News | Artificial Intelligence | March 18, 2020

Breakthrough AI technology for 3-D Reconstruction of Knees from X-ray Images

New technology creates a rich 3-D modeling of each knee bone based solely on widely available X-ray images, enabling optimal pre-op planning and precise implant tailoring

RSIP Vision, a global leader in artificial intelligence (AI) and computer vision technology, announced a new innovative AI-based solution for 3-D reconstruction of knees from X-ray images

March 18, 2020 — RSIP Vision, a global leader in artificial intelligence (AI) and computer vision technology, announced a new innovative AI-based solution for 3-D reconstruction of knees from X-ray images. This technology provides physicians with a rich 3-D modeling of each bone, which could provide critical data for surgery planning and implants fitting, improving physicians' workflow and reducing the need for high-cost and high-radiation currently used methods. Physicians will receive a precise 3-D anatomical model of the patient knee, enabling optimal pre-op planning and precise implant tailoring.

X-ray scanners are widely available and cheaper than computed tomography (CT) or magnetic resonance imaging (MRI) scanners. Moreover, they expose the patients to much less radiation compared to CT scanners. However, X-ray images give only 2-D information resulting from the summation of the 3D rays through the anatomical objects. As a result, doctors usually take two X-rays images of lateral and AP views for a rough estimate of the 3-D anatomical structure. Nevertheless, what is still missing is a rich 3-D modelling of each bone, which could provide critical data for surgery planning and implants fitting. The new technology developed by RSIP Vision generates a 3D model of the knee joint from two X-ray images of AP and lateral views.

The model is based on convolutional neural networks, a recent technique which have been proven to be very effective for various types of tasks. In particular, deep neural networks-based models outperform all previous approaches for image segmentation. However, 3-D reconstruction from 2-D images is still challenging for neural networks, due to the difficulty of representing a dimensional enlargement with standard differentiable layers. Reconstruction of bone surfaces in particular is extremely challenging, due to the transparent nature of the X-ray images. RSIP Vision addresses these challenges by introducing a special dimensional enlargement layer.

The main usage of the 3-D model is for planning and accurate measurements that are needed to precise fit of the implant or for patient specific intraoperative guidance.

Accordingly, the testing has been done by comparing the 3-D model to a CT scan of the patient. The distance between the model and the real scan is the precision measure we need.

From our testing - the accuracy of this technology is close to 1mm which is the required precision needed for best fit for the implant in total knee replacement.

The results show that this new technology is very effective for reconstructing 3D models of knee bones from two standard bi-planar X-ray views. The deep neural network model, together with synthetic data creation and effective training process, proves to be a powerful technique to create a rich 3-D modeling of each bone with low-cost, widely available and low-radiation imaging modality.

"Knee replacement surgeries are common, among other joint surgeries. The most important factor for achieving high accuracy and success rates is preoperative planning, during which the orthopedic surgeon normally uses an expensive, time consuming, scarcely available modalities (CT, MRI…). To overcome this obstacle, RSIP Vision developed a new technology based solely on X-ray beams that is readily available, accurate, cheap and reproducible, which could be applied in poor peripheral as in rich central areas, while preserving the segmentation quality," said Rabeeh Fares, M.D., radiologist; Department of Diagnostic Radiology, Sourasky Medical Center, Tel Aviv.

For more information: www.rsipvision.com

Related Content

AI has the potential to help radiologists improve the efficiency and effectiveness of breast cancer imaging

Getty Images

Feature | Breast Imaging | May 28, 2020 | By January Lopez, M.D.
Headlines around the world the past several months declared that...
United Imaging's uMR OMEGA is designed to provide greater access to magnetic resonance imaging (MRI) with the world’s first ultra-wide 75-cm bore 3T MRI.
News | Magnetic Resonance Imaging (MRI) | May 27, 2020
May 27, 2020 — United Imaging's...
An example of DiA'a automated ejection fraction AI software on the GE vScan POCUS system at RSNA 2019.

An example of DiA'a automated ejection fraction AI software on the GE vScan POCUS system at RSNA 2019. Photo by Dave Fornell.

News | Ultrasound Imaging | May 26, 2020
May 12, 2020 — DiA Imaging Analysis, a provider of AI based ultrasound analysis solutions, said it received a governm
A new technique developed by researchers at UC Davis offers a significant advance in using magnetic resonance imaging to pick out even very small tumors from normal tissue. The team created a probe that generates two magnetic resonance signals that suppress each other until they reach the target, at which point they both increase contrast between the tumor and surrounding tissue

A new technique developed by researchers at UC Davis offers a significant advance in using magnetic resonance imaging to pick out even very small tumors from normal tissue. The team created a probe that generates two magnetic resonance signals that suppress each other until they reach the target, at which point they both increase contrast between the tumor and surrounding tissue. Image courtesy of Xiandoing Xue, UC Davis

News | Magnetic Resonance Imaging (MRI) | May 26, 2020
May 26, 2020 — Researchers at the University of California, Davis offers a...
Researchers from Tokyo Metropolitan University have surveyed the amount of gadolinium found in river water in Tokyo. Gadolinium is contained in contrast agents given to patients undergoing medical magnetic resonance imaging (MRI) scans, and it has been shown in labs to become toxic when exposed to ultraviolet rays. The researchers found significantly elevated levels, particularly near water treatment plants, highlighting the need for new public policy and removal technologies as MRI become even more commonp

Samples were taken along rivers around Tokyo. Measurements of rare earth element quantities indicate a clearly elevated amount of gadolinium compared to that in natural shale. Graphics courtesy of Tokyo Metropolitan University

News | Magnetic Resonance Imaging (MRI) | May 26, 2020
May 26, 2020 — Researchers from Tokyo Metropolitan...
 Recently the versatility of mixed and augmented reality products has come to the forefront of the news, with an Imperial led project at the Imperial College Healthcare NHS Trust. Doctors have been wearing the Microsoft Hololens headsets whilst working on the front lines of the COVID pandemic, to aid them in their care for their patients. IDTechEx have previously researched this market area in its report “Augmented, Mixed and Virtual Reality 2020-2030: Forecasts, Markets and Technologies”, which predicts th

Doctors wearing the Hololens Device. Source: Imperial.ac.uk

News | Artificial Intelligence | May 22, 2020
May 22, 2020 — Recently the versatility of
In response to the significant healthcare delivery changes brought on by COVID-19, Varian has launched new capabilities for its Noona software application, a powerful tool designed to engage cancer patients in their care for continuous reporting and symptom monitoring.
News | Radiation Oncology | May 21, 2020
May 21, 2020 — In response to the significant healthcare delivery changes brought on by...
NucleusHealth, a provider of cloud-based medical image management technology and teleradiology services, announced today that it has received Conformité Européene (CE) Mark approval for Nucleus.io.
News | Teleradiology | May 21, 2020
May 21, 2020 — NucleusHealth, a provider of cloud-based medical image management technology and teleradiology service