Dataset Information

Multiclass classification of autofluorescence images of oral cavity lesions based on quantitative analysis.

ABSTRACT: BACKGROUND:Oral cancer is one of the most common diseases globally. Conventional oral examination and histopathological examination are the two main clinical methods for diagnosing oral cancer early. VELscope is an oral cancer-screening device that exploited autofluorescence. It yields inconsistent results when used to differentiate between normal, premalignant and malignant lesions. We develop a new method to increase the accuracy of differentiation. MATERIALS AND METHODS:Five samples (images) of each of 21 normal mucosae, as well as 31 premalignant and 16 malignant lesions of the tongue and buccal mucosa were collected under both white light and autofluorescence (VELscope, 400-460 nm wavelength). The images were developed using an iPod (Apple, Atlanta Georgia, USA). RESULTS:The normalized intensity and standard deviation of intensity were calculated to classify image pixels from the region of interest (ROI). Linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA) classifiers were used. The performance of both of the classifiers was evaluated with respect to accuracy, precision, and recall. These parameters were used for multiclass classification. The accuracy rate of LDA with un-normalized data was increased by 2% and 14% and that of QDA was increased by 16% and 25% for the tongue and buccal mucosa, respectively. CONCLUSION:The QDA algorithm outperforms the LDA classifier in the analysis of autofluorescence images with respect to all of the standard evaluation parameters.

SUBMITTER: Jeng MJ

PROVIDER: S-EPMC6999883 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Multiclass classification of autofluorescence images of oral cavity lesions based on quantitative analysis.

Jeng Ming-Jer MJ Sharma Mukta M Chao Ting-Yu TY Li Ying-Chang YC Huang Shiang-Fu SF Chang Liann-Be LB Chow Lee L

PloS one 20200204 2

<h4>Background</h4>Oral cancer is one of the most common diseases globally. Conventional oral examination and histopathological examination are the two main clinical methods for diagnosing oral cancer early. VELscope is an oral cancer-screening device that exploited autofluorescence. It yields inconsistent results when used to differentiate between normal, premalignant and malignant lesions. We develop a new method to increase the accuracy of differentiation.<h4>Materials and methods</h4>Five sa ...[more]

PMID: 32017775

Similar Datasets

Project description:Motor imagery (MI) allows the design of self-paced brain-computer interfaces (BCIs), which can potentially afford an intuitive and continuous interaction. However, the implementation of non-invasive MI-based BCIs with more than three commands is still a difficult task. First, the number of MIs for decoding different actions is limited by the constraint of maintaining an adequate spacing among the corresponding sources, since the electroencephalography (EEG) activity from near regions may add up. Second, EEG generates a rather noisy image of brain activity, which results in a poor classification performance. Here, we propose a solution to address the limitation of identifiable motor activities by using combined MIs (i.e., MIs involving 2 or more body parts at the same time). And we propose two new multilabel uses of the Common Spatial Pattern (CSP) algorithm to optimize the signal-to-noise ratio, namely MC2CMI and MC2SMI approaches. We recorded EEG signals from seven healthy subjects during an 8-class EEG experiment including the rest condition and all possible combinations using the left hand, right hand, and feet. The proposed multilabel approaches convert the original 8-class problem into a set of three binary problems to facilitate the use of the CSP algorithm. In the case of the MC2CMI method, each binary problem groups together in one class all the MIs engaging one of the three selected body parts, while the rest of MIs that do not engage the same body part are grouped together in the second class. In this way, for each binary problem, the CSP algorithm produces features to determine if the specific body part is engaged in the task or not. Finally, three sets of features are merged together to predict the user intention by applying an 8-class linear discriminant analysis. The MC2SMI method is quite similar, the only difference is that any of the combined MIs is considered during the training phase, which drastically accelerates the calibration time. For all subjects, both the MC2CMI and the MC2SMI approaches reached a higher accuracy than the classic pair-wise (PW) and one-vs.-all (OVA) methods. Our results show that, when brain activity is properly modulated, multilabel approaches represent a very interesting solution to increase the number of commands, and thus to provide a better interaction.

Project description:Breast cancer is a common malignancy and a leading cause of cancer-related deaths in women worldwide. Its early diagnosis can significantly reduce the morbidity and mortality rates in women. To this end, histopathological diagnosis is usually followed as the gold standard approach. However, this process is tedious, labor-intensive, and may be subject to inter-reader variability. Accordingly, an automatic diagnostic system can assist to improve the quality of diagnosis. This paper presents a deep learning approach to automatically classify hematoxylin-eosin-stained breast cancer microscopy images into normal tissue, benign lesion, in situ carcinoma, and invasive carcinoma using our collected dataset. Our proposed model exploited six intermediate layers of the Xception (Extreme Inception) network to retrieve robust and abstract features from input images. First, we optimized the proposed model on the original (unnormalized) dataset using 5-fold cross-validation. Then, we investigated its performance on four normalized datasets resulting from Reinhard, Ruifrok, Macenko, and Vahadane stain normalization. For original images, our proposed framework yielded an accuracy of 98% along with a kappa score of 0.969. Also, it achieved an average AUC-ROC score of 0.998 as well as a mean AUC-PR value of 0.995. Specifically, for in situ carcinoma and invasive carcinoma, it offered sensitivity of 96% and 99%, respectively. For normalized images, the proposed architecture performed better for Makenko normalization compared to the other three techniques. In this case, the proposed model achieved an accuracy of 97.79% together with a kappa score of 0.965. Also, it attained an average AUC-ROC score of 0.997 and a mean AUC-PR value of 0.991. Especially, for in situ carcinoma and invasive carcinoma, it offered sensitivity of 96% and 99%, respectively. These results demonstrate that our proposed model outperformed the baseline AlexNet as well as state-of-the-art VGG16, VGG19, Inception-v3, and Xception models with their default settings. Furthermore, it can be inferred that although stain normalization techniques offered competitive performance, they could not surpass the results of the original dataset.

Dataset Information

Multiclass classification of autofluorescence images of oral cavity lesions based on quantitative analysis.

Publications

Multiclass classification of autofluorescence images of oral cavity lesions based on quantitative analysis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets