Breast Cancer Diagnosis using SHG Laser Microscopy and Statistical Image Analysis

Gregory Falzon

Abstract

Second-Harmonic Laser Microscopy promises to be a useful diagnostic modality for breast cancer. Statistical image analysis has provided key insights into the differences between images of normal, benign and malignant breast tissue. Spectral analysis of image features coupled with a support-vector machine classifier is demonstrated to accurately separate normal from tumour tissue. Further analysis of the tumour group using the multi-scale, multi-directional, steerable pyramid filter has revealed features that can be used to separate benign from malignant breast tissue. The classifier presented can serve as a prototype for devices developed to serve in a clinical setting.

Original language	English
Publication status	Published - 2007
Event	NZSA 2007 Conference: The New Zealand Statistical Association Annual Conference - Christchurch, New Zealand Duration: 4 Jul 2007 → …

Conference

Conference	NZSA 2007 Conference: The New Zealand Statistical Association Annual Conference
City	Christchurch, New Zealand
Period	4/07/07 → …

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Medical Physics
Medical Biotechnology Diagnostics (incl Biosensors)
Applied Statistics

Access to Document

https://hdl.handle.net/1959.11/13370

Handle.net

Persistent link

Cite this

@conference{9851272fd99c42529a97d4afc6633ece,

title = "Breast Cancer Diagnosis using SHG Laser Microscopy and Statistical Image Analysis",

abstract = "Second-Harmonic Laser Microscopy promises to be a useful diagnostic modality for breast cancer. Statistical image analysis has provided key insights into the differences between images of normal, benign and malignant breast tissue. Spectral analysis of image features coupled with a support-vector machine classifier is demonstrated to accurately separate normal from tumour tissue. Further analysis of the tumour group using the multi-scale, multi-directional, steerable pyramid filter has revealed features that can be used to separate benign from malignant breast tissue. The classifier presented can serve as a prototype for devices developed to serve in a clinical setting.",

keywords = "Medical Physics, Medical Biotechnology Diagnostics (incl Biosensors), Applied Statistics",

author = "Gregory Falzon",

year = "2007",

language = "English",

note = "NZSA 2007 Conference: The New Zealand Statistical Association Annual Conference ; Conference date: 04-07-2007",

}

TY - CONF

T1 - Breast Cancer Diagnosis using SHG Laser Microscopy and Statistical Image Analysis

AU - Falzon, Gregory

PY - 2007

Y1 - 2007

N2 - Second-Harmonic Laser Microscopy promises to be a useful diagnostic modality for breast cancer. Statistical image analysis has provided key insights into the differences between images of normal, benign and malignant breast tissue. Spectral analysis of image features coupled with a support-vector machine classifier is demonstrated to accurately separate normal from tumour tissue. Further analysis of the tumour group using the multi-scale, multi-directional, steerable pyramid filter has revealed features that can be used to separate benign from malignant breast tissue. The classifier presented can serve as a prototype for devices developed to serve in a clinical setting.

AB - Second-Harmonic Laser Microscopy promises to be a useful diagnostic modality for breast cancer. Statistical image analysis has provided key insights into the differences between images of normal, benign and malignant breast tissue. Spectral analysis of image features coupled with a support-vector machine classifier is demonstrated to accurately separate normal from tumour tissue. Further analysis of the tumour group using the multi-scale, multi-directional, steerable pyramid filter has revealed features that can be used to separate benign from malignant breast tissue. The classifier presented can serve as a prototype for devices developed to serve in a clinical setting.

KW - Medical Physics

KW - Medical Biotechnology Diagnostics (incl Biosensors)

KW - Applied Statistics

UR - http://www.math.canterbury.ac.nz/nzsa2007/s3d1.shtml

M3 - Abstract

T2 - NZSA 2007 Conference: The New Zealand Statistical Association Annual Conference

Y2 - 4 July 2007

ER -