3D hippocampal segmentation based on spatial and frequency domain features adaptive fusion and inter⁃class boundary region enhancement / 解剖学报

Objective Hippocampal atrophy is a clinically important marker for the diagnosis of many psychiatric disorders such as Alzheimer’s disease‚ so accurate segmentation of the hippocampus is an important scientific issue. With the development of deep learning‚ a large number of advanced automatic segmentation method have been proposed. However‚ 3D hippocampal segmentation is still challenging due to the effects of various noises in MRI and unclear boundaries between various classes of the hippocampus. Therefore‚ the aim of this paper is to propose new method to segment the hippocampal head‚ body‚ and tail more accurately. Methods To overcome these challenges‚ this paper proposed two strategies. One was the spatial and frequency domain features adaptive fusion strategy‚ which reduced the influence of noise on feature extraction by automatically selecting the appropriate frequency combination through fast Fourier transform and convolution. The other was an inter-class boundary region enhancement strategy‚ which allowed the network to focus on learning the boundary regions by weighting the loss function of the boundary regions between each class to achieve the goal of pinpointing the boundaries and regulating the size of the hippocampal head‚ body and tail. Results Experiments performed on a 50-case teenager brain MRI dataset show that our method achieves state-of-the-art hippocampal segmentation. Hippocampal head‚ body and tail had been improved compared to the existing method. Ablation experiments demonstrated the effectiveness of our two proposed strategies‚ and we also validated that the network had a strong generalization ability on a 260-case Task04_Hippocampus dataset. It was shown that the method proposed in this paper could be used in more hippocampal segmentation scenarios. Conclusion The method proposed in this paper can help clinicians to observe hippocampal atrophy more clearly and accomplish more accurate diagnosis and follow-up of the condition.

Application of cases-based flipped class in hybrid teaching for neuroanatomy / 解剖学报

Objective To explore the effects of cases-based flipped class in the hybrid teaching for neuroanatomy. Methods A comparative study was conducted among 102 students majored in clinical medicine of 2019 grade, one was the experiment group (n = 51) and another was the control group (n = 51). The traditional teaching method was applied in control group, while the teaching during neuroanatomy based on cases-based flipped class was applied in experimental group. The teaching effects were evaluated by theory and experiment examination and investigated by the questionnaire of students' satisfaction with the new teaching mode. Results Most students supported the cases-based flipped class teaching and thought it was helpful to improve the autonomous learning ability. The satisfaction rate of experimental group on the cases-based flipped class teaching effectiveness was 98.04%. The total scores, the scores of neuroanatomy and the student number who got 81-90 and 91-100 of experiment group were significantly higher than those of control group, and the difference was statistically significant (P<0.05). Conclusion Cases-based flipped class could effectively improve the quality of neuroanatomy teaching and students' learning ability and effects for undergraduates.

A comparative study on improved Arrhenius-type and artificial neural network models to predict high-temperature flow behaviors in 20MnNiMo alloy.

The stress-strain data of 20MnNiMo alloy were collected from a series of hot compressions on Gleeble-1500 thermal-mechanical simulator in the temperature range of 1173 ∼ 1473 K and strain rate range of 0.01 ∼ 10 s(-1). Based on the experimental data, the improved Arrhenius-type constitutive model and the artificial neural network (ANN) model were established to predict the high temperature flow stress of as-cast 20MnNiMo alloy. The accuracy and reliability of the improved Arrhenius-type model and the trained ANN model were further evaluated in terms of the correlation coefficient (R), the average absolute relative error (AARE), and the relative error (η). For the former, R and AARE were found to be 0.9954 and 5.26%, respectively, while, for the latter, 0.9997 and 1.02%, respectively. The relative errors (η) of the improved Arrhenius-type model and the ANN model were, respectively, in the range of -39.99% ∼ 35.05% and -3.77% ∼ 16.74%. As for the former, only 16.3% of the test data set possesses η-values within ± 1%, while, as for the latter, more than 79% possesses. The results indicate that the ANN model presents a higher predictable ability than the improved Arrhenius-type constitutive model.

[Finite element analysis of a new shape memory alloy cervical hook for atlantoaxial instability].

The mechanics of a new shape memory alloy cervical hook for atlantoaxial instability was analyzed with finite element method on the basis of a three-dimensional model reconstructed from the images of CT scanning of an adult cadaveric upper cervical at 1-mm interval. The stress and displacement of every nodule and element in the course of deformation of the internal fixation were tested, and the results showed that the cervical hook was strong enough against tensile stress, which concentrates in the middle of the device. The pull was 237.58 N at the loading point. With such mechanical performance, this cervical hook can be reliable for correction of atlantoaxial instability.

[Study of three-dimensional computerized reconstruction and CT scanning with thin slice after filling hepatic duct system].

OBJECTIVE: To establish the modal of perfusing and casting in hepatic duct system and explore the methods of three dimensional reconstruction with CT scanning image after filling hepatic duct. METHODS: All canal of livers with integral porta hepatic were perfused with various filling material after pretreatment, then fixed and casted. Hepatic preparations that had been perfused were put into the model of modelling abdominal cavity and scanned with thin slice. The three dimensional duct structures of hepatic with three methods of MIP, SSD and computerized treatment. RESULTS: Fourteen hepatic samples were filled and casted. Nine hepatic samples were scanned with slice height 1.0 mm, all 2514 slice images and average 279 images. Five hepatic samples were scanned with slice height 3.0 mm, all 512 slice images and average 102 images. Intrahepatic vein and portal vein system of three dimensional reconstruction were seen clearly with MIP method. The three dimensional established three dimensional images with SSD method was shown much stronger than that of MIP method. The three dimensional images of hepatic solid and hepatic vein system were established with method of comperized treatment. Vary three dimensional shape of hepatic solid and hepatic vein was obtained through different direction rotational. CONCLUSIONS: The modal filled and casted hepatic duct system were practise. The images established three dimensional with methods of MIP, SSD and comperized treatment were seen clearly. The modal and images of thin slice CT scanning are a better method for researching hepatic duct system.