Super-resolution method for SEM images based on pixelwise weighted loss function.

Scanning electron microscopy (SEM) has realized high-throughput defect monitoring of semiconductor devices. As miniaturization and complexification of semiconductor circuit patterns increase in recent years, so has the number of defects. There is thus a great need to further increase the throughput of SEM defect monitoring. Toward this end, we propose a deep learning-based super-resolution method that reproduces high-resolution (HR) images from corresponding low-resolution images. Image quality factors such as pattern contrast and sharpness are important in SEM HR images in order to evaluate the quality of printed circuit patterns. Our proposed method meets various image quality requirements by changing the loss calculation method pixelwise based on the pattern in the image. It realizes super-resolved images that compare favorably with actual HR images and can improve SEM throughput by 100% or more.

Machine-learning-based quality-level-estimation system for inspecting steel microstructures.

Quality control of special steel is accomplished through visual inspection of its microstructure based on microscopic images. This study proposes an 'automatic-quality-level-estimation system' based on machine learning. Visual inspection of this type is sensory-based, so training data may include variations in judgments and training errors due to individual differences between inspectors, which makes it easy for a drop in generalization performance to occur due to overfitting. To deal with this issue, we here propose the preprocessing of inspection images and a data augmentation technique. Preprocessing reduces variation in images by extracting features that are highly related to the level of quality from inspection images. Data augmentation, meanwhile, suppresses the problem of overfitting when training with a small number of images by taking into account information on variation in judgment values obtained from on-site experience. While the correct-answer rate for judging the quality level by an inspector was about 90%, the proposed method achieved a correct-answer rate of 92.5%, which indicates that the method shows promise for practical applications.

Role of the Nh (Non-hair) mutation in the development of dermatitis and hyperproduction of IgE in DS-Nh mice.

The DS-Nh (DS Non-hair) mouse is a spontaneous hairless mutant of the DS mouse. The inheritance mode of the Nh mutation is autosomal dominant, and the Nh locus is mapped to Chromosome 11. The roles of the Nh mutation in spontaneous dermatitis and IgE hyperproduction were studied using an Nh congenic strain with a genetic background from the BALB/c mouse. In contrast to DS-Nh (Nh/+) mice, BALB/c-Nh (Nh/+) mice under conventional conditions showed a marked increase in serum IgE, without the development of dermatitis. These results suggest that IgE hyperproduction is regulated by the Nh mutation, while other genetic factor(s) are also involved in the development of dermatitis.

Spontaneous development of dermatitis in DS-Nh mice under specific pathogen-free conditions.

Spontaneous development of dermatitis in DS-Nh mice under specific pathogen-free conditions was examined to verify the hypothesis [Exp. Anim. 46: 225-229, 1997] that Stapylococcus aureus (S. aureus) infection is causally associated with the dermatitis. Observation of the mice up to 28 weeks of age indicated that obvious dermatitis does occur under S. aureus-free conditions, though the incidence was low (six of 42 females and two of 90 males). Skin lesions in the absence of this bacterium showed histological changes very similar to those that can be observed under conventional conditions. In addition, hyperproduction of serum IgE was demonstrated in the dermatitis-positive mouse. These findings suggested that the dermatitis is triggered by IgE-mediated allergic reactions.