Vocal Cord Leukoplakia Classification Using Siamese Network Under Small Samples of White Light Endoscopy Images.

OBJECTIVE: Accurate vocal cord leukoplakia classification is instructive for clinical diagnosis and surgical treatment. This article introduces a reliable very deep Siamese network for accurate vocal cord leukoplakia classification. STUDY DESIGN: A study of a classification network based on a retrospective database. SETTING: Academic university and hospital. METHODS: The white light image datasets of vocal cord leukoplakia used in this article were classified into 6 classes: normal tissues, inflammatory keratosis, mild dysplasia, moderate dysplasia, severe dysplasia, and squamous cell carcinoma. The classification performance was assessed by comparing it with 6 classical deep learning models, including AlexNet, VGG Net, Google Inception, ResNet, DenseNet, and Vision Transformer. RESULTS: Experiments show the superior classification performance of our proposed network compared to state-of-the-art methods. The overall accuracy is 0.9756. The values of sensitivity and specificity are very high as well. The confusion matrix provides information for the 6-class classification task and demonstrates the superiority of our proposed network. CONCLUSION: Our very deep Siamese network can provide accurate classification results of vocal cord leukoplakia, which facilitates early detection, clinical diagnosis, and surgical treatment. The excellent performance obtained in white light images can reduce the cost for patients, especially those living in developing countries.

Vocal cord leukoplakia classification using deep learning models in white light and narrow band imaging endoscopy images.

BACKGROUND: Accurate vocal cord leukoplakia classification is critical for the individualized treatment and early detection of laryngeal cancer. Numerous deep learning techniques have been proposed, but it is unclear how to select one to apply in the laryngeal tasks. This article introduces and reliably evaluates existing deep learning models for vocal cord leukoplakia classification. METHODS: We created white light and narrow band imaging (NBI) image datasets of vocal cord leukoplakia which were classified into six classes: normal tissues (NT), inflammatory keratosis (IK), mild dysplasia (MiD), moderate dysplasia (MoD), severe dysplasia (SD), and squamous cell carcinoma (SCC). Vocal cord leukoplakia classification was performed using six classical deep learning models, AlexNet, VGG, Google Inception, ResNet, DenseNet, and Vision Transformer. RESULTS: GoogLeNet (i.e., Google Inception V1), DenseNet-121, and ResNet-152 perform excellent classification. The highest overall accuracy of white light image classification is 0.9583, while the highest overall accuracy of NBI image classification is 0.9478. These three neural networks all provide very high sensitivity, specificity, and precision values. CONCLUSION: GoogLeNet, ResNet, and DenseNet can provide accurate pathological classification of vocal cord leukoplakia. It facilitates early diagnosis, providing judgment on conservative treatment or surgical treatment of different degrees, and reducing the burden on endoscopists.

Insight into the Effect of Counterions on the Chromatic Properties of Cr-Doped Rutile TiO2-Based Pigments.

Rutile TiO2 pigments codoped with chromophore ion Cr3+ and various charge-balancing ions (i.e., counterions species of Sb, Nb, W and Mo) were prepared by a solid-phase reaction method. The effects of the counterions and calcination temperatures on the phase structure, color-rendering and spectroscopic properties, microstructure, and stability of the synthesized pigments were investigated in detail. The results showed that the introduction of 5-10% counterions improved the solubility of Cr3+ in the TiO2 lattice to form the single-phase rutile pigments calcined at 1100 °C for 2 h. The 10% Cr-doped pigment showed a dark brown color. Depending on the content and type of counterions, the color of the codoped pigments was tailored from yellow to reddish or yellowish-orange to black with different brightness and hue. The influence mechanism of counterions was ascribed to the lattice distortion and variation in the charge balance condition. It was found that the addition of Sb, Nb, or Mo resulted in a remarkable improvement in the NIR reflectance of pigments. The grain growth was inhibited with the codoping of Cr/Sb and Cr/Nb to achieve the nano-sized pigments. In addition, the prepared pigments exhibited good acid and alkali corrosion resistance as well as excellent stability and coloring performance in transparent ceramic glazes.

Influence of Oxidation Damages on Mechanical Properties of SiC/SiC Composite Using Domestic Hi-Nicalon Type SiC Fibers.

Here, we show that when the oxidation treatment temperature exceeded 600°C, the tensile strength of SiC/SiC begins to decrease. Oxidation leads to the damages on the PyC fiber/matrix interface, which is replaced by SiO2 at higher temperature. The fracture mode converts from fiber pull-out to fiber-break as the fiber/matrix interface is filled with SiO2. Oxidation time also plays an important role in affecting the tensile strength of SiC/SiC. The tensile modulus decreases with temperature from RT to 800°C, then increases above 800°C due to the decomposition of remaining CSi x O y and crystallization of the SiC matrix. A special surface densification treatment performed in this study is confirmed to be an effective approach to reduce the oxidation damages and improve the tensile strength of SiC/SiC after oxidation.