Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
. Significance Optical mammography as a promising tool for cancer diagnosis has largely fallen behind expectations. Modern machine learning (ML) methods offer ways to improve cancer detection in diffuse optical transmission data. Aim We aim to quantitatively evaluate the classification of cancer-positive versus cancer-negative patients using ML methods on raw transmission time series data from bilateral breast scans during subjects’ rest. Approach We use a support vector machine (SVM) with hyperparameter optimization and cross-validation to systematically explore a range of data preprocessing and feature-generation strategies. We also apply an automated ML (AutoML) framework to validate our findings. We use receiver operating characteristics and the corresponding area under the curve (AUC) to quantify classification performance. Results For the sample group available ( , 18 cancer patients), we demonstrate an AUC score of up to 93.3% for SVM classification and up to 95.0% for the AutoML classifier. Conclusions ML offers a viable strategy for clinically relevant breast cancer diagnosis using diffuse-optical transmission measurements. The diagnostic performance of ML on raw data can outperform traditional statistical biomarkers derived from reconstructed image time series. To achieve clinically relevant performance, our ML approach requires simultaneous bilateral scanning of the breasts with spatially dense channel coverage.
. Significance Optical mammography as a promising tool for cancer diagnosis has largely fallen behind expectations. Modern machine learning (ML) methods offer ways to improve cancer detection in diffuse optical transmission data. Aim We aim to quantitatively evaluate the classification of cancer-positive versus cancer-negative patients using ML methods on raw transmission time series data from bilateral breast scans during subjects’ rest. Approach We use a support vector machine (SVM) with hyperparameter optimization and cross-validation to systematically explore a range of data preprocessing and feature-generation strategies. We also apply an automated ML (AutoML) framework to validate our findings. We use receiver operating characteristics and the corresponding area under the curve (AUC) to quantify classification performance. Results For the sample group available ( , 18 cancer patients), we demonstrate an AUC score of up to 93.3% for SVM classification and up to 95.0% for the AutoML classifier. Conclusions ML offers a viable strategy for clinically relevant breast cancer diagnosis using diffuse-optical transmission measurements. The diagnostic performance of ML on raw data can outperform traditional statistical biomarkers derived from reconstructed image time series. To achieve clinically relevant performance, our ML approach requires simultaneous bilateral scanning of the breasts with spatially dense channel coverage.
This study presents and compares two methods for identifying the types of extracellular vesicles (EVs) from different cell lines. Through SDS-PAGE analysis, we discovered that the ratio of CD63 to CD81 in different EVs is consistent and distinct, making it a reliable characteristic for recognizing EVs secreted by cancer cells. However, the electrophoresis and imaging processes may introduce errors in the concentration values, especially at lower concentrations, rendering this method potentially less effective. An alternative approach involves the use of quartz crystal microbalance (QCM) and electroanalytical interdigitated electrode (IDT) biosensors for EV type identification and quantification. The QCM frequency shift caused by EVs is directly proportional to their concentration, while electroanalysis relies on measuring the curvature of the I−V curve as a distinguishing feature, which is also proportional to EV concentration. Linear regression lines for the QCM frequency shift and the electroanalysis curvature of various EV types are plotted separately, enabling the estimation of the corresponding concentration for an unknown EV type on the graphs. By intersecting the results from both biosensors, the unknown EV type can be identified. The biosensor analysis method proves to be an effective means of analyzing both the type and concentration of EVs from different cell lines.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.