No abstract

The computed tomography angiography (CTA) postprocessing manually recognized by technologists is extremely labor intensive and error prone. We propose an artificial intelligence reconstruction system supported by an optimized physiological anatomical-based 3D convolutional neural network that can automatically achieve CTA reconstruction in healthcare services. This system is trained and tested with 18,766 head and neck CTA scans from 5 tertiary hospitals in China collected between June 2017 and November 2018. The overall reconstruction accuracy of the independent testing dataset is 0.931. It is clinically applicable due to its consistency with manually processed images, which achieves a qualification rate of 92.1%. This system reduces the time consumed from 14.22 ± 3.64 min to 4.94 ± 0.36 min, the number of clicks from 115.87 ± 25.9 to 4 and the labor force from 3 to 1 technologist after five months application. Thus, the system facilitates clinical workflows and provides an opportunity for clinical technologists to improve humanistic patient care.

No abstract

No abstract

Brain tumor image classification is an important part of medical image processing. It assists doctors to make accurate diagnosis and treatment plans. Magnetic resonance (MR) imaging is one of the main imaging tools to study brain tissue. In this article, we propose a brain tumor MR image classification method using convolutional dictionary learning with local constraint (CDLLC). Our method integrates the multi-layer dictionary learning into a convolutional neural network (CNN) structure to explore the discriminative information. Encoding a vector on a dictionary can be considered as multiple projections into new spaces, and the obtained coding vector is sparse. Meanwhile, in order to preserve the geometric structure of data and utilize the supervised information, we construct the local constraint of atoms through a supervised k-nearest neighbor graph, so that the discrimination of the obtained dictionary is strong. To solve the proposed problem, an efficient iterative optimization scheme is designed. In the experiment, two clinically relevant multi-class classification tasks on the Cheng and REMBRANDT datasets are designed. The evaluation results demonstrate that our method is effective for brain tumor MR image classification, and it could outperform other comparisons.

The digit ratio (2D:4D) is sexually dimorphic and has been considered an indicator of prenatal sex hormone exposure. Previous studies have shown that males tend to have lower 2D to 4D ratio than females, and this sexual dimorphism has been reported across different ethnic groups and different countries. However, digit ratio data are missing from the Han ethnicity in China. Furthermore, most of the previous studies used direct measurement for digit ratio. In this article, we used multiple measurement methods, including the direct measurement and two X-ray measurement methods to examine the trait of 2D:4D in Chinese Han. Our sample consisted of 128 men and 122 women from Liaoning Medical University. They were 18–20 years old. The direct measurement and two types of X-ray measurements of the length of their 2nd and 4th fingers were used separately to calculate digit ratios. Soft tissue thickness of 2D and 4D fingertips were also assessed from the two X-ray methods. The results suggest that (1) sex differences in 2D:4D tend to be stronger in the two X-ray measurements in comparison to the direct measurement; (2) 2D:4D ratios from X-ray measurements tend to be lower than that from the direct measurement; (3) Han ethnicity have a lower mean value of 2D:4D than other ethnic groups; (4) no sex difference in the soft tissue of finger tips. In conclusion, the digit ratio is lower in both men and women in Han, and the sexual dimorphism in digit ratio was stronger with X-ray measurements in comparison to the direct measurement.

No abstract

The variety of accents has posed a big challenge to speech recognition. The Accented English Speech Recognition Challenge (AESRC2020) is designed for providing a common testbed and promoting accent-related research. Two tracks are set in the challenge -English accent recognition (track 1) and accented English speech recognition (track 2). A set of 160 hours of accented English speech collected from 8 countries is released with labels as the training set. Another 20 hours of speech without labels is later released as the test set, including two unseen accents from another two countries used to test the model generalization ability in track 2. We also provide baseline systems for the participants. This paper first reviews the released dataset, track setups, baselines and then summarizes the challenge results and major techniques used in the submissions.