Automated classification of breast pathology using local measures of broadband reflectance
Open Access
- 1 January 2010
- journal article
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 15 (6) , 066019-066019-12
Abstract
We demonstrate that morphological features pertinent to a tissue's pathology may be ascertained from localized measures of broadband reflectance, with a mesoscopic resolution (100-μm lateral spot size) that permits scanning of an entire margin for residual disease. The technical aspects and optimization of a k-nearest neighbor classifier for automated diagnosis of pathologies are presented, and its efficacy is validated in 29 breast tissue specimens. When discriminating between benign and malignant pathologies, a sensitivity and specificity of 91 and 77% was achieved. Furthermore, detailed subtissue-type analysis was performed to consider how diverse pathologies influence scattering response and overall classification efficacy. The increased sensitivity of this technique may render it useful to guide the surgeon or pathologist where to sample pathology for microscopic assessment.Keywords
This publication has 54 references indexed in Scilit:
- Scanning elastic scattering spectroscopy detects metastatic breast cancer in sentinel lymph nodesJournal of Biomedical Optics, 2010
- Rapid noninvasive optical imaging of tissue composition in breast tumor marginsThe American Journal of Surgery, 2009
- Obtaining Adequate Surgical Margins in Breast-Conserving Therapy for Patients with Early-Stage Breast Cancer: Current Modalities and Future DirectionsAnnals of Surgical Oncology, 2009
- Automated identification of tumor microscopic morphology based on macroscopically measured scatter signaturesJournal of Biomedical Optics, 2009
- Quantitative imaging of scattering changes associated with epithelial proliferation, necrosis, and fibrosis in tumors using microsampling reflectance spectroscopyJournal of Biomedical Optics, 2009
- Diagnosis of breast cancer using fluorescence and diffuse reflectance spectroscopy: a Monte-Carlo-model-based approachJournal of Biomedical Optics, 2008
- Role for Intraoperative Margin Assessment in Patients Undergoing Breast-Conserving SurgeryAnnals of Surgical Oncology, 2007
- Evaluation of Margin Status in Lumpectomy Specimens and Residual Breast CarcinomaThe Breast Journal, 2006
- Near-Infrared Raman Spectroscopy for In Vitro Detection of Cervical PrecancersPhotochemistry and Photobiology, 1998
- Fluorophore quantitation in tissue-simulating media with confocal detectionIEEE Journal of Selected Topics in Quantum Electronics, 1996