Spinal Vertebral Fracture Detection and Fracture Level Assessment Based on Deep Learning

This paper addresses the common orthopedic trauma of spinal vertebral fractures and aims to enhance doctors’diagnostic efficiency.Therefore,a deep-learning-based automated diagnostic systemwithmulti-label segmentation is proposed to recognize the condition of vertebral fractures.The whole spine Computed Tomography(CT)image is segmented into the fracture,normal,and background using U-Net,and the fracture degree of each vertebra is evaluated(Genant semi-qualitative evaluation).The main work of this paper includes:First,based on the spatial configuration network(SCN)structure,U-Net is used instead of the SCN feature extraction network.The attention mechanismandthe residual connectionbetweenthe convolutional layers are added in the local network(LN)stage.Multiple filtering is added in the global network(GN)stage,and each layer of the LN decoder feature map is filtered separately using dot product,and the filtered features are re-convolved to obtain the GN output heatmap.Second,a network model with improved SCN(M-SCN)helps automatically localize the center-of-mass position of each vertebra,and the voxels around each localized vertebra were clipped,eliminating a large amount of redundant information(e.g.,background and other interfering vertebrae)and keeping the vertebrae to be segmented in the center of the image.Multilabel segmentation of the clipped portion was subsequently performed using U-Net.This paper uses VerSe’19,VerSe’20(using only data containing vertebral fractures),and private data(provided by Guizhou Orthopedic Hospital)for model training and evaluation.Compared with the original SCN network,the M-SCN reduced the prediction error rate by 1.09%and demonstrated the effectiveness of the improvement in ablation experiments.In the vertebral segmentation experiment,the Dice Similarity Coefficient(DSC)index reached 93.50%and the Maximum Symmetry Surface Distance(MSSD)index was 4.962 mm,with accuracy and recall of 95.82%and 91.73%,respectively.Fractured vertebrae were also marked as red and normal vertebrae were marked as white in the experiment,and the semi-qualitative assessment results of Genant were provided,as well as the results of spinal localization visualization and 3D reconstructed views of the spine to analyze the actual predictive ability of the model.It provides a promising tool for vertebral fracture detection.

An attention-based cascade R-CNN model for sternum fracture detection in X-ray images

Fracture is one of the most common and unexpected traumas.If not treated in time,it may cause serious consequences such as joint stiffness,traumatic arthritis,and nerve injury.Using computer vision technology to detect fractures can reduce the workload and misdiagnosis of fractures and also improve the fracture detection speed.However,there are still some problems in sternum fracture detection,such as the low detection rate of small and occult fractures.In this work,the authors have constructed a dataset with 1227 labelled X-ray images for sternum fracture detection.The authors designed a fully automatic fracture detection model based on a deep convolution neural network(CNN).The authors used cascade R-CNN,attention mechanism,and atrous convolution to optimise the detection of small fractures in a large X-ray image with big local variations.The authors compared the detection results of YOLOv5 model,cascade R-CNN and other state-of-the-art models.The authors found that the convolution neural network based on cascade and attention mechanism models has a better detection effect and arrives at an mAP of 0.71,which is much better than using the YOLOv5 model(mAP=0.44)and cascade R-CNN(mAP=0.55).

Seismic prediction method of multiscale fractured reservoir

Common prestack fracture prediction methods cannot clearly distinguish multiplescale fractures. In this study, we propose a prediction method for macro- and mesoscale fractures based on fracture density distribution in reservoirs. First, we detect the macroscale fractures （larger than 1/4 wavelength） using the multidirectional coherence technique that is based on the curvelet transform and the mesoscale fractures （1/4-1/100 wavelength） using the seismic azimuthal anisotropy technique and prestack attenuation attributes, e.g., frequency attenuation gradient. Then, we combine the obtained fracture density distributions into a map and evaluate the variably scaled fractures. Application of the method to a seismic physical model of a fractured reservoir shows that the method overcomes the problem of discontinuous fracture density distribution generated by the prestack seismic azimuthal anisotropy method, distinguishes the fracture scales, and identifies the fractured zones accurately.

P-wave fracture prediction algorithm using pre-stack data with limited azimuth distribution:A case study in the TZ45 area,Tarim Basin,China

Fractured reservoirs always show anisotropic amplitude features,i.e.the reflection amplitude of seismic waves varies with offset and azimuth （AVOZ）.A noise attenuation fracture inversion algorithm is presented for fracture detection based on P-wave AVOZ.The conventional inversion method always fails when applied to limited azimuth data because of the existence of noise.In our inversion algorithm,special attention is paid to suppressing the noise during inversion,to overcome the limitation of the conventional inversion method on limited azimuth data.Numerical models are employed to illustrate the effectiveness of the method.The inversion algorithm is then applied to Tazhong 45 area field data which is acquired under limited azimuth distribution.Compared with cores and fullbore formation microimage （FMI）,the inverted results （fracture density and orientation） are reasonable,suggesting that the inversion algorithm is feasible for fracture prediction in the Tarim Basin.

Design of comprehensive test system for detecting overlying strata mining-induced fractures on surface with radon gas

Based on radon gas properties and its existing projects applications, we firstly attempted to apply geo- physical and chemical properties of radon gas in the field of mining engineering, and imported radioac- tive measurement method to detect the development process of the overlying strata mining-induced fractures and their contained water quality in underground coal mining, which not only innovates a more simple-fast-reliable detection method, but also further expands the applications of radon gas detection technology in mining field. A 3D simulation design of comprehensive testing system for detecting strata mining-induced fractures on surface with radon gas (CTSR) was carried out by using a large-scale 3D solid model design software Pro/Engineer (Pro/E), which overcame three main disadvantages of ''static design thought, 2D planar design and heavy workload for remodification design'' on exiting design for mining engineering test systems. Meanwhile, based on the simulation design results of Pro/E software, the sta- bility of the jack-screw pressure bar for the key component in CTSR was checked with a material mechan- ics theory, which provided a reliable basis for materials selection during the latter machining process.

Fracture detecting based on Ant Colony Algorithm

Image processing plays an important role in engineering treatment. The authors mainly introduced the feature recognition of borehole image process based on Ant Colony Algorithm (ACA). The most important geological structure-fracture on the borehole image was identified, and quantitative parameters were obtained by HOUGH transform. Several case studies show that the method is feasible.

Several boundary identification methods of gravity data and application in Vientiane of Laos area

The authors studied the potential field boundary identification of the new technology in order to find out the possible fractures or contact zones using the following methods such as tilt derivative,horizontal derivative of tilt derivative,normalized standard deviation and normalized differential method. Combined with Euler deconvolution and small subdomain filtering,the actual data processing results show that these methods are all able to identify wider range extending fractures and obtain abundant geological information. The horizontal derivative of tilt derivative and normalized differential method have a better resolution for the small cutting fractures and lacunae in the studied area. They provide a reliable basis for study of the cutting relationship between fractures.