To extract a genuine peptide signal from a mass spectrum, an observed series of peaks at a particular mass can be compared with the isotope distribution expected for a peptide of that mass. To decide whether the observed series of peaks is similar to the isotope distribution, a similarity measure is needed. In this short communication, we investigate whether the Mahalanobis distance could be an alternative measure for the commonly employed Pearson's χ(2) statistic. We evaluate the performance of the two measures by using a controlled MALDI-TOF experiment. The results indicate that Pearson's χ(2) statistic has better discriminatory performance than the Mahalanobis distance and is a more robust measure.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1007/s13361-013-0773-z | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Spatiotemporal multi-feature fusion vehicle trajectory anomaly detection for intelligent transportation: An improved method combining autoencoders and dynamic Bayesian networks.
Accid Anal Prev
January 2025
School of Computer Science and Informatics, De Montfort University, Leicester LE1 9BH, UK.
With the continuous development of intelligent transportation systems, traffic safety has become a major societal concern, and vehicle trajectory anomaly detection technology has emerged as a crucial method to ensure safety. However, current technologies face significant challenges in handling spatiotemporal data and multi-feature fusion, including difficulties in big data processing, and have room for improvement in these areas. To address these issues, this paper proposes a novel method that combines autoencoders, Mahalanobis distance, and dynamic Bayesian networks for anomaly detection.
View Article and Find Full Text PDFTowards safe and reliable deep learning for lung nodule malignancy estimation using out-of-distribution detection.
Comput Biol Med
December 2024
Diagnostic Imaging Analysis Group, Medical Imaging Department, Radboud University Medical Center, Geert Grooteplein Zuid 10, 6525 GA, Nijmegen, the Netherlands.
Artificial Intelligence (AI) models may fail or suffer from reduced performance when applied to unseen data that differs from the training data distribution, referred to as dataset shift. Automatic detection of out-of-distribution (OOD) data contributes to safe and reliable clinical implementation of AI models. In this study, we propose a recognized OOD detection method that utilizes the Mahalanobis distance (MD) and compare its performance to widely known classical methods.
View Article and Find Full Text PDFComparison of rigid and elastic registration methods in software-based targeted prostate biopsy: a multicenter cohort study.
Turk J Med Sci
December 2024
Department of Urology, Faculty of Medicine, Acibadem University, İstanbul, Turkiye.
Background/aim: This study aims to compare the success rates of rigid registration (RR) and elastic registration (ER) systems in diagnosing all cancers and clinically significant prostate cancer (csPC) in software-based targeted prostate biopsies (TPBs) by performing matching analysis.
Materials And Methods: The data of 2061 patients from six centers where software-based TPB is performed were used. All cancer and csPC detection rates of the RR and ER systems were compared following Mahalanobis distance matching with the propensity score caliper method.
Cacao agroforestry adoption by smallholder farmers and forest loss prevention in the Maya Golden Landscape, Belize.
Ambio
December 2024
Center for Space and Remote Sensing Research, Zhongli District, National Central University, Taoyuan City, 32001, Taiwan.
Unsustainable land use practices have led to increased forest loss rates. Implementing cacao agroforestry can reduce forest loss by preventing the clear-cutting of forests for monoculture plantations. However, research is needed on its effectiveness in preventing forest loss and the factors influencing its adoption between full-time and part-time farmers.
View Article and Find Full Text PDFPost-hoc out-of-distribution detection for cardiac MRI segmentation.
Comput Med Imaging Graph
December 2024
ICMUB, Université de Bourgogne, Dijon, France. Electronic address:
In real-world scenarios, medical image segmentation models encounter input images that may deviate from the training images in various ways. These differences can arise from changes in image scanners and acquisition protocols, or even the images can come from a different modality or domain. When the model encounters these out-of-distribution (OOD) images, it can behave unpredictably.
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!