,School of Physical and Occupational Therapy, McGill University , Montreal, Quebec , Canada
| |
Collapse
|
9
|
Gastounioti A, Oustimov A, Hsieh MK, Pantalone L, Conant EF, Kontos D. Using Convolutional Neural Networks for Enhanced Capture of Breast Parenchymal Complexity Patterns Associated with Breast Cancer Risk. Acad Radiol 2018; 25:977-984. [PMID: 29395798 PMCID: PMC6026048 DOI: 10.1016/j.acra.2017.12.025] [Citation(s) in RCA: 19] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/14/2017] [Revised: 12/15/2017] [Accepted: 12/22/2017] [Indexed: 01/08/2023]
Abstract
RATIONALE AND OBJECTIVES We evaluate utilizing convolutional neural networks (CNNs) to optimally fuse parenchymal complexity measurements generated by texture analysis into discriminative meta-features relevant for breast cancer risk prediction. MATERIALS AND METHODS With Institutional Review Board approval and Health Insurance Portability and Accountability Act compliance, we retrospectively analyzed "For Processing" contralateral digital mammograms (GE Healthcare 2000D/DS) from 106 women with unilateral invasive breast cancer and 318 age-matched controls. We coupled established texture features (histogram, co-occurrence, run-length, structural), extracted using a previously validated lattice-based strategy, with a multichannel CNN into a hybrid framework in which a multitude of texture feature maps are reduced to meta-features predicting the case or control status. We evaluated the framework in a randomized split-sample setting, using the area under the curve (AUC) of the receiver operating characteristic (ROC) to assess case-control discriminatory capacity. We also compared the framework to CNNs directly fed with mammographic images, as well as to conventional texture analysis, where texture feature maps are summarized via simple statistical measures that are then used as inputs to a logistic regression model. RESULTS Strong case-control discriminatory capacity was demonstrated on the basis of the meta-features generated by the hybrid framework (AUC = 0.90), outperforming both CNNs applied directly to raw image data (AUC = 0.63, P <.05) and conventional texture analysis (AUC = 0.79, P <.05). CONCLUSIONS Our results suggest that informative interactions between patterns exist in texture feature maps derived from mammographic images, which can be extracted and summarized via a multichannel CNN architecture toward leveraging the associations of textural measurements to breast cancer risk.
Collapse
Affiliation(s)
- Aimilia Gastounioti
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 3710 Hamilton Walk, Rm D601E Goddard Bldg., Philadelphia, PA 19104.
| | - Andrew Oustimov
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 3710 Hamilton Walk, Rm D601E Goddard Bldg., Philadelphia, PA 19104
| | - Meng-Kang Hsieh
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 3710 Hamilton Walk, Rm D601E Goddard Bldg., Philadelphia, PA 19104
| | - Lauren Pantalone
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 3710 Hamilton Walk, Rm D601E Goddard Bldg., Philadelphia, PA 19104
| | - Emily F Conant
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 3710 Hamilton Walk, Rm D601E Goddard Bldg., Philadelphia, PA 19104
| | - Despina Kontos
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 3710 Hamilton Walk, Rm D601E Goddard Bldg., Philadelphia, PA 19104
| |
Collapse
|
10
|
Acciavatti RJ, Hsieh MK, Gastounioti A, Hu Y, Chen J, Maidment ADA, Kontos D. Validation of the Textural Realism of a 3D Anthropomorphic Phantom for Digital Breast Tomosynthesis. PROCEEDINGS OF SPIE--THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING 2018; 10718:107180R. [PMID: 38222313 PMCID: PMC10786666 DOI: 10.1117/12.2318029] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/16/2024]
Abstract
In this paper, texture calculations are used to validate the realism of a physical anthropomorphic phantom for digital breast tomosynthesis. The texture features were compared against clinical mammography data. Three groups of features (grey-level histogram, co-occurrence, and run-length) were considered. The features were analyzed over a broad range of technique settings (kV and mAs). These calculations were done in the central slice of the reconstruction as well as the synthetic 2D mammogram. For each feature, the clinical data were binned into strata based on the compressed breast thickness. It was demonstrated that the clinical features vary by thickness. To evaluate the realism of the phantom, each feature was compared against clinical data in the same thickness stratum. For the purpose of this paper, a feature was considered to be realistic if it was within the middle 95% of the statistical distribution of clinical values. In the reconstruction, most features were found to exhibit realism; specifically, all 12 grey-level histogram features, four out of seven co-occurrence features, and three out of seven run-length features. The realism of most features was robust to changes in the technique settings. However, in the synthetic 2D mammogram, fewer features were found to exhibit realism. In conclusion, this paper provides a validation of the textural realism of the phantom in the reconstruction, and shows that there is less realism in the synthetic 2D mammogram. We identify the features that should be considered to refine the design of the phantom in future work.
Collapse
Affiliation(s)
- Raymond J Acciavatti
- University of Pennsylvania, Department of Radiology, 3400 Spruce Street, Philadelphia PA 19104
| | - Meng-Kang Hsieh
- University of Pennsylvania, Department of Radiology, 3400 Spruce Street, Philadelphia PA 19104
| | - Aimilia Gastounioti
- University of Pennsylvania, Department of Radiology, 3400 Spruce Street, Philadelphia PA 19104
| | - Yifan Hu
- University of Pennsylvania, Department of Radiology, 3400 Spruce Street, Philadelphia PA 19104
| | - Jinbo Chen
- University of Pennsylvania, Department of Epidemiology, Biostatistics, & Informatics, 423 Guardian Drive, Philadelphia PA 19104
| | - Andrew D A Maidment
- University of Pennsylvania, Department of Radiology, 3400 Spruce Street, Philadelphia PA 19104
| | - Despina Kontos
- University of Pennsylvania, Department of Radiology, 3400 Spruce Street, Philadelphia PA 19104
| |
Collapse
|
11
|
Radiogenomics analysis identifies correlations of digital mammography with clinical molecular signatures in breast cancer. PLoS One 2018; 13:e0193871. [PMID: 29596496 PMCID: PMC5875760 DOI: 10.1371/journal.pone.0193871] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/09/2017] [Accepted: 02/19/2018] [Indexed: 12/21/2022] Open
Abstract
In breast cancer, well-known gene expression subtypes have been related to a specific clinical outcome. However, their impact on the breast tissue phenotype has been poorly studied. Here, we investigate the association of imaging data of tumors to gene expression signatures from 71 patients with breast cancer that underwent pre-treatment digital mammograms and tumor biopsies. From digital mammograms, a semi-automated radiogenomics analysis generated 1,078 features describing the shape, signal distribution, and texture of tumors along their contralateral image used as control. From tumor biopsy, we estimated the OncotypeDX and PAM50 recurrence scores using gene expression microarrays. Then, we used multivariate analysis under stringent cross-validation to train models predicting recurrence scores. Few univariate features reached Spearman correlation coefficients above 0.4. Nevertheless, multivariate analysis yielded significantly correlated models for both signatures (correlation of OncotypeDX = 0.49 ± 0.07 and PAM50 = 0.32 ± 0.10 in stringent cross-validation and OncotypeDX = 0.83 and PAM50 = 0.78 for a unique model). Equivalent models trained from the unaffected contralateral breast were not correlated suggesting that the image signatures were tumor-specific and that overfitting was not a considerable issue. We also noted that models were improved by combining clinical information (triple negative status and progesterone receptor). The models used mostly wavelets and fractal features suggesting their importance to capture tumor information. Our results suggest that molecular-based recurrence risk and breast cancer subtypes have observable radiographic phenotypes. To our knowledge, this is the first study associating mammographic information to gene expression recurrence signatures.
Collapse
|
12
|
Davatzikos C, Rathore S, Bakas S, Pati S, Bergman M, Kalarot R, Sridharan P, Gastounioti A, Jahani N, Cohen E, Akbari H, Tunc B, Doshi J, Parker D, Hsieh M, Sotiras A, Li H, Ou Y, Doot RK, Bilello M, Fan Y, Shinohara RT, Yushkevich P, Verma R, Kontos D. Cancer imaging phenomics toolkit: quantitative imaging analytics for precision diagnostics and predictive modeling of clinical outcome. J Med Imaging (Bellingham) 2018; 5:011018. [PMID: 29340286 PMCID: PMC5764116 DOI: 10.1117/1.jmi.5.1.011018] [Citation(s) in RCA: 97] [Impact Index Per Article: 16.2] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2017] [Accepted: 12/05/2017] [Indexed: 12/26/2022] Open
Abstract
The growth of multiparametric imaging protocols has paved the way for quantitative imaging phenotypes that predict treatment response and clinical outcome, reflect underlying cancer molecular characteristics and spatiotemporal heterogeneity, and can guide personalized treatment planning. This growth has underlined the need for efficient quantitative analytics to derive high-dimensional imaging signatures of diagnostic and predictive value in this emerging era of integrated precision diagnostics. This paper presents cancer imaging phenomics toolkit (CaPTk), a new and dynamically growing software platform for analysis of radiographic images of cancer, currently focusing on brain, breast, and lung cancer. CaPTk leverages the value of quantitative imaging analytics along with machine learning to derive phenotypic imaging signatures, based on two-level functionality. First, image analysis algorithms are used to extract comprehensive panels of diverse and complementary features, such as multiparametric intensity histogram distributions, texture, shape, kinetics, connectomics, and spatial patterns. At the second level, these quantitative imaging signatures are fed into multivariate machine learning models to produce diagnostic, prognostic, and predictive biomarkers. Results from clinical studies in three areas are shown: (i) computational neuro-oncology of brain gliomas for precision diagnostics, prediction of outcome, and treatment planning; (ii) prediction of treatment response for breast and lung cancer, and (iii) risk assessment for breast cancer.
Collapse
Affiliation(s)
- Christos Davatzikos
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Saima Rathore
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Spyridon Bakas
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Sarthak Pati
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Mark Bergman
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Ratheesh Kalarot
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Patmaa Sridharan
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Aimilia Gastounioti
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Nariman Jahani
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Eric Cohen
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Hamed Akbari
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Birkan Tunc
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Jimit Doshi
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Drew Parker
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Michael Hsieh
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Aristeidis Sotiras
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Hongming Li
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Yangming Ou
- Massachusetts General Hospital, Martinos Center for Biomedical Imaging, Boston, Massachusetts, United States
| | - Robert K. Doot
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Michel Bilello
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Yong Fan
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Russell T. Shinohara
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
- University of Pennsylvania, Perelman School of Medicine, Center for Clinical Epidemiology and Biostatistics (CCEB), Department of Biostatistics, Epidemiology, and Informatics, Philadelphia, Pennsylvania, United States
| | - Paul Yushkevich
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Ragini Verma
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| | - Despina Kontos
- Center for Biomedical Image Computing and Analytics (CBICA), Philadelphia, Pennsylvania, United States
| |
Collapse
|
13
|
Gastounioti A, Oustimov A, Keller BM, Pantalone L, Hsieh MK, Conant EF, Kontos D. Breast parenchymal patterns in processed versus raw digital mammograms: A large population study toward assessing differences in quantitative measures across image representations. Med Phys 2017; 43:5862. [PMID: 27806604 DOI: 10.1118/1.4963810] [Citation(s) in RCA: 21] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/22/2022] Open
Abstract
PURPOSE With raw digital mammograms (DMs), which retain the relationship with x-ray attenuation of the breast tissue, not being routinely available, processed DMs are often the only viable means to acquire imaging measures. The authors investigate differences in quantitative measures of breast density and parenchymal texture, shown to have value in breast cancer risk assessment, between the two DM representations. METHODS The authors report data from 8458 pairs of bilateral raw ("FOR PROCESSING") and processed ("FOR PRESENTATION") DMs acquired from 4278 women undergoing routine screening evaluation, collected with DM units from two different vendors. Breast dense tissue area and percent density (PD), as well as a range of quantitative descriptors of breast parenchymal texture (statistical, co-occurrence, run-length, and structural descriptors), were measured using previously validated, fully automated software. Feature measurements were compared using matched-pairs Wilcoxon signed-ranks test, correlation (r), and linear-mixed-effects (LME) models, where potential interactions with woman- and system-specific factors were also assessed. The authors also compared texture feature correlations with the established risk factors of the Gail lifetime risk score (rG) and breast PD (rPD), and evaluated the within woman intraclass feature correlation (ICC), a measure of bilateral breast-tissue symmetry, in raw versus processed images. RESULTS All density measures and most of the texture features were strongly (r ≥ 0.6) or moderately (0.4 ≤ r < 0.6) correlated between raw and processed images. However, measurements were significantly different between the two imaging formats (Wilcoxon signed-ranks test, pw < 0.05). The association between measurements varied across features and vendors, and was substantially modified by woman- and system-specific image acquisition factors, such as age, BMI, and mAs/kVp, respectively. The strongest correlation, combined with minimal LME-model interactions, was observed for structural texture features. Overall, texture measures from either image representation were weakly associated with Gail lifetime risk (-0.2 ≤ rG ≤ 0.2), weakly to moderately associated with breast PD (-0.6 ≤ rPD ≤ 0.6), and had overall strong bilateral symmetry (ICC ≥ 0.6). CONCLUSIONS Differences in measures from processed versus raw DM depend highly on the feature, the DM vendor, and image acquisition settings, where structural features appear to be more robust across the different DM settings. The reported findings may serve as a reference in the design of future large-scale studies on mammographic features and breast cancer risk assessment involving multiple DM representations.
Collapse
Affiliation(s)
- Aimilia Gastounioti
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 3700 Hamilton Walk, Rm D702 Richards Bldg., Philadelphia, Pennsylvania 19104
| | - Andrew Oustimov
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 3700 Hamilton Walk, Rm D702 Richards Bldg., Philadelphia, Pennsylvania 19104
| | - Brad M Keller
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 3700 Hamilton Walk, Rm D702 Richards Bldg., Philadelphia, Pennsylvania 19104
| | - Lauren Pantalone
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 3700 Hamilton Walk, Rm D702 Richards Bldg., Philadelphia, Pennsylvania 19104
| | - Meng-Kang Hsieh
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 3700 Hamilton Walk, Rm D702 Richards Bldg., Philadelphia, Pennsylvania 19104
| | - Emily F Conant
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 3700 Hamilton Walk, Rm D702 Richards Bldg., Philadelphia, Pennsylvania 19104
| | - Despina Kontos
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 3700 Hamilton Walk, Rm D702 Richards Bldg., Philadelphia, Pennsylvania 19104
| |
Collapse
|
14
|
Gastounioti A, Conant EF, Kontos D. Beyond breast density: a review on the advancing role of parenchymal texture analysis in breast cancer risk assessment. Breast Cancer Res 2016; 18:91. [PMID: 27645219 PMCID: PMC5029019 DOI: 10.1186/s13058-016-0755-8] [Citation(s) in RCA: 84] [Impact Index Per Article: 10.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/25/2022] Open
Abstract
BACKGROUND The assessment of a woman's risk for developing breast cancer has become increasingly important for establishing personalized screening recommendations and forming preventive strategies. Studies have consistently shown a strong relationship between breast cancer risk and mammographic parenchymal patterns, typically assessed by percent mammographic density. This paper will review the advancing role of mammographic texture analysis as a potential novel approach to characterize the breast parenchymal tissue to augment conventional density assessment in breast cancer risk estimation. MAIN TEXT The analysis of mammographic texture provides refined, localized descriptors of parenchymal tissue complexity. Currently, there is growing evidence in support of textural features having the potential to augment the typically dichotomized descriptors (dense or not dense) of area or volumetric measures of breast density in breast cancer risk assessment. Therefore, a substantial research effort has been devoted to automate mammographic texture analysis, with the aim of ultimately incorporating such quantitative measures into breast cancer risk assessment models. In this paper, we review current and emerging approaches in this field, summarizing key methodological details and related studies using novel computerized approaches. We also discuss research challenges for advancing the role of parenchymal texture analysis in breast cancer risk stratification and accelerating its clinical translation. CONCLUSIONS The objective is to provide a comprehensive reference for researchers in the field of parenchymal pattern analysis in breast cancer risk assessment, while indicating key directions for future research.
Collapse
Affiliation(s)
- Aimilia Gastounioti
- Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA
| | - Emily F Conant
- Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA
| | - Despina Kontos
- Department of Radiology, University of Pennsylvania, Philadelphia, PA, 19104, USA.
| |
Collapse
|
15
|
Ray S, Chen L, Keller BM, Chen J, Conant EF, Kontos D. Association between Breast Parenchymal Complexity and False-Positive Recall From Digital Mammography Versus Breast Tomosynthesis: Preliminary Investigation in the ACRIN PA 4006 Trial. Acad Radiol 2016; 23:977-86. [PMID: 27236612 DOI: 10.1016/j.acra.2016.02.019] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/09/2016] [Accepted: 02/29/2016] [Indexed: 11/20/2022]
Abstract
RATIONALE AND OBJECTIVES We investigate associations between measures of mammographic parenchymal complexity and false-positive (FP) recall from screening with digital mammography (DM) versus digital breast tomosynthesis (DBT). MATERIALS AND METHODS We retrospectively analyzed data from 541 women recruited by the American College of Radiology Imaging Network 4006 trial, designed to evaluate callback and detection rates from screening with DM versus combined DM and DBT. Of these, 68 and 56 were FPs based on DM alone versus the combined DM/DBT readings, respectively. Mammographic complexity was quantified with computerized texture analysis and percent density. Logistic regression was performed to evaluate associations between extracted features and FP recall, after adjusting for age and number of previous benign biopsies. Odds ratios and area under the curve (AUC) of the receiver operating characteristic were used to assess association strength. RESULTS For DM, age, previous benign biopsies and texture features of correlation, inverse difference moment, sum average, and sum variance were deemed as significant predictors (P <.05) of FP recall, with an AUC = 0.77. For DBT, age was the only significant predictor of FP recall with AUC = 0.64. Using exploratory receiver operating characteristic thresholds for which no true-positives would be missed, a potential FP reduction of 23.5% and 8.9% was demonstrated, respectively, for DM alone versus DM/DBT. CONCLUSION Measures of breast complexity measured on 2D digital mammograms are indicative of the likelihood for FP recall from screening with DM, and could help identify women who could benefit from supplemental screening, including DBT.
Collapse
Affiliation(s)
- Shonket Ray
- Department of Radiology, University of Pennsylvania, 1 Silverstein Bldg., 3400 Spruce St, Philadelphia PA 19104
| | - Lin Chen
- Department of Radiology, University of Pennsylvania, 1 Silverstein Bldg., 3400 Spruce St, Philadelphia PA 19104
| | - Brad M Keller
- Department of Radiology, University of Pennsylvania, 1 Silverstein Bldg., 3400 Spruce St, Philadelphia PA 19104
| | - Jinbo Chen
- Department of Biostatistics and Epidemiology, University of Pennsylvania School of Medicine, Philadelphia, Pennsylvania
| | - Emily F Conant
- Department of Radiology, University of Pennsylvania, 1 Silverstein Bldg., 3400 Spruce St, Philadelphia PA 19104
| | - Despina Kontos
- Department of Radiology, University of Pennsylvania, 1 Silverstein Bldg., 3400 Spruce St, Philadelphia PA 19104.
| |
Collapse
|
16
|
Zheng Y, Keller BM, Ray S, Wang Y, Conant EF, Gee JC, Kontos D. Parenchymal texture analysis in digital mammography: A fully automated pipeline for breast cancer risk assessment. Med Phys 2016; 42:4149-60. [PMID: 26133615 DOI: 10.1118/1.4921996] [Citation(s) in RCA: 64] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/19/2022] Open
Abstract
PURPOSE Mammographic percent density (PD%) is known to be a strong risk factor for breast cancer. Recent studies also suggest that parenchymal texture features, which are more granular descriptors of the parenchymal pattern, can provide additional information about breast cancer risk. To date, most studies have measured mammographic texture within selected regions of interest (ROIs) in the breast, which cannot adequately capture the complexity of the parenchymal pattern throughout the whole breast. To better characterize patterns of the parenchymal tissue, the authors have developed a fully automated software pipeline based on a novel lattice-based strategy to extract a range of parenchymal texture features from the entire breast region. METHODS Digital mammograms from 106 cases with 318 age-matched controls were retrospectively analyzed. The lattice-based approach is based on a regular grid virtually overlaid on each mammographic image. Texture features are computed from the intersection (i.e., lattice) points of the grid lines within the breast, using a local window centered at each lattice point. Using this strategy, a range of statistical (gray-level histogram, co-occurrence, and run-length) and structural (edge-enhancing, local binary pattern, and fractal dimension) features are extracted. To cover the entire breast, the size of the local window for feature extraction is set equal to the lattice grid spacing and optimized experimentally by evaluating different windows sizes. The association between their lattice-based texture features and breast cancer was evaluated using logistic regression with leave-one-out cross validation and further compared to that of breast PD% and commonly used single-ROI texture features extracted from the retroareolar or the central breast region. Classification performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC). DeLong's test was used to compare the different ROCs in terms of AUC performance. RESULTS The average univariate performance of the lattice-based features is higher when extracted from smaller than larger window sizes. While not every individual texture feature is superior to breast PD% (AUC: 0.59, STD: 0.03), their combination in multivariate analysis has significantly better performance (AUC: 0.85, STD: 0.02, p < 0.001). The lattice-based texture features also outperform the single-ROI texture features when extracted from the retroareolar or the central breast region (AUC: 0.60-0.74, STD: 0.03). Adding breast PD% does not make a significant performance improvement to the lattice-based texture features or the single-ROI features (p > 0.05). CONCLUSIONS The proposed lattice-based strategy for mammographic texture analysis enables to characterize the parenchymal pattern over the entire breast. As such, these features provide richer information compared to currently used descriptors and may ultimately improve breast cancer risk assessment. Larger studies are warranted to validate these findings and also compare to standard demographic and reproductive risk factors.
Collapse
Affiliation(s)
- Yuanjie Zheng
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 3600 Market Street, Suite 370, Philadelphia, Pennsylvania 19104
| | - Brad M Keller
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 3600 Market Street, Suite 370, Philadelphia, Pennsylvania 19104
| | - Shonket Ray
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 3600 Market Street, Suite 370, Philadelphia, Pennsylvania 19104
| | - Yan Wang
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 3600 Market Street, Suite 370, Philadelphia, Pennsylvania 19104
| | - Emily F Conant
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 3600 Market Street, Suite 370, Philadelphia, Pennsylvania 19104
| | - James C Gee
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 3600 Market Street, Suite 370, Philadelphia, Pennsylvania 19104
| | - Despina Kontos
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, 3600 Market Street, Suite 370, Philadelphia, Pennsylvania 19104
| |
Collapse
|