Does FDG PET-Based Radiomics Have an Added Value for Prediction of Overall Survival in Non-Small Cell Lung Cancer?

Objectives: Radiomics and machine learning are innovative approaches to improve the clinical management of NSCLC. However, there is less information about the additive value of FDG PET-based radiomics compared with clinical and imaging variables. Methods: This retrospective study included 320 NSCLC patients who underwent PET/CT with FDG at initial staging. VOIs were placed on primary tumors only. We included a total of 94 variables, including 87 textural features extracted from PET studies, SUVmax, MTV, TLG, TNM stage, histology, age, and gender. We used the least absolute shrinkage and selection operator (LASSO) regression to select variables with the highest predictive value. Although several radiomics variables are available, the added value of these predictors compared with clinical and imaging variables is still under evaluation. Three hundred and twenty NSCLC patients were included in this retrospective study and underwent 18F-FDG PET/CT at initial staging. In this study, we evaluated 94 variables, including 87 textural features, SUVmax, MTV, TLG, TNM stage, histology, age, and gender. Image-based predictors were extracted from a volume of interest (VOI) positioned on the primary tumor. The least absolute shrinkage and selection operator (LASSO) Cox regression was used to reduce the number of variables and select only those with the highest predictive value. The predictive model implemented with the variables selected using the LASSO analysis was compared with a reference model using only a tumor stage and SUVmax. Results: NGTDM coarseness, SUVmax, and TNM stage survived the LASSO analysis and were used for the radiomic model. The AUCs obtained from the reference and radiomic models were 80.82 (95%CI, 69.01-92.63) and 81.02 (95%CI, 69.07-92.97), respectively (p = 0.98). The median OS in the reference model was 17.0 months in high-risk patients (95%CI, 11-21) and 113 months in low-risk patients (HR 7.47, p < 0.001). In the radiomic model, the median OS was 16.5 months (95%CI, 11-20) and 113 months in high- and low-risk groups, respectively (HR 9.64, p < 0.001). Conclusions: Our results indicate that a radiomic model composed using the tumor stage, SUVmax, and a selected radiomic feature (NGTDM_Coarseness) predicts survival in NSCLC patients similarly to a reference model composed only by the tumor stage and SUVmax. Replication of these preliminary results is necessary.

Radium-223 dichloride in clinical practice: a review.

The onset of skeletal metastases is typical of advanced-stage prostate cancer and requires a multidisciplinary approach to alleviate bone pain and try to delay disease progression. The current therapeutic armamentarium includes conventional analgesics, chemotherapeutic agents, immunotherapy, androgen-deprivation therapy, osteoclast inhibitors (bisphosphonates, denosumab), surgical interventions, external-beam radiotherapy and radionuclide metabolic therapy. Many studies in recent decades have demonstrated the efficacy of various radiopharmaceuticals, including strontium-89 and samarium-153, for palliation of pain from diffuse skeletal metastases, but no significant benefit in terms of disease progression and overall survival has been shown. The therapeutic landscape of metastatic skeletal cancer significantly changed after the introduction of radium-223, the first bone-homing radiopharmaceutical with disease-modifying properties. In this paper we extensively review the literature on the use of radium-223 dichloride in metastatic castration-resistant prostate cancer.

Impact of 123I-Ioflupane SPECT in Patient Management: Essential Tremor.

The usefulness of I-ioflupane imaging for detecting loss of functional dopaminergic neuron terminals in the striatum of patients with clinically uncertain parkinsonian syndromes is well known, especially to differentiate essential tremor from parkinsonisms. Here we present a case of a patient suspected of essential tremor but not responding to standard therapy, in which the results of DaTscan were fundamental to set up an alternative therapeutic approach.

Colorectal Cancer with Uncommon Metastatic Spread.

The prevalence of bone metastases from colorectal cancer (CRC) is quite low and the presence of isolated osseous metastases at the time of diagnosis or the onset of bone metastases without other organ involvement during follow-up is even lower. Here, we present an interesting case of diffuse skeletal metastases from CRC in which both the atypical presentation of the metastatic spread and the presence of infective comorbidities created some troubles in getting the final diagnosis.

Missing sentinel lymph node in cutaneous melanoma.

The American Society of Clinical Oncology guidelines recommend sentinel lymph node biopsy (SLNB) for all patients with melanoma tumors of intermediate thickness (between 1 and 4 mm). In case of patients with thick melanoma tumors (>4 mm), SLNB may be recommended as well, for staging purposes and to facilitate regional disease control. We report a case of an 82-year-old man, undergone excision of a cutaneous melanoma of the right thigh, which shows some limitation of SLNB in thick melanoma. Lymphoscintigraphy, performed as single-photon emission computed tomography/computed tomography (SPECT/CT), failed to identify the real sentinel lymph node, as tracer uptake was seen in A right inguinal node. Due to the presence on CT co-registered images of another suspicious node (with no radiopharmaceutical uptake) in the crural region, and considering the "high-risk" pathologic features of the removed primary lesion, a 18F-fluorodeoxyglucose positron emission tomography/CT (18F-FDG PET/CT) staging scan was planned. PET/CT showed high metabolic activity in the suspected crural lymphadenopathy. Histopathology demonstrated massive invasion of the crural ("sentinel") node and no metastatic cells in the inguinal node. This report highlights both the higher accuracy of lymphoscintigraphy, when performed as SPECT/CT and the potential utility of 18F-FDG PET/CT in regional staging.

The role of PET with 13N-ammonia and 18F-FDG in the assessment of myocardial perfusion and metabolism in patients with recent AMI and intracoronary stem cell injection.

UNLABELLED: Over the last decade, the effects of stem cell therapy on cardiac repair after acute myocardial infarction (AMI) have been investigated with different imaging techniques. We evaluated a new imaging approach using (13)N-ammonia and (18)F-FDG PET for a combined analysis of cardiac perfusion, metabolism, and function in patients treated with intracoronary injection of endothelial progenitors or with conventional therapy for AMI. METHODS: A total of 15 patients were randomly assigned to 3 groups based on different treatments (group A: bone marrow-derived stem cells; group B: peripheral blood-derived stem cells; group C: standard therapy alone). The number of scarred and viable segments, along with the infarct size and the extent of the viable area, were determined on a 9-segment (13)N-ammonia/(18)F-FDG PET polar map. Myocardial blood flow (MBF) was calculated for each segment on the ammonia polar map, whereas a global evaluation of left ventricular function was obtained by estimating left ventricular ejection fraction (LVEF) and end-diastolic volume, both derived from electrocardiography-gated (18)F-FDG images. Both intragroup and intergroup comparative analyses of the mean values of each parameter were performed at baseline and 3, 6, and 12 mo after AMI. During follow-up, major cardiac events were also registered. RESULTS: A significant decrease (P < 0.05) in the number of scarred segments and infarct size was observed in group A, along with an increase in MBF (P < 0.05) and a mild improvement in cardiac function. Lack of infarct size shrinkage in group B was associated with a marked impairment of MBF (P = 0.01) and cardiac dysfunction. Ambiguous changes in infarct size, MBF, and LVEF were found in group C. No differences in number of viable segments or in extent of viable area were found among the groups. At clinical follow-up, no major cardiac events occurred in group A patients, whereas 2 patients of group B experienced in-stent occlusion and one patient of group C received a transplant for heart failure. CONCLUSION: Our data suggest that a single nuclear imaging technique accurately analyzes changes in myocardial perfusion and metabolism occurring after stem cell transplantation.

The prognostic value of F-18 fluorodeoxyglucose bone marrow uptake in patients with recent diagnosis of multiple myeloma: a comparative study with Tc-99m sestamibi.

PURPOSE: We assessed the prognostic value of F-18 fluorodeoxyglucose (FDG) uptake in the bone marrow of patients with multiple myeloma (MM) in comparison with Tc-99m methoxy-isobutyl-isonitrile (MIBI). METHODS: The extent and intensity of FDG and MIBI uptake in the bone marrow of 18 patients with a recent diagnosis of MM were assessed by visual score and by calculating the mean SUV (mSUV) for FDG and the femora/thigh ratio (TG/BKG, [Target/Background ratio]) for MIBI images. These parameters were correlated with clinical indexes of disease using hemoglobin and beta-2-microglobulin levels and plasma cell infiltrate (PCI) percentage. The mean values of the visual score, mSUV, and TG/BKG levels were compared in patients deceased after a relatively short follow-up (n = 9; group A) and in patients with a longer survival or were alive at the end of the study (n = 9; group B). RESULTS: Significant correlations of mSUV and TG/BKG values with PCI percentages and beta-2-microglobulin were found (P < 0.05). The extent of FDG and MIBI bone marrow uptake was greater in patients of group A (P < 0.01). Higher values of mSUV (P < 0.01) and TG/BKG (P < 0.05) were also observed in patients of group A. These results were consistent with the differences (not statistically significant) in hemoglobin, albumin, beta-2-microglobulin levels, and PCI percentages observed in the 2 groups. CONCLUSION: Our study demonstrates that an increase of FDG bone marrow uptake may predict a more aggressive disease, as much as MIBI uptake. Therefore, an additional analysis of FDG bone marrow images should be performed in patients undergoing PET studies during the initial staging of MM.