The effect of the re-segmentation method on improving the performance of rectal cancer image segmentation models.

BACKGROUND: Rapid and accurate segmentation of tumor regions from rectal cancer images can better understand the patientâs lesions and surrounding tissues, providing more effective auxiliary diagnostic information. However, cutting rectal tumors with deep learning still cannot be compared with manual segmentation, and a major obstacle to cutting rectal tumors with deep learning is the lack of high-quality data sets. OBJECTIVE: We propose to use our Re-segmentation Method to manually correct the model segmentation area and put it into training and training ideas. The data set has been made publicly available. Methods: A total of 354 rectal cancer CT images and 308 rectal region images labeled by experts from Jiangxi Cancer Hospital were included in the data set. Six network architectures are used to train the data set, and the region predicted by the model is manually revised and then put into training to improve the ability of model segmentation and then perform performance measurement. RESULTS: In this study, we use the Resegmentation Method for various popular network architectures. CONCLUSION: By comparing the evaluation indicators before and after using the Re-segmentation Method, we prove that our proposed Re-segmentation Method can further improve the performance of the rectal cancer image segmentation model.

In vitro generation of trophoblast like stem cells from goat pluripotent stem cells.

Since the first mouse induced pluripotent stem cells (iPSCs) was derived, the in vitro culture of domestic iPSCs functionally and molecularly comparable with mouse iPSCs has been a challenge. Here, we established dairy goat iPSCs (giPSCs) from goat ear fibroblast cells with mouse iPSCs morphology, the expression of pluripotent markers and differentiation ability in vitro delivered by piggyBac transposon with nine Dox-inducible exogenous reprogramming factors. These reprogramming factors were bOMSK (bovine OCT4, CMYC, SOX2, and KLF4), pNhL (porcine NANOG and human LIN28), hRL (human RARG and LRH1), and SV40 Large T. Notably, AF-giPSCs (induced in activin A and bFGF condition) were capable of differentiation in embryoid bodies in vitro and could contribute to interspecies chimerism in mouse E6.5 embryos in vitro, demonstrating that AF-giPSCs have the developmental capability to generate some embryonic cell lineages. Moreover, Wnt/ß-catenin signaling has an important role in driving goat induced trophoblast-like stem cells (giTLSCs) from Dox-independent giPSCs. This study will support further establishment of the stable giPSC lines without any integration of exogenous genes.

SP6 controls human cytotrophoblast fate decisions and trophoblast stem cell establishment by targeting MSX2 regulatory elements.

The commitment and differentiation of human placental progenitor cytotrophoblast (CT) cells are crucial for a successful pregnancy, but the underlying mechanism remains poorly understood. Here, we identified the transcription factor (TF), specificity protein 6 (SP6), as a human species-specific trophoblast lineage TF expressed in human placental CT cells. Using pluripotent stem cells as a model, we demonstrated that SP6 controls CT generation and the establishment of trophoblast stem cells (TSCs) and identified msh homeobox 2 (MSX2) as the downstream effector in these events. Mechanistically, we showed that SP6 interacts with histone acetyltransferase P300 to alter the landscape of H3K27ac at targeted regulatory elements, thereby favoring transcriptional activation and facilitating CT cell fate decisions and TSC maintenance. Our results established SP6 as a regulator of the human trophoblast lineage and implied its role in placental development and the pathogenies of placental diseases.