Artificial intelligence learns muscle anatomy in CT images

October 30, 2019

Personalized medicine has stirred the imagination of drugs and therapies that are individually tailored to patients. In the future, there will no longer be a need to worry about side effects, and patients will be screened to identify which treatment will be most effective for them, instead of for the average population. Deep learning is one tool that will be key to realizing personalized medicine. A new study by Japanese researchers describes a new deep learning tool that will advance personalized medicine for musculoskeletal diseases. The tool can segment individual muscles for a comprehensive model of the musculoskeletal system, which is expected to advance personalized biomechanics.

Accurate measurements of the musculoskeletal system can have a tremendous impact for the extremely ill, like those suffering from ALS or other severe forms of atrophy, to influence the design of rehabilitation devices, and for the extraordinarily gifted, like high-performance athletes who want to take their game to the next level. These measurements come from computed tomography or other imaging modality with which researchers build computer models to study the forces and stresses on muscles and bones.

"Once we have the CT images, we need to segment the individual muscles for building our model," explains Professor Yoshinobu Sato of Nara Institute of Science and Technology (NAIST), Japan, who led the study.

"However, this segmentation was time consuming and depended on expert-knowledge. The figure shows an overview of our system. We used deep learning to automate the segmentation of individual muscles to generate a musculoskeletal model that is personalized to the patient," he continues.

While it is normal to expect a physician to evaluate the images, this adds a level of subjectivity to the diagnosis. The system is especially beneficial for patients in remote areas with limited access to expert orthopedic surgeons, for decisions based on a more quantitative interpretation should improve outcomes.

The method depends on Bayesian U-net architecture.

"U-Net is a deep learning framework based on a fully convolutional neural network for the precise segmentation of images. Our colleague, Dr. Yuta Hiasa, extended U-net by combining Bayesian inference to formulate Bayesian U-net, in which uncertainty is associated with segmentation results," says Sato.

The challenge in segmenting individual muscles is the low contrast of the imaging at border regions of neighboring muscles. To test their system, the researchers examined 19 muscles in the thigh and hips. Bayesian U-Net had better segmentation accuracy than other methods including the hierarchical multi-atlas method, which is viewed as state-of-the-art, and did so while reducing the time to train and validate the system by a surgeon.

"Some pixels in the images had high uncertainty. It was these pixels that especially need confirmation by surgeons," notes Sato.

The researchers thus defined an uncertainty threshold to identify which pixels required human verification.

"Bayesian U-Net learned the musculoskeletal anatomy to create segmentations that would have been created by experts with high fidelity and our collaborator orthopedic surgeon, Prof. Nobuhiko Sugano of Osaka University Hospital, is quite satisfied with this achievement," says Sato.

Title: Automated muscle segmentation from clinical CT using Bayesian U-net for personalized musculoskeletal modeling

Authors: Yuta Hiasa, Yoshito Otake, Masaki Takao, Takeshi Ogawa, Nobuhiko Sugano & Yoshinobu Sato

Journal: IEEE Transactions on Medical Imaging

DOI: 10.1109/TMI.2019.2940555

Information about Prof. Sato lab can be found at the following website:

Nara Institute of Science and Technology

Related Personalized Medicine Articles from Brightsurf:

Implementing microbiome diagnostics in personalized medicine: Rise of pharmacomicrobiomics
A new Commentary identifies three actionable challenges for translating pharmacomicrobiomics to personalized medicine in 2020.

Implementing post-genomic personalized medicine: The rise of glycan biomarkers
An in-depth look at the science of glycobiology and glycan diagnostics, and their promise in personalized medicine in the current post-genomic era are featured in a special issue of OMICS: A Journal of Integrative Biology, the peer-reviewed interdisciplinary journal published by Mary Ann Liebert, Inc., publishers.

Personalized medicine for atrial fibrillation
The study, published in Europace, uses signals from implantable devices -- pacemakers and defibrillators -- to analyze electrical signals in the heart during episodes of atrial fibrillation.

Fruit flies help in the development of personalized medicine
It is common knowledge that there is a connection between our genes and the risk of developing certain diseases.

Expanding the limits of personalized medicine with high-performance computing
Imagine that you have a serious medical condition. Then imagine that when you visit a team of doctors, they could build an identical virtual 'twin' of the condition and simulate millions of ways to treat it until they develop an effective treatment.

Personalized medicine software vulnerability uncovered by Sandia researchers
A weakness in one common open source software for genomic analysis left DNA-based medical diagnostics vulnerable to cyberattacks.

'Organs in a dish' pave the way for personalized medicine in gut and liver disease
One of the most exciting advancements in stem cell research has been the development of organoid systems, which are organ-like three-dimensional structures that mimic their corresponding organ in vivo.

Understanding gene interactions holds key to personalized medicine, scientists say
Scientists outline a new framework for studying gene function -- not in isolation, gene by gene, but as a network, to understand how multiple genes and genetic background influence trait inheritance.

Mount Sinai researchers call for diversity in the next generation of personalized medicine
Researchers from the Icahn School of Medicine at Mount Sinai reveal that genomic data extracted from population biobanks across the globe contain much less ethnic diversity than desirable.

Researchers call for big data infrastructure to support future of personalized medicine
Researchers from the George Washington University, the US Food and Drug Administration, and industry leaders published in PLOS Biology, describing a standardized communication method for researchers performing high-throughput sequencing called BioCompute.

Read More: Personalized Medicine News and Personalized Medicine Current Events is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to