Machine Learning Techniques Improve X-ray Materials Analysis
November 21, 2023 | ACN NewswireEstimated reading time: 2 minutes

Researchers of RIKEN at Japan’s state-of-the-art synchrotron radiation facility, SPring-8, and their collaborators, have developed a faster and simpler way to carry out segmentation analysis, a vital process in materials science. The new method was published in the journal Science and Technology of Advanced Materials: Methods.
Segmentation analysis is used to understand the fine-scale composition of a material. It identifies distinct regions (or ‘segments’) with specific compositions, structural characteristics, or properties. This helps evaluate the suitability of a material for specific functions, as well as its possible limitations. It can also be used for quality control in material fabrication and for identifying points of weakness when analyzing materials that have failed.
Segmentation analysis is very important for synchrotron radiation X-ray computed tomography (SR-CT), which is similar to conventional medical CT scanning but uses intense focused X-rays produced by electrons circulating in a storage ring at nearly the speed of light. The team have demonstrated that machine learning is capable in conducting the segmentation analysis for the refraction contrast CT, which is especially useful for visualizing the three-dimensional structure in samples with small density differences between regions of interest, such as epoxy resins.
“Until now, no general segmentation analysis method for synchrotron radiation refraction contrast CT has been reported,” says first author Satoru Hamamoto. “Researchers have generally had to do segmentation analysis by trial and error, which has made it difficult for those who are not experts.”
The team’s solution was to use machine learning methods established in biomedical fields in combination with a transfer learning technique to finely adjust to the segmentation analysis of SR-CTs. Building on the existing machine learning model greatly reduced the amount of training data needed to get results.
“We’ve demonstrated that fast and accurate segmentation analysis is possible using machine learning methods, at a reasonable computational cost, and in a way that should allow non-experts to achieve levels of accuracy similar to experts,” says Takaki Hatsui, who led the research group.
The researchers carried out a proof-of-concept analysis in which they successfully detected regions created by water within an epoxy resin. Their success suggests that the technique will be useful for analyzing a wide range of materials.
To make this analysis method available as widely and quickly as possible, the team plans to establish segmentation analysis as a service offered to external researchers by the SPring-8 data center, which has recently started its operation.
Suggested Items
Standard of Excellence: Anticipating Customer Needs Early and Often
03/26/2025 | Anaya Vardya -- Column: Standard of ExcellenceSuccessful companies don’t simply respond to customer needs, they anticipate them. The heart of excellent customer service lies in being proactive, where businesses foresee challenges, provide solutions, and create opportunities before customers know they need them. Here are seven ways to anticipate customer needs and implement them to ensure successful outcomes.
Datest to Highlight Flying Probe Programming and X-ray Testing Services at Upcoming SMTA Texas Expos
03/25/2025 | DatestDatest, a leading provider of integrated PCBA testing, imaging, inspection, and failure analysis services for the electronics industry, is excited to announce it will exhibit in the upcoming SMTA Dallas Expo on Tuesday, April 1st, and the SMTA Houston Expo on Thursday, April 3rd, 2025.
Datest Expands Reach in Florida with Whitlock Associates Partnership
01/23/2025 | DatestDatest, a trusted leader in advanced testing, engineering, inspection, and failure analysis services, is excited to announce the addition of Whitlock Associates to its network of sales representatives.
DARPA Taps RTX to Strengthen Cyber Resiliency
11/11/2024 | RTXRTX's BBN Technologies was awarded a contract to support DARPA's Compartmentalization and Privilege Management, or CPM, program. The CPM program aims to enhance cyber resilience by automatically subdividing software systems into smaller, secure compartments, preventing initial breaches from escalating into successful cyberattacks while maintaining system efficiency.
The Quest for Perfect Products
11/11/2024 | Marcy LaRont, I-Connect007Anna-Katrina Shedletsky is a former Apple engineer who formed her own company, Instrumental, to address what she felt were frustrating and costly engineering problems and inefficiencies at Apple. She’s passionate about her quest to build perfect products faster than ever before. In this interview, Anna shares her journey from creating innovative products like the Apple Watch to addressing the complexities of failure analysis in manufacturing. She also discusses an upcoming educational webinar she is hosting with Valentina Ratner, CEO of AllSpice.io, for engineering leaders in the manufacturing space. They look forward to providing “real talk” and value to their engineering colleagues.