This study uses hyperspectral imaging (HSI) and a deep learning diagnosis model that can identify the stage of esophageal cancer and mark the locations. This model simulates the spectrum data from the image using an algorithm developed in this study which is combined with deep learning for the classification and diagnosis of esophageal cancer using a single-shot multibox detector (SSD)-based identification system. Some 155 white-light endoscopic images and 153 narrow-band endoscopic images of esophageal cancer were used to evaluate the prediction model. The algorithm took 19 s to predict the results of 308 test images and the accuracy of the test results of the WLI and NBI esophageal cancer was 88 and 91%, respectively, when using the spectral data. Compared with RGB images, the accuracy of the WLI was 83% and the NBI was 86%. In this study, the accuracy of the WLI and NBI was increased by 5%, confirming that the prediction accuracy of the HSI detection method is significantly improved.

Early detection of esophageal cancer has always been difficult, thereby reducing the overall five-year survival rate of patients. In this study, semantic segmentation was used to predict and label esophageal cancer in its early stages. U-Net was used as the basic artificial neural network along with Resnet to extract feature maps that will classify and predict the location of esophageal cancer. A total of 75 white-light images (WLI) and 90 narrow-band images (NBI) were used. These images were classified into three categories: normal, dysplasia, and squamous cell carcinoma. After labeling, the data were divided into a training set, verification set, and test set. The training set was approved by the encoder–decoder model to train the prediction model. Research results show that the average time of 111 ms is used to predict each image in the test set, and the evaluation method is calculated in pixel units. Sensitivity is measured based on the severity of the cancer. In addition, NBI has higher accuracy of 84.724% when compared with the 82.377% accuracy rate of WLI, thereby making it a suitable method to detect esophageal cancer using the algorithm developed in this study.

In this study, n-type MoS2 monolayer flakes are grown through chemical vapor deposition (CVD), and a p-type Cu2O thin film is grown via electrochemical deposition. The crystal structure of the grown MoS2 flakes is analyzed through transmission electron microscopy. The monolayer structure of the MoS2 flakes is verified with Raman spectroscopy, multiphoton excitation microscopy, atomic force microscopy, and photoluminescence (PL) measurements. After the preliminary processing of the grown MoS2 flakes, the sample is then transferred onto a Cu2O thin film to complete a p-n heterogeneous structure. Data are confirmed via scanning electron microscopy, SHG, and Raman mapping measurements. The luminous energy gap between the two materials is examined through PL measurements. Results reveal that the thickness of the single-layer MoS2 film is 0.7 nm. PL mapping shows a micro signal generated at the 627 nm wavelength, which belongs to the B2 excitons of MoS2 and tends to increase gradually when it approaches 670 nm. Finally, the biosensor is used to detect lung cancer cell types in hydroplegia significantly reducing the current busy procedures and longer waiting time for detection. The results suggest that the fabricated sensor is highly sensitive to the change in the photocurrent with the number of each cell, the linear regression of the three cell types is as high as 99%. By measuring the slope of the photocurrent, we can identify the type of cells and the number of cells.