Show simple item record

dc.contributor.authorDobbs, Jessica L
Mueller, Jenna L
Krishnamurthy, Savitri
Shin, Dongsuk
Kuerer, Henry
Yang, Wei
Ramanujam, Nirmala
Richards-Kortum, Rebecca
dc.date.accessioned 2017-02-02T07:05:09Z
dc.date.available 2017-02-02T07:05:09Z
dc.date.issued 2015
dc.identifier.citation Dobbs, Jessica L, Mueller, Jenna L, Krishnamurthy, Savitri, et al.. "Micro-anatomical quantitative optical imaging: toward automated assessment of breast tissues." Breast Cancer Research, (2015) BioMed Central: http://dx.doi.org/10.1186/s13058-015-0617-9.
dc.identifier.urihttps://hdl.handle.net/1911/93840
dc.description.abstract Abstract Introduction Pathologists currently diagnose breast lesions through histologic assessment, which requires fixation and tissue preparation. The diagnostic criteria used to classify breast lesions are qualitative and subjective, and inter-observer discordance has been shown to be a significant challenge in the diagnosis of selected breast lesions, particularly for borderline proliferative lesions. Thus, there is an opportunity to develop tools to rapidly visualize and quantitatively interpret breast tissue morphology for a variety of clinical applications. Methods Toward this end, we acquired images of freshly excised breast tissue specimens from a total of 34 patients using confocal fluorescence microscopy and proflavine as a topical stain. We developed computerized algorithms to segment and quantify nuclear and ductal parameters that characterize breast architectural features. A total of 33 parameters were evaluated and used as input to develop a decision tree model to classify benign and malignant breast tissue. Benign features were classified in tissue specimens acquired from 30 patients and malignant features were classified in specimens from 22 patients. Results The decision tree model that achieved the highest accuracy for distinguishing between benign and malignant breast features used the following parameters: standard deviation of inter-nuclear distance and number of duct lumens. The model achieved 81 % sensitivity and 93 % specificity, corresponding to an area under the curve of 0.93 and an overall accuracy of 90 %. The model classified IDC and DCIS with 92 % and 96 % accuracy, respectively. The cross-validated model achieved 75 % sensitivity and 93 % specificity and an overall accuracy of 88 %. Conclusions These results suggest that proflavine staining and confocal fluorescence microscopy combined with image analysis strategies to segment morphological features could potentially be used to quantitatively diagnose freshly obtained breast tissue at the point of care without the need for tissue preparation.
dc.publisher BioMed Central
dc.rights Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
dc.title Micro-anatomical quantitative optical imaging: toward automated assessment of breast tissues
dc.type Journal article
dc.citation.journalTitle Breast Cancer Research
dc.date.updated 2017-02-02T07:05:09Z
dc.type.dcmi Text
dc.identifier.doihttp://dx.doi.org/10.1186/s13058-015-0617-9
dc.language.rfc3066 en
dc.type.publication publisher version
dcterms.bibliographicCitation Breast Cancer Research. 2015 Aug 20;17(1):105
dc.rights.holder Dobbs et al.
local.sword.agent BioMed Central


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record