Cervical cancer ranks as the fourth most prevalent cancer globally, emphasizing the critical need for early detection, which is vital for effective treatment. Traditional diagnostic methods have shown limitations in detecting the progression of the disease. Optical techniques, known for their high sensitivity and specificity, are emerging as reliable tools, especially in cancer-related applications. Among these techniques, fluorescence spectroscopy is one of the highly sensitive approaches for identifying biochemical changes that occur during the advancement of cancer. In our study, fluorescence spectral data was collected from human cervix from a diverse group of individuals using a portable smartphone-based fluorescence spectroscopy device. The spectral signals were processed by initially breaking them down into Fourier Bessel series (FBS) coefficients. Subsequently, the Hessian locally linear embedding (HLLE) based dimensionality reduction method was applied to the FBS coefficients, followed by the implementation of a 1D convolutional neural network classifier. The combination of polarized fluorescence spectra acquired from the device and the proposed classification approach has shown promising results, thus it is proven to be a minimally invasive method with the capability to provide real-time diagnoses for patients
A smartphone-based prototype has been demonstrated and calibrated as a tool to identify the spectral differences from fluorophores during disease progression. Polarized fluorescence is captured through smartphone camera using a 405nm laser source.
Breast cancer arises either in the lobules or the ducts of the tissue. Structural changes occurring with malignancy manifest as refractive index variations inside the tissue. It is crucial to quantify these depth wise variation in refractive index for early cancer detection. In this study, three types of unstained breast tissue sections - fibrocystic, fibroadenoma, and invasive carcinoma have been examined for the ultra-structural changes using `Fourier domain low coherence interferometry'. The resulting interference spectra of the backscattered light from the front and the rear surface of the sample are Fourier analyzed to provide depth correlation function. The subtle small-scale fluctuations in the Fourier analyzed spectra are then evaluated using Discrete Wavelet Transform (DWT). Daubechies-1 wavelet of DWT is used to calculate the high pass and low pass coefficients. The sixth level low pass coefficients of DWT clearly discriminate among normal, benign, and malignant breast tissue. Skewness and kurtosis values for these coefficients are also able to well distinguish the type of tissues.
Most cervical cancers originate from the epithelial layer by an uncontrolled growth of abnormal squamous cells and are known as carcinomas. Early stages of this disease manifest as biochemical and morphological changes in the superficial layer. Such changes can be captured from the spectral behavior of intrinsic fluorophores present in the layered cervical tissue. Fluorescence spectroscopy is thus widely used for detection of pre-cancers, also due to its capability as a fast, non-invasive and quantitative probe. This study focuses on analysis of the spectral information of the fluorophores using spatially resolved fluorescence spectroscopy for diagnosis of cervical cancer at an early stage. An in-house fabricated fiber-optic probe of diameter 1mm, consisting of 77 fibers in approximately five circular rings with very high sensitivity for superficial layer changes, has been used to collect fluorescence spectra from different spatially resolved positions of two layered solid phantoms. The phantoms are prepared by varying the thickness and fluorophore concentration of the upper layer. Optical properties of these layered phantoms have been kept similar to cervical tissue to replicate the subtle changes that occur in the tissue with the growth of abnormality. A 405 nm laser diode source is used to excite the samples with two different fluorophores in the two layers, Flavin Adenine Dinucleotide (FAD) in upper layer and Proto-porphyrin (PpIX) in bottom layer. A `Look-up Table' method is used to finally reconstruct thickness and fluorophore concentrations of upper layer of an unknown phantom by evaluating the peak ratios of fluorophores from spectra obtained at different spatially resolved positions.
Phase contrast images of stromal region of different stages of cervical pre-cancer were captured from tissue sections. A wavelet leader based multifractal analysis was performed on the phase contrast images to estimate multifractal spectrum for each image. Wavelet leaders were calculated through discrete wavelet transform using bi-orthogonal mother wavelets. The derived multifractal parameters, namely, width of singularity spectrum shows good discrimination between different grades of cervical pre-cancer.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.