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 Significance of 18F-FDG PET/CT Radiomics in Patients With Resectable Pancreatic Ductal Adenocarcinoma Undergoing Curative Surgery.

PURPOSE: This study aimed to investigate the prognostic significance of PET/CT radiomics to predict overall survival (OS) in patients with resectable pancreatic ductal adenocarcinoma (PDAC). METHODS: We enrolled 627 patients with resectable PDAC who underwent preoperative 18F-FDG PET/CT and subsequent curative surgery. Radiomics analysis of the PET/CT images for the primary tumor was performed using the Chang-Gung Image Texture Analysis toolbox. Radiomics features were subjected to least absolute shrinkage and selection operator (LASSO) regression to select the most valuable imaging features of OS. The prognostic significance was evaluated by Cox proportional hazards regression analysis. Conventional PET parameters and LASSO score were assessed as predictive factors for OS by time-dependent receiver operating characteristic curve analysis. RESULTS: During a mean follow-up of 28.8 months, 378 patients (60.3%) died. In the multivariable Cox regression analysis, tumor differentiation, resection margin status, tumor stage, and LASSO score were independent prognostic factors for OS (HR, 1.753, 1.669, 2.655, and 2.946; all P < 0.001, respectively). The time-dependent receiver operating characteristic curve analysis showed that the LASSO score had better predictive performance for OS than conventional PET parameters. CONCLUSION: The LASSO score using the 18F-FDG PET/CT radiomics of the primary tumor was the independent prognostic factor for predicting OS in patients with resectable PDAC and may be helpful in determining therapeutic and follow-up plans for these patients.

Dynamic blood flow imaging with 99mTc-hydroxymethylene diphosphonate as a therapeutic response marker in patients with Raynaud's phenomenon.

We evaluated the predictive value of dynamic blood flow scintigraphy with 99mTc-HDP (hydroxymethylene diphosphonate) for therapeutic response in patients with Raynaud's phenomenon (RP). Eighty patients who underwent dynamic blood flow scintigraphy using the one-hand chilling method were enrolled. We analyzed the quantitative variables as the ratio of chilled fingers to ambient fingers (CAfinger), that of the chilled hand to ambient hand (CAhand), and that of chilled fingers to ambient palm (FPR) (CAFPR) at 15 and 30 s after 99mTc-HDP bolus injection. Total cumulative radioactivity counts for 180 s were obtained. We evaluated the clinical utility of these quantitative parameters with other clinical variables, including RP severity, therapeutic compliance, types of RP, and scintigraphic interpretation of findings in patients with RP. Fifty-two patients showed poor therapeutic response. There were significant differences between good- and poor-therapeutic responder groups in RP intensity (p = 0.003), CAfinger15s (p = 0.008), CAfinger30s (p = 0.002), CAfinger180s (p = 0.011), CAhand15s (p = 0.008), CAhand30s (p = 0.007), CAhand180s (p = 0.017), CAFPR30s (p = 0.004), and CAFPR180s (p = 0.002). After multivariate logistic regression analysis, only CAfinger30s (p = 0.002) had an independent predictive value of the therapeutic response. 99mTc-HDP dynamic blood flow scintigraphy could be helpful in predicting the therapeutic response in patients with RP.

Pulmonary and Liver Toxocariasis Mimicking Metastatic Tumors in a Patient with Colon Cancer.

Toxocariasis is an uncommon cause of multiple cavitary lung lesions and an ill-defined liver lesion. We herein report a patient with lung and liver toxocariasis, which mimicked metastatic lesions of colon cancer on 18F-FDG PET-CT and chest and abdominal CT performed for cancer staging after diagnosis of colon cancer. The patient was diagnosed with lung and liver toxocariasis by a positive enzyme-linked immunosorbent assay. Lung toxocariasis may occur as multiple cavitary lung lesions, and liver toxocariasis may appear as a solitary ill-defined nodule, which may be misdiagnosed as metastatic tumors. Clinicians should consider toxocariasis when multiple cavitary lung lesions and a solitary ill-defined focal liver lesion are detected, especially in a patient with cancer.

18F-FDG PET/CT and Whole-Body Bone Scan Findings in Gorlin-Goltz Syndrome.

Gorlin-Goltz syndrome (basal cell nevus syndromes) is an uncommon, autosomal dominant inherited disorder characterized by developing basal cell carcinomas from a young age. Other distinct clinical features include keratocystic odontogenic tumors, dyskeratotic palmar and plantar pitting, and skeletal abnormalities. Clinicopathological findings of the syndrome are very diverse, and many symptoms manifest during a certain period of life. We present the compelling whole-body bone scan and 18F-FDG PET/CT findings in a 32-year-old man with odontogenic keratocyst, early-onset basal cell carcinoma, multiple ectopic calcifications in extremities, calcified falx cerebri, spinal scoliosis, macrocephaly, and ocular hypertelorism.

Enhanced Computed Tomography and 18F-fluorodeoxyglucose Positron Emission Tomography/Computed Tomography in the Uncommon Histiocytic Sarcoma of Small Intestine Arising after Gastric Large B-Cell Lymphoma.

Histiocytic sarcoma (HS) is an extremely rare and aggressive malignant neoplasm of hematopoietic origin that shows morphologic and immunophenotypic evidence of histiocytic differentiation. In approximately 25% of the cases, presumed transdifferentiation of a preexisting hematolymphoid disorder can be demonstrated. Various extranodal sites, particularly the gastrointestinal tract, soft tissue, skin, and spleen, can be involved. Enhanced CT and FDG PET/CT findings of extranodal histiocytic sarcoma have been barely reported. We present a case with extranodal HS originating in the small intestine after gastric large B-cell lymphoma, mistaken for prostate cancer metastasis in a 76-year-old man.

A Case Report of Early-Onset Alzheimer's Disease Using 18F-FDG PET and 18F-FBB PET.

We describe a 40-year-old female patient who presented with sleep disturbance, intermittent headache, and gradual subjective cognitive decline. 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) showed mild FDG hypometabolism in bilateral parietal and temporal lobes. However, 18F-florbetaben (FBB) amyloid PET revealed diffuse amyloid retention in the lateral temporal cortex, frontal cortex, posterior cingulate cortex/precuneus, parietal cortex, and cerebellum. This finding supports the clinical significance of amyloid imaging in diagnostic work-up of early-onset Alzheimer's disease (EOAD).

Striatal Dopaminergic Loss and Dysphagia in Parkinson Disease.

PURPOSE: To better understand the development of dysphagia in patients with Parkinson disease (PD) and to identify possible neuromodulatory target regions of dysphagia, we studied the striatal dopamine transporter (DAT) availability distribution by subtype of dysphagia. METHODS: In this retrospective cross-sectional study, patients with PD who underwent videofluoroscopic swallowing study and N-(3-[18F]fluoropropyl)-2ß-carbon ethoxy-3ß-(4-iodophenyl) nortropane (18F-FP-CIT) PET at intervals of less than 1 month were analyzed. The 14 binarized subitem scores of the Videofluoroscopic Dysphagia Scale were analyzed using a voxel-wise Firth's penalized binary logistic regression model, adjusting for age and disease duration at videofluoroscopic swallowing study. RESULTS: Sixty-five patients with PD were finally included. Striatal mapping showed association of decreased DAT availability with 5 subitems with 1 or more clusters surviving the statistical threshold: 1 oral phase and 4 pharyngeal phase subitems. The overlap maps created by superimposing clusters for all 5 statistically significant subitems revealed associations of dysphagia in PD with decreased DAT availability in the bilateral ventral striatum. Of these, 4 subitems belonging to the pharyngeal phase-specific dysphagia were additionally found to be related to dopaminergic degeneration of the bilateral anterior-to-posterior caudate and ventral striatum. CONCLUSIONS: These findings suggest that subitem/phase-specific striatal subregional dopaminergic depletion may explain the dysphagia of PD. This dopaminergic degeneration of striatal subregions specific to the phases of dysphagia may serve as a potential target for neuromodulatory brain stimulation through stimulation of cortices functionally connected.

Association of dysphagia with altered brain glucose metabolism in Parkinson's disease.

AIMS: Dysphagia is a major clinical concern in Parkinson's disease (PD). However, the relationship between the development of phase-specific dysphagia and the regional brain glucose metabolism remains unclear. Our objective was to investigate the distributions of brain glucose metabolism specific to oral and pharyngeal phases of dysphagia in PD. METHODS: In this retrospective cross-sectional study, patients with PD who underwent videofluoroscopic swallowing study (VFSS) and 18 F-fluorodeoxy-glucose positron emission tomography at intervals of <1 month were included. Each swallow was assessed by the binarized Videofluoroscopic Dysphagia Scale with 14 subitems, seven each for the oral and pharyngeal phases. Metabolism mapping was performed by superimposing significant clusters of subitems belonging to each of the two phases using voxel-wise Firth's penalized binary logistic regression model, adjusting for age and PD duration at VFSS. RESULTS: Eighty-two patients with PD who met the inclusion criteria were included in the analysis. The oral phase dysphagia-specific overlap map showed hypermetabolism in the right inferior temporal gyrus, bilateral cerebellum, superior frontal gyrus, and anterior cingulate cortices. Hypometabolism in the bilateral orbital and triangular parts of the inferior to middle frontal gyrus was also correlated with the occurrence of oral phase dysphagia. The development of pharyngeal phase dysphagia was related to hypermetabolism of posterior aspects of the bilateral parietal lobes, cerebellum, and hypometabolism of the mediodorsal aspects of anterior cingulate and middle to superior frontal gyri. CONCLUSION: These findings suggest that phase-specific distribution of brain glucose metabolism may explain the dysphagia of PD.

Radiomics Analysis of 18F-FDG PET/CT for Prognosis Prediction in Patients with Stage III Non-Small Cell Lung Cancer Undergoing Neoadjuvant Chemoradiation Therapy Followed by Surgery.

We investigated the prognostic significance of radiomic features from 18F-FDG PET/CT to predict overall survival (OS) in patients with stage III NSCLC undergoing neoadjuvant chemoradiation therapy followed by surgery. We enrolled 300 patients with stage III NSCLC who underwent PET/CT at the initial work-up (PET1) and after neoadjuvant concurrent chemoradiotherapy (PET2). Radiomic primary tumor features were subjected to LASSO regression to select the most useful prognostic features of OS. The prognostic significance of the LASSO score and conventional PET parameters was assessed by Cox proportional hazards regression analysis. In conventional PET parameters, metabolic tumor volume (MTV) and total lesion glycolysis (TLG) of each PET1 and PET2 were significantly associated with OS. In addition, both the PET1-LASSO score and the PET2-LASSO score were significantly associated with OS. In multivariate Cox regression analysis, only the PET2-LASSO score was an independently significant factor for OS. The LASSO score showed better predictive performance for OS regarding the time-dependent receiver operating characteristic curve and decision curve analysis than conventional PET parameters. Radiomic features from PET/CT were an independent prognostic factor for the estimation of OS in stage III NSCLC. The newly developed LASSO score using radiomic features showed better prognostic results for individualized OS estimation than conventional PET parameters.

Differential diagnosis of patients with atypical Parkinsonian syndrome using 18F-FDG and 18F-FP CIT PET: A report of five cases.

We describe 5 cases of patients who presented atypical parkinsonian syndrome (APS), including gait disturbance, postural instability, decreasing facial expression, dyskinesia, and subjective cognitive impairment. The patients underwent 18F-FP-CIT PET and 18F-FDG PET consecutively for differential diagnosis of APS. Through PET imaging examination, it was possible to offer a suggestive diagnosis and determine individual strategic management for patients with APS.

A Case Report of a Gluteus Hematoma Detected on 99mTc-MDP Bone Scan.

This is a case report of a gluteal hematoma detected on 99mTc-methylene diphosphonate (MDP) whole-body bone scan in a 77-year-old male who had experienced a road traffic accident.

Visualization of Dialysis-Related Amyloid Arthropathy on 18F-FDG PET-CT Scan.

We report a case of dialysis-related amyloid arthropathy in a patient with end-stage renal disease. It presented in our patient as moderately increased FDG uptake in the amyloid deposition in the periarticular tissues and eroding into adjacent bones.

Septic Pulmonary Emboli Detected by 18F-FDG PET/CT in a Patient with Central Venous Catheter-Related Staphylococcus aureus Bacteremia.

We describe a case of 18F-FDG PET/CT detecting septic pulmonary emboli in a patient with Staphylococcus aureus catheter-related bloodstream infection (CRBSI). The patient, who had an implantable venous access port for chemotherapy, underwent 18F-FDG PET/CT to diagnose unsuspected infectious foci. The PET/CT examination made it possible to offer a suggestive diagnosis and yielded metastatic infectious foci.

Diagnostic Performance for Differential Diagnosis of Atypical Parkinsonian Syndromes from Parkinson's Disease Using Quantitative Indices of 18F-FP-CIT PET/CT.

We are aimed to evaluate the diagnostic performances of quantitative indices obtained from dual-phase 18F-FP-CIT PET/CT for differential diagnosis of atypical parkinsonian syndromes (APS) from Parkinson's disease (PD). We analyzed 172 subjects, including 105 non-Parkinsonism, 26 PD, 8 PSP, 1 CBD, 8 MSA-P, 9 MSA-C, and 15 DLB retrospectively. Two sequential PET/CT scans were acquired at 5 min and 3 h. We compared subregional binding potentials, putamen-to-caudate nucleus ratio of the binding potential, asymmetry index, and degree of washout. To differentiate APS, all BPs in both early and late phases (except late BPbrainstem) and all factors of the percent change except for putamen in APS significantly differed from PD. When a cut-off for early BPcerebellum was set as 0.79, the sensitivity, specificity (SP), positive predictive value (PPV), negative predictive value (NPV), and accuracy for differentiating APS 73.2%, 91.7%, 93.8%, 66.7%, and 80.0%. The early BPcerebellum showed significantly greater SP and PPV than the late quantitative indices. Combined criteria regarding both early and late indices exhibited only greater NPV. The quantitative indices showed high diagnostic performances in differentiating APS from PD. Our findings provide the dual-phase 18F-FP-CIT PET/CT would be useful for differentiating APS from PD.

Predictive Value of 18F-FDG PET/CT Using Machine Learning for Pathological Response to Neoadjuvant Concurrent Chemoradiotherapy in Patients with Stage III Non-Small Cell Lung Cancer.

We investigated predictions from 18F-FDG PET/CT using machine learning (ML) to assess the neoadjuvant CCRT response of patients with stage III non-small cell lung cancer (NSCLC) and compared them with predictions from conventional PET parameters and from physicians. A retrospective study was conducted of 430 patients. They underwent 18F-FDG PET/CT before initial treatment and after neoadjuvant CCRT followed by curative surgery. We analyzed texture features from segmented tumors and reviewed the pathologic response. The ML model employed a random forest and was used to classify the binary outcome of the pathological complete response (pCR). The predictive accuracy of the ML model for the pCR was 93.4%. The accuracy of predicting pCR using the conventional PET parameters was up to 70.9%, and the accuracy of the physicians' assessment was 80.5%. The accuracy of the prediction from the ML model was significantly higher than those derived from conventional PET parameters and provided by physicians (p < 0.05). The ML model is useful for predicting pCR after neoadjuvant CCRT, which showed a higher predictive accuracy than those achieved from conventional PET parameters and from physicians.

Role of 11C-Methionine PET/CT in 99mTc-Sestamibi-Negative Parathyroid Adenoma: A Case Report.

We report a case of 16-year-old female primary hyperparathyroidism patient who underwent cervical ultrasonography and 99mTc-sestamibi single photon emission computed tomography/computed tomography, both of which were negative for parathyroid adenoma. Subsequent 11C-methionine positron emission tomography/CT showed positive focal uptake suggesting parathyroid adenoma, which then was confirmed pathologically.

Metastatic Pulmonary Calcification Detected on 18F-FDG PET/CT and 99mTc-MDP Bone Scan.

Metastatic calcification relates to abnormal calcification resulting from hypercalcemia and can affect soft tissues, skeletal muscle, myocardium, lungs, stomach, kidneys, and blood vessels. We describe a case of metastatic pulmonary calcification in a 71-year-old male, images with 18F-fluorodeoxyglucose (FDG) PET/CT and 99mTc- methylene diphosphonate (MDP) bone scan.

A Case of Chronic Neutrophilic Leukemia Incidentally Detected by 18F-FDG PET/CT.

Chronic neutrophilic leukemia (CNL) is a rare, potentially aggressive, myeloproliferative neoplasm. To the best of our knowledge, there are no previous reports dealing with 18F-FDG PET findings in CNL. We describe a case of CNL in a 69-year-old male, imaged with 18F-FDG PET/CT at diagnosis and during treatment.

Image Registration of 18F-FDG PET/CT Using the MotionFree Algorithm and CT Protocols through Phantom Study and Clinical Evaluation.

We evaluated the benefits of the MotionFree algorithm through phantom and patient studies. The various sizes of phantom and vacuum vials were linked to RPM moving with or without MotionFree application. A total of 600 patients were divided into six groups by breathing protocols and CT scanning time. Breathing protocols were applied as follows: (a) patients who underwent scanning without any breathing instructions; (b) patients who were instructed to hold their breath after expiration during CT scan; and (c) patients who were instructed to breathe naturally. The length of PET/CT misregistration was measured and we defined the misregistration when it exceeded 10 mm. In the phantom tests, the images produced by the MotionFree algorithm were observed to have excellent agreement with static images. There were significant differences in PET/CT misregistration according to CT scanning time and each breathing protocol. When applying the type (c) protocol, decreasing the CT scanning time significantly reduced the frequency and length of misregistrations (p < 0.05). The MotionFree application is able to correct respiratory motion artifacts and to accurately quantify lesions. The shorter time of CT scan can reduce the frequency, and the natural breathing protocol also decreases the lengths of misregistrations.