The Al-Containing Silicates Modified with Organic Ligands and SnO2 Nanoparticles for Catalytic Baeyer-Villiger Oxidation and Aerobic Carboxylation of Carbonyl Compounds.

The Baeyer-Villiger Oxidation (BVO) of ketones and aldehydes produce lactones and formates, while aerobic carboxylation of aldehydes manufactures carboxylic acids, both having high added value. This work prepared a series of Al-containing silicates modified with organic ligands and SnO2 nanoparticles, which were then employed as catalyst in BVO and carboxylation. Characterizations revealed the morphology of the synthesized catalyst was changed from micron-sized thin sheets to smaller blocks, and then to uniform nanoparticles (size of 50 nm) having the doped SnO2 nanoparticles with a size of 29 nm. All catalysts showed high BET surface areas featuring silt-like mesopores. In determining the priority of BVO and carboxylation, an influence evaluation of the parameters showed the order to be substrate > oxidant > solvent > catalyst. Cyclic aliphatic ketones were suitable for BVO, but linear aliphatic and aromatic aldehydes for carboxylation. Coordination of (S)-binaphthol or doping of Sn into catalyst showed little influence on BVO under m-CPBA, but the Sn-doped catalyst largely increased BVO under (NH4)2S2O8 and H2O2. Calculations revealed that the catalyst containing both Al and Sn could give BVO intermediates lower energies than the Sn-beta zeolite model. The present system exhibited merits including wider substrate scope, innocuous catalytic metal, greener oxidant, as well as lower catalyst cost.

Deep learning assisted contrast-enhanced CT-based diagnosis of cervical lymph node metastasis of oral cancer: a retrospective study of 1466 cases.

OBJECTIVES: Lymph node (LN) metastasis is a common cause of recurrence in oral cancer; however, the accuracy of distinguishing positive and negative LNs is not ideal. Here, we aimed to develop a deep learning model that can identify, locate, and distinguish LNs in contrast-enhanced CT (CECT) images with a higher accuracy. METHODS: The preoperative CECT images and corresponding postoperative pathological diagnoses of 1466 patients with oral cancer from our hospital were retrospectively collected. In stage I, full-layer images (five common anatomical structures) were labeled; in stage II, negative and positive LNs were separately labeled. The stage I model was innovatively employed for stage II training to improve accuracy with the idea of transfer learning (TL). The Mask R-CNN instance segmentation framework was selected for model construction and training. The accuracy of the model was compared with that of human observers. RESULTS: A total of 5412 images and 5601 images were labeled in stage I and II, respectively. The stage I model achieved an excellent segmentation effect in the test set (AP50-0.7249). The positive LN accuracy of the stage II TL model was similar to that of the radiologist and much higher than that of the surgeons and students (0.7042 vs. 0.7647 (p = 0.243), 0.4216 (p < 0.001), and 0.3629 (p < 0.001)). The clinical accuracy of the model was highest (0.8509 vs. 0.8000, 0.5500, 0.4500, and 0.6658 of the Radiology Department). CONCLUSIONS: The model was constructed using a deep neural network and had high accuracy in LN localization and metastasis discrimination, which could contribute to accurate diagnosis and customized treatment planning. KEY POINTS: • Lymph node metastasis is not well recognized with modern medical imaging tools. • Transfer learning can improve the accuracy of deep learning model prediction. • Deep learning can aid the accurate identification of lymph node metastasis.