Dataset Information

Automatic Valve Plane Localization in Myocardial Perfusion SPECT/CT by Machine Learning: Anatomic and Clinical Validation.

ABSTRACT: Precise definition of the mitral valve plane (VP) during segmentation of the left ventricle for SPECT myocardial perfusion imaging (MPI) quantification often requires manual adjustment, which affects the quantification of perfusion. We developed a machine learning approach using support vector machines (SVM) for automatic VP placement. Methods: A total of 392 consecutive patients undergoing ^99mTc-tetrofosmin stress (5 min; mean ± SD, 350 ± 54 MBq) and rest (5 min; 1,024 ± 153 MBq) fast SPECT MPI attenuation corrected (AC) by CT and same-day coronary CT angiography were studied; included in the 392 patients were 48 patients who underwent invasive coronary angiography and had no known coronary artery disease. The left ventricle was segmented with standard clinical software (quantitative perfusion SPECT) by 2 experts, adjusting the VP if needed. Two-class SVM models were computed from the expert placements with 10-fold cross validation to separate the patients used for training and those used for validation. SVM probability estimates were used to compute the best VP position. Automatic VP localizations on AC and non-AC images were compared with expert placement on coronary CT angiography. Stress and rest total perfusion deficits and detection of per-vessel obstructive stenosis by invasive coronary angiography were also compared. Results: Bland-Altman 95% confidence intervals (CIs) for VP localization by SVM and experts for AC stress images (bias, 1; 95% CI, -5 to 7 mm) and AC rest images (bias, 1; 95% CI, -7 to 10 mm) were narrower than interexpert 95% CIs for AC stress images (bias, 0; 95% CI, -8 to 8 mm) and AC rest images (bias, 0; 95% CI, -10 to 10 mm) (P < 0.01). Bland-Altman 95% CIs for VP localization by SVM and experts for non-AC stress images (bias, 1; 95% CI, -4 to 6 mm) and non-AC rest images (bias, 2; 95% CI, -7 to 10 mm) were similar to interexpert 95% CIs for non-AC stress images (bias, 0; 95% CI, -6 to 5 mm) and non-AC rest images (bias, -1; 95% CI, -9 to 7 mm) (P was not significant [NS]). For regional detection of obstructive stenosis, ischemic total perfusion deficit areas under the receiver operating characteristic curve for the 2 experts (AUC, 0.79 [95% CI, 0.7-0.87]; AUC, 0.81 [95% CI, 0.73-0.89]) and the SVM (0.82 [0.74-0.9]) for AC data were the same (P = NS) and were higher than those for the unadjusted VP (0.63 [0.53-0.73]) (P < 0.01). Similarly, for non-AC data, areas under the receiver operating characteristic curve for the experts (AUC, 0.77 [95% CI, 0.69-0.89]; AUC, 0.8 [95% CI, 0.72-0.88]) and the SVM (0.79 [0.71-0.87]) were the same (P = NS) and were higher than those for the unadjusted VP (0.65 [0.56-0.75]) (P < 0.01). Conclusion: Machine learning with SVM allows automatic and accurate VP localization, decreasing user dependence in SPECT MPI quantification.

SUBMITTER: Betancur J

PROVIDER: S-EPMC5450369 | biostudies-literature | 2017 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automatic Valve Plane Localization in Myocardial Perfusion SPECT/CT by Machine Learning: Anatomic and Clinical Validation.

Betancur Julian J Rubeaux Mathieu M Fuchs Tobias A TA Otaki Yuka Y Arnson Yoav Y Slipczuk Leandro L Benz Dominik C DC Germano Guido G Dey Damini D Lin Chih-Jen CJ Berman Daniel S DS Kaufmann Philipp A PA Slomka Piotr J PJ

Journal of nuclear medicine : official publication, Society of Nuclear Medicine 20161103 6

Precise definition of the mitral valve plane (VP) during segmentation of the left ventricle for SPECT myocardial perfusion imaging (MPI) quantification often requires manual adjustment, which affects the quantification of perfusion. We developed a machine learning approach using support vector machines (SVM) for automatic VP placement. <b>Methods:</b> A total of 392 consecutive patients undergoing <sup>99m</sup>Tc-tetrofosmin stress (5 min; mean ± SD, 350 ± 54 MBq) and rest (5 min; 1,024 ± 153 M ...[more]

PMID: 27811121

Similar Datasets

Project description:BackgroundIn patients with pulmonary embolism (PE), there is a growing interest in quantifying the pulmonary vascular obtruction index (PVOI), which may be an independent risk factor for PE recurrence. Perfusion SPECT/CT is a very attractive tool to provide an accurate quantification of the PVOI. However, there is currently no reliable method to automatically delineate and quantify it. The aim of this phantom study was to assess and compare 3 segmentation methods for PVOI quantification with perfusion SPECT/CT imaging.MethodsThree hundred ninety-six SPECT/CT scans, with various PE scenarios (n = 44), anterior to posterior perfusion gradients (n = 3), and lung volumes (n = 3) were simulated using Simind software. Three segmentation methods were assesssed: (1) using an intensity threshold expressed as a percentage of the maximal voxel value (MaxTh), (2) using a Z-score threshold (ZTh) after building a Z-score parametric lung map, and (3) using a relative difference threshold (RelDiffTh) after building a relative difference parametric map. Ninety randomly selected simulations were used to define the optimal threshold, and 306 simulations were used for the complete analysis. Spacial correlation between PE volumes from the phantom data and the delineated PE volumes was assessed by computing DICEPE indices. Bland-Altman statistics were used to calculate agreement for PVOI between the phantom data and the segmentation methods.ResultsMean DICEPE index was higher with the RelDiffTh method (0.85 ± 0.08), as compared with the MaxTh method (0.78 ± 0.16) and the ZTh method (0.67 ± 0.15). Using the RelDiffTh method, mean DICEPE index remained high (> 0.81) regardless of the perfusion gradient and the lung volumes. Using the RelDiffTh method, mean relative difference in PVOI was - 12%, and the limits of agreement were - 40% to 16%. Values were 3% (- 75% to 81%) for MaxTh method and 0% (- 120% to 120%) for ZTh method. Graphycal analysis of the Bland-Altman graph for the RelDiffTh method showed very close estimation of the PVOI for small and medium PE, and a trend toward an underestimation of large PE.ConclusionIn this phantom study, a delineation method based on a relative difference parametric map provided a good estimation of the PVOI, regardless of the extent of PE, the intensity of the anterior to posterior gradient, and the whole lung volumes.

Project description:This study aimed to investigate the diagnostic performance of machine learning-based radiomics analysis to diagnose coronary artery disease status and risk from rest/stress Myocardial Perfusion Imaging (MPI) single-photon emission computed tomography (SPECT). A total of 395 patients suspicious of coronary artery disease who underwent 2-day stress-rest protocol MPI SPECT were enrolled in this study. The left ventricle myocardium, excluding the cardiac cavity, was manually delineated on rest and stress images to define a volume of interest. Added to clinical features (age, sex, family history, diabetes status, smoking, and ejection fraction), a total of 118 radiomics features, were extracted from rest and stress MPI SPECT images to establish different feature sets, including Rest-, Stress-, Delta-, and Combined-radiomics (all together) feature sets. The data were randomly divided into 80% and 20% subsets for training and testing, respectively. The performance of classifiers built from combinations of three feature selections, and nine machine learning algorithms was evaluated for two different diagnostic tasks, including 1) normal/abnormal (no CAD vs. CAD) classification, and 2) low-risk/high-risk CAD classification. Different metrics, including the area under the ROC curve (AUC), accuracy (ACC), sensitivity (SEN), and specificity (SPE), were reported for models' evaluation. Overall, models built on the Stress feature set (compared to other feature sets), and models to diagnose the second task (compared to task 1 models) revealed better performance. The Stress-mRMR-KNN (feature set-feature selection-classifier) reached the highest performance for task 1 with AUC, ACC, SEN, and SPE equal to 0.61, 0.63, 0.64, and 0.6, respectively. The Stress-Boruta-GB model achieved the highest performance for task 2 with AUC, ACC, SEN, and SPE of 0.79, 0.76, 0.75, and 0.76, respectively. Diabetes status from the clinical feature family, and dependence count non-uniformity normalized, from the NGLDM family, which is representative of non-uniformity in the region of interest were the most frequently selected features from stress feature set for CAD risk classification. This study revealed promising results for CAD risk classification using machine learning models built on MPI SPECT radiomics. The proposed models are helpful to alleviate the labor-intensive MPI SPECT interpretation process regarding CAD status and can potentially expedite the diagnostic process.

Project description:Left ventricular (LV) segmentation, including accurate assignment of LV contours, is essential for the quantitative assessment of myocardial perfusion SPECT (MPS). Two major types of segmentation failures are observed in clinical practices: incorrect LV shape determination and incorrect valve-plane (VP) positioning. We have developed a technique to automatically detect these failures for both nongated and gated studies.A standard Cedars-Sinai perfusion SPECT (quantitative perfusion SPECT [QPS]) algorithm was applied to derive LV contours in 318 consecutive (99m)Tc-sestamibi rest/stress MPS studies consisting of stress/rest scans with or without attenuation correction and gated stress/rest images (1,903 scans total). Two numeric parameters, shape quality control (SQC) and valve-plane quality control, were derived to categorize the respective contour segmentation failures. The results were compared with the visual classification of automatic contour adequacy by 3 experienced observers.The overall success of automatic LV segmentation in the 1,903 scans ranged from 66% on nongated images (incorrect shape, 8%; incorrect VP, 26%) to 87% on gated images (incorrect shape, 3%; incorrect VP, 10%). The overall interobserver agreement for visual classification of automatic LV segmentation was 61% for nongated scans and 80% for gated images; the agreement between gray-scale and color-scale display for these scans was 86% and 91%, respectively. To improve the reliability of visual evaluation as a reference, the cases with intra- and interobserver discrepancies were excluded, and the remaining 1,277 datasets were considered (101 with incorrect LV shape and 102 with incorrect VP position). For the SQC, the receiver-operating-characteristic area under the curve (ROC-AUC) was 1.0 +/- 0.00 for the overall dataset, with an optimal sensitivity of 100% and a specificity of 98%. The ROC-AUC was 1.0 in all specific datasets. The algorithm was also able to detect the VP position errors: VP overshooting with ROC-AUC, 0.91 +/- 0.01; sensitivity, 100%; and specificity, 70%; and VP undershooting with ROC-AUC, 0.96 +/- 0.01; sensitivity, 100%; and specificity, 70%.A new automated method for quality control of LV MPS contours has been developed and shows high accuracy for the detection of failures in LV segmentation with a variety of acquisition protocols. This technique may lead to an improvement in the objective, automated quantitative analysis of MPS.

Dataset Information

Automatic Valve Plane Localization in Myocardial Perfusion SPECT/CT by Machine Learning: Anatomic and Clinical Validation.

Publications

Automatic Valve Plane Localization in Myocardial Perfusion SPECT/CT by Machine Learning: Anatomic and Clinical Validation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets