No abstract

Demosaicking and denoising are critical for deciding on digital camera performance. However, conventional joint demosaicking and denoising methods use traditional hand-crafted filters for preprocessing and image restoration. Therefore, it is susceptible to noise and can produce many artifacts for images with numerous edges. This paper proposes an end-to-end multi-level wavelet attention convolutional neural network (CNN) that improves image restoration performance by reducing false color artifacts, over-smoothing, and blurring during demosaicing and denoising. In detail, this paper proposes a CNN-based preprocessing method that learns the mosaic image's inter-color correlation, improving the edge's color restoration performance. Furthermore, this paper presents a multi-level feature extraction convolutional block using the Haar wavelet-based discrete wavelet transform (DWT) to remove noise from images and restore colors better at the same time. Therefore, it preserves the information of input image and feature maps, learns the correlation between global and local features, improves image restoration performance, and suppresses phenomena such as over-smoothing that tend to occur in DWT-based denoising. The proposed method is an end-to-end network structure with CNN-based preprocessing methods. In experimental results, the proposed method improves PSNR by 3.67 dB and 0.35 dB on average compared with the traditional methods and the CNN-based methods, respectively, for the dataset with many high-frequency components.

Outpatient detection of total bilirubin levels should be performed regularly to monitor the recurrence of jaundice in hepatobiliary and pancreatic disease patients. However, frequent hospital visits for blood testing are burdensome for patients with poor medical conditions. This study validates a novel deep-learning-based smartphone application for the self-diagnosis of scleral jaundice in such patients. The system predicts total serum bilirubin levels using the deep-learning-based regression analysis of scleral photos taken by the smartphone’s built-in camera. Enrolled patients were randomly assigned to either the training cohort (n = 90, 1034 photos) or the validation cohort (n = 40, 426 photos). The intraclass correlation coefficient value for predicted serum total bilirubin (PSB) derived from the images repeatedly taken at the same time for the same patient showed good reliability (0.86). A strong correlation between measured serum total bilirubin (MSB) and PSB was observed in the subgroup with MSB levels ≥1.5 mg/dL (Spearman rho = 0.70, p < 0.001). The receiver operating characteristic curve for PSB showed that the area under the curve was 0.93, demonstrating good test performance as a predictor of hyperbilirubinemia (p < 0.001). Using a cut-off PSB ≥1.5, the prediction sensitivity of hyperbilirubinemia was 80.0%, with a specificity of 92.6%. Hence, the tool is effective for patient monitoring.

No abstract

No abstract