Deep learning assists detection of esophageal cancer and precursor lesions in a prospective, randomized controlled study.

Endoscopy is the primary modality for detecting asymptomatic esophageal squamous cell carcinoma (ESCC) and precancerous lesions. Improving detection rate remains challenging. We developed a system based on deep convolutional neural networks (CNNs) for detecting esophageal cancer and precancerous lesions [high-risk esophageal lesions (HrELs)] and validated its efficacy in improving HrEL detection rate in clinical practice (trial registration ChiCTR2100044126 at www.chictr.org.cn). Between April 2021 and March 2022, 3117 patients ≥50 years old were consecutively recruited from Taizhou Hospital, Zhejiang Province, and randomly assigned 1:1 to an experimental group (CNN-assisted endoscopy) or a control group (unassisted endoscopy) based on block randomization. The primary endpoint was the HrEL detection rate. In the intention-to-treat population, the HrEL detection rate [28 of 1556 (1.8%)] was significantly higher in the experimental group than in the control group [14 of 1561 (0.9%), P = 0.029], and the experimental group detection rate was twice that of the control group. Similar findings were observed between the experimental and control groups [28 of 1524 (1.9%) versus 13 of 1534 (0.9%), respectively; P = 0.021]. The system's sensitivity, specificity, and accuracy for detecting HrELs were 89.7, 98.5, and 98.2%, respectively. No adverse events occurred. The proposed system thus improved HrEL detection rate during endoscopy and was safe. Deep learning assistance may enhance early diagnosis and treatment of esophageal cancer and may become a useful tool for esophageal cancer screening.

Cyclic Amplification of the Afterglow Luminescent Nanoreporter Enables the Prediction of Anti-cancer Efficiency.

We developed a cyclic amplification method for an organic afterglow nanoreporter for the real-time visualization of self-generated reactive oxygen species (ROS). We promoted semiconducting polymer nanoparticles (PFODBT) as a candidate for emitting near-infrared afterglow luminescence. Introduction of a chemiluminescent substrate (CPPO) into PFODBT (PFODBT@CPPO) resulted in a significant enhancement of afterglow intensity through the dual cyclic amplification pathway involving singlet oxygen (1 O2 ). 1 O2 produced by PFODBT@CPPO induced cancer cell necrosis and promoted the release of damage-related molecular patterns, thereby evoking immunogenic cell death (ICD)-associated immune responses through ROS-based oxidative stress. The afterglow luminescent signals of the nanoreporter were well correlated with light-driven 1 O2 generation and anti-cancer efficiency. This imaging strategy provides a non-invasive tool for predicting the therapeutic outcome that occurs during ROS-mediated cancer therapy.

The adsorption characteristics and degradation mechanism of tinidazole on an anatase TiO2 surface: a DFT study.

The adsorption characteristics and degradation mechanism of tinidazole on TiO2(101) and (001) surfaces under vacuum and aqueous solution conditions were studied by density functional theory (DFT). The results show that tinidazole can adsorb on the surfaces of TiO2(101) and (001) under different conditions. The hydrogen bond generated during the adsorption process can enhance the stability of the adsorption configuration, which makes the bond length of C-N of tinidazole longer and finally facilitates the ring-opening degradation reaction. As for the mechanism of the ring-opening degradation reaction, it was found that ring-opening can be carried out along reaction route II on both crystal surfaces, and the reaction activation energy is lower on (101) surface. Under the conditions of aqueous solution, the decrease of the activation energy of the ring-opening degradation reaction indicates that the solvent conditions can promote the degradation reaction.

Theoretical study of adsorption characteristics and the environmental influence for metronidazole on photocatalytic TiO2 anatase surfaces.

The adsorption characteristics of metronidazole on anatase TiO2(101) and (001) surfaces were studied by density functional theory (DFT). The adsorption structure of metronidazole on anatase TiO2(101) and (001) surfaces has been optimized under vacuum, water, acidic, and alkaline conditions, respectively. The optimum adsorption site, adsorption energy, and electronic structure of the stable adsorption model were calculated. The adsorption characteristics of metronidazole on two different surfaces of TiO2 were studied under acidic and alkaline conditions. Our calculated results found that the adsorption energy range is -0.95 ~ -3.11 eV on the TiO2 (101) surface, and the adsorption energy range is -0.84 ~ -3.29 eV on the TiO2 (001) surface. The adsorption wavelengths of electron transition between valence band and conduction band of metronidazole on the anatase TiO2(101) surface is in the range of visible wavelength, indicating that the TiO2(101) surface can effectively utilize visible light. However, the photocatalytic effect of the TiO2(001) surface is greatly affected by the environment. The results reveal the adsorption characteristics and the environmental influence for metronidazole on photocatalytic anatase TiO2 surfaces. Graphical abstract The adsorption characteristics of metronidazole on anatase TiO2(101) and (001) crystal surfaces were studied by density functional theory (DFT).