Search

Summary: Accurate pathological classification and grading of gliomas is crucial in clinical diagnosis and treatment. The application of deep learning techniques holds promise for automated histological pathology diagnosis. In this study, we collected 733 whole slide images from four medical centers, of which 456 were used for model training, 150 for internal validation, and 127 for multi-center testing. The study includes 5 types of common gliomas.A subtask-guided multi-instance learning image-to-label training pipeline was employed. The pipeline leveraged “patch prompting” for the model to converge with reasonable computational cost. Experiments showed that an overall accuracy of 0.79 in the internal validation dataset. The performance on the multi-center testing dataset showed an overall accuracy to 0.73. The findings suggest a minor yet acceptable performance decrease in multi-center data, demonstrating the model’s strong generalizability and establishing a robust foundation for future clinical applications.

Color is an important trait of pearls which significantly affects their economic value. Golden seawater pearls with excellent luster are becoming popular among consumers, but golden freshwater pearls are rare. Hyriopsis cumingii is the most important freshwater mussel for pearl production in China and a selective breeding program has recently been developed to improve the yellowness and luster of the inner shell of H. cumingii for better production of golden freshwater pearls. As part of this breeding program, it has been necessary to evaluate the genetic parameters of the target traits and possible genotype-by-environment interactions. In this study, we investigated the effects of the environment on the genetic parameters of the inner shell color and luster of F1 golden strain H. cumingii, reared at two sites (Chongming and Wuyi). Inner shell color parameters and inner shell luster were recorded in 570 19-month-old individuals. Microsatellite-based DNA parentage analysis was used to assign the mussels to 19 maternal half-sib families, including 41 full-sib families. The results showed that the estimated heritability of the inner shell color parameters L*, a*, b* and dE were low, 0.13 ± 0.04, 0.14 ± 0.04, 0.12 ± 0.03 and 0.14 ± 0.05, respectively. The heritability of inner shell luster was medium (0.28 ± 0.07). The correlations between the genetic and phenotypic parameters for inner shell color and inner shell luster were insignificant at less than 0.8. Genetic correlations between the inner shell color parameters and inner shell luster in Chongming and Wuyi ranged from −0.07 ± 0.28 to −0.37 ± 0.24 and showed significant genotype-by-environment interaction. This study demonstrated that inner shell color parameters and inner shell luster could be improved by selective breeding. Environmental influences on genotype for inner shell color and inner shell luster should be taken into account in future selective breeding programs in golden strain H. cumingii.