Tags

Type your tag names separated by a space and hit enter

Structured light imaging for breast-conserving surgery, part II: texture analysis and classification.
J Biomed Opt 2019; 24(9):1-12JB

Abstract

Subdiffuse spatial frequency domain imaging (sd-SFDI) data of 42 freshly excised, bread-loafed tumor resections from breast-conserving surgery (BCS) were evaluated using texture analysis and a machine learning framework for tissue classification. Resections contained 56 regions of interest (RoIs) determined by expert histopathological analysis. RoIs were coregistered with sd-SFDI data and sampled into ∼4 × 4 mm2 subimage samples of confirmed and homogeneous histological categories. Sd-SFDI reflectance textures were analyzed using gray-level co-occurrence matrix pixel statistics, image primitives, and power spectral density curve parameters. Texture metrics exhibited statistical significance (p-value < 0.05) between three benign and three malignant tissue subtypes. Pairs of benign and malignant subtypes underwent texture-based, binary classification with correlation-based feature selection. Classification performance was evaluated using fivefold cross-validation and feature grid searching. Classification using subdiffuse, monochromatic reflectance (illumination spatial frequency of fx = 1.37 mm − 1, optical wavelength of λ = 490 nm) achieved accuracies ranging from 0.55 (95% CI: 0.41 to 0.69) to 0.95 (95% CI: 0.90 to 1.00) depending on the benign–malignant diagnosis pair. Texture analysis of sd-SFDI data maintains the spatial context within images, is free of light transport model assumptions, and may provide an alternative, computationally efficient approach for wide field-of-view (cm2) BCS tumor margin assessment relative to pixel-based optical scatter or color properties alone.

Authors+Show Affiliations

Thayer School of Engineering at Dartmouth, Optics in Medicine, Hanover, New Hampshire, United States.Thayer School of Engineering at Dartmouth, Optics in Medicine, Hanover, New Hampshire, United States.Thayer School of Engineering at Dartmouth, Optics in Medicine, Hanover, New Hampshire, United States.Thayer School of Engineering at Dartmouth, Optics in Medicine, Hanover, New Hampshire, United States.Thayer School of Engineering at Dartmouth, Optics in Medicine, Hanover, New Hampshire, United States. Geisel School of Medicine at Dartmouth, Department of Surgery, Hanover, New Hampshire, United States. Geisel School of Medicine at Dartmouth, Department of Pathology, Hanover, New Hampshire, United States.Geisel School of Medicine at Dartmouth, Department of Pathology, Hanover, New Hampshire, United States. Norris Cotton Cancer Center, Dartmouth-Hitchcock Medical Center, Lebanon, New Hampshire, United States.Geisel School of Medicine at Dartmouth, Department of Pathology, Hanover, New Hampshire, United States. Norris Cotton Cancer Center, Dartmouth-Hitchcock Medical Center, Lebanon, New Hampshire, United States.Thayer School of Engineering at Dartmouth, Optics in Medicine, Hanover, New Hampshire, United States. Geisel School of Medicine at Dartmouth, Department of Surgery, Hanover, New Hampshire, United States. Geisel School of Medicine at Dartmouth, Department of Pathology, Hanover, New Hampshire, United States.

Pub Type(s)

Journal Article

Language

eng

PubMed ID

31522486

Citation

Streeter, Samuel S., et al. "Structured Light Imaging for Breast-conserving Surgery, Part II: Texture Analysis and Classification." Journal of Biomedical Optics, vol. 24, no. 9, 2019, pp. 1-12.
Streeter SS, Maloney BW, McClatchy DM, et al. Structured light imaging for breast-conserving surgery, part II: texture analysis and classification. J Biomed Opt. 2019;24(9):1-12.
Streeter, S. S., Maloney, B. W., McClatchy, D. M., Jermyn, M., Pogue, B. W., Rizzo, E. J., ... Paulsen, K. D. (2019). Structured light imaging for breast-conserving surgery, part II: texture analysis and classification. Journal of Biomedical Optics, 24(9), pp. 1-12. doi:10.1117/1.JBO.24.9.096003.
Streeter SS, et al. Structured Light Imaging for Breast-conserving Surgery, Part II: Texture Analysis and Classification. J Biomed Opt. 2019;24(9):1-12. PubMed PMID: 31522486.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Structured light imaging for breast-conserving surgery, part II: texture analysis and classification. AU - Streeter,Samuel S, AU - Maloney,Benjamin W, AU - McClatchy,David M, AU - Jermyn,Michael, AU - Pogue,Brian W, AU - Rizzo,Elizabeth J, AU - Wells,Wendy A, AU - Paulsen,Keith D, PY - 2019/04/10/received PY - 2019/08/14/accepted PY - 2019/9/16/entrez PY - 2019/9/16/pubmed PY - 2019/9/16/medline KW - breast-conserving surgery KW - classification KW - machine learning KW - spatial frequency domain imaging KW - structured light KW - texture analysis SP - 1 EP - 12 JF - Journal of biomedical optics JO - J Biomed Opt VL - 24 IS - 9 N2 - Subdiffuse spatial frequency domain imaging (sd-SFDI) data of 42 freshly excised, bread-loafed tumor resections from breast-conserving surgery (BCS) were evaluated using texture analysis and a machine learning framework for tissue classification. Resections contained 56 regions of interest (RoIs) determined by expert histopathological analysis. RoIs were coregistered with sd-SFDI data and sampled into ∼4 × 4 mm2 subimage samples of confirmed and homogeneous histological categories. Sd-SFDI reflectance textures were analyzed using gray-level co-occurrence matrix pixel statistics, image primitives, and power spectral density curve parameters. Texture metrics exhibited statistical significance (p-value < 0.05) between three benign and three malignant tissue subtypes. Pairs of benign and malignant subtypes underwent texture-based, binary classification with correlation-based feature selection. Classification performance was evaluated using fivefold cross-validation and feature grid searching. Classification using subdiffuse, monochromatic reflectance (illumination spatial frequency of fx = 1.37 mm − 1, optical wavelength of λ = 490 nm) achieved accuracies ranging from 0.55 (95% CI: 0.41 to 0.69) to 0.95 (95% CI: 0.90 to 1.00) depending on the benign–malignant diagnosis pair. Texture analysis of sd-SFDI data maintains the spatial context within images, is free of light transport model assumptions, and may provide an alternative, computationally efficient approach for wide field-of-view (cm2) BCS tumor margin assessment relative to pixel-based optical scatter or color properties alone. SN - 1560-2281 UR - https://www.unboundmedicine.com/medline/citation/31522486/Structured_light_imaging_for_breast-conserving_surgery,_part_II:_texture_analysis_and_classification L2 - https://doi.org/10.1117/1.JBO.24.9.096003 DB - PRIME DP - Unbound Medicine ER -