Validation of an automatic segmentation method to detect vertebral interfaces in ultrasound images

Abstract

Aim of this study was to perform a detailed clinical validation of a new fully automatic algorithm for vertebral interface segmentation in echographic images. Abdominal echographic scans of lumbar vertebrae L1-L4 were carried out on 150 female subjects with variable age and body mass index (BMI). Acquired datasets were automatically processed by the algorithm and the accuracy of the obtained segmentations was then evaluated by three independent experienced operators. Obtained results showed a very good specificity in vertebra detection (93.3%), coupled with a reasonable sensitivity (68.1%), representing a suitable compromise between the detection of a sufficient number of vertebrae for reliable diagnoses and the limitation of the corresponding computation time. Importantly, there was only a minimum presence of 'false vertebrae' detected (2.8%), resulting in a very low influence on subsequent diagnostic analyses. Furthermore, the algorithm was specifically tuned to provide an improved sensitivity (up to 73.1%) with increasing patient BMI, to keep a suitable number of correctly detected vertebrae even when the acquisition was intrinsically more difficult because of the augmented thickness of abdominal soft tissues. The proposed algorithm will represent an essential added value for developing echographic methods for the diagnosis of osteoporosis on lumbar vertebrae.

A novel quantitative method for estimating bone mineral density using B‑mode ultrasound and radiofrequency signals‑a pilot study on patients with rheumatoid arthritis

“…The system is equipped with a convex 3.5 MHz transducer, which simultaneously detects B-mode ultrasound signals and unprocessed radiofrequency signals. Those which are analyzed by the machine's statistical algorithm (EchoStudio ® ; Echolight SRL) for each region of interest (ROI), taking into account the patient's ethnicity, age, sex and BMI and comparing them to a database of ~10,000 subjects (18,20,24–26). The ROI for each patient included the usual sites for the diagnosis of osteoporosis: The lumbar spine (L1-L4 vertebrae approached from the abdomen) and the femoral necks.…”

“…However, QUS may have particular advantages over DXA, which make it suitable for a potentially wider use in the primary screening or pre-screening of osteoporosis and the identification of cases requiring DXA scanning (18,19): It is less expensive, does not use ionising radiation, uses smaller hardware and is portable. A recently introduced QUS method that integrates ultrasound imaging and radiofrequency signals is being used for the diagnosis of osteoporosis and it produced results comparable to those obtained with the DXA method (20,21). To the best of our knowledge, this technique has never been used in a controlled study environment to assess BMD in Romanian RA patients and healthy controls.…”

O Envelhecer Nas Ruas: Agravos Na Saúde Física E Mental E Repercussões No Trabalho

“…Assim, o desafio para novos estudos está em identificar estratégias seguras e eficazes de intervenções que possam simultaneamente aperfeiçoar a saúde muscular, óssea e tratar a fragilidade física de idosos, para redução de quedas e fraturas. (AVENTAGGIATO, et al, 2016).…”

Assessment of Fracture Risk through Radiofrequency Echographic Multi Spectrometry (REMS) based Bone Mineral Density

“…A previous published study showed a high degree of correlation between the T-score values provided by the two techniques -REMS and DXA for both lumbar spine (r = 0.94, p < 0.001) and femoral neck (r = 0.93, p < 0.001), [12]. Furthermore, REMS technology may have some advantages over DXA method -it is non-ionizing approach and it is portable, so this make it possible to do wider screening of osteoporosis and to detect earlier the cases requiring DXA scanning [15][16][17][18][19].…”