Language：Japanese   Publisher：Japanese Journal of Radiology  

Objectives: To develop and identify machine learning (ML) models using pretreatment 2-deoxy-2-[18F]fluoro-D-glucose ([18F]-FDG)-positron emission tomography (PET)-based radiomic features to differentiate benign from malignant parotid gland diseases (PGDs). Materials and methods: This retrospective study included 62 patients with 63 PGDs who underwent pretreatment [18F]-FDG-PET/computed tomography (CT). The lesions were assigned to the training (n = 44) and testing (n = 19) cohorts. In total, 49 [18F]-FDG-PET-based radiomic features were utilized to differentiate benign from malignant PGDs using five different conventional ML algorithmic models (random forest, neural network, k-nearest neighbors, logistic regression, and support vector machine) and the deep learning (DL)-based ensemble ML model. In the training cohort, each conventional ML model was constructed using the five most important features selected by the recursive feature elimination method with the tenfold cross-validation and synthetic minority oversampling technique. The DL-based ensemble ML model was constructed using the five most important features of the bagging and multilayer stacking methods. The area under the receiver operating characteristic curves (AUCs) and accuracies were used to compare predictive performances. Results: In total, 24 benign and 39 malignant PGDs were identified. Metabolic tumor volume and four GLSZM features (GLSZM_ZSE, GLSZM_SZE, GLSZM_GLNU, and GLSZM_ZSNU) were the five most important radiomic features. All five features except GLSZM_SZE were significantly higher in malignant PGDs than in benign ones (each p < 0.05). The DL-based ensemble ML model had the best performing classifier in the training and testing cohorts (AUC = 1.000, accuracy = 1.000 vs AUC = 0.976, accuracy = 0.947). Conclusions: The DL-based ensemble ML model using [18F]-FDG-PET-based radiomic features can be useful for differentiating benign from malignant PGDs. Second abstract: The DL-based ensemble ML model using [18F]-FDG-PET-based radiomic features can overcome the previously reported limitation of [18F]-FDG-PET/CT scan for differentiating benign from malignant PGDs. The DL-based ensemble ML approach using [18F]-FDG-PET-based radiomic features can provide useful information for managing PGD.

DOI： 10.1007/s11604-024-01649-6

Scopus

PubMed

Language：English   Publisher：(公社)日本医学放射線学会  

Language：Japanese   Publisher：Japanese Journal of Radiology  

Purpose: To clarify the usefulness of electron density (ED) using dual-energy CT (DECT) parameters for predicting treatment response in patients with pulmonary embolism (PE). Materials and methods: The study population comprised 30 patients with PE (49 thrombi) who underwent pretreatment DECT. The study coordinator diagnosed PE using contrast-enhanced CT (CECT) as the gold standard and annotated the location of thrombi on CECT prior to the DECT image analyses. CT attenuation values on conventional 120 kVp, 40 keV, and 70 keV virtual monochromatic (VM) images; effective atomic number; and ED of pretreatment pulmonary thrombi were measured on unenhanced CT. Thrombi were classified into dissolved and residual groups according to the findings of posttreatment follow-up CT. DECT parameters were compared between the two groups using the Mann–Whitney U test. For statistically significant parameters, receiver-operating characteristic (ROC) analysis was used to evaluate their performance for differentiating two groups. Diagnostic accuracy for predicting treatment response in patients with PE was determined by calculating the area under the ROC curve (AUC). Results: ED values, CT values on conventional 120 kVp imaging, and those on 70 keV VM imaging were significantly higher in thrombi in the dissolved group than the residual group (p < 0.001, p = 0.012, p = 0.009, respectively). AUC values for predicting dissolution response by ED, conventional 120 kVp imaging, and 70 keV VM imaging (cut-off value, 3.49 × 1023/cm3, 53.4 HU, and 50.7 HU, respectively) were 0.856, 0.744, and 0.755, respectively. AUC was significantly higher for ED than for conventional 120 kVp imaging and 70 keV VM imaging (p = 0.032, p = 0.016). Conclusions: ED derived from unenhanced DECT may help predict therapeutic efficacy in patients with PE.

DOI： 10.1007/s11604-025-01747-z

Scopus

PubMed

Language：Japanese   Publisher：Molecular Imaging and Biology  

Purpose: To examine the usefulness of semi-quantitative analysis using the standardized uptake value (SUV) of iodine-123 metaiodobenzylguanidine ([123I]-MIBG) for predicting metastatic potential in patients with pheochromocytoma (PHEO) and paraganglioma (PGL). Procedures: This study included 18 PHEO and 2 PGL patients. [123I]-MIBG visibility and SUV-related parameters (SUVmax, SUVmean, tumor volume of [123I]-MIBG uptake [TV_MIBG], and total lesion [123I]-MIBG uptake) were compared with the pathological grading obtained using the Pheochromocytoma of the Adrenal Gland Scaled Score (PASS) and the Grading System for Adrenal Pheochromocytoma and Paraganglioma (GAPP), which are used to predict metastatic potential. The PASS scores were categorized as < 4 and ≥ 4. Based on the GAPP scores, PHEOs/PGLs were categorized as follows: well, moderately, and poorly differentiated tumors. The Mann–Whitney U test or Spearman’s rank correlation was used to assess differences or associations between two quantitative variables. Results: All PHEOs/PGLs were visualized on [123I]-MIBG scintigraphy. There were 16 PASS < 4 and 4 PASS ≥ 4 tumors. Moreover, 11 and 9 tumors were well and moderately differentiated, respectively. The uptake scores and SUV-related parameters significantly differed between tumors with a PASS score of < 4 and those with a PASS score of ≥ 4 (each, p > 0.05). Moderately differentiated tumors had significantly higher uptake scores and SUV-related parameters except TV_MIBG than well-differentiated tumors (each, p < 0.05). The GAPP score was positively correlated with the uptake scores and SUV-related parameters (each, p < 0.05) except TV_MIBG. Conclusions: The primary tumor [123I]-MIBG uptake assessed using SUV-related parameters can be an imaging tool for predicting metastatic potential in patients with PHEO/PGL.

DOI： 10.1007/s11307-024-01952-8

Scopus

PubMed

Language：Japanese   Publisher：Japanese Journal of Radiology  

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.

DOI： 10.1007/s11604-024-01546-y

Scopus

PubMed

Language：English   Publisher：(公社)日本医学放射線学会  

Language：English  

Language：Japanese  

Language：English  

Language：Japanese  

Language：Japanese