| 1. |
- Arvidsson, Ida, et al.
(författare)
-
Detection of left bundle branch block and obstructive coronary artery disease from myocardial perfusion scintigraphy using deep neural networks
- 2021
-
Ingår i: Medical Imaging 2021 : Computer-Aided Diagnosis - Computer-Aided Diagnosis. - : SPIE. - 1605-7422. - 9781510640238 ; 11597
-
Konferensbidrag (refereegranskat)abstract
- Myocardial perfusion scintigraphy, which is a non-invasive imaging technique, is one of the most common cardiological examinations performed today, and is used for diagnosis of coronary artery disease. Currently the analysis is performed visually by physicians, but this is both a very time consuming and a subjective approach. These are two of the motivations for why an automatic tool to support the decisions would be useful. We have developed a deep neural network which predicts the occurrence of obstructive coronary artery disease in each of the three major arteries as well as left bundle branch block. Since multiple, or none, of these could have a defect, this is treated as a multi-label classification problem. Due to the highly imbalanced labels, the training loss is weighted accordingly. The prediction is based on two polar maps, captured during stress in upright and supine position, together with additional information such as BMI and angina symptoms. The polar maps are constructed from myocardial perfusion scintigraphy examinations conducted in a dedicated Cadmium-Zinc-Telluride cardio camera (D-SPECT Spectrum Dynamics). The study includes data from 759 patients. Using 5-fold cross-validation we achieve an area under the receiver operating characteristics curve of 0.89 as average on per-vessel level for the three major arteries, 0.94 on per-patient level and 0.82 for left bundle branch block.
|
|
| 2. |
- Arvidsson, Ida, et al.
(författare)
-
Prediction of Obstructive Coronary Artery Disease from Myocardial Perfusion Scintigraphy using Deep Neural Networks
- 2021
-
Ingår i: 2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR). - : IEEE COMPUTER SOC. - 1051-4651. - 9781728188089 ; , s. 4442-4449
-
Konferensbidrag (refereegranskat)abstract
- For diagnosis and risk assessment in patients with stable ischemic heart disease, myocardial perfusion scintigraphy is one of the most common cardiological examinations performed today. There are however many motivations for why an artificial intelligence algorithm would provide useful input to this task. For example to reduce the subjectiveness and save time for the nuclear medicine physicians working with this time consuming task. In this work we have developed a deep learning algorithm for multi-label classification based on a convolutional neural network to estimate the probability of obstructive coronary artery disease in the left anterior artery, left circumflex artery and right coronary artery. The prediction is based on data from myocardial perfusion scintigraphy studies conducted in a dedicated Cadmium-Zinc-Telluride cardio camera (D-SPECT Spectrum Dynamics). Data from 588 patients was available, with stress images in both upright and supine position, as well as a number of auxiliary parameters such as angina symptoms and age. The data was used to train and evaluate the algorithm using 5-fold cross-validation. We achieve state-of-the-art results for this task with an area under the receiver operating characteristics curve of 0.89 as average on per-vessel level and 0.95 on per-patient level.
|
|
| 3. |
- Ochoa-Figueroa, Miguel, et al.
(författare)
-
Rendimiento diagnóstico de diferentes protocolos de estrés cardiaco usados en imagen de perfusión miocárdica para el diagnóstico de enfermedad coronaria usando una cámara de cadmio-zinc-telurio con correlación con angiografía coronaria [Diagnostic performance of different cardiac stress protocols for myocardial perfusion imaging for the diagnosis of coronary artery disease using a cadmium-zinc-telluride camera with invasive coronary angiography correlation]
- 2023
-
Ingår i: REVISTA ESPANOLA DE MEDICINA NUCLEAR E IMAGEN MOLECULAR. - : ELSEVIER ESPANA SLU. - 2253-654X. ; 42:5, s. 281-288
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose: To evaluate the diagnostic performance of three different cardiac stress protocols for myo-cardial perfusion imaging (MPI) using a cadmium-zinc-telluride (CZT) camera with invasive coronary angiography (ICA) correlation for the diagnosis of coronary artery disease in a high risk population. Methods: Retrospective study of 263 patients (96 women and 167 males, mean age 68 years) from which 119 patients performed a bicycle stress test (BST), 113 pharmacological stress test (PST) and 31 a com-bination of the two (CST) between September 2014 and December 2018. The patients then underwent myocardial perfusion imaging (MPI), followed by ICA and evaluated by means of quantitative angio-graphy software, within six months after the MPI. The mean pre-test probability score for coronary disease according to the European Society of Cardiology criteria was 36% for the whole population. The MPI was performed in a dedicated CZT cardio camera (D-SPECT Spectrum Dynamics) with a two-day protocol, according to the European Association of Nuclear Medicine guidelines.Results: No significant difference was observed between the three stress protocols in terms of diagnostic accuracy (BST 85%, PST 88% and CST 84%). The overall diagnostic accuracy of MPI to identify patients with any obstructive CAD at ICA was 86%, Sensitivity 93%, Specificity 54%, PPV 90% and NPV 63%.Conclusion: The CZT D-SPECT camera achieves overall satisfactory results in the diagnosis of CAD, obser-ving no significant differences in the diagnostic performance when the stress test was performed as a BST, PST or CST.& COPY; 2023 Sociedad Espanola de Medicina Nuclear e Imagen Molecular. Published by Elsevier Espana, S.L.U. All rights reserved.
|
|
| 4. |
- Ochoa-Figueroa, Miguel, et al.
(författare)
-
Rendimiento diagnóstico de un nuevo software de aprendizaje profundo para corrección de atenuación en la imagen de perfusión miocárdica utilizando una cámara CZT cardiodedicada. Experiencia en la práctica clínica [Diagnostic performance of a novel deep learning attenuation correction software for MPI using a cardio dedicated CZT camera: Experience in the clinical practice]
- 2024
-
Ingår i: REVISTA ESPANOLA DE MEDICINA NUCLEAR E IMAGEN MOLECULAR. - : ELSEVIER ESPANA SLU. - 2253-654X. ; 43:1, s. 23-30
-
Tidskriftsartikel (refereegranskat)abstract
- PurposeTo evaluate the diagnostic performance of a novel deep learning attenuation correction software (SAPCA) for myocardial perfusion imaging (MPI) using a cadmium-zinc-telluride (CZT) cardio dedicated camera with invasive coronary angiography (ICA) correlation for the diagnosis of coronary artery disease (CAD) in a high-risk population.MethodsRetrospective study of 300 patients (196 males [65%], mean age 68 years) from September 2014 to October 2019 undergoing MPI, followed by ICA and evaluated by means of quantitative angiography software, within six months after the MPI. The mean pre-test probability score for coronary disease according to the European Society of Cardiology criteria was 37% for the whole cohort. The MPI was performed in a dedicated CZT cardio camera (D-SPECT® Spectrum Dynamics) with a two-day protocol, according to the European Association of Nuclear Medicine guidelines. MPI was retrospectively evaluated with and without the SAPCA.ResultsThe overall diagnostic accuracy of MPI without SAPCA to identify patients with any obstructive CAD at ICA was 87%, Sensitivity 94%, Specificity 57%, positive predictive value 91% and negative predictive value 64%. Using SAPCA the overall diagnostic accuracy was 90%, sensitivity 91%, specificity 86%, positive predictive value 97% and negative predictive value 66%.ConclusionUse of the novel SAPCA enhances performance of the MPI using the CZT D-SPECT® camera and achieves improved results, especially avoiding artefacts and reducing the number of false positive results.
|
|
| 5. |
- Arvidsson, Ida, et al.
(författare)
-
Deep learning prediction of quantitative coronary angiography values using myocardial perfusion images with a CZT camera
- 2023
-
Ingår i: Journal of Nuclear Cardiology. - : Springer Science and Business Media LLC. - 1071-3581 .- 1532-6551. ; 30:1, s. 116-126
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose: Evaluate the prediction of quantitative coronary angiography (QCA) values from MPI, by means of deep learning. Methods: 546 patients (67% men) undergoing stress 99mTc-tetrofosmin MPI in a CZT camera in the upright and supine position were included (1092 MPIs). Patients were divided into two groups: ICA group included 271 patients who performed an ICA within 6 months of MPI and a control group with 275 patients with low pre-test probability for CAD and a normal MPI. QCA analyses were performed using radiologic software and verified by an expert reader. Left ventricular myocardium was segmented using clinical nuclear cardiology software and verified by an expert reader. A deep learning model was trained using a double cross-validation scheme such that all data could be used as test data as well. Results: Area under the receiver-operating characteristic curve for the prediction of QCA, with > 50% narrowing of the artery, by deep learning for the external test cohort: per patient 85% [95% confidence interval (CI) 84%-87%] and per vessel; LAD 74% (CI 72%-76%), RCA 85% (CI 83%-86%), LCx 81% (CI 78%-84%), and average 80% (CI 77%-83%). Conclusion: Deep learning can predict the presence of different QCA percentages of coronary artery stenosis from MPIs.
|
|
| 6. |
- Bauckneht, Matteo, et al.
(författare)
-
Associations among education, age, and the dementia with Lewy bodies (DLB) metabolic pattern: A European-DLB consortium project
- 2021
-
Ingår i: Alzheimer's & Dementia. - : WILEY. - 1552-5260 .- 1552-5279. ; 17:8, s. 1277-1286
-
Tidskriftsartikel (refereegranskat)abstract
- Introduction We assessed the influence of education as a proxy of cognitive reserve and age on the dementia with Lewy bodies (DLB) metabolic pattern. Methods Brain 18F-fluorodeoxyglucose positron emission tomography and clinical/demographic information were available in 169 probable DLB patients included in the European DLB-consortium database. Principal component analysis identified brain regions relevant to local data variance. A linear regression model was applied to generate age- and education-sensitive maps corrected for Mini-Mental State Examination score, sex (and either education or age). Results Age negatively covaried with metabolism in bilateral middle and superior frontal cortex, anterior and posterior cingulate, reducing the expression of the DLB-typical cingulate island sign (CIS). Education negatively covaried with metabolism in the left inferior parietal cortex and precuneus (making the CIS more prominent). Discussion These findings point out the importance of tailoring interpretation of DLB biomarkers considering the concomitant effect of individual, non-disease-related variables such as age and cognitive reserve.
|
|
| 7. |
|
|
| 8. |
- Etminani, Kobra, 1984-, et al.
(författare)
-
A 3D deep learning model to predict the diagnosis of dementia with Lewy bodies, Alzheimers disease, and mild cognitive impairment using brain 18F-FDG PET
- 2022
-
Ingår i: European Journal of Nuclear Medicine and Molecular Imaging. - New York : Springer. - 1619-7070 .- 1619-7089. ; 49, s. 563-584
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose The purpose of this study is to develop and validate a 3D deep learning model that predicts the final clinical diagnosis of Alzheimers disease (AD), dementia with Lewy bodies (DLB), mild cognitive impairment due to Alzheimers disease (MCI-AD), and cognitively normal (CN) using fluorine 18 fluorodeoxyglucose PET (18F-FDG PET) and compare models performance to that of multiple expert nuclear medicine physicians readers. Materials and methods Retrospective 18F-FDG PET scans for AD, MCI-AD, and CN were collected from Alzheimers disease neuroimaging initiative (556 patients from 2005 to 2020), and CN and DLB cases were from European DLB Consortium (201 patients from 2005 to 2018). The introduced 3D convolutional neural network was trained using 90% of the data and externally tested using 10% as well as comparison to human readers on the same independent test set. The models performance was analyzed with sensitivity, specificity, precision, F1 score, receiver operating characteristic (ROC). The regional metabolic changes driving classification were visualized using uniform manifold approximation and projection (UMAP) and network attention. Results The proposed model achieved area under the ROC curve of 96.2% (95% confidence interval: 90.6-100) on predicting the final diagnosis of DLB in the independent test set, 96.4% (92.7-100) in AD, 71.4% (51.6-91.2) in MCI-AD, and 94.7% (90-99.5) in CN, which in ROC space outperformed human readers performance. The network attention depicted the posterior cingulate cortex is important for each neurodegenerative disease, and the UMAP visualization of the extracted features by the proposed model demonstrates the reality of development of the given disorders. Conclusion Using only 18F-FDG PET of the brain, a 3D deep learning model could predict the final diagnosis of the most common neurodegenerative disorders which achieved a competitive performance compared to the human readers as well as their consensus.
|
|
| 9. |
- Etminani, Kobra, 1984-, et al.
(författare)
-
Peeking inside the box : Transfer Learning vs 3D convolutional neural networks applied in neurodegenerative diseases
- 2021
-
Ingår i: Proceedings of CIBB 2021.
-
Konferensbidrag (refereegranskat)abstract
- Convolutional Neural Networks (CNNs) have shown their effectiveness in a variety of imaging applications including medical imaging diagnostics. However, these deep learning models are data-hungry and need enough labeled samples for the training phase which is limited in the medical domain. Transfer learning is one possible solution to this challenge with training a new model. Assessing model performance should be done not only based on criteria like accuracy, and area under the ROC curve, but also it is important to investigate what regions were of most interest for the classification decisions, especially for medical applications. We performed a case study on neurodegenerative disorders, in specific Alzheimer’s disease, mild cognitive im- pairment, dementia with lewy bodies and cognitively normal brains using 3D 18F-FDG-PET brain scans. Two transfer learning models, InceptionV3 and ResNet50, as well as a custom 3D-CNN that is trained from scratch are compared. Two XAI methods, occlusion and Grad-CAM are chosen to visualize the important brain regions using correctly classified cases. We found that the TL models learn significantly different decision surfaces than the 3D-CNN model. The 3D spatial structure of the brain regions are better kept in the 3D-CNN model, and that might explain the higher performance of this model over 2D-TL models. Moreover, we found out the two XAI methods provide different results, where occlusion method focused more on specific brain regions.
|
|
| 10. |
- Good, Elin, et al.
(författare)
-
18Fluorodeoxyglucose uptake in relation to fat fraction and R2*in atherosclerotic plaques, using PET/MRI : a pilot study
- 2021
-
Ingår i: Scientific Reports. - : Springer Nature. - 2045-2322. ; 11:1
-
Tidskriftsartikel (refereegranskat)abstract
- Inflammation inside Atherosclerotic plaques represents a major pathophysiological process driving plaques towards rupture. Pre-clinical studies suggest a relationship between lipid rich necrotic core, intraplaque hemorrhage and inflammation, not previously explored in patients. Therefore, we designed a pilot study to investigate the feasibility of assessing the relationship between these plaque features in a quantitative manner using PET/MRI. In 12 patients with high-grade carotid stenosis the extent of lipid rich necrotic core and intraplaque hemorrhage was quantified from fat and R2* maps acquired with a previously validated 4-point Dixon MRI sequence in a stand-alone MRI. PET/MRI was used to measure 18F-FDG uptake. T1-weighted images from both scanners were used for registration of the quantitative Dixon data with the PET images. The plaques were heterogenous with respect to their volumes and composition. The mean values for the group were as follows: fat fraction (FF) 0.17% (± 0.07), R2* 47.6 s−1 (± 10.9) and target-to-blood pool ratio (TBR) 1.49 (± 0.48). At group level the correlation between TBR and FFmean was − 0.406, p 0.19 and for TBR and R2*mean 0.259, p 0.42. The lack of correlation persisted when analysed on a patient-by-patient basis but the study was not powered to draw definitive conclusions. We show the feasibility of analysing the quantitative relationship between lipid rich necrotic cores, intraplaque haemorrhage and plaque inflammation. The 18F-FDG uptake for most patients was low. This may reflect the biological complexity of the plaques and technical aspects inherent to 18F-FDG measurements.
|
|
