A Three-Stage Semi-Supervised Learning Approach to Spine Image Segmentation.

Spine segmentation in computed tomography (CT) images is critical for automatic analysis, especially when focusing on varied spinal anatomy. Despite having comprehensive annotations for normal vertebrae, many datasets do not encompass labeled fracture data, posing challenges for predictive modeling. This research presents a three-stage 2.

Novel dammarane-type glycosides from Gynostemma pentaphyllum.

Three new dammarane glycosides (1-3), together with five known compounds, gypenoside LXIX (4), gylongiposide I (5), gypenoside XLVIII (6), allantion (7) and vitexin (8) were isolated from the MeOH extract of the aerial parts of Gynostemma pentaphyllum. Compounds 5, 7, and 8 were isolated from this plant for the first time. Their structures were elucidated by 1D and 2D NMR spectra interpretation as well as by chemical degradation.

Dammarane-type glycosides from Gynostemma pentaphyllum.

Fifteen new dammarane glycosides (1-15), together with four known compounds, gypenosides IV, VIII, LXXI, and XLIX, were isolated from the MeOH extract of the aerial parts of Gynostemma pentaphyllum. Their structures were elucidated by 1D and 2D NMR spectra interpretation as well as by chemical degradation.