In the process of detecting heterogeneity in breast tissue based on multi-spectral transmission imaging, the detection accuracy will be affected due to the high redundancy degree of information between bands. In order to select the reasonable wavelength combination, this paper uses various nonlinear transformations to convert the multi-spectral images into spectral data for the first time, so as to select the set optimal wavelength combination based on the successive projections algorithm (SPA). Firstly, we design the collection experiment of 4-wavelength multi-spectral image. And then, K-SVD dictionary learning method, texture extraction method and gray correlation analysis method are used to obtain the feature spectral information. Finally, the set optimal wavelength combination is selected based on SPA. The experimental results show that random forest (RF) classification model and Faster-RCNN recognition models effectively verify that the combination of wavelengths 1,2,4 selected has the highest accuracy in the heterogeneous detection. In conclusion, this paper uses modulation-frame accumulation technique to improve the quality of multi-spectral transmission images. And based on the RF and Faster-RCNN models, the effectiveness of SPA-based optimal wavelength combination method proposed is verified, which will provide a new idea of feature wavelength selection for screening early breast masses through multi-spectral transmission imaging.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.saa.2021.120080 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Green Assessment of Sensitive Spectrofluorimetric Methods for Simultaneous Estimation of Formoterol Fumarate and Fluticasone Propionate Using a Micelle-Mediated Approach.
J Fluoresc
January 2025
Analytical Chemistry Department, Faculty of Pharmacy, Cairo University, Kasr Al-Aini Street, Cairo, 11562, Egypt.
Highly sensitive spectrofluorimetric methods were developed for the quantitative estimation of formoterol fumarate dihydrate (FFD) and fluticasone propionate (FP) in both authentic raw materials and marketed dosage forms using a micellar-enhanced spectrofluorimetric approach. The proposed methods are based on the determination of FP in the presence of FFD using the first derivative emission spectrofluorimetry. The peak amplitude of the emission spectra of the formed micellar fluorescence was measured at 465 nm after excitation at 236 nm (λ max of FP).
View Article and Find Full Text PDFNIRFluor: A Deep Learning Platform for Rapid Screening of Small Molecule Near-Infrared Fluorophores with Desired Optical Properties.
Anal Chem
January 2025
State Key Laboratory of Chemo/Biosensing and Chemometrics, College of Chemistry and Chemical Engineering, Hunan University, Changsha 410082, China.
Small molecule near-infrared (NIR) fluorophores play a critical role in disease diagnosis and early detection of various markers in living organisms. To accelerate their development and design, a deep learning platform, NIRFluor, was established to rapidly screen small molecule NIR fluorophores with the desired optical properties. The core component of NIRFluor is a state-of-the-art deep learning model trained on 5179 experimental big data.
View Article and Find Full Text PDFThe control of temporal noise of the pump could add an additional degree of freedom to manipulate the spectrum of continuous-wave (CW) pumped SC generation. In this paper, we experimentally tailor the CW-pumped supercontinuum (SC) generation in a cascaded Raman random fiber laser (CRRFL) based on a 1 µm pump with tunable temporal dynamics. The pump is based on a spectrally filtered ytterbium-doped random fiber laser (YRFL) seed laser, which can be amplified to a 10 W level with the tunable temporal noise.
View Article and Find Full Text PDFDesign, Synthesis, and Imaging of a Stable Xanthene-Based Dye with NIR-II Emission up to 1450 nm.
Anal Chem
January 2025
Center for Advanced Materials Research & Faculty of Arts and Sciences, Beijing Normal University, Zhuhai 519087, P. R. China.
The development of long-wavelength near-infrared II (NIR-II, 900-1700 nm) dyes is highly desirable but challenging. To achieve both red-shifted absorption/emission and superior imaging capabilities, a donor-acceptor-donor (D-A-D) xanthene core was strategically modified by extending π-conjugated double bonds and enhancing electron-donating properties. Two dyes named and were synthesized and exhibited notably red-shifted absorption/emission peaks at 942/1250 and 1098/1450 nm, respectively.
View Article and Find Full Text PDFFabrication of nanoparticles with precisely controllable plasmonic properties as tools for biomedical applications.
Nanoscale
January 2025
AIT Austrian Institute of Technology, Molecular Diagnostics, 1210 Vienna, Austria.
Metal nanoparticles are established tools for biomedical applications due to their unique optical properties, primarily attributed to localized surface plasmon resonances. They show distinct optical characteristics, such as high extinction cross-sections and resonances at specific wavelengths, which are tunable across the wavelength spectrum by modifying the nanoparticle geometry. These attributes make metal nanoparticles highly valuable for sensing and imaging in biology and medicine.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!