Although posterior-only approach using pedicle screw fixation had good correction rate, complications were similar to previous reports. There were few unusual complications like coccygodynia.

No abstract

Deep learning techniques, especially Convolutional Neural Networks (CNN), dominate the benchmarks for most computer vision tasks. These state-of-the-art results are typically obtained through supervised learning, for which large annotated datasets are required. However, acquiring such datasets for manufacturing applications remains a challenging proposition due to the time and costs involved in their collection. To overcome this disadvantage, a novel framework is proposed for data augmentation by creating synthetic images using Generative Adversarial Networks (GANs). The generator synthesizes new surface defect images from random noise which is trained over time to get realistic fakes. These synthetic images can be used further for training of classification algorithms. Three GAN architectures are trained, and the entire data augmentation pipeline is implemented for the Northeastern University (China) Classification (NEU-CLS) dataset for hot-rolled steel strips from NEU Surface Defect Database. The classification accuracy of a simple CNN architecture is measured on synthetic augmented data and further it is compared with similar state-of-the-arts. It is observed that the proposed GANs-based augmentation scheme significantly improves the performance of CNN for classification of surface defects. The classically augmented CNN yields sensitivity and specificity of 90.28% and 98.06% respectively. In contrast, the synthetically augmented CNN yields better results, with sensitivity and specificity of 95.33% and 99.16% respectively. Also, the use of GANs is demonstrated to disentangle the representation space and to add additional domain knowledge through synthetic augmentation that can be difficult to replicate through classic augmentation. The proposed framework demonstrates high generalization capability. It may be applied to other supervised surface inspection tasks, and thus facilitate the development of advanced vision-based inspection instruments for manufacturing applications.

Early experience has a profound influence on brain development, and the modulation of prenatal perceptual learning by external environmental stimuli has been shown in birds, rodents and mammals. In the present study, the effect of prenatal complex rhythmic music sound stimulation on postnatal spatial learning, memory and isolation stress was observed. Auditory stimulation with either music or species-specific sounds or no stimulation (control) was provided to separate sets of fertilized eggs from day 10 of incubation. Following hatching, the chicks at age 24, 72 and 120 h were tested on a T-maze for spatial learning and the memory of the learnt task was assessed 24 h after training. In the posthatch chicks at all ages, the plasma corticosterone levels were estimated following 10 min of isolation. The chicks of all ages in the three groups took less (p < 0.001) time to navigate the maze over the three trials thereby showing an improvement with training. In both sound-stimulated groups, the total time taken to reach the target decreased significantly (p < 0.01) in comparison to the unstimulated control group, indicating the facilitation of spatial learning. However, this decline was more at 24 h than at later posthatch ages. When tested for memory after 24 h of training, only the music-stimulated chicks at posthatch age 24 h took a significantly longer (p < 0.001) time to traverse the maze, suggesting a temporary impairment in their retention of the learnt task. In both sound-stimulated groups at 24 h, the plasma corticosterone levels were significantly decreased (p < 0.001) and increased thereafter at 72 h (p < 0.001) and 120 h which may contribute to the differential response in spatial learning. Thus, prenatal auditory stimulation with either species-specific or complex rhythmic music sounds facilitates spatial learning, though the music stimulation transiently impairs postnatal memory.

This chapter focuses on the use of in vitro techniques, i.e. protoplast-, cell-, tissue- and organ culture, in various steps and for different purposes in mutation breeding of vegetatively propagated crops. The principles and key steps of in vitro mutagenesis and in vitro selection are described and examples are given in the section of case studies, i.e. banana, sugarcane and chrysanthemum.