2
|
Wan S, Lee HC, Huang X, Xu T, Xu T, Zeng X, Zhang Z, Sheikine Y, Connolly JL, Fujimoto JG, Zhou C. Integrated local binary pattern texture features for classification of breast tissue imaged by optical coherence microscopy. Med Image Anal 2017; 38:104-116. [PMID: 28327449 DOI: 10.1016/j.media.2017.03.002] [Citation(s) in RCA: 19] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/29/2016] [Revised: 03/06/2017] [Accepted: 03/07/2017] [Indexed: 12/20/2022]
Abstract
This paper proposes a texture analysis technique that can effectively classify different types of human breast tissue imaged by Optical Coherence Microscopy (OCM). OCM is an emerging imaging modality for rapid tissue screening and has the potential to provide high resolution microscopic images that approach those of histology. OCM images, acquired without tissue staining, however, pose unique challenges to image analysis and pattern classification. We examined multiple types of texture features and found Local Binary Pattern (LBP) features to perform better in classifying tissues imaged by OCM. In order to improve classification accuracy, we propose novel variants of LBP features, namely average LBP (ALBP) and block based LBP (BLBP). Compared with the classic LBP feature, ALBP and BLBP features provide an enhanced encoding of the texture structure in a local neighborhood by looking at intensity differences among neighboring pixels and among certain blocks of pixels in the neighborhood. Fourty-six freshly excised human breast tissue samples, including 27 benign (e.g. fibroadenoma, fibrocystic disease and usual ductal hyperplasia) and 19 breast carcinoma (e.g. invasive ductal carcinoma, ductal carcinoma in situ and lobular carcinoma in situ) were imaged with large field OCM with an imaging area of 10 × 10 mm2 (10, 000 × 10, 000 pixels) for each sample. Corresponding H&E histology was obtained for each sample and used to provide ground truth diagnosis. 4310 small OCM image blocks (500 × 500 pixels) each paired with corresponding H&E histology was extracted from large-field OCM images and labeled with one of the five different classes: adipose tissue (n = 347), fibrous stroma (n = 2,065), breast lobules (n = 199), carcinomas (pooled from all sub-types, n = 1,127), and background (regions outside of the specimens, n = 572). Our experiments show that by integrating a selected set of LBP and the two new variant (ALBP and BLBP) features at multiple scales, the classification accuracy increased from 81.7% (using LBP features alone) to 93.8% using a neural network classifier. The integrated feature was also used to classify large-field OCM images for tumor detection. A receiver operating characteristic (ROC) curve was obtained with an area under the curve value of 0.959. A sensitivity level of 100% and specificity level of 85.2% was achieved to differentiate benign from malignant samples. Several other experiments also demonstrate the complementary nature of LBP and the two variants (ALBP and BLBP features) and the significance of integrating these texture features for classification. Using features from multiple scales and performing feature selection are also effective mechanisms to improve accuracy while maintaining computational efficiency.
Collapse
Affiliation(s)
- Sunhua Wan
- Department of Computer Science and Engineering, Lehigh University, Bethlehem, PA 18015, USA
| | - Hsiang-Chieh Lee
- Department of Electrical Engineering and Computer Science and Research Laboratory of Electronics, MIT, Cambridge, MA 02139, USA
| | - Xiaolei Huang
- Department of Computer Science and Engineering, Lehigh University, Bethlehem, PA 18015, USA.
| | - Ting Xu
- Department of Computer Science and Engineering, Lehigh University, Bethlehem, PA 18015, USA
| | - Tao Xu
- Department of Electrical and Computer Engineering, Lehigh University, Bethlehem, PA 18015, USA
| | - Xianxu Zeng
- Department of Electrical and Computer Engineering, Lehigh University, Bethlehem, PA 18015, USA; The Third Affiliated Hospital of Zhengzhou University, Henan, China
| | - Zhan Zhang
- The Third Affiliated Hospital of Zhengzhou University, Henan, China
| | - Yuri Sheikine
- Department of Pathology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA 02115, USA
| | - James L Connolly
- Department of Pathology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA 02115, USA
| | - James G Fujimoto
- Department of Electrical Engineering and Computer Science and Research Laboratory of Electronics, MIT, Cambridge, MA 02139, USA
| | - Chao Zhou
- Department of Electrical and Computer Engineering, Lehigh University, Bethlehem, PA 18015, USA; Center for Photonics and Nanoelectronics, Lehigh University, Bethlehem, PA 18015, USA; Bioengineering Program, Lehigh University, Bethlehem, PA 18015, USA.
| |
Collapse
|
3
|
Kim W, Ferguson VL, Borden M, Neu CP. Application of Elastography for the Noninvasive Assessment of Biomechanics in Engineered Biomaterials and Tissues. Ann Biomed Eng 2016; 44:705-24. [PMID: 26790865 DOI: 10.1007/s10439-015-1542-x] [Citation(s) in RCA: 18] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2015] [Accepted: 12/18/2015] [Indexed: 12/11/2022]
Abstract
The elastic properties of engineered biomaterials and tissues impact their post-implantation repair potential and structural integrity, and are critical to help regulate cell fate and gene expression. The measurement of properties (e.g., stiffness or shear modulus) can be attained using elastography, which exploits noninvasive imaging modalities to provide functional information of a material indicative of the regeneration state. In this review, we outline the current leading elastography methodologies available to characterize the properties of biomaterials and tissues suitable for repair and mechanobiology research. We describe methods utilizing magnetic resonance, ultrasound, and optical coherent elastography, highlighting their potential for longitudinal monitoring of implanted materials in vivo, in addition to spatiotemporal limits of each method for probing changes in cell-laden constructs. Micro-elastography methods now allow acquisitions at length scales approaching 5-100 μm in two and three dimensions. Many of the methods introduced in this review are therefore capable of longitudinal monitoring in biomaterials and tissues approaching the cellular scale. However, critical factors such as anisotropy, heterogeneity and viscoelasity-inherent in many soft tissues-are often not fully described and therefore require further advancements and future developments.
Collapse
|
4
|
Abstract
Electrical stimulation is currently the gold standard for cardiac pacing. However, it is invasive and nonspecific for cardiac tissues. We recently developed a noninvasive cardiac pacing technique using optogenetic tools, which are widely used in neuroscience. Optogenetic pacing of the heart provides high spatial and temporal precisions, is specific for cardiac tissues, avoids artifacts associated with electrical stimulation, and therefore promises to be a powerful tool in basic cardiac research. We demonstrated optogenetic control of heart rhythm in a well-established model organism, Drosophila melanogaster. We developed transgenic flies expressing a light-gated cation channel, channelrhodopsin-2 (ChR2), specifically in their hearts and demonstrated successful optogenetic pacing of ChR2-expressing Drosophila at different developmental stages, including the larva, pupa, and adult stages. A high-speed and ultrahigh-resolution optical coherence microscopy imaging system that is capable of providing images at a rate of 130 frames/s with axial and transverse resolutions of 1.5 and 3.9 μm, respectively, was used to noninvasively monitor Drosophila cardiac function and its response to pacing stimulation. The development of a noninvasive integrated optical pacing and imaging system provides a novel platform for performing research studies in developmental cardiology.
Collapse
Affiliation(s)
- Aneesh Alex
- Department of Electrical and Computer Engineering, Lehigh University, Bethlehem, PA 18015, USA
- Center for Photonics and Nanoelectronics, Lehigh University, Bethlehem, PA 18015, USA
| | - Airong Li
- Genetics and Aging Research Unit, Department of Neurology, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02129, USA
| | - Rudolph E. Tanzi
- Genetics and Aging Research Unit, Department of Neurology, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02129, USA
- Corresponding author. E-mail: (R.E.T.); (C.Z.)
| | - Chao Zhou
- Department of Electrical and Computer Engineering, Lehigh University, Bethlehem, PA 18015, USA
- Center for Photonics and Nanoelectronics, Lehigh University, Bethlehem, PA 18015, USA
- Bioengineering Program, Lehigh University, Bethlehem, PA 18015, USA
- Corresponding author. E-mail: (R.E.T.); (C.Z.)
| |
Collapse
|