Intervertebral disc detection in X-ray images using faster R-CNN.

Automatic identification of specific osseous landmarks on the spinal radiograph can be used to automate calculations for correcting ligament instability and injury, which affect 75% of patients injured in motor vehicle accidents. In this work, we propose to use deep learning based object detection method as the first step towards identifying landmark points in lateral lumbar X-ray images. The significant breakthrough of deep learning technology has made it a prevailing choice for perception based applications, however, the lack of large annotated training dataset has brought challenges to utilizing the technology in medical image processing field. In this work, we propose to fine tune a deep network, Faster-RCNN, a state-of-the-art deep detection network in natural image domain, using small annotated clinical datasets. In the experiment we show that, by using only 81 lateral lumbar X-Ray training images, one can achieve much better performance compared to traditional sliding window detection method on hand crafted features. Furthermore, we fine-tuned the network using 974 training images and tested on 108 images, which achieved average precision of 0.905 with average computation time of 3 second per image, which greatly outperformed traditional methods in terms of accuracy and efficiency.

Fast scale-invariant lateral lumbar vertebrae detection and segmentation in X-ray images.

Fully automatic localization of lumbar vertebrae from clinical X-ray images is very challenging due to the variation of X-ray quality, scale, contrast, number of visible vertebrae, etc. To overcome these challenges, we present a novel framework, where we accelerate a scale-invariant object detection method using Support Vector Machines (SVM) trained on Histogram of Oriented Gradients (HOG) features and segmenting a fine vertebra contour using Gradient Vector Flow (GVF) based snake model. Support Vector Machines trained on HOG features are now an object detection standard in many perception fields and have demonstrated good performance on medical images as well. However, the computational complexity and lack of robustness brought by rescaling the original images have prevented its applicability. The proposed multistage detection framework uses lower-level detection result to determine the rescaling regions to reduce the region of interest, thereby decreasing the execution time. We further refine the detection result by segmenting the contour of vertebra using GVF snake, where we use edge detection techniques to increase the robustness of the GVF snake. Finally, we experimentally demonstrate the effectiveness of this framework using a large set of clinical X-ray images.

Cervical spine geometry correlated to cervical degenerative disease in a symptomatic group.

OBJECTIVE: To investigate whether a statistical correlation exists between lateral cervical geometry and cervical pathology, as identified on neutral anteroposterior (AP) and lateral radiographs within a symptomatic group; describe the cervical pathology and determine its location and frequency; and identify the subject's age, sex, and chief complaint. SETTING: Department of radiology at a chiropractic college. METHODS: One hundred eighty-six consecutive pairs of AP and lateral cervical radiographs were reviewed for pathology. A 5-category severity scale was used to describe degenerative joint disease, the most common pathological finding. The subject's age, sex, and symptoms were recorded. Geometric analysis was focused on vertebral position, alignment, and gravitational loading acquired from the neutral lateral cervical radiograph. RESULTS: Regression and discriminant analysis identified 5 geometric variables that correctly classified pathology subjects from nonpathology subjects 79% of the time. Those variables were: (1) forward flexion angle of the lower cervical curve; (2) gravitational loading on the C5 superior vertebral end plate; (3) horizontal angle of C2 measured from its inferior vertebral end plate; (4) disk angle of C3; and (5) posterior disk height of C5. Degenerative joint disease was the most common pathological finding identified within discrete age, sex, and symptom groups. CONCLUSION: We identified 5 geometric variables from the lateral cervical spine that were predictive 79% of the time for cervical degenerative joint disease. There were discrete age, sex, and symptom groups, which demonstrated an increased incidence of degenerative joint disease.