scholarly journals Fisher linear discriminant analysis for classification and prediction of genomic susceptibility to stomach and colorectal cancers based on six STR loci in a northern Chinese Han population

PeerJ ◽  
2019 ◽  
Vol 7 ◽  
pp. e7004
Author(s):  
Shuhong Hao ◽  
Ming Ren ◽  
Dong Li ◽  
Yujie Sui ◽  
Qingyu Wang ◽  
...  
Keyword(s):  
Discriminant Analysis ◽  
Linear Discriminant Analysis ◽  
Cancer Patients ◽  
Tumor Markers ◽  
Cross Validation ◽  
Healthy Controls ◽  
Fisher Linear Discriminant ◽  
Linear Discriminant ◽  
Str Loci ◽  
Leave One Out

Objective Gastrointestinal cancer is the leading cause of cancer-related death worldwide. The aim of this study was to verify whether the genotype of six short tandem repeat (STR) loci including AR, Bat-25, D5S346, ER1, ER2, and FGA is associated with the risk of gastric cancer (GC) and colorectal cancer (CRC) and to develop a model that allows early diagnosis and prediction of inherited genomic susceptibility to GC and CRC. Methods Alleles of six STR loci were determined using the peripheral blood of six colon cancer patients, five rectal cancer patients, eight GC patients, and 30 healthy controls. Fisher linear discriminant analysis (FDA) was used to establish the discriminant formula to distinguish GC and CRC patients from healthy controls. Leave-one-out cross validation and receiver operating characteristic (ROC) curves were used to validate the accuracy of the formula. The relationship between the STR status and immunohistochemical (IHC) and tumor markers was analyzed using multiple correspondence analysis. Results D5S346 was confirmed as a GC- and CRC-related STR locus. For the first time, we established a discriminant formula on the basis of the six STR loci, which was used to estimate the risk coefficient of suffering from GC and CRC. The model was statistically significant (Wilks’ lambda = 0.471, χ2 = 30.488, df = 13, and p = 0.004). The results of leave-one-out cross validation showed that the sensitivity of the formula was 73.7% and the specificity was 76.7%. The area under the ROC curve (AUC) was 0.926, with a sensitivity of 73.7% and a specificity of 93.3%. The STR status was shown to have a certain relationship with the expression of some IHC markers and the level of some tumor markers. Conclusions The results of this study complement clinical diagnostic criteria and present markers for early prediction of GC and CRC. This approach will aid in improving risk awareness of susceptible individuals and contribute to reducing the incidence of GC and CRC by prevention and early detection.

Momen Ortogon Legendre sebagai Suatu Fitur untuk Pengecaman Kedudukan Penumpang

2012 ◽  
Author(s):  
Choong Yeun Liong ◽  
Nor Azura Md. Ghani ◽  
Abdul Aziz Jemain ◽  
Chris Thompson
Keyword(s):  
Discriminant Analysis ◽  
Linear Discriminant Analysis ◽  
Cross Validation ◽  
Research Work ◽  
The United States ◽  
Highway Safety ◽  
Linear Discriminant ◽  
Segmented Images ◽  
Leave One Out

Makalah ini membincangkan penggunaan momen ortogon Legendre (MOL) sebagai suatu fitur untuk pengelasan imej kedudukan penumpang yang tersegmen-sempurna. Keupayaan mengenal pasti kedudukan penumpang dalam kenderaan adalah penting misalnya sebagai input kepada suatu sistem kereta pintar yang dapat memberikan maklumat untuk pelepasan beg udara keselamatannya. Hasil kajian oleh Insurance Institute for Highway Safety di Amerika Syarikat telah menunjukkan bahawa kedudukan relatif seseorang penumpang itu kepada beg udara adalah penting demi keselamatannya. Lantaran itu kajian ini adalah suatu usaha ke arah menghasilkan satu sistem untuk pengecaman kedudukan penumpang dalam kereta. Sebanyak 1283 imej daripada sepuluh kelas kedudukan penumpang yang telah disegmen-sempurna secara manual diguna dalam kajian ini dan sembilan fitur MOL telah dijana untuk setiap imej menggunakan atur cara C++. Fitur-fitur itu seterusnya telah dimasukkan ke dalam pakej SPSS dan kajian pengelasan telah dijalankan menggunakan analisis diskriminan linear Fisher. Analisis diskriminan linear Fisher digunakan untuk memperlihatkan kepentingan dan perbezaan yang timbul di antara fitur-fitur yang diguna ke arah menerangkan kedudukan-kedudukan penumpang tersebut. Pengelasan data telah dijalankan menggunakan kaedah pengesahan-silang (pengelasan keluarkan-satu) untuk memaksimumkan penyelidikan ke atas data yang ada. Kaedah ini membolehkan kesemua data yang ada diguna untuk latihan, dan juga dalam pengesahan, di samping masih tetap menghasilkan suatu anggaran tak-bersandar akan keupayaan pengelas secara teritlak. Hasil pengelasan yang diperoleh menunjukkan bahawa kesemua kedudukan penumpang telah dikelaskan ke dalam kelas yang sepatutnya dengan kadar kejayaan 100%. Oleh itu kesimpulannya, imej yang tersegmen-sempurna itu telah didiskriminan dengan sempurna ke dalam kelas yang sepatutnya dan ini menyokong MOL sebagai suatu fitur yang boleh digunakan untuk pengecaman kedudukan penumpang yang dikaji. Kata kunci: Momen ortogon Legendre, kelas kedudukan penumpang, tersegmen–sempurna, analisis diskriminan linear Fisher In this article, the application of Legendre orthogonal moment (LOM) for the classification of perfectly hand-segmented passenger position images is discussed. The ability to identify the passenger position in a car is important for instance as an input to a smart car’s system for the deployment of its safety airbag. Reseach reports by the Insurance Institute for Highway Safety in the United States have shown that the relative position of a passenger to the airbag is important to his/her safety. Hence this research work is towards developing a system for passenger position recognition in a car. A total of 1283 images of ten passenger position classes that have been perfectly segmented by hand were used in this work, and nine LOM features have been generated for each image by using a C++ program. The features were then fed into the SPSS package for classification by using Fisher’s linear discriminant analysis. Fisher’s linear discriminant analysis was used to show the importance and the differences among the features used toward describing the passenger positions. Data classification has been performed by using cross-validation (leave-one-out classification) in order to maximise the investigation on the data available. This method enables all of the available data to be utilised for training, as well as for validation, while still generating an independent estimate of the classifier generalisation capability. The classification results produced showed that the various passenger classes have been classified into the respective classes with a 100% success rate. Therefore, it can be concluded that the perfectly segmented images has been well discriminated into the respectively classes and this supports LOM as a potential feature for the recognition of the passenger positions investigated. Kata kunci: Momen ortogon Legendre, kelas kedudukan penumpang, tersegmen–sempurna, analisis diskriminan linear Fisher

2D Image Matrix-Based Discriminator

2006 ◽  
pp. 258-286
Author(s):  
David Zhang ◽  
Xiao-Yuan Jing ◽  
Jian Yang
Keyword(s):  
Principal Component Analysis ◽  
Discriminant Analysis ◽  
Linear Discriminant Analysis ◽  
Principal Component ◽  
Component Analysis ◽  
Two Dimensional ◽  
Fisher Linear Discriminant ◽  
Linear Discriminant ◽  
Image Projection ◽  
Projection Techniques

This chapter presents two straightforward image projection techniques — two-dimensional (2D) image matrix-based principal component analysis (IMPCA, 2DPCA) and 2D image matrix-based Fisher linear discriminant analysis (IMLDA, 2DLDA). After a brief introduction, we first introduce IMPCA. Then IMLDA technology is given. As a result, we summarize some useful conclusions.

Sign in / Sign up

Export Citation Format

Share Document