Automatic spinal canal detection in lumbar MR images in the sagittal view using dynamic programming

Localization and Edge-Based Segmentation of Lumbar Spine Vertebrae to Identify the Deformities Using Deep Learning Models

The lumbar spine plays a very important role in our load transfer and mobility. Vertebrae localization and segmentation are useful in detecting spinal deformities and fractures. Understanding of automated medical imagery is of main importance to help doctors in handling the time-consuming manual or semi-manual diagnosis. Our paper presents the methods that will help clinicians to grade the severity of the disease with confidence, as the current manual diagnosis by different doctors has dissimilarity and variations in the analysis of diseases. In this paper we discuss the lumbar spine localization and segmentation which help for the analysis of lumbar spine deformities. The lumber spine is localized using YOLOv5 which is the fifth variant of the YOLO family. It is the fastest and the lightest object detector. Mean average precision (mAP) of 0.975 is achieved by YOLOv5. To diagnose the lumbar lordosis, we correlated the angles with region area that is computed from the YOLOv5 centroids and obtained 74.5% accuracy. Cropped images from YOLOv5 bounding boxes are passed through HED U-Net, which is a combination of segmentation and edge detection frameworks, to obtain the segmented vertebrae and its edges. Lumbar lordortic angles (LLAs) and lumbosacral angles (LSAs) are found after detecting the corners of vertebrae using a Harris corner detector with very small mean errors of 0.29° and 0.38°, respectively. This paper compares the different object detectors used to localize the vertebrae, the results of two methods used to diagnose the lumbar deformity, and the results with other researchers.

DOES DECUBITUS AFFECT NEURAL ELEMENTS POSITIONING? A MRI STUDY COMPARING DORSAL AND LATERAL POSITION

ABSTRACT Objective To evaluate the displacement of nerve structures according to the decubitus position of the patient in a magnetic resonance imaging (MRI) study. Methods MRI was performed at a radiology clinic in 20 patients in dorsal and right lateral decubitus. The measurement considered was the shortest distance between the dura mater and the medial wall of the pedicle. Results The largest measurement was 11.6 mm in left lateral decubitus, 12.2 mm in right lateral decubitus, 10.5 mm in right dorsal decubitus, and 9.2 mm in left dorsal decubitus. In some patients the space between the medial wall of the pedicle and the dura mater was larger when in lateral decubitus, while in others when in dorsal decubitus. The mean displacement of the measurements on the left was 1.14 mm and on the right 1.355 mm. Conclusions The structures moved on average little more than 1 mm in the positions studied. The positioning of the patient for surgery does not change the space to be approached, being the surgeon’s choice according to his learning curve. Level of evidence II; Prospective study of lower quality.

Dynamic Programming Based Segmentation in Biomedical Imaging

Many applications in biomedical imaging have a demand on automatic detection of lines, contours, or boundaries of bones, organs, vessels, and cells. Aim is to support expert decisions in interactive applications or to include it as part of a processing pipeline for automatic image analysis. Biomedical images often suffer from noisy data and fuzzy edges. Therefore, there is a need for robust methods for contour and line detection. Dynamic programming is a popular technique that satisfies these requirements in many ways. This work gives a brief overview over approaches and applications that utilize dynamic programming to solve problems in the challenging field of biomedical imaging.

Population reference range for developmental lumbar spinal canal size

BACKGROUND

Considerable variability exists in normal developmental lumbar spinal canal size. This impacts the likelihood of neural compromise. Spinal canal development is complete by 17 years. As diseases incurred thereafter do not knowingly affect the developmental size of the spinal canal, it is reasonable to use a selected population undergoing abdominopelvic computed tomography (CT) examination to determine developmental lumbar spinal canal size.

METHODS

Study approval was granted by the Clinical Research Ethics Committee. Between Feb 2014 and Jan 2015, mid-vertebral spinal canal cross-sectional area (CSA), depth, width, and vertebral body CSA at each level from L1-L5 was measured, using a semi-automated computerized method in 1,080 ambulatory patients (540 males, 540 females, mean age, 50.5±17 years). Patient height and weight was measured.

RESULTS

A reference range for developmental lumbar spinal canal dimensions was developed at each lumbar level for each sex. There was a 34% variation in spinal canal CSA between smallest and largest quartiles. Developmental spinal canal CSA and depth were consistently smallest at L3, enlarging cranially and caudally. Taller people had slightly larger lumbar spinal canals (P<0.0001). Males had larger spinal canal CSAs than females though relative to vertebral body CSA, spinal canal CSA was larger in females. There was no change in spinal canal CSA with age, weight or BMI (P<0.05).

CONCLUSIONS

A population reference range for developmental lumbar spinal canal size was developed. This allows one to objectively determine the degree of developmental spinal canal stenosis present on an individual patient basis.