Real-time testing of coal ash plays a vital role in the chemical, power generation, metallurgical, and coal separation sectors. The rapid online testing of coal ash using radiation measurement as the mainstream technology has problems such as strict coal sample requirements, poor radiation safety, low accuracy, and complicated equipment replacement. In this study, an intelligent detection technique based on feed-forward neural networks and improved particle swarm optimization (IPSO-FNN) is proposed to predict coal quality ash content in a fast, accurate, safe，and convenient manner. The data set was obtained by testing the elemental content of 198 coal samples with X-ray fluorescence (XRF). The types of input elements for machine learning (Si, Al, Fe, K, Ca, Mg, Ti, Zn, Na, P) were determined by combining the X-ray photoelectron spectroscopy (XPS) data with the change in the physical phase of each element in the coal samples during combustion. The mean squared error and coefficient of determination were chosen as the performance measures for the model. The results show that the IPSO algorithm is useful in adjusting the optimal number of nodes in the hidden layer. The IPSO-FNN model has strong prediction ability and good accuracy in coal ash prediction. The effect of the input element content of the IPSO-FNN model on the ash content was investigated, and it was found that the potassium content was the most significant factor affecting the ash content. This study is essential for real-time online, accurate, and fast prediction of coal ash.

To solve the problems of missing and false detection of pulmonary nodules in complex lung environments, as well as trivial and inefficient detection procedures, an end-to-end pulmonary nodules detection and recognition model based on deep learning was proposed. Innovation and improvement are made on the basis of YOLOv5. In the feature extraction stage of the model, a convolutional structure integrating self-attention mechanism is proposed to capture the global feature and the dependence relationship of long-distance information, and screen the key pathological information. Then, a convolution structure integrating internal convolution operators is proposed to reduce the computational redundancy in the feature channel and improve the inference speed of the model. In the feature fusion stage of the model, the structure of cross-scale coordinate attention feature fusion is proposed, and the different features enhanced with attention are weighted by jumping links to promote the fusion of multi-scale feature information. The proposed model obtained 97.8% mAP@0.5 indexes in the self-built diagnosis and treatment data set of pulmonary nodules in Huaihai area. The pulmonary nodule detection model proposed in this paper can significantly reduce the false positive rate and obtain the location and classification results of diseased nodules with higher detection accuracy and faster detection speed, which has important practical value in clinical application.

Chromosomal numerical and structural abnormalities are common in newborn defects. Karyotype analysis, which can detect abnormalities based on chromosome microscope images, has emerged as one of the gold standards for the diagnosis of such diseases. Individual chromosomes are segmented, numbered and identified throughout this procedure. Thus, precise chromosomal segmentation, as the key of karyotyping, affects the success of subsequent missions. Most segmentation methods cannot identify a chromosome in case of overlapping since there is little distinction between inter and intra chromosomal classes. The loss and redundancy of the segmentation mask may be to blame for that. An end-to-end framework named Edge Supervised Network (ESNet) based on Mask RCNN is proposed in this paper. To incorporate edge prior knowledge, an edge supervised branch and feature fusion module are designed to help recognize individual chromosomes from clusters, and a spatial attention module to capture more contextual information for better edge identification. Balance loss weight is also proposed for edge loss in the training phase. Experimental results reveal that ESNet achieves better segmentation performance in comparison with other competing methods, which can be a potential baseline network for end-to-end chromosome instance segmentation. Code is available at https://github.com/labiip/ESNet.

Scanning electron microscopy (SEM) plays an important role in the intuitive understanding of microstructures because it can provide ultrahigh magnification. Tens or hundreds of images are regularly generated and saved during a typical microscopy imaging process. Given the subjectivity of a microscopist’s focusing operation, blurriness is an important distortion that debases the quality of micrographs. The selection of high-quality micrographs using subjective methods is expensive and time-consuming. This study proposes a new no-reference quality assessment method for evaluating the blurriness of SEM micrographs. The human visual system is more sensitive to the distortions of cartoon components than to those of redundant textured components according to the Gestalt perception psychology and the entropy masking property. Micrographs are initially decomposed into cartoon and textured components. Then, the spectral and spatial sharpness maps of the cartoon components are extracted. One metric is calculated by combining the spatial and spectral sharpness maps of the cartoon components. The other metric is calculated on the basis of the edge of the maximum local variation map of the cartoon components. Finally, the two metrics are combined as the final metric. The objective scores generated using this method exhibit high correlation and consistency with the subjective scores.

The widespread use of scanning electron microscopy (SEM) has increased the requirements for SEM image quality. SEM images obtained by electron beam feedback have more complex texture features than natural images obtained by optical imaging, and this condition results in poor performance of algorithms used for assessing natural image quality on SEM datasets,meanwhile,the field of SEM image quality assessment(IQA) is mostly aimed at specific distortion types. In order to solve the above two problems,to address the rich texture, few edges, and extreme sensitivity to the distortion degree of SEM images, we propose a texture and semantic IQA (TSIQA) method for SEM images based on sparse mask and information entropy increase. First, we construct a neural network containing sparse mask module (SMM), which is used to extract intuitive texture features in the spatial and channel domains. Simultaneously, information growth attention (IGA) is introduced into SMM to detect the difference between current and past features of the network for extracting deep semantic information. The quality assessment experiments on SEM image datasets show that compared with the state-of-the-art IQA methods, including popular no-reference techniques adapted to the SEM-IQA, the TSIQA has superiority in typical criteria.