Clinical application of 18F-fluorodeoxyglucose positron emission tomography/computed tomography radiomics-based machine learning analyses in the field of oncology.

Machine learning (ML) analyses using 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT) radiomics features have been applied in the field of oncology. The current review aimed to summarize the current clinical articles about 18F-FDG PET/CT radiomics-based ML analyses to solve issues in classifying or constructing prediction models for several types of tumors. In these studies, lung and mediastinal tumors were the most commonly evaluated lesions, followed by lymphatic, abdominal, head and neck, breast, gynecological, and other types of tumors. Previous studies have commonly shown that 18F-FDG PET radiomics-based ML analysis has good performance in differentiating benign from malignant tumors, predicting tumor characteristics and stage, therapeutic response, and prognosis by examining significant differences in the area under the receiver operating characteristic curves, accuracies, or concordance indices (> 0.70). However, these studies have reported several ML algorithms. Moreover, different ML models have been applied for the same purpose. Thus, various procedures were used in 18F-FDG PET/CT radiomics-based ML analysis in oncology, and 18F-FDG PET/CT radiomics-based ML models, which are easy and universally applied in clinical practice, would be expected to be established.

Applying deep learning-based ensemble model to [18F]-FDG-PET-radiomic features for differentiating benign from malignant parotid gland diseases.

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. 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.

Usefulness of the Primary Tumor Standardized Uptake Value of Iodine-123 Metaiodobenzylguanidine for Predicting Metastatic Potential in Pheochromocytoma and Paraganglioma.

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.

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: 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.

CT and MRI features of undifferentiated carcinomas with osteoclast-like giant cells of the pancreas: a case series.

PURPOSE: The purpose of this case series was to describe computed tomography (CT) and magnetic resonance imaging (MRI) features of undifferentiated carcinoma with osteoclast-like giant cells of the pancreas. METHODS: Institutional ethics review board approval was obtained, and informed consent was waived for this case series. We reviewed CT and MRI of patients with pathologically confirmed undifferentiated carcinoma with osteoclast-like giant cells of the pancreas found in the medical records of our hospital between 2006 and 2016. RESULTS: Seven patients (3 males and 4 females; age, 59-82 years (mean, 71)) with confirmation by surgical resection (n = 3) or biopsy (n = 4) were identified. They underwent CT (n = 7) and MRI (n = 6). The tumors 26-83 mm in diameter (mean, 44 mm) were located in the head (n = 4) or body (n = 3) of the pancreas. They were demonstrated as lower attenuation areas relative to the adjacent pancreas on CT images obtained in both pancreatic and portal vein phases (n = 7) with a well-defined smooth margin (n = 5). They were demonstrated as hypointense areas relative to the pancreas on T2-weighted images (n = 4) and T2*-weighted images (n = 4) and diffusion-weighted images (n = 3). They contained hemosiderin deposits on histology (n = 7). CONCLUSIONS: Undifferentiated carcinoma with osteoclast-like giant cells of the pancreas might be present as low attenuation areas with a well-defined smooth margin on CT images obtained in pancreatic and portal vein phases, and hypointense areas on T2-, T2*-, and diffusion-weighted images caused by hemosiderin deposits.