Dual-Responsive Carbon Quantum Dots for the Simultaneous Detection of Cytosine and 5-Methylcytosine Interpreted by a Machine Learning-Assisted Smartphone.

DNA methylation is an epigenetic alteration that results in 5-methylcytosine (5-mC) through the addition of a methyl group to the fifth carbon of a cytosine (C) residue. The methylation level, the ratio of 5-mC to C, in urine might be related to the whole-body epigenetic status and the occurrence of common cancers. To date, never before have any nanomaterials been developed to simultaneously determine C and 5-mC in urine samples. Herein, a dual-responsive fluorescent sensor for the urinary detection of C and 5-mC has been developed. This assay relied on changes in the optical properties of nitrogen-doped carbon quantum dots (CQDs) prepared by microwave-assisted pyrolysis. In the presence of C, the blue-shifted fluorescence intensity of the CQDs increased. However, fluorescence quenching was observed upon the addition of 5-mC. This was primarily due to photoinduced electron transfer as confirmed by the density functional theory calculation. In urine samples, our sensitive fluorescent sensor had detection limits for C and 5-mC of 43.4 and 74.4 µM, respectively, and achieved satisfactory recoveries ranging from 103.5 to 115.8%. The simultaneous detection of C and 5-mC leads to effective methylation level detection, achieving recoveries in the range of 104.6-109.5%. Besides, a machine learning-enabled smartphone was also developed, which can be effectively applied to the determination of methylation levels (0-100%). These results demonstrate a simple but very effective approach for detecting the methylation level in urine, which could have significant implications for predicting the clinical prognosis.

BiTNet: Hybrid deep convolutional model for ultrasound image analysis of human biliary tract and its applications.

Certain life-threatening abnormalities, such as cholangiocarcinoma, in the human biliary tract are curable if detected at an early stage, and ultrasonography has been proven to be an effective tool for identifying them. However, the diagnosis often requires a second opinion from experienced radiologists, who are usually overwhelmed by many cases. Therefore, we propose a deep convolutional neural network model, named biliary tract network (BiTNet), developed to solve problems in the current screening system and to avoid overconfidence issues of traditional deep convolutional neural networks. Additionally, we present an ultrasound image dataset for the human biliary tract and demonstrate two artificial intelligence (AI) applications: auto-prescreening and assisting tools. The proposed model is the first AI model to automatically screen and diagnose upper-abdominal abnormalities from ultrasound images in real-world healthcare scenarios. Our experiments suggest that prediction probability has an impact on both applications, and our modifications to EfficientNet solve the overconfidence problem, thereby improving the performance of both applications and of healthcare professionals. The proposed BiTNet can reduce the workload of radiologists by 35% while keeping the false negatives to as low as 1 out of every 455 images. Our experiments involving 11 healthcare professionals with four different levels of experience reveal that BiTNet improves the diagnostic performance of participants of all levels. The mean accuracy and precision of the participants with BiTNet as an assisting tool (0.74 and 0.61, respectively) are statistically higher than those of participants without the assisting tool (0.50 and 0.46, respectively (p<0.001)). These experimental results demonstrate the high potential of BiTNet for use in clinical settings.