1
|
van Praagh GD, Nienhuis PH, Reijrink M, Davidse MEJ, Duff LM, Spottiswoode BS, Mulder DJ, Prakken NHJ, Scarsbrook AF, Morgan AW, Tsoumpas C, Wolterink JM, Mouridsen KB, Borra RJH, Sinha B, Slart RHJA. Automated multiclass segmentation, quantification, and visualization of the diseased aorta on hybrid PET/CT-SEQUOIA. Med Phys 2024. [PMID: 38323867 DOI: 10.1002/mp.16967] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/07/2023] [Revised: 11/10/2023] [Accepted: 01/16/2024] [Indexed: 02/08/2024] Open
Abstract
BACKGROUND Cardiovascular disease is the most common cause of death worldwide, including infection and inflammation related conditions. Multiple studies have demonstrated potential advantages of hybrid positron emission tomography combined with computed tomography (PET/CT) as an adjunct to current clinical inflammatory and infectious biochemical markers. To quantitatively analyze vascular diseases at PET/CT, robust segmentation of the aorta is necessary. However, manual segmentation is extremely time-consuming and labor-intensive. PURPOSE To investigate the feasibility and accuracy of an automated tool to segment and quantify multiple parts of the diseased aorta on unenhanced low-dose computed tomography (LDCT) as an anatomical reference for PET-assessed vascular disease. METHODS A software pipeline was developed including automated segmentation using a 3D U-Net, calcium scoring, PET uptake quantification, background measurement, radiomics feature extraction, and 2D surface visualization of vessel wall calcium and tracer uptake distribution. To train the 3D U-Net, 352 non-contrast LDCTs from (2-[18 F]FDG and Na[18 F]F) PET/CTs performed in patients with various vascular pathologies with manual segmentation of the ascending aorta, aortic arch, descending aorta, and abdominal aorta were used. The last 22 consecutive scans were used as a hold-out internal test set. The remaining dataset was randomly split into training (n = 264; 80%) and validation (n = 66; 20%) sets. Further evaluation was performed on an external test set of 49 PET/CTs. The dice similarity coefficient (DSC) and Hausdorff distance (HD) were used to assess segmentation performance. Automatically obtained calcium scores and uptake values were compared with manual scoring obtained using clinical softwares (syngo.via and Affinity Viewer) in six patient images. intraclass correlation coefficients (ICC) were calculated to validate calcium and uptake values. RESULTS Fully automated segmentation of the aorta using a 3D U-Net was feasible in LDCT obtained from PET/CT scans. The external test set yielded a DSC of 0.867 ± 0.030 and HD of 1.0 [0.6-1.4] mm, similar to an open-source model with a DSC of 0.864 ± 0.023 and HD of 1.4 [1.0-1.8] mm. Quantification of calcium and uptake values were in excellent agreement with clinical software (ICC: 1.00 [1.00-1.00] and 0.99 [0.93-1.00] for calcium and uptake values, respectively). CONCLUSIONS We present an automated pipeline to segment the ascending aorta, aortic arch, descending aorta, and abdominal aorta on LDCT from PET/CT and to accurately provide uptake values, calcium scores, background measurement, radiomics features, and a 2D visualization. We call this algorithm SEQUOIA (SEgmentation, QUantification, and visualizatiOn of the dIseased Aorta) and is available at https://github.com/UMCG-CVI/SEQUOIA. This model could augment the utility of aortic evaluation at PET/CT studies tremendously, irrespective of the tracer, and potentially provide fast and reliable quantification of cardiovascular diseases in clinical practice, both for primary diagnosis and disease monitoring.
Collapse
Affiliation(s)
- Gijs D van Praagh
- Medical Imaging Center, Department of Nuclear Medicine & Molecular Imaging, University of Groningen, University Medical Center Groningen, Groningen, the Netherlands
| | - Pieter H Nienhuis
- Medical Imaging Center, Department of Nuclear Medicine & Molecular Imaging, University of Groningen, University Medical Center Groningen, Groningen, the Netherlands
| | - Melanie Reijrink
- Department of Internal Medicine, division of Vascular Medicine, University of Groningen, University Medical Center Groningen, Groningen, the Netherlands
| | - Mirjam E J Davidse
- Department of Applied Mathematics and Technical Medicine Center, University of Twente, Enschede, the Netherlands
| | - Lisa M Duff
- Faculty of Engineering and Physical Sciences, University of Leeds, Leeds, UK
| | | | - Douwe J Mulder
- Department of Internal Medicine, division of Vascular Medicine, University of Groningen, University Medical Center Groningen, Groningen, the Netherlands
| | - Niek H J Prakken
- Medical Imaging Center, Department of Nuclear Medicine & Molecular Imaging, University of Groningen, University Medical Center Groningen, Groningen, the Netherlands
| | - Andy F Scarsbrook
- University of Leeds, School of Medicine, Leeds, UK
- NIHR Leeds Biomedical Research Centre, Leeds Teaching Hospitals NHS Trust, Leeds, UK
- NIHR Leeds Medtech and In vitro Diagnostics Co-operative, Leeds Teaching Hospitals NHS Trust, Leeds, UK
| | - Ann W Morgan
- University of Leeds, School of Medicine, Leeds, UK
- NIHR Leeds Biomedical Research Centre, Leeds Teaching Hospitals NHS Trust, Leeds, UK
- NIHR Leeds Medtech and In vitro Diagnostics Co-operative, Leeds Teaching Hospitals NHS Trust, Leeds, UK
| | - Charalampos Tsoumpas
- Medical Imaging Center, Department of Nuclear Medicine & Molecular Imaging, University of Groningen, University Medical Center Groningen, Groningen, the Netherlands
- Faculty of Engineering and Physical Sciences, University of Leeds, Leeds, UK
| | - Jelmer M Wolterink
- Department of Applied Mathematics and Technical Medicine Center, University of Twente, Enschede, the Netherlands
| | - Kim B Mouridsen
- Medical Imaging Center, Department of Nuclear Medicine & Molecular Imaging, University of Groningen, University Medical Center Groningen, Groningen, the Netherlands
- Center of Functionally Integrative Neuroscience, Aarhus University, Aarhus, Denmark
| | - Ronald J H Borra
- Medical Imaging Center, Department of Nuclear Medicine & Molecular Imaging, University of Groningen, University Medical Center Groningen, Groningen, the Netherlands
- Department of Diagnostic Radiology, Turku University Hospital, Turku, Finland
| | - Bhanu Sinha
- Department of Medical Microbiology and Infection Prevention, University of Groningen, University Medical Center Groningen, Groningen, the Netherlands
| | - Riemer H J A Slart
- Medical Imaging Center, Department of Nuclear Medicine & Molecular Imaging, University of Groningen, University Medical Center Groningen, Groningen, the Netherlands
- Department of Biomedical Photonic Imaging, University of Twente, Enschede, the Netherlands
| |
Collapse
|
2
|
Duff LM, Scarsbrook AF, Ravikumar N, Frood R, van Praagh GD, Mackie SL, Bailey MA, Tarkin JM, Mason JC, van der Geest KSM, Slart RHJA, Morgan AW, Tsoumpas C. An Automated Method for Artifical Intelligence Assisted Diagnosis of Active Aortitis Using Radiomic Analysis of FDG PET-CT Images. Biomolecules 2023; 13:343. [PMID: 36830712 PMCID: PMC9953018 DOI: 10.3390/biom13020343] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2022] [Revised: 01/30/2023] [Accepted: 02/01/2023] [Indexed: 02/12/2023] Open
Abstract
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.
Collapse
Affiliation(s)
- Lisa M. Duff
- School of Medicine, University of Leeds, Leeds LS2 9JT, UK
- Institute of Medical and Biological Engineering, University of Leeds, Leeds LS2 9JT, UK
| | - Andrew F. Scarsbrook
- School of Medicine, University of Leeds, Leeds LS2 9JT, UK
- Department of Radiology, St. James University Hospital, Leeds LS9 7TF, UK
| | - Nishant Ravikumar
- School of Medicine, University of Leeds, Leeds LS2 9JT, UK
- Center for Computational Imaging and Simulation Technologies in Biomedicine, University of Leeds, Leeds LS2 9JT, UK
| | - Russell Frood
- School of Medicine, University of Leeds, Leeds LS2 9JT, UK
- Department of Radiology, St. James University Hospital, Leeds LS9 7TF, UK
| | - Gijs D. van Praagh
- Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen, 9713 GZ Groningen, The Netherlands
| | - Sarah L. Mackie
- School of Medicine, University of Leeds, Leeds LS2 9JT, UK
- NIHR Leeds Biomedical Research Centre and NIHR Leeds MedTech and In Vitro Diagnostics Co-Operative, Leeds Teaching Hospitals NHS Trust, Leeds LS7 4SA, UK
| | - Marc A. Bailey
- School of Medicine, University of Leeds, Leeds LS2 9JT, UK
- The Leeds Vascular Institute, Leeds General Infirmary, Leeds LS2 9NS, UK
| | - Jason M. Tarkin
- Division of Cardiovascular Medicine, University of Cambridge, Cambridge CB2 0QQ, UK
| | - Justin C. Mason
- National Heart and Lung Institute, Imperial College London, London SW3 6LY, UK
| | - Kornelis S. M. van der Geest
- Department of Rheumatology and Clinical Immunology, University of Groningen, University Medical Center Groningen, 9713 GZ Groningen, The Netherlands
| | - Riemer H. J. A. Slart
- Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen, 9713 GZ Groningen, The Netherlands
- Department of Biomedical Photonic Imaging, Faculty of Science and Technology, University of Twente, 7522 NB Enschede, The Netherlands
| | - Ann W. Morgan
- School of Medicine, University of Leeds, Leeds LS2 9JT, UK
- NIHR Leeds Biomedical Research Centre and NIHR Leeds MedTech and In Vitro Diagnostics Co-Operative, Leeds Teaching Hospitals NHS Trust, Leeds LS7 4SA, UK
| | - Charalampos Tsoumpas
- School of Medicine, University of Leeds, Leeds LS2 9JT, UK
- Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen, 9713 GZ Groningen, The Netherlands
| |
Collapse
|