| Title: |
An Automated Method for Artifical Intelligence Assisted Diagnosis of Active Aortitis Using Radiomic Analysis of FDG PET-CT Images |
| Authors: |
Duff, Lisa M.; Scarsbrook, Andrew F.; Ravikumar, Nishant; Frood, Russell; van Praagh, Gijs D.; Mackie, Sarah L.; Bailey, Marc A.; Tarkin, Jason M.; Mason, Justin C.; van der Geest, Kornelis S.M.; Slart, Riemer H.J.A.; Morgan, Ann W.; Tsoumpas, Charalampos |
| Source: |
Duff, L M, Scarsbrook, A F, Ravikumar, N, Frood, R, van Praagh, G D, Mackie, S L, Bailey, M A, Tarkin, J M, Mason, J C, van der Geest, K S M, Slart, R H J A, Morgan, A W & Tsoumpas, C 2023, 'An Automated Method for Artifical Intelligence Assisted Diagnosis of Active Aortitis Using Radiomic Analysis of FDG PET-CT Images', Biomolecules, vol. 13, no. 2, 343. https://doi.org/10.3390/biom13020343 |
| Publication Year: |
2023 |
| Collection: |
University of Groningen research database |
| Subject Terms: |
aortitis; convolutional neural network; machine learning; positron emission tomography/computed tomography; radiomics |
| Description: |
The aim of this study was to develop and validate an automated pipeline that could assist the diagnosis of active aortitis using radiomic imaging biomarkers derived from [18F]-Fluorodeoxyglucose Positron Emission Tomography-Computed Tomography (FDG PET-CT) images. The aorta was automatically segmented by convolutional neural network (CNN) on FDG PET-CT of aortitis and control patients. The FDG PET-CT dataset was split into training (43 aortitis:21 control), test (12 aortitis:5 control) and validation (24 aortitis:14 control) cohorts. Radiomic features (RF), including SUV metrics, were extracted from the segmented data and harmonized. Three radiomic fingerprints were constructed: A—RFs with high diagnostic utility removing highly correlated RFs; B used principal component analysis (PCA); C—Random Forest intrinsic feature selection. The diagnostic utility was evaluated with accuracy and area under the receiver operating characteristic curve (AUC). Several RFs and Fingerprints had high AUC values (AUC > 0.8), confirmed by balanced accuracy, across training, test and external validation datasets. Good diagnostic performance achieved across several multi-centre datasets suggests that a radiomic pipeline can be generalizable. These findings could be used to build an automated clinical decision tool to facilitate objective and standardized assessment regardless of observer experience. |
| Document Type: |
article in journal/newspaper |
| File Description: |
application/pdf |
| Language: |
English |
| ISSN: |
2218-273X |
| Relation: |
info:eu-repo/semantics/altIdentifier/pmid/36830712; info:eu-repo/semantics/altIdentifier/hdl/https://hdl.handle.net/11370/9a1b8a07-2cd6-4f57-891e-07b9637aba5d; info:eu-repo/semantics/altIdentifier/pissn/2218-273X; info:eu-repo/semantics/altIdentifier/eissn/2218-273X |
| DOI: |
10.3390/biom13020343 |
| Availability: |
https://hdl.handle.net/11370/9a1b8a07-2cd6-4f57-891e-07b9637aba5d; https://research.rug.nl/en/publications/9a1b8a07-2cd6-4f57-891e-07b9637aba5d; https://doi.org/10.3390/biom13020343; https://pure.rug.nl/ws/files/606450314/biomolecules_13_00343_v3.pdf |
| Rights: |
info:eu-repo/semantics/openAccess ; http://creativecommons.org/licenses/by/4.0/ |
| Accession Number: |
edsbas.6EDECD36 |
| Database: |
BASE |