Dataset Information

Machine learning approach using ¹⁸F-FDG-PET-radiomic features and the visibility of right ventricle ¹⁸F-FDG uptake for predicting clinical events in patients with cardiac sarcoidosis.

ABSTRACT:

Objectives

To investigate the usefulness of machine learning (ML) models using pretreatment ¹⁸F-FDG-PET-based radiomic features for predicting adverse clinical events (ACEs) in patients with cardiac sarcoidosis (CS).

Materials and methods

This retrospective study included 47 patients with CS who underwent ¹⁸F-FDG-PET/CT scan before treatment. The lesions were assigned to the training (n = 38) and testing (n = 9) cohorts. In total, 49 ¹⁸F-FDG-PET-based radiomic features and the visibility of right ventricle ¹⁸F-FDG uptake were used to predict ACEs using seven different ML algorithms (namely, decision tree, random forest [RF], neural network, k-nearest neighbors, Naïve Bayes, logistic regression, and support vector machine [SVM]) with tenfold cross-validation and the synthetic minority over-sampling technique. The ML models were constructed using the top four features ranked by the decrease in Gini impurity. The AUCs and accuracies were used to compare predictive performances.

Results

Patients who developed ACEs presented with a significantly higher surface area and gray level run length matrix run length non-uniformity (GLRLM_RLNU), and lower neighborhood gray-tone difference matrix_coarseness and sphericity than those without ACEs (each, p < 0.05). In the training cohort, all seven ML algorithms had a good classification performance with AUC values of > 0.80 (range: 0.841-0.944). In the testing cohort, the RF algorithm had the highest AUC and accuracy (88.9% [8/9]) with a similar classification performance between training and testing cohorts (AUC: 0.945 vs 0.889). GLRLM_RLNU was the most important feature of the modeling process of this RF algorithm.

Conclusion

ML analyses using ¹⁸F-FDG-PET-based radiomic features may be useful for predicting ACEs in patients with CS.

SUBMITTER: Nakajo M

PROVIDER: S-EPMC11217075 | biostudies-literature | 2024 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning approach using <sup>18</sup>F-FDG-PET-radiomic features and the visibility of right ventricle <sup>18</sup>F-FDG uptake for predicting clinical events in patients with cardiac sarcoidosis.

Nakajo Masatoyo M Hirahara Daisuke D Jinguji Megumi M Ojima Satoko S Hirahara Mitsuho M Tani Atsushi A Takumi Koji K Kamimura Kiyohisa K Ohishi Mitsuru M Yoshiura Takashi T

Japanese journal of radiology 20240316 7

<h4>Objectives</h4>To investigate the usefulness of machine learning (ML) models using pretreatment <sup>18</sup>F-FDG-PET-based radiomic features for predicting adverse clinical events (ACEs) in patients with cardiac sarcoidosis (CS).<h4>Materials and methods</h4>This retrospective study included 47 patients with CS who underwent <sup>18</sup>F-FDG-PET/CT scan before treatment. The lesions were assigned to the training (n = 38) and testing (n = 9) cohorts. In total, 49 <sup>18</sup>F-FDG-PET-ba ...[more]

PMID: 38491333

Similar Datasets

Project description:Knowledge of the intrinsic variability of radiomic features is essential to the proper interpretation of changes in these features over time. The primary aim of this study was to assess the test-retest repeatability of radiomic features extracted from 18F-FDG PET images of cervical tumors. The impact of different image preprocessing methods was also explored. Methods: Patients with cervical cancer underwent baseline and repeat 18F-FDG PET/CT imaging within 7 d. PET images were reconstructed using 2 methods: ordered-subset expectation maximization (PETOSEM) or ordered-subset expectation maximization with point-spread function (PETPSF). Tumors were segmented to produce whole-tumor volumes of interest (VOIWT) and 40% isocontours (VOI40). Voxels were either left at the default size or resampled to 3-mm isotropic voxels. SUV was discretized to a fixed number of bins (32, 64, or 128). Radiomic features were extracted from both VOIs, and repeatability was then assessed using the Lin concordance correlation coefficient (CCC). Results: Eleven patients were enrolled and completed the test-retest PET/CT imaging protocol. Shape, neighborhood gray-level difference matrix, and gray-level cooccurrence matrix features were repeatable, with a mean CCC value of 0.81. Radiomic features extracted from PETOSEM images showed significantly better repeatability than features extracted from PETPSF images (P < 0.001). Radiomic features extracted from VOI40 were more repeatable than features extracted from VOIWT (P < 0.001). For most features (78.4%), a change in bin number or voxel size resulted in less than a 10% change in feature value. All gray-level emphasis and gray-level run emphasis features showed poor repeatability (CCC values < 0.52) when extracted from VOIWT but were highly repeatable (mean CCC values > 0.96) when extracted from VOI40 Conclusion: Shape, gray-level cooccurrence matrix, and neighborhood gray-level difference matrix radiomic features were consistently repeatable, whereas gray-level run length matrix and gray-level zone length matrix features were highly variable. Radiomic features extracted from VOI40 were more repeatable than features extracted from VOIWT Changes in voxel size or SUV discretization parameters typically resulted in relatively small differences in feature value, though several features were highly sensitive to these changes.

Project description:Background18F-Fluorodeoxyglucose (FDG) PET/CT is emerging as a tool in the diagnosis and evaluation of pulmonary sarcoidosis, however, there is limited consensus regarding its diagnostic performance and prognostic value.MethodA meta-analysis was conducted with PubMed, Science Direct, MEDLINE, Scopus, and CENTRAL databases searched up to and including September 2023. 1355 studies were screened, with seventeen (n = 708 patients) suitable based on their assessment of the diagnostic performance or prognostic value of FDG-PET/CT. Study quality was assessed using the QUADAS-2 tool. Forest plots of pooled sensitivity and specificity were generated to assess diagnostic performance. Pooled changes in SUVmax were correlated with changes in pulmonary function tests (PFT).ResultsFDG-PET/CT in diagnosing suspected pulmonary sarcoidosis (six studies, n = 400) had a pooled sensitivity of 0.971 (95%CI 0.909-1.000, p = < 0.001) and specificity of 0.873 (95%CI 0.845-0.920)(one study, n = 169). Eleven studies for prognostic analysis (n = 308) indicated a pooled reduction in pulmonary SUVmax of 4.538 (95%CI 5.653-3.453, p = < 0.001) post-treatment. PFTs displayed improvement post-treatment with a percentage increase in predicted forced vital capacity (FVC) and diffusion capacity of the lung for carbon monoxide (DLCO) of 7.346% (95%CI 2.257-12.436, p = 0.005) and 3.464% (95%CI -0.205-7.132, p = 0.064), respectively. Reduction in SUVmax correlated significantly with FVC (r = 0.644, p < 0.001) and DLCO (r = 0.582, p < 0.001) improvement.ConclusionIn cases of suspected pulmonary sarcoidosis, FDG-PET/CT demonstrated good diagnostic performance and correlated with functional health scores. FDG-PET/CT may help to guide immunosuppression in cases of complex sarcoidosis or where treatment rationalisation is needed.Clinical relevance statementFDG-PET/CT has demonstrated a high diagnostic performance in the evaluation of suspected pulmonary sarcoidosis with radiologically assessed disease activity correlating strongly with clinically derived pulmonary function tests.Key pointsIn diagnosing pulmonary sarcoidosis, FDG-PET/CT had a sensitivity and specificity of 0.971 and 0.873, respectively. Disease activity, as determined by SUVmax, reduced following treatment in all the included studies. Reduction in SUVmax correlated with an improvement in functional vital capacity, Diffusion Capacity of the Lungs for Carbon Monoxide, and subjective health scoring systems.

Project description:BackgroundIdentification of epidermal growth factor receptor (EGFR) mutation types is crucial before tyrosine kinase inhibitors (TKIs) treatment. Radiomics is a new strategy to noninvasively predict the genetic status of cancer. In this study, we aimed to develop a predictive model based on 18F-fluorodeoxyglucose positron emission tomography-computed tomography (18F-FDG PET/CT) radiomic features to identify the specific EGFR mutation subtypes.MethodsWe retrospectively studied 18F-FDG PET/CT images of 148 patients with isolated lung lesions, which were scanned in two hospitals with different CT scan setting (slice thickness: 3 and 5 mm, respectively). The tumor regions were manually segmented on PET/CT images, and 1,570 radiomic features (1,470 from CT and 100 from PET) were extracted from the tumor regions. Seven hundred and ninety-four radiomic features insensitive to different CT settings were first selected using the Mann white U test, and collinear features were further removed from them by recursively calculating the variation inflation factor. Then, multiple supervised machine learning models were applied to identify prognostic radiomic features through: (I) a multi-variate random forest to select features of high importance in discriminating different EGFR mutation status; (II) a logistic regression model to select features of the highest predictive value of the EGFR subtypes. The EGFR mutation predicting model was constructed from prognostic radiomic features using the popular Xgboost machine-learning algorithm and validated using 3-fold cross-validation. The performance of predicting model was analyzed using the receiver operating characteristic curve (ROC) and measured with the area under the curve (AUC).ResultsTwo sets of prognostic radiomic features were found for specific EGFR mutation subtypes: 5 radiomic features for EGFR exon 19 deletions, and 5 radiomic features for EGFR exon 21 L858R missense. The corresponding radiomic predictors achieved the prediction accuracies of 0.77 and 0.92 in terms of AUC, respectively. Combing these two predictors, the overall model for predicting EGFR mutation positivity was also constructed, and the AUC was 0.87.ConclusionsIn our study, we established predictive models based on radiomic analysis of 18F-FDG PET/CT images. And it achieved a satisfying prediction power in the identification of EGFR mutation status as well as the certain EGFR mutation subtypes in lung cancer.

Project description:BackgroundTo develop and validate a survival model with clinico-biological features and 18F- FDG PET/CT radiomic features via machine learning, and for predicting the prognosis from the primary tumor of colorectal cancer.MethodsA total of 196 pathologically confirmed patients with colorectal cancer (stage I to stage IV) were included. Preoperative clinical factors, serum tumor markers, and PET/CT radiomic features were included for the recurrence-free survival analysis. For the modeling and validation, patients were randomly divided into the training (n = 137) and validation (n = 59) set, while the 78 stage III patients [training (n = 55), and validation (n = 23)] was divided for the further experiment. After selecting features by the log-rank test and variable-hunting methods, random survival forest (RSF) models were built on the training set to analyze the prognostic value of selected features. The performance of models was measured by C-index and was tested on the validation set with bootstrapping. Feature importance and the Pearson correlation were also analyzed.ResultsRadiomics signature (containing four PET/CT features and four clinical factors) achieved the best result for prognostic prediction of 196 patients (C-index 0.780, 95% CI 0.634-0.877). Moreover, four features (including two clinical features and two radiomics features) were selected for prognostic prediction of the 78 stage III patients (C-index was 0.820, 95% CI 0.676-0.900). K-M curves of both models significantly stratified low-risk and high-risk groups (P < 0.0001). Pearson correlation analysis demonstrated that selected radiomics features were correlated with tumor metabolic factors, such as SUVmean, SUVmax.ConclusionThis study presents integrated clinico-biological-radiological models that can accurately predict the prognosis in colorectal cancer using the preoperative 18F-FDG PET/CT radiomics in colorectal cancer. It is of potential value in assisting the management and decision making for precision treatment in colorectal cancer. Trial registration The retrospectively registered study was approved by the Ethics Committee of Fudan University Shanghai Cancer Center (No. 1909207-14-1910) and the data were analyzed anonymously.

Project description:BackgroundThere is evidence that metabolic disease burden in lymphoma influences patient outcome. However, the impact of disease severity on the cardiovascular system is unknown.ObjectivesThe aim of this study was to examine whether lymphoma is associated with arterial inflammation by investigating the relationship between disease metabolic burden and arterial fluorodeoxyglucose (FDG) uptake.MethodsSixty-two chemotherapy-naïve patients with active Hodgkin's or non-Hodgkin's lymphoma were matched (2:1) to individual control groups of lymphoma patients previously treated and free of active disease. All groups underwent 18F-FDG position emission tomography-computed tomography imaging. Disease severity was quantified by metabolic tumor volume (MTV) and total lesion glycolysis corresponding to standardized uptake values (SUVs) ≥41% or ≥2.5 of the maximum SUV within lymphoma regions, and aortic FDG uptake was quantified through the target-to-background ratio (TBR). Inflammatory and disease severity biomarkers were also measured.ResultsMTV and total lesion glycolysis measurements were significantly correlated with inflammatory and disease biomarkers. Aortic TBR was higher in patients with active non-Hodgkin's lymphoma compared with control subjects (median difference 0.51; 95% confidence interval [CI]: 0.28 to 0.78; p < 0.001). Similarly, patients with active Hodgkin's lymphoma had higher values of aortic TBR compared with control subjects (median difference 0.31; 95% CI: 0.15 to 0.49; p < 0.001). In addition, aortic TBR was modestly increased in patients with stage III to IV disease compared with those with stage I to II disease (median aortic TBR: 2.23 [interquartile range: 2.01 to 2.54] vs. 2.06 [interquartile range: 1.83 to 2.27; p = 0.050). In multivariable analysis, aortic FDG uptake and MTV≥2.5 values were independently associated (β = 0.425; 95% CI: 0.189 to 0.662; p = 0.001; R2 = 0.208), as were aortic FDG uptake and MTV≥41% (β = 0.407; 95% CI: 0.167 to 0.649, p = 0.001; R2 = 0.191).ConclusionsAortic wall FDG uptake is related with disease severity indicative of a possible vascular effect of lymphoma. This work highlights a new potential role of molecular imaging in cardio-oncology for evaluating disease severity and its consequences on the vasculature.

Dataset Information

Machine learning approach using ¹⁸F-FDG-PET-radiomic features and the visibility of right ventricle ¹⁸F-FDG uptake for predicting clinical events in patients with cardiac sarcoidosis.

Objectives

Materials and methods

Results

Conclusion

Publications

Machine learning approach using <sup>18</sup>F-FDG-PET-radiomic features and the visibility of right ventricle <sup>18</sup>F-FDG uptake for predicting clinical events in patients with cardiac sarcoidosis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets

Dataset Information

Machine learning approach using 18F-FDG-PET-radiomic features and the visibility of right ventricle 18F-FDG uptake for predicting clinical events in patients with cardiac sarcoidosis.

Objectives

Materials and methods

Results

Conclusion

Publications

Machine learning approach using <sup>18</sup>F-FDG-PET-radiomic features and the visibility of right ventricle <sup>18</sup>F-FDG uptake for predicting clinical events in patients with cardiac sarcoidosis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets

Machine learning approach using ¹⁸F-FDG-PET-radiomic features and the visibility of right ventricle ¹⁸F-FDG uptake for predicting clinical events in patients with cardiac sarcoidosis.