Lung Cancer screening trials have demonstrated significant mortality reduction. Low-Dose Computed Tomography (LDCT) screening can frequently discover many small nodules in at risk participants. However classification of these, sub-cm nodules as cancerous or benign is a challenging task even for expert clinicians.
We use machine learning (ML) and deep learning (CNN) techniques to differentiate, sub-cm cancerous and benign nodules. Data for this study is drawn from a screening study (PanCan) from which we selected 612 distinct nodules (140 cancerous, and ~size matched 472 benign). Both methods demonstrated a ~80% accuracy, whereas currently used measures (size) had a 68% accuracy.
KEYWORDS: Reflectivity, Imaging systems, RGB color model, Optical coherence tomography, Endoscopes, Fiber optics, Endoscopy, Signal to noise ratio, Tongue, In vivo imaging
A fiber-based endoscopic imaging system combining narrowband red-green-blue (RGB) reflectance with optical coherence tomography (OCT) and autofluorescence imaging (AFI) has been developed. The system uses a submillimeter diameter rotary-pullback double-clad fiber imaging catheter for sample illumination and detection. The imaging capabilities of each modality are presented and demonstrated with images of a multicolored card, fingerprints, and tongue mucosa. Broadband imaging, which was done to compare with narrowband sources, revealed better contrast but worse color consistency compared with narrowband RGB reflectance. The measured resolution of the endoscopic system is 25 μm in both the rotary direction and the pullback direction. OCT can be performed simultaneously with either narrowband RGB reflectance imaging or AFI.
KEYWORDS: Endoscopes, RGB color model, In vivo imaging, Fiber optics, Cancer, Signal to noise ratio, Oncology, Imaging systems, Prototyping, Image resolution
The early detection of cancer brings increased success in the treatment of cancer patients. A prototype sub-millimeter diameter high resolution fibre endoscope for the in-vivo imaging in oral, lung, cervix, ovarian and pancreas sites for the early detection and delineation of cancers is currently in its early stages of development. The endoscope is to utilize a combination of rotary and pullback motion to allow a wide field-of-view while capturing high-resolution (10 to 20 um) RGB images. In this system an RGB laser module uses the core of a dual-clad fibre for illumination and the inner cladding for detection to achieve real time in-vivo reflectance imaging .
Signal detection for each laser (RGB) has been tested using a white card printed with black lines of varying widths. The contrast between the white and black portions of the card and the Signal to Noise Ratio (SNR) for the pullback mechanism of the system were determined. The card contrast values for red, green and blue light were calculated to be 25.0, 15.6 and 8.3 respectively, while the SNR values were 180, 155, and 154 respectively. These values suggest that the performance of the system is wavelength dependent. The imaging performance characteristics of the endoscope with rotary and pullback motion combined will be further quantified, and results and images will be presented.
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.