Frugal 3D scanning using smartphones provides an accessible framework for capturing the external ear

Nightingale, Renee C.; Ross, Maureen T.; Cruz, Rena L. J.; Allenby, Mark C.; Powell, Sean K.; Woodruff, Maria A.

doi:10.1016/j.bjps.2021.03.131

Cited by 14 publications

(12 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using an Artec Spider structured light scanner as a clinical "gold standard" reference, [10] found that photogrammetric reconstructions of facial scans using 80 images captured had RMSE accuracy values of 1.3 mm ± 0.3 mm. In a similar study, [11] achieved RMSE accuracy values of 1.5 mm ± 0.4 mm with 30 photographs on reconstructions of the external ear. Using spherical objects with known geometry as a reference, [4] was able to achieve an MAE accuracy of 0.3 mm ± 0.2 mm using 95 images with tie point aids.…”

Section: A Photogrammetry For Medical Imagingmentioning

confidence: 71%

“…The development of digital cameras and the accompanying transition to digital photogrammetry has led to technologies for the reconstruction of 3D models using photogrammetric algorithms [18]. Digital photogrammetry has been used successfully to reconstruct patient anatomy in many medical contexts such as cranial deformation scanning [8], [9], [19], facial scanning [10], [11], [20], and amputated limb scanning [3], [5]- [7].…”

Section: A Photogrammetry For Medical Imagingmentioning

confidence: 99%

“…2. Agisoft is the most commonly used photogrammetric software in medical imaging being used by [3], [4], [10], [11], [19]. This step of the workflow was automated with no manual tie point alignment or point cloud segmentation.…”

Section: Rendering Proceduresmentioning

confidence: 99%

“…The main advantage of photogrammetric scanning is that models can be rendered using photographs captured via smartphones [3]- [9]. Scanning with smartphones is significantly cheaper than other medical imaging modalities [1], [2] and results in reliable and robust surface accuracy on par with existing clinical gold standard technologies [10], [11]. Unfortunately, photogrammetry workflows often require extensive image segmentation, at the expense of human operator time and effort, in order to render 3D models [1].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Image Segmentation using Transfer Learning with DeepLabv3 to Facilitate Photogrammetric Limb Scanning

Cabrera¹,

Zhou²,

Ngo³

et al. 2022

Preprint

View full text Add to dashboard Cite

In this paper, we explore the use of deep learning (DL) in conjunction with photogrammetry for scanning amputated limbs. Combining these two technologies can expand the scope of prosthetic telemedicine by facilitating low-cost limb scanning using cell phones. Previous research identified image segmentation as one of the main limitations of using photogrammetry for limb scanning. Based on those limitations, this work sought to answer two main research questions: (1) Can a neural network be trained to identify and segment an amputated limb automatically? (2) Will segmenting 2D limb images using neural networks impact the accuracy of 3D models generated via photogrammetry? To answer the first question, transfer learning was applied to a neural network with the DeepLabv3 architecture. After training, the model was able to successfully identify and segment limb images with an IoU of 79.9\%. To answer the second question, the fine-tuned DL model was applied to a dataset of 22 scans comprising 6312 limb images, then 3D models were rendered utilizing Agisoft Metashape. The Mean Absolute Error (MAE) of models rendered from images segmented with DL was 0.57 mm ± 0.63 mm when compared to models rendered from ground truth images. These results are important because segmentation with DL makes photogrammetry for limb scanning feasible on a large clinical scale. Future work should focus on generalizing the segmentation model for different types of amputations and imaging conditions.

show abstract

Section: A Photogrammetry For Medical Imagingmentioning

confidence: 71%

Section: A Photogrammetry For Medical Imagingmentioning

confidence: 99%

Section: Rendering Proceduresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Image Segmentation using Transfer Learning with DeepLabv3 to Facilitate Photogrammetric Limb Scanning

Cabrera¹,

Zhou²,

Ngo³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Nightingale et al developed and validated a low-cost framework for clinical 3D scanning of the external ear using photogrammetry and a smartphone camera. Their results show that the smartphone-based photogrammetry methodology for 3D external ear model acquisition is accurate to 1,5±0,4mm and were 71±14% complete compared with those from a gold standard reference scanner [12]. Mai et al compared accuracy of face models acquired by a smartphone face scanner app with those scanned with a professional 3D facial scanner.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Optical Handheld 3D Scanners Suitable for Prosthetic and Orthotic Applications

STEFANOVIC¹,

Ondrejova²,

BEDNARCIKOVA³

et al. 2022

Proceedings of 3DBODY.TECH 2022 - 13th International Conference and Exhibition on 3D Body Scanning and Processing Technologies,

View full text Add to dashboard Cite

3D scanning technology is globally frequently used in the field of prosthetics and orthotics. Techniques and methods using 3D scanners make it easier and faster for CPOs (Certified prosthetic orthotist) to obtain important data for prosthetic and orthotic device design. Nevertheless, in low-income countries, this is still a new approach, and some CPOs might find it hard to trust. Also, the prices of some of these 3D scanning devices and data processing software are too high. Because of these issues, modern methods are being neglected and the whole prosthetic device designing process isn´t advancing. The aim of this study is to compare optical handheld 3D scanners of different brands, designs, and price ranges. A polystyrene model of the human torso with predetermined geometric forms will be scanned with multiple handheld optical 3D scanning devices. For the precision evaluation of the 3D scanners and hand measurement it is necessary to position the reference forms in a way that it will allow measurement by both methods. Selected dimensions must include all three axes of the cartesian coordinate system, so it will be possible to scanners precision in all individual axes. Scanning will be performed by one person in a room with stable lighting and room conditions. The torso model will be scanned by individual scanners and measured by hand 3 times and a mean value and standard deviation will be calculated. The geometric forms will be also used for the alignment of obtained 3D models in VGStudio Max software, which will be used for the analysis process. Distances between predetermined forms on the obtained 3D models will be evaluated. These nominal values will be compared with the actual values from the torso model, which were measured by hand. The quality and surface precision of actual obtained 3D models will be compared to determine the minimal or ideal requirements of optical handheld 3D scanners for the use in the field of prosthetics and orthotics.

show abstract

Accuracy Comparison of 3D Face Scans Obtained by Portable Stereophotogrammetry and Smartphone Applications

Van Lint,

Christiaens,

Stroo

et al. 2023

J. Med. Biol. Eng.

View full text Add to dashboard Cite

Frugal 3D scanning using smartphones provides an accessible framework for capturing the external ear

Cited by 14 publications

References 22 publications

Image Segmentation using Transfer Learning with DeepLabv3 to Facilitate Photogrammetric Limb Scanning

Image Segmentation using Transfer Learning with DeepLabv3 to Facilitate Photogrammetric Limb Scanning

Comparison of Optical Handheld 3D Scanners Suitable for Prosthetic and Orthotic Applications

Accuracy Comparison of 3D Face Scans Obtained by Portable Stereophotogrammetry and Smartphone Applications

Contact Info

Product

Resources

About