Automatic identification of lumbar level with ultrasound

Kerby, Benjamin; Rohling, Robert; Nair, Vishnu S.; Abolmaesumi, Purang

doi:10.1109/iembs.2008.4649829

Cited by 29 publications

(19 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method detects the lamina and ligamentum flavium with a success rate of 87%. Kerby et al (2008) proposed a method for the automatic identification of lumbar levels in panoramic ultrasound images. This method extracts a wave-like profile from the image with a median filter and two linear filters operating in the horizontal and vertical directions.…”

Section: Introductionmentioning

confidence: 99%

Segmentation of the spinous process and its acoustic shadow in vertebral ultrasound images

Berton

Cheriet

Marie-Claude

et al. 2016

Computers in Biology and Medicine

View full text Add to dashboard Cite

Spinal ultrasound imaging is emerging as a low-cost, radiation-free alternative to conventional X-ray imaging for the clinical follow-up of patients with scoliosis. Currently, deformity measurement relies almost entirely on manual identification of key vertebral landmarks. However, the interpretation of vertebral ultrasound images is challenging, primarily because acoustic waves are entirely reflected by bone. To alleviate this problem, we propose an algorithm to segment these images into three regions: the spinous process, its acoustic shadow and other tissues. This method consists, first, in the extraction of several image features and the selection of the most relevant ones for the discrimination of the three regions. Then, using this set of features and a LDA classifier, each pixel of the image is classified as belonging to one of the three * Corresponding author Email addresses: florian.berton@polymtl.ca (Florian Berton), farida.cheriet@polymtl.ca (Farida Cheriet), marie-claude_miron@ssss.gouv.qc.ca regions. Finally, the image is segmented by regularizing the pixel-wise classification results to account for some geometrical properties of vertebrae. The feature set was first validated by analyzing the classification results across a learning database. The database contained 107 vertebral ultrasound images acquired with convex and linear probes. Classification rates of 84%, 92% and 91% were achieved for the spinous process, the acoustic shadow and other tissues, respectively. Dice similarity coefficients of 0.72 and 0.88 were obtained respectively for the spinous process and acoustic shadow, confirming that the proposed method accurately segments the spinous process and its acoustic shadow in vertebral ultrasound images. Furthermore, the centroid of the automatically segmented spinous process was located at an average distance of 0.38 mm from that of the manually labeled spinous process, which is on the order of image resolution. This suggests that the proposed method is a promising tool for the measurement of the Spinous Process Angle and, more generally, for assisting ultrasound-based assessment of scoliosis progression.

show abstract

Section: Introductionmentioning

confidence: 99%

Segmentation of the spinous process and its acoustic shadow in vertebral ultrasound images

Berton

Cheriet

Marie-Claude

et al. 2016

Computers in Biology and Medicine

View full text Add to dashboard Cite

show abstract

“…Among various software systems reported, some aid in correct identification of intervertebral levels,[4142] while others automatically identify structures such as vertebral body, lamina, articular process, and EDS. [4344] Unlike ultrasonography for vascular access or nerve blocks, vertebral anatomy is more complex, making pattern recognition difficult.…”

Section: Discussionmentioning

confidence: 99%

“…Nevertheless, various investigators were able to identify structures automatically using parasagittal and transverse interspinous views at the lumbar level. [41424344] However, thoracic scans are more challenging and have not been evaluated. The ability of these systems to identify structures in the presence of uncommon or distorted anatomy is unknown.…”

Section: Discussionmentioning

confidence: 99%

Localization of epidural space: A review of available technologies

Elsharkawy

Sonny

Chin

2017

J Anaesthesiol Clin Pharmacol

View full text Add to dashboard Cite

Although epidural analgesia is widely used for pain relief, it is associated with a significant failure rate. Loss of resistance technique, tactile feedback from the needle, and surface landmarks are traditionally used to guide the epidural needle tip into the epidural space (EDS). The aim of this narrative review is to critically appraise new and emerging technologies for identification of EDS and their potential role in the future. The PubMed, Cochrane Central Register of Controlled Clinical Studies, and Web of Science databases were searched using predecided search strategies, yielding 1048 results. After careful review of abstracts and full texts, 42 articles were selected to be included. Newer techniques for localization of EDS can be broadly classified into techniques that (1) guide the needle to the EDS, (2) identify needle entry into the EDS, and (3) confirm catheter location in EDS. An ideal method should be easy to learn and perform, easily reproducible with high sensitivity and specificity, identifies inadvertent intrathecal and intravascular catheter placements with ease, feasible in perioperative setting and have a cost-benefit advantage. Though none of them in their current stages of development qualify as an ideal method, many show tremendous potential. Some techniques are useful in patients with difficult spinal anatomy and infants, and thus are complementary to traditional methods. In addition to improving the existing technology, future research should aim at proving the superiority of these techniques over traditional methods, specifically regarding successful EDS localization, better safety profile, and a favorable cost-benefit ratio.

show abstract

“…Methods enhancing US volumes with anatomical information, such as fitting a statistical shape model [14], automatic detection of vertebral levels [13], and automatic identification of needle insertion sites [35], have not been found applicable to guidance systems due to their computational complexity. A mechanical approach to the problem in which a needle guide (called EpiGuide) allows live imaging with a standard 3D US transducer of the needle path to the epidural target has recently been introduced [18]; however, image interpretation still remains an issue.…”

Section: Introductionmentioning

confidence: 99%