Automatic recognition of surface landmarks of anatomical structures of back and posture

Michoński, Jakub; Glinkowski, Wojciech; Witkowski, Marcin; Sitnik, Robert

doi:10.1117/1.jbo.17.5.056015

Cited by 32 publications

(32 citation statements)

References 60 publications

(58 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Static standing posture was evaluated using markerless, structured light back surface topography measurement system for posture and scoliosis -3D Orthoscreen [18][19][20][21]. The system used in this study consists of three modules: 3D measurement system, centralized database, and data analysis software on the client side.…”

Section: Methodsmentioning

confidence: 99%

Posture and low back pain during pregnancy — 3D study

Glinkowski

Tomasik²,

Walesiak³

et al. 2016

Ginekol Pol

Self Cite

View full text Add to dashboard Cite

Objectives: Back pain is a common complaint of pregnant women. The posture, curvatures of the spine and the center of gravity changes are considered as the mechanisms leading to pain. The study aimed to assess spinal curvatures and static postural characteristics with three-dimensional surface topography and search for relationships with the occurrence of back pain complaints among pregnant women. Material and methods:The study was conducted from December 2012 to February 2014. Patients referred from University Clinic of Gynecology and Obstetrics were examined outpatient at the Posture Study Unit of Department of Orthopaedics and Traumatology. Sixty-five women at 4-39 weeks of pregnancy were assessed and surveyed with Oswestry Disability Index; posture was evaluated using surface topography. Results:The study confirmed that difficulties in sitting and standing are significant in the third trimester of the pregnancy. The overall tendency for significant lumbar curvature changes in pregnant women was not confirmed. Major changes in sagittal trunk inclination in relation to the plumb line were not observed in the study group. Conclusions:The issue regarding how the pregnancy causes changes in spinal curvature and posture remains open for further studies. Presented method of 3D surface topography can reveal postural changes, but that requires several exams of each subject and strict follow-up of the series of cases.

show abstract

Section: Methodsmentioning

confidence: 99%

Posture and low back pain during pregnancy — 3D study

Glinkowski

Tomasik²,

Walesiak³

et al. 2016

Ginekol Pol

Self Cite

View full text Add to dashboard Cite

show abstract

“…There are many fields which benefit from using precise measurements based on 3D scans. In medicine, examples of usage can be found in spine deformation detection [1,2], CT/MRI image analysis [3] or maxillo-facial diagnosis [4]. Other applications relate to, e.g., the skeleton rig processing for animation [5], motion capture [6], and human system engineering in the clothing industry [7,8].…”

Section: Introductionmentioning

confidence: 99%

“…Both traditional tape measurements and the manual point selection on a scan are time-consuming tasks. They also require human involvement which is naturally exposed to the subjectivity of researcher and human-related errors [2,11]. The semi-automatic methods are widely used among researchers [12,13].…”

Section: Introductionmentioning

confidence: 99%

Algorithm for Detecting Characteristic Points on a Three-Dimensional, Whole-Body Human Scan

2020

Self Cite

View full text Add to dashboard Cite

Anthropometric landmarks obtained from three-dimensional (3D) body scans are widely used in medicine, civil engineering, and virtual reality. For all those fields, an acquisition of certain and accurate landmark positions is crucial for obtaining satisfying results. Manual marking is time-consuming and is affected by the subjectivity of the human operator. Therefore, an automatic approach has become increasingly popular. This paper provides a short survey of different attempts for automatic landmark localization, from which one machine learning-based method was further analyzed and extended in the case of input data preparation for a convolutional neural network (CNN). A novel method of data processing is presented which utilize a mid-surface projection followed by further unwrapping. The article emphasizes its significance and the way it affects the outcome of a deep neural network. The workflow and the detailed description of algorithms used are included in this paper. To validate the method, it was compared with the orthogonal projection used for the state-of-the-art approach. Datasets consisting of 200 specimens, acquired using both methods, were used for convolutional neural networks training and 20 for validation. In this paper, we used YOLO v.3 architecture for detection and ResNet-152 for classification. For each approach, localizations of 22 normalized body landmarks for 10 male and 10 female subjects of different ages and various postures were obtained. To compare the accuracy of approaches, errors and their distribution were measured for each characteristic point. Experiments confirmed that the mid-surface projections resulted, on average, in a 14% accuracy improvement and up to 15% enhancement of resistance on errors related to scan imperfections.

show abstract

“…2-dimensional X ray remains the primary imaging modality[1]. However, recent progress in 3D-optical imaging may improve diagnostics and increase its safety for scoliosis patients[2]. …”

Section: Introductionmentioning

confidence: 99%