Metabolic bulk volume from FDG PET as an independent predictor of progression-free survival in follicular lymphoma.

Background: Total metabolic tumor volume (TMTV) in 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) predicts patient outcome in follicular lymphoma (FL); however, it requires laborious segmentation of all lesions. We investigated the prognostic value of the metabolic bulk volume (MBV) obtained from the single largest lesion. Methods: Pretreatment FDG PET/computed tomography (CT) scans of 201 patients were analyzed for TMTV and MBV using a 41% maximum standardized uptake value (SUVmax) threshold. Results: During a median follow-up of 3.2 years, 54 events, including 14 deaths, occurred. Optimal cut-offs were 121.1 cm3 for TMTV and 24.8 cm3 for MBV. Univariable predictors of progression-free survival (PFS) included a high Follicular Lymphoma International Prognostic Index 2 (FLIPI2) score, TMTV, and MBV. In the multivariable analysis, high TMTV and MBV were independent predictors of worse PFS (P =0.015 and 0.033). Furthermore, in a sub-group with FLIP2 scores of 0-2 (n = 132), high MBV could identify patients with worse PFS (P = 0.007). . Conclusion: Readily measurable MBV is useful for stratifying risk in FL patients.

Semi-quantitative FDG parameters predict survival in multiple myeloma patients without autologous stem cell transplantation.

BACKGROUND: F-18 fluorodeoxyglucose positron emission tomography/computed tomography (FDG PET/CT) is useful in multiple myeloma (MM) for initial workup and treatment response evaluation. Herein, we evaluated the prognostic value of semi-quantitative FDG parameters for predicting the overall survival (OS) of MM patients with or without autologous stem cell transplantation (ASCT). METHODS: Study subjects comprised 227 MM patients who underwent baseline FDG PET/CT. Therein, 123 underwent ASCT while 104 did not. Volumes of interest (VOIs) of bones were drawn on CT images using a threshold of 150 Hounsfield units. FDG parameters of maximum standardized uptake value (SUVmax), mean SUV (SUVmean), metabolic tumor volume (MTV), total lesion glycolysis (TLG), and number of focal lesions (FLs) were measured. Kaplan-Meier survival analysis with log-rank tests and Cox proportional hazards regression analyses were performed for overall survival (OS). RESULTS: In the ASCT cohort, R-ISS stage, MTV, and TLG were associated with survival. In the non-ASCT cohort, however, R-ISS stage was not associated with patient outcomes. In contrast, high SUVmax, SUVmean, MTV, TLG, and FL could predict worse OS (hazard ratio [HR] = 2.569, 2.649, 2.506, 2.839, and 1.988, respectively). Importantly, combining FDG parameters with R-ISS stage provided a new risk classification system that discriminated worse OS in the non-ASCT cohort significantly better than did R-ISS stage alone. CONCLUSIONS: In the non-ASCT cohort, semi-quantitative FDG parameters were significant predictors of worse OS. Furthermore, combining FDG parameters with R-ISS stage may provide a new risk staging system that can better stratify the survival of MM patients without ASCT.

A Machine Learning Approach Using FDG PET-Based Radiomics for Prediction of Tumor Mutational Burden and Prognosis in Stage IV Colorectal Cancer.

INTRODUCTION: We assessed the performance of F-18 fluorodeoxyglucose positron emission tomography (FDG PET)-based radiomics for the prediction of tumor mutational burden (TMB) and prognosis using a machine learning (ML) approach in patients with stage IV colorectal cancer (CRC). METHODS: Ninety-one CRC patients who underwent pretreatment FDG PET/computed tomography (CT) and palliative chemotherapy were retrospectively included. PET-based radiomics were extracted from the primary tumor on PET imaging using the software LIFEx. For feature selection, PET-based radiomics associated with TMB were selected by logistic regression analysis. The performances of seven ML algorithms to predict high TMB were compared by the area under the receiver's operating characteristic curves (AUCs) and validated by five-fold cross-validation. A PET radiomic score was calculated by averaging the z-score of each radiomic feature. The prognostic power of the PET radiomic score was assessed using Cox proportional hazards regression analysis. RESULTS: Ten significant radiomic features associated with TMB were selected: surface-to-volume ratio, total lesion glycolysis, tumor volume, area, compacity, complexity, entropy, correlation, coarseness, and zone size non-uniformity. The k-nearest neighbors model obtained the good performance for prediction of high TMB (AUC: 0.791, accuracy: 0.814, sensitivity: 0.619, specificity: 0.871). On multivariable Cox regression analysis, the PET radiomic score (Hazard ratio = 4.498, 95% confidential interval = 1.024-19.759; p = 0.046) was a significant independent prognostic factor for OS. CONCLUSIONS: This study demonstrates that PET-based radiomics are useful image biomarkers for the prediction of TMB status in stage IV CRC. PET radiomic score, which integrates significant radiomic features, has the potential to predict survival in stage IV CRC patients.

A Machine Learning Approach Using [18F]FDG PET-Based Radiomics for Prediction of Tumor Grade and Prognosis in Pancreatic Neuroendocrine Tumor.

PURPOSE: We sought to develop and validate machine learning (ML) models for predicting tumor grade and prognosis using 2-[18F]fluoro-2-deoxy-D-glucose ([18F]FDG) positron emission tomography (PET)-based radiomics and clinical features in patients with pancreatic neuroendocrine tumors (PNETs). PROCEDURES: A total of 58 patients with PNETs who underwent pretherapeutic [18F]FDG PET/computed tomography (CT) were retrospectively enrolled. PET-based radiomics extracted from segmented tumor and clinical features were selected to develop prediction models by the least absolute shrinkage and selection operator feature selection method. The predictive performances of ML models using neural network (NN) and random forest algorithms were compared by the areas under the receiver operating characteristic curves (AUROCs) and validated by stratified five-fold cross validation. RESULTS: We developed two separate ML models for predicting high-grade tumors (Grade 3) and tumors with poor prognosis (disease progression within two years). The integrated models consisting of clinical and radiomic features with NN algorithm showed the best performances than the other models (stand-alone clinical or radiomics models). The performance metrics of the integrated model by NN algorithm were AUROC of 0.864 in the tumor grade prediction model and AUROC of 0.830 in the prognosis prediction model. In addition, AUROC of the integrated clinico-radiomics model with NN was significantly higher than that of tumor maximum standardized uptake model in predicting prognosis (P < 0.001). CONCLUSIONS: Integration of clinical features and [18F]FDG PET-based radiomics using ML algorithms improved the prediction of high-grade PNET and poor prognosis in a non-invasive manner.

Cluster analysis of autoencoder-extracted FDG PET/CT features identifies multiple myeloma patients with poor prognosis.

F-18 fluorodeoxyglucose positron emission tomography/computed tomography (FDG PET/CT) is a robust imaging modality used for staging multiple myeloma (MM) and assessing treatment responses. Herein, we extracted features from the FDG PET/CT images of MM patients using an artificial intelligence autoencoder algorithm that constructs a compressed representation of input data. We then evaluated the prognostic value of the image-feature clusters thus extracted. Conventional image parameters including metabolic tumor volume (MTV) were measured on volumes-of-interests (VOIs) covering only the bones. Features were extracted with the autoencoder algorithm on bone-covering VOIs. Supervised and unsupervised clustering were performed on image features. Survival analyses for progression-free survival (PFS) were performed for conventional parameters and clusters. In result, supervised and unsupervised clustering of the image features grouped the subjects into three clusters (A, B, and C). In multivariable Cox regression analysis, unsupervised cluster C, supervised cluster C, and high MTV were significant independent predictors of worse PFS. Supervised and unsupervised cluster analyses of image features extracted from FDG PET/CT scans of MM patients by an autoencoder allowed significant and independent prediction of worse PFS. Therefore, artificial intelligence algorithm-based cluster analyses of FDG PET/CT images could be useful for MM risk stratification.

A Machine Learning Approach Using PET/CT-based Radiomics for Prediction of PD-L1 Expression in Non-small Cell Lung Cancer.

BACKGROUND/AIM: We explored the prediction of programmed cell death ligand 1 (PD-L1) expression level in non-small cell lung cancer using a machine learning approach with positron emission tomography/computed tomography (PET/CT)-based radiomics. PATIENTS AND METHODS: A total of 312 patients (189 adenocarcinomas, 123 squamous cell carcinomas) who underwent F-18 fluorodeoxyglucose PET/CT were retrospectively analysed. Imaging biomarkers with 46 CT and 48 PET radiomic features were extracted from segmented tumours on PET and CT images using the LIFEx package. Radiomic features were ranked, and the top five best feature subsets were selected using the Gini index based on associations with PD-L1 expression in at least 50% of tumour cells. The areas under the receiver operating characteristic curves (AUCs) of binary classifications afforded by several machine learning algorithms (random forest, neural network, Naïve Bayes, logistic regression, adaptive boosting, stochastic gradient descent, support vector machine) were compared. The model performances were tested by 10-fold cross validation. RESULTS: We developed and validated a PET/CT-based radiomic model predicting PD-L1 expression levels in lung cancer. Long run high grey-level emphasis, homogeneity, mean Hounsfield unit, long run emphasis from CT, and maximum standardised uptake value from PET were the five best feature subsets for positive PD-L1 expression. The Naïve Bayes model (AUC=0.712), with a sensitivity of 75.3% and specificity of 58.2%, outperformed all other classifiers. It was followed by the neural network model (AUC=0.711), random forest (AUC=0.700), logistic regression (AUC=0.673) and adaptive boosting (AUC=0.604). CONCLUSION: PET/CT-based radiomic features may help clinicians identify tumours with positive PD-L1 expression in a non-invasive manner using machine learning algorithms.

The Role of Preoperative 18F-fluorodeoxyglucose Positron Emission Tomography/Computed Tomography in Retroperitoneal Sarcoma.

18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) was used to predict pathologic grades based on the maximum standardized uptake value (SUVmax) in soft tissue sarcoma and bone sarcoma. In retroperitoneal sarcoma (RPS), the effectiveness of PET was not well known. This study was designed to investigate the association of SUVmax with histopathologic grade and evaluate the usefulness of 18F-FDG PET/CT before operation. Patients at Samsung Medical Center undergoing primary surgery for retroperitoneal sarcoma with preoperative 18F-FDG PET/CT imaging between January 2001 and February 2020 were investigated. The relationship between SUVmax and histologic features was assessed. The association of SUVmax with overall survival (OS), local recurrence (LR), and distant metastasis (DM) were studied. Of the total 129 patients, the most common histologic subtypes were liposarcoma (LPS; 68.2%) and leiomyosarcoma (LMS; 15.5%). The median SUVmax was 4.5 (range, 1- 29). Moreover, SUVmax was correlated with tumor grade (p < 0.001, Spearman coefficient; 0.627) and mitosis (p < 0.001, Spearman coefficient; 0.564) and showed a higher value in LMS (12.04 ± 6.73) than in dedifferentiated liposarcoma (DDLPS; 6.32 ± 4.97, p = 0.0054). SUVmax was correlated with pathologic parameters (tumor grade and mitosis) in RPS and was higher in the LMS group than the DDLPS group. The optimal SUVmax threshold to distinguish high tumor grade was 4.8. Those with a SUVmax greater than the threshold showed poor prognosis regarding OS, LR, and DM (p < 0.001).

Metabolism-Associated Gene Signatures for FDG Avidity on PET/CT and Prognostic Validation in Hepatocellular Carcinoma.

INTRODUCTION: The prognostic value of F-18 fluorodeoxyglucose positron emission tomography/computed tomography (FDG PET/CT) in hepatocellular carcinoma (HCC) was established in previous reports. However, there is no evidence suggesting the prognostic value of transcriptomes associated with tumor FDG uptake in HCC. It was aimed to elucidate metabolic genes and functions associated with FDG uptake, followed by assessment of those prognostic value. METHODS: Sixty HCC patients with Edmondson-Steiner grade II were included. FDG PET/CT scans were performed before any treatment. RNA sequencing data were obtained from tumor and normal liver tissue. Associations between each metabolism-associated gene and tumor FDG uptake were investigated by Pearson correlation analyses. A novel score between glucose and lipid metabolism-associated gene expression was calculated. In The Cancer Genome Atlas Liver Hepatocellular Carcinoma dataset, the prognostic power of selected metabolism-associated genes and a novel score was evaluated for external validation. RESULTS: Nine genes related to glycolysis and the HIF-1 signaling pathway showed positive correlations with tumor FDG uptake; 21 genes related to fatty acid metabolism and the PPAR signaling pathway demonstrated negative correlations. Seven potential biomarker genes, PFKFB4, ALDOA, EGLN3, EHHADH, GAPDH, HMGCS2, and ENO2 were identified. A metabolic gene expression balance score according to the dominance between glucose and lipid metabolism demonstrated good prognostic value in HCC. CONCLUSIONS: The transcriptomic evidence of this study strongly supports the prognostic power of FDG PET/CT and indicates the potential usefulness of FDG PET/CT imaging biomarkers to select appropriate patients for metabolism-targeted therapy in HCC.

Predictive role of lymphoscintigraphy undergoing lymphovenous anastomosis in patients with lower extremity lymphedema: a preliminary study.

BACKGROUND: We investigated whether preoperative lymphoscintigraphy could predict the treatment response of unilateral lymphovenous anastomosis (LVA) in patients with lower extremity lymphedema. MATERIALS AND METHODS: A total of 17 patients undergoing lymphoscintigraphy subsequent to LVA was included. As qualitative lymphoscintigraphic indicators, ilioinguinal lymph node uptake, main lymphatic vessel, collateral vessel, and four types of dermal backflow patterns (absent; distal only; proximal only; whole lower limb) were evaluated. Lymph node uptake ratio, extremity uptake ratio, and injection site clearance ratio were obtained as quantitative lymphoscintigraphic indicators at 1 and 2-h after injection. To evaluate therapy response, the volume difference ratio of the whole lower limb at 3 months (early response) and 1 year (late response) was measured. Volume difference ratios (continuous variable and binary variable with a cut-off value of zero) were compared according to the lymphoscintigraphic variables. RESULTS: The group with whole lower limb dermal backflow had a greater volume change than the other groups (p = 0.047). The group with dermal backflow in the whole lower limb OR only in the distal part had a higher rate of volume reduction than the group with dermal backflow only in the proximal part OR absent (p = 0.050). The 2-h extremity uptake ratio was the only indicator that positively correlated with early and late volume difference ratio (p = 0.016, p = 0.001). The rate of volume decrease at 1 year was high in patients with high 2-h extremity uptake ratio (p = 0.027). As the amount of dermal backflow increases, the postoperative therapeutic effect increases (p = 0.040). CONCLUSIONS: Preoperative lymphoscintigraphy is useful to predict both early and late therapy response in patients with lower extremity lymphedema undergoing LVA. Both dermal backflow pattern and extremity uptake ratio may be predictive lymphoscintigraphic indicators.

Performance Evaluation of a Deep Learning System for Differential Diagnosis of Lung Cancer With Conventional CT and FDG PET/CT Using Transfer Learning and Metadata.

PURPOSE: We aimed to evaluate the performance of a deep learning system for differential diagnosis of lung cancer with conventional CT and FDG PET/CT using transfer learning (TL) and metadata. METHODS: A total of 359 patients with a lung mass or nodule who underwent noncontrast chest CT and FDG PET/CT prior to treatment were enrolled retrospectively. All pulmonary lesions were classified by pathology (257 malignant, 102 benign). Deep learning classification models based on ResNet-18 were developed using the pretrained weights obtained from ImageNet data set. We propose a deep TL model for differential diagnosis of lung cancer using CT imaging data and metadata with SUVmax and lesion size derived from PET/CT. The area under the receiver operating characteristic curve (AUC) of the deep learning model was measured as a performance metric and verified by 5-fold cross-validation. RESULTS: The performance metrics of the conventional CT model were generally better than those of the CT of PET/CT model. Introducing metadata with SUVmax and lesion size derived from PET/CT into baseline CT models improved the diagnostic performance of the CT of PET/CT model (AUC = 0.837 vs 0.762) and the conventional CT model (AUC = 0.877 vs 0.817). CONCLUSIONS: Deep TL models with CT imaging data provide good diagnostic performance for lung cancer, and the conventional CT model showed overall better performance than the CT of PET/CT model. Metadata information derived from PET/CT can improve the performance of deep learning systems.

Role in staging and prognostic value of pretherapeutic F-18 FDG PET/CT in patients with gastric MALT lymphoma without high-grade transformation.

The purpose of this retrospective study was to investigate the role in staging and prognostic value of pretherapeutic fluorine-18-fluorodeoxyglucose (F-18 FDG) positron emission tomography (PET)/computed tomography (CT) in patients with gastric mucosa-associated lymphoid tissue (MALT) lymphoma without high-grade transformation (HT). We retrospectively reviewed 115 consecutive patients with histopathologically confirmed gastric MALT lymphoma without HT who underwent pretherapeutic F-18 FDG PET/CT. Kaplan-Meier and Cox proportional-hazards regression analyses were used to identify independent prognostic factors for disease free survival (DFS) among 13 clinical parameters and three PET parameters. In two of 115 patients (1.7%), the clinical stage appeared higher according to F-18 FDG PET/CT. In univariate analysis, Helicobacter pylori (HP) infection (P = 0.023), treatment modality (P < 0.001), and stage including PET/CT (P = 0.015) were significant prognostic factors for DFS. In multivariate analysis, only treatment modality was an independent prognostic factor (P = 0.003). In conclusion, F-18 FDG PET/CT played an important role in enabling upstaging of patients with gastric MALT lymphoma without HT. F-18 FDG PET/CT may have a prognostic role in gastric MALT lymphoma without HT by contributing to better staging.

Machine learning-based diagnostic method of pre-therapeutic 18F-FDG PET/CT for evaluating mediastinal lymph nodes in non-small cell lung cancer.

OBJECTIVES: We aimed to find the best machine learning (ML) model using 18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) for evaluating metastatic mediastinal lymph nodes (MedLNs) in non-small cell lung cancer, and compare the diagnostic results with those of nuclear medicine physicians. METHODS: A total of 1329 MedLNs were reviewed. Boosted decision tree, logistic regression, support vector machine, neural network, and decision forest models were compared. The diagnostic performance of the best ML model was compared with that of physicians. The ML method was divided into ML with quantitative variables only (MLq) and adding clinical information (MLc). We performed an analysis based on the 18F-FDG-avidity of the MedLNs. RESULTS: The boosted decision tree model obtained higher sensitivity and negative predictive values but lower specificity and positive predictive values than the physicians. There was no significant difference between the accuracy of the physicians and MLq (79.8% vs. 76.8%, p = 0.067). The accuracy of MLc was significantly higher than that of the physicians (81.0% vs. 76.8%, p = 0.009). In MedLNs with low 18F-FDG-avidity, ML had significantly higher accuracy than the physicians (70.0% vs. 63.3%, p = 0.018). CONCLUSION: Although there was no significant difference in accuracy between the MLq and physicians, the diagnostic performance of MLc was better than that of MLq or of the physicians. The ML method appeared to be useful for evaluating low metabolic MedLNs. Therefore, adding clinical information to the quantitative variables from 18F-FDG PET/CT can improve the diagnostic results of ML. KEY POINTS: • Machine learning using two-class boosted decision tree model revealed the highest value of area under curve, and it showed higher sensitivity and negative predictive values but lower specificity and positive predictive values than nuclear medicine physicians. • The diagnostic results from machine learning method after adding clinical information to the quantitative variables improved accuracy significantly than nuclear medicine physicians. • Machine learning could improve the diagnostic significance of metastatic mediastinal lymph nodes, especially in mediastinal lymph nodes with low 18F-FDG-avidity.

Prognostic value of LI-RADS category on gadoxetic acid-enhanced MRI and 18F-FDG PET-CT in patients with primary liver carcinomas.

OBJECTIVES: To evaluate the postoperative prognostic value of the Liver Imaging Reporting and Data System (LI-RADS) category on gadoxetic acid-enhanced MRI and 18F-fluorodeoxyglucose PET-CT in patients with primary liver carcinomas (PLCs). METHODS: A total of 189 patients with chronic liver disease and surgically proven single PLC (42 intrahepatic cholangiocarcinomas and 21 combined hepatocellular-cholangiocarcinomas and 126 hepatocellular carcinomas [2:1 matching to non-HCC malignancies]) were retrospectively evaluated with gadoxetic acid-enhanced MRI and PET-CT. Two independent reviewers assigned an LI-RADS category for each observation. The tumor-to-liver standardized uptake value ratio (TLR) was calculated. The overall survival (OS), recurrence-free survival (RFS), and the associated factors were evaluated. RESULTS: In multivariable analysis, LI-RADS category (LR-4 or LR-5 [LR-4/5] vs. LR-M; OS, hazard ratio [HR] 2.24, p = 0.006; RFS, HR 1.61, p = 0.028) and TLR (low, < 2.3 vs. high, ≥ 2.3; OS, HR 2.09, p = 0.014; RFS, HR 2.17, p < 0.001) were the independent factors for OS and RFS. For the LR-M group, the high TLR group showed lower OS and RFS rates than the low TLR group (OS, p = 0.008; RFS, p < 0.001). For the LR-4/5 group, the OS and RFS rates were not significantly different between the high TLR and low TLR groups (both p > 0.05). CONCLUSIONS: Both LI-RADS category on MRI and TLR on PET-CT are associated with the postoperative prognosis of PLCs. The prognosis of PLCs classified as LR-M can be further stratified according to the TLR group, but not for the PLCs classified as LR-4/5. KEY POINTS: • The LI-RADS category (LR-4/5 vs. LR-M) and tumor-to-liver standardized uptake value ratio (TLR, low vs. high) were independent factors for postoperative prognosis of primary liver carcinomas (PLCs). • For PLCs classified as LR-M, the TLR group helps stratify the postoperative prognosis of PLCs, with the high TLR group having a poor prognosis and the low TLR group having a better prognosis (p = 0.008 for OS and p < 0.001 for RFS). • For PLCs classified as LR-4/5, the OS and RFS rates were not significantly different between the high TLR and low TLR groups (both p > 0.05).

Comparison of the prognostic values of 18F-fluorodeoxyglucose parameters from colon and non-colon sites of involvement in diffuse large B-cell lymphoma of the colon.

We examined the prognostic values of 18F-fluorodeoxyglucose (18F-FDG) parameters from colon, non-colon, and total lesions in patients with diffuse large B-cell lymphoma (DLBCL) of the colon. Positron emission tomography/computed tomography (PET/CT) in 50 patients was retrospectively analyzed for maximum standardized uptake value (SUVmax), metabolic tumor volume (MTV) and total lesion glycolysis (TLG). During follow-up, 13 patients showed progression and 9 died from disease. Receiver operating characteristics (ROC) curve analysis showed that non-colon and total lesion MTV and TLG and colon lesion SUVmax were associated with progression or death. Significant univariate predictors of poor event-free survival (EFS) included stage III-IV, greater International Prognostic Index (IPI) score, no resection, high non-colon lesion SUVmax, MTV and TLG, and high total lesion MTV and TLG. Univariate predictors of poor overall survival (OS) included stage III-IV, greater IPI score, no resection, high non-colon lesion MTV and TLG, high total lesion MTV, and low colon lesion SUVmax. Multivariate analysis revealed that high non-colon lesion TLG was independently associated with poor EFS and OS. Low colon lesion SUVmax was also independently associated with poor OS. In a subgroup with colon-dominant involvement (n = 35), non-colon lesion MTV and TLG were associated with events and non-colon lesion MTV was associated with patient death. Univariate analysis showed that high non-colon lesion MTV was a significant predictor of poor EFS and OS, while non-colon lesion TLG was a significant predictor of poor OS. Thus, volumetric FDG parameters of non-colon lesions offered significant prognostic information in patients with DLBCL of the colon.

Development and Validation of a Deep Learning System for Diagnosing Glaucoma Using Optical Coherence Tomography.

This study aimed to develop and validate a deep learning system for diagnosing glaucoma using optical coherence tomography (OCT). A training set of 1822 eyes (332 control, 1490 glaucoma) with 7288 OCT images, an internal validation set of 425 eyes (104 control, 321 glaucoma) with 1700 images, and an external validation set of 355 eyes (108 control, 247 glaucoma) with 1420 images were included. Deviation and thickness maps of retinal nerve fiber layer (RNFL) and ganglion cell-inner plexiform layer (GCIPL) analyses were used to develop the deep learning system for glaucoma diagnosis based on the visual geometry group deep convolutional neural network (VGG-19) model. The diagnostic abilities of deep learning models using different OCT maps were evaluated, and the best model was compared with the diagnostic results produced by two glaucoma specialists. The glaucoma-diagnostic ability was highest when the deep learning system used the RNFL thickness map alone (area under the receiver operating characteristic curve (AUROC) 0.987), followed by the RNFL deviation map (AUROC 0.974), the GCIPL thickness map (AUROC 0.966), and the GCIPL deviation map (AUROC 0.903). Among combination sets, use of the RNFL and GCIPL deviation map showed the highest diagnostic ability, showing similar results when tested via an external validation dataset. The inclusion of the axial length did not significantly affect the diagnostic performance of the deep learning system. The location of glaucomatous damage showed generally high level of agreement between the heatmap and the diagnosis of glaucoma specialists, with 90.0% agreement when using the RNFL thickness map and 88.0% when using the GCIPL thickness map. In conclusion, our deep learning system showed high glaucoma-diagnostic abilities using OCT thickness and deviation maps. It also showed detection patterns similar to those of glaucoma specialists, showing promising results for future clinical application as an interpretable computer-aided diagnosis.

Correction to: Imaging phenotype using 18F-fluorodeoxyglucose positron emission tomography-based radiomics and genetic alterations of pancreatic ductal adenocarcinoma.

After publication of this article we received a request from Dr. Jong Kyun Lee to have his name removed from the author list as he felt he did not fully meet the authorship criteria. The original version of this article was inadvertently published with an incorrect inclusion period of study.

Imaging phenotype using 18F-fluorodeoxyglucose positron emission tomography-based radiomics and genetic alterations of pancreatic ductal adenocarcinoma.

PURPOSE: This study aimed to determine if major gene mutations including in KRAS, SMAD4, TP53, and CDKN2A were related to imaging phenotype using 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET)-based radiomics in patients with pancreatic ductal adenocarcinoma (PDAC). METHODS: Data on 48 PDAC patients with pretreatment FDG PET/CT who underwent genomic analysis of their tumor tissue were retrospectively analyzed. A total of 35 unique quantitative radiomic features were extracted from PET images, including imaging phenotypes such as pixel intensity, shape, and textural features. Targeted exome sequencing using a customized cancer panel was used for genomic analysis. To assess the predictive performance of genetic alteration using PET-based radiomics, areas under the receiver operating characteristic curve (AUC) were used. RESULTS: Mutation frequencies were KRAS 87.5%, TP53 70.8%, SMAD4 25.0%, and CDKN2A 18.8%. KRAS gene mutations were significantly associated with low-intensity textural features, including long-run emphasis (AUC = 0.806), zone emphasis (AUC = 0.794), and large-zone emphasis (AUC = 0.829). SMAD4 gene mutations showed significant relationships with standardized uptake value skewness (AUC = 0.727), long-run emphasis (AUC = 0.692), and high-intensity textural features such as run emphasis (AUC = 0.775), short-run emphasis (AUC = 0.736), zone emphasis (AUC = 0.750), and short-zone emphasis (AUC = 0.725). No significant associations were seen between the imaging phenotypes and genetic alterations in TP53 and CDKN2A. CONCLUSION: Genetic alterations of KRAS and SMAD4 had significant associations with FDG PET-based radiomic features in PDAC. PET-based radiomics may help clinicians predict genetic alteration status in a noninvasive way.

Tumor SUVs on 18F-FDG PET/CT and Aggressive Pathological Features in Esophageal Squamous Cell Carcinoma.

PURPOSE: Considerable discrepancies are observed between clinical staging and pathological staging after surgical resection in patients with esophageal squamous cell carcinoma (ESCC). In this study, we examined the relationships between tumor SUVs on FDG PET/CT and aggressive pathological features in resected ESCC patients. METHODS: A total of 220 patients with surgically resected clinical stage I-II ESCC without neoadjuvant treatment were retrospectively analyzed. SUVmax of the primary tumor was measured on pretreatment FDG PET/CT. Pathological features included depth of tumor invasion, lymph node metastasis, tumor differentiation, lymphatic vessel tumor embolus, perineural invasion, Ki-67 index, and p53 protein expression. Receiver operating characteristic curve analysis was used to determine an optimal cutoff of SUVmax to predict pathologically advanced disease. Differences in pathological features associated with SUVmax were examined by t test or χ test. RESULTS: The number of patients upstaged from clinical stage I-II to pathological stage III-IV was 43 (19.5%). Receiver operating characteristic curve analysis showed that the optimal cutoff SUVmax of 4.0 had good performance for predicting locally advanced disease (area under the receiver operating characteristic curve = 0.844, P < 0.001). Higher tumor SUVmax was significantly associated with advanced depth of tumor invasion (deeper than submucosa, P < 0.001), positive lymph node metastasis (P < 0.001), presence of lymphatic vessel tumor embolus (P < 0.001), presence of perineural invasion (P < 0.001), higher Ki-67 index (P = 0.025), and poor tumor differentiation (P = 0.039). CONCLUSIONS: SUVmax measured on pretreatment FDG PET/CT is significantly associated with aggressive pathological features and may help clinicians identify patients at risk of advanced disease.

Serum uric acid in asymptomatic adults is weakly associated with carotid artery FDG uptake but not intima-media thickness.

BACKGROUND: This study investigated the association of serum uric acid (UA) with carotid fluoro-2-deoxyglucose (FDG) uptake as a marker of inflammatory atherosclerosis. METHODS AND RESULTS: In this cross-sectional retrospective study of 970 otherwise healthy adults, subjects in the greater serum UA quartiles had higher triglyceride (P < .001), lower high-density lipoprotein cholesterol (P < .05), and lower estimated GFR (P < .001). Mean and maximum Target-to-background ratios (TBRs) of carotid FDG uptake measured by positron emission tomography were significantly increased across greater serum UA quartiles (1.35 and 1.57 for Q1, 1.38 and 1.60 for Q2, 1.39 and 1.62 for Q3, and 1.39 and 1.61 for Q4; P = .001 and < .001). Carotid intima-media thickness was not different. Serum UA showed weak but significant correlations with estimated GFR (P < .001), and with mean (P < .001) and maximum carotid TBR (P = .004). Serum UA correlated with mean TBR in male (P = .008) and female subjects (P = .011), in high (≥ 70; P = .015) and low estimated GFR (< 70; P = .035), and in normotensive (P = .001) but not in hypertensive subjects. CONCLUSIONS: Elevated serum UA in asymptomatic adults is associated with increased carotid FDG uptake, which suggests a potential role of UA in carotid inflammatory atherosclerosis.

A Machine-Learning Approach Using PET-Based Radiomics to Predict the Histological Subtypes of Lung Cancer.

PURPOSE: We sought to distinguish lung adenocarcinoma (ADC) from squamous cell carcinoma using a machine-learning algorithm with PET-based radiomic features. METHODS: A total of 396 patients with 210 ADCs and 186 squamous cell carcinomas who underwent FDG PET/CT prior to treatment were retrospectively analyzed. Four clinical features (age, sex, tumor size, and smoking status) and 40 radiomic features were investigated in terms of lung ADC subtype prediction. Radiomic features were extracted from the PET images of segmented tumors using the LIFEx package. The clinical and radiomic features were ranked, and a subset of useful features was selected based on Gini coefficient scores in terms of associations with histological class. The areas under the receiver operating characteristic curves (AUCs) of classifications afforded by several machine-learning algorithms (random forest, neural network, naive Bayes, logistic regression, and a support vector machine) were compared and validated via random sampling. RESULTS: We developed and validated a PET-based radiomic model predicting the histological subtypes of lung cancer. Sex, SUVmax, gray-level zone length nonuniformity, gray-level nonuniformity for zone, and total lesion glycolysis were the 5 best predictors of lung ADC. The logistic regression model outperformed all other classifiers (AUC = 0.859, accuracy = 0.769, F1 score = 0.774, precision = 0.804, recall = 0.746) followed by the neural network model (AUC = 0.854, accuracy = 0.772, F1 score = 0.777, precision = 0.807, recall = 0.750). CONCLUSIONS: A machine-learning approach successfully identified the histological subtypes of lung cancer. A PET-based radiomic features may help clinicians improve the histopathologic diagnosis in a noninvasive manner.