Limits...
Near-infrared spectroscopy as a diagnostic tool for distinguishing between normal and malignant colorectal tissues.

Chen H, Lin Z, Mo L, Wu T, Tan C - Biomed Res Int (2015)

Bottom Line: The successive projection algorithm-linear discriminant analysis (SPA-LDA) was used to seek a reduced subset of variables/wavenumbers and build a diagnostic model of LDA.The results showed that, compared to PLS-DA, SPA-LDA provided more parsimonious model using only three wavenumbers/variables (4065, 4173, and 5758 cm(-1)) to achieve the sensitivity of 84.6%, 92.3%, and 92.3% for the training, validation, and test sets, respectively, and the specificity of 100% for each subset.It indicated that the combination of NIR spectroscopy and SPA-LDA algorithm can serve as a potential tool for distinguishing between normal and malignant colorectal tissues.

View Article: PubMed Central - PubMed

Affiliation: Yibin University Hospital, Yibin, Sichuan 644000, China ; Key Lab of Process Analysis and Control of Sichuan Universities, Yibin University, Yibin, Sichuan 644000, China.

ABSTRACT
Cancer diagnosis is one of the most important tasks of biomedical research and has become the main objective of medical investigations. The present paper proposed an analytical strategy for distinguishing between normal and malignant colorectal tissues by combining the use of near-infrared (NIR) spectroscopy with chemometrics. The successive projection algorithm-linear discriminant analysis (SPA-LDA) was used to seek a reduced subset of variables/wavenumbers and build a diagnostic model of LDA. For comparison, the partial least squares-discriminant analysis (PLS-DA) based on full-spectrum classification was also used as the reference. Principal component analysis (PCA) was used for a preliminary analysis. A total of 186 spectra from 20 patients with partial colorectal resection were collected and divided into three subsets for training, optimizing, and testing the model. The results showed that, compared to PLS-DA, SPA-LDA provided more parsimonious model using only three wavenumbers/variables (4065, 4173, and 5758 cm(-1)) to achieve the sensitivity of 84.6%, 92.3%, and 92.3% for the training, validation, and test sets, respectively, and the specificity of 100% for each subset. It indicated that the combination of NIR spectroscopy and SPA-LDA algorithm can serve as a potential tool for distinguishing between normal and malignant colorectal tissues.

Show MeSH
The prediction performance of the final PLS-DA model on different subsets.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4309295&req=5

fig5: The prediction performance of the final PLS-DA model on different subsets.

Mentions: When the PLS-DA model was constructed, one major issue was the choice of the optimal number of latent variables (LVs), which was carried out by a 5-fold cross validation procedure. When performing cross validation, the samples in the training set were first divided into five cross validation groups, that is, cancellation groups. Each cancellation group was first assigned 5 cancerous spectra and 7 normal spectra and the remaining spectra entered into the fifth group. Each cross validation group was removed from the training set, one at a time. Each time, the model was trained on the remaining samples and then used to predict the samples in the cross validation group. Figure 4 illustrated the influence of the number of LVs in the PLS-DA model on the classification error (Err.). It seemed that the minimum misclassification ratio corresponded to 2 LVs, meaning that a relatively simple classification model was obtained, that is, a model based on few latent variables, which was preferable in terms of both model interpretation and stability. Considering that the loading can offer the possibility of observing the importance of features, the loading vectors of the selected LVs were also provided in Figure 4. Clearly, the LV1 and LV2 focused on the CH first overtones and CH, NH, CH, and CC combinations regions, respectively. Figure 5 showed the prediction performance of the final PLS-DA model on the training, validation, and test sets. For either the training or test set, seven spectra were misclassified. The sensitivity and specificity were 84.6%, 84.6%, and 91.7% and 92.3%, 88.9%, and 86.1% for the training, validation, and test sets, respectively.


Near-infrared spectroscopy as a diagnostic tool for distinguishing between normal and malignant colorectal tissues.

Chen H, Lin Z, Mo L, Wu T, Tan C - Biomed Res Int (2015)

The prediction performance of the final PLS-DA model on different subsets.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4309295&req=5

fig5: The prediction performance of the final PLS-DA model on different subsets.
Mentions: When the PLS-DA model was constructed, one major issue was the choice of the optimal number of latent variables (LVs), which was carried out by a 5-fold cross validation procedure. When performing cross validation, the samples in the training set were first divided into five cross validation groups, that is, cancellation groups. Each cancellation group was first assigned 5 cancerous spectra and 7 normal spectra and the remaining spectra entered into the fifth group. Each cross validation group was removed from the training set, one at a time. Each time, the model was trained on the remaining samples and then used to predict the samples in the cross validation group. Figure 4 illustrated the influence of the number of LVs in the PLS-DA model on the classification error (Err.). It seemed that the minimum misclassification ratio corresponded to 2 LVs, meaning that a relatively simple classification model was obtained, that is, a model based on few latent variables, which was preferable in terms of both model interpretation and stability. Considering that the loading can offer the possibility of observing the importance of features, the loading vectors of the selected LVs were also provided in Figure 4. Clearly, the LV1 and LV2 focused on the CH first overtones and CH, NH, CH, and CC combinations regions, respectively. Figure 5 showed the prediction performance of the final PLS-DA model on the training, validation, and test sets. For either the training or test set, seven spectra were misclassified. The sensitivity and specificity were 84.6%, 84.6%, and 91.7% and 92.3%, 88.9%, and 86.1% for the training, validation, and test sets, respectively.

Bottom Line: The successive projection algorithm-linear discriminant analysis (SPA-LDA) was used to seek a reduced subset of variables/wavenumbers and build a diagnostic model of LDA.The results showed that, compared to PLS-DA, SPA-LDA provided more parsimonious model using only three wavenumbers/variables (4065, 4173, and 5758 cm(-1)) to achieve the sensitivity of 84.6%, 92.3%, and 92.3% for the training, validation, and test sets, respectively, and the specificity of 100% for each subset.It indicated that the combination of NIR spectroscopy and SPA-LDA algorithm can serve as a potential tool for distinguishing between normal and malignant colorectal tissues.

View Article: PubMed Central - PubMed

Affiliation: Yibin University Hospital, Yibin, Sichuan 644000, China ; Key Lab of Process Analysis and Control of Sichuan Universities, Yibin University, Yibin, Sichuan 644000, China.

ABSTRACT
Cancer diagnosis is one of the most important tasks of biomedical research and has become the main objective of medical investigations. The present paper proposed an analytical strategy for distinguishing between normal and malignant colorectal tissues by combining the use of near-infrared (NIR) spectroscopy with chemometrics. The successive projection algorithm-linear discriminant analysis (SPA-LDA) was used to seek a reduced subset of variables/wavenumbers and build a diagnostic model of LDA. For comparison, the partial least squares-discriminant analysis (PLS-DA) based on full-spectrum classification was also used as the reference. Principal component analysis (PCA) was used for a preliminary analysis. A total of 186 spectra from 20 patients with partial colorectal resection were collected and divided into three subsets for training, optimizing, and testing the model. The results showed that, compared to PLS-DA, SPA-LDA provided more parsimonious model using only three wavenumbers/variables (4065, 4173, and 5758 cm(-1)) to achieve the sensitivity of 84.6%, 92.3%, and 92.3% for the training, validation, and test sets, respectively, and the specificity of 100% for each subset. It indicated that the combination of NIR spectroscopy and SPA-LDA algorithm can serve as a potential tool for distinguishing between normal and malignant colorectal tissues.

Show MeSH