Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
AI-driven Ossification Assessment in Knee MRI: A Product-Service System Development for Informed Clinical Decision-Making
Blekinge Institute of Technology, Faculty of Engineering, Department of Mechanical Engineering. (PDRL - Product Development Research Lab)ORCID iD: 0000-0002-3876-5602
Blekinge Institute of Technology, Faculty of Engineering, Department of Mechanical Engineering. (PDRL - Product Development Research Lab)ORCID iD: 0000-0002-7804-7306
Blekinge Institute of Technology, Faculty of Engineering, Department of Health. (Health Technology Research Lab)ORCID iD: 0000-0003-4312-2246
Blekinge Institute of Technology, Faculty of Engineering, Department of Health. (Health Technology Research Lab)ORCID iD: 0000-0001-9870-8477
Show others and affiliations
(English)Manuscript (preprint) (Other academic)
Abstract [en]

Background: Traditionally, assessing the degree of ossification in the epiphyseal plate for growth plate development relies on manual evaluation, which can be inefficient due to the complexities of the distal femoral epiphysis anatomy. Existing methods lack efficient detection techniques.

Method: This study proposes an AI-based decision support system, designed within a product-service system (PSS) framework, to automate ossification assessment and detection of the distal femoral epiphysis in knee magnetic resonance imaging (MRI) data. The system leverages advanced machine learning techniques, specifically two Convolutional Neural Networks (CNNs), combined with computer vision techniques. This intelligent system analyzes MRI slices to predict the optimal slice for analysis and identify variations in the degree of ossification within individual datasets.

Results: The proposed method's effectiveness is demonstrated using a set of T2-weighted gradient echo grayscale knee MRI data. The system successfully detects the complex anatomy of the distal femoral epiphysis, revealing variations in the degree of ossification ranging from completely closed/open to fully open/closed regions.

Conclusions: This study presents a robust and efficient AI-based method, integrated within a PSS framework, for measuring the degree of ossification in the distal femoral epiphysis. This approach automates ossification assessment, providing valuable insights for clinical decision-making by clinicians and forensic practitioners. The PSS framework ensures seamless integration of the AI technology into existing workflows.

Keywords [en]
Degree of Ossification, Artificial Intelligence, Decision Support System, Product-Service Systems, Knee MRI
National Category
Mechanical Engineering
Identifiers
URN: urn:nbn:se:bth-26160OAI: oai:DiVA.org:bth-26160DiVA, id: diva2:1855993
Available from: 2024-05-03 Created: 2024-05-03 Last updated: 2024-05-08Bibliographically approved
In thesis
1. Navigating Data Challenges: AI-Driven Decision Support for Product-Service System Development
Open this publication in new window or tab >>Navigating Data Challenges: AI-Driven Decision Support for Product-Service System Development
2024 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Solution providers are transitioning from product-centric models to service-oriented solutions. This shift has led to the rise of Product-Service Systems (PSS), which offer a holistic approach by integrating physical products with associated services. However, the inherent complexity and collaborative nature of PSS development present a significant challenge: information gathering, analysis, and knowledge building. This is further amplified in the early stages of PSS development due to data challenges such as uncertainty, ambiguity, and complexity. This complicates informed decision-making, potentially leading to the risk of sub-optimal outcomes and impacting the success of final offerings.

This research proposes an AI-powered data analysis approach to address these data challenges and augment the decision-making process of PSS development. The focus is on supporting early-stage decision-making, as decisions made at this stage greatly impact the success of final solutions. The research investigates how data can be utilized and visualized to extract actionable insights, ultimately facilitating informed decision-making.

The presented research demonstrates that AI-powered data analysis effectively supports informed decision-making in early-stage PSS development. By extracting actionable insights from complex data, handling data limitations, and enabling informed strategic decisions, knowledge sharing, and collaboration are facilitated among stakeholders. Furthermore, integrating AI with visualization tools fosters knowledge building and a deeper understanding of system behavior, ultimately leading to more successful PSS solutions. The efficacy of AI-powered data analysis for handling diverse data types across application domains is demonstrated, potentially leading to benefits such as a deeper understanding of system behavior and proactive solution strategies. These advancements contribute to developing decision support systems specifically for PSS development.

Overall, this research demonstrates the efficacy of AI-powered data analysis in overcoming data challenges and empowering decision-makers in early-stage PSS development. This translates to more informed choices, leading to the creation of successful and efficient PSS solutions.

Place, publisher, year, edition, pages
Karlskrona: Blekinge Tekniska Högskola, 2024
Series
Blekinge Institute of Technology Doctoral Dissertation Series, ISSN 1653-2090 ; 2024:11
Keywords
Product-Service System (PSS), Artificial Intelligence, Early-stage Decision Support, Data Challenges, Informed Decision-making
National Category
Mechanical Engineering Other Engineering and Technologies
Research subject
Mechanical Engineering
Identifiers
urn:nbn:se:bth-26162 (URN)978-91-7295-484-7 (ISBN)
Public defence
2024-06-14, J1630, Campus Gräsvik, Karlskrona, 09:30 (English)
Opponent
Supervisors
Available from: 2024-05-08 Created: 2024-05-07 Last updated: 2025-02-10Bibliographically approved

Open Access in DiVA

No full text in DiVA

Authority records

Aeddula, OmsriWall, JohanSanmartin Berglund, JohanAnderberg, PeterLarsson, Tobias

Search in DiVA

By author/editor
Aeddula, OmsriWall, JohanSanmartin Berglund, JohanAnderberg, PeterLarsson, Tobias
By organisation
Department of Mechanical EngineeringDepartment of Health
Mechanical Engineering

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 738 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf