An EANM position paper on the application of artificial intelligence in nuclear medicine.

Artificial intelligence (AI) is coming into the field of nuclear medicine, and it is likely here to stay. As a society, EANM can and must play a central role in the use of AI in nuclear medicine. In this position paper, the EANM explains the preconditions for the implementation of AI in NM and takes position.

Application of artificial intelligence in nuclear medicine and molecular imaging: a review of current status and future perspectives for clinical translation.

Artificial intelligence (AI) will change the face of nuclear medicine and molecular imaging as it will in everyday life. In this review, we focus on the potential applications of AI in the field, both from a physical (radiomics, underlying statistics, image reconstruction and data analysis) and a clinical (neurology, cardiology, oncology) perspective. Challenges for transferability from research to clinical practice are being discussed as is the concept of explainable AI. Finally, we focus on the fields where challenges should be set out to introduce AI in the field of nuclear medicine and molecular imaging in a reliable manner.

Is C-11 Methionine PET an alternative to 18-F FDG-PET for identifying recurrent laryngeal cancer after radiotherapy?

OBJECTIVE: 18F FDG-PET is superior to other imaging techniques in revealing residual laryngeal cancer after radiotherapy. Unfortunately, its specificity is low, due to FDG uptake in inflammation and in anaerobic conditions. PET imaging with the amino acid-based radiopharmaceutical C11-methionine (MET) should be less influenced by post-radiation conditions. The aim of this study was to investigate the potential of MET in diagnosing recurrent laryngeal cancer after radiotherapy as compared to 18F-FDG. METHODS: Forty-eight patients with a clinical suspicion of local residual disease at least 3 months after completion of radiotherapy or chemoradiotherapy for a T2-4 laryngeal carcinoma, along with an indication for direct laryngoscopy, were included. They received MET-PET and FDG-PET prior to the direct laryngoscopy. One senior nuclear medicine physician assessed both the FDG-PET and MET-PET images visually for the degree of abnormal uptake. The gold standard was a biopsy-proven recurrence 12 months after PET. The nuclear physician had no access to the medical charts and was blinded to the results of the other PET. Sensitivity, specificity and positive and negative predictive value were calculated. RESULTS: The sensitivity of FDG was 77.3% and the specificity 56.0% after the conservative reading, with these values equalling 54.5% and 76.0% for MET. The positive predictive value of FDG was 60.7% and the negative predictive value 73.7%. The PPV of MET was 66.7%, and the NPV was 65.5%. The McNemar test within diseased (sensitivity comparison) shows a p-value of 0.125, and the McNemar test within non-diseased (specificity comparison) shows a P-value of 0.180. CONCLUSION: MET-PET is not superior to FDG-PET in terms of identifying recurrent laryngeal cancer.

Serial FLT PET imaging to discriminate between true progression and pseudoprogression in patients with newly diagnosed glioblastoma: a long-term follow-up study.

PURPOSE: Response evaluation in patients with glioblastoma after chemoradiotherapy is challenging due to progressive, contrast-enhancing lesions on MRI that do not reflect true tumour progression. In this study, we prospectively evaluated the ability of the PET tracer 18F-fluorothymidine (FLT), a tracer reflecting proliferative activity, to discriminate between true progression and pseudoprogression in newly diagnosed glioblastoma patients treated with chemoradiotherapy. METHODS: FLT PET and MRI scans were performed before and 4 weeks after chemoradiotherapy. MRI scans were also performed after three cycles of adjuvant temozolomide. Pseudoprogression was defined as progressive disease on MRI after chemoradiotherapy with stabilisation or reduction of contrast-enhanced lesions after three cycles of temozolomide, and was compared with the disease course during long-term follow-up. Changes in maximum standardized uptake value (SUVmax) and tumour-to-normal uptake ratios were calculated for FLT and are presented as the mean SUVmax for multiple lesions. RESULTS: Between 2009 and 2012, 30 patients were included. Of 24 evaluable patients, 7 showed pseudoprogression and 7 had true progression as defined by MRI response. FLT PET parameters did not significantly differ between patients with true progression and pseudoprogression defined by MRI. The correlation between change in SUVmax and survival (p = 0.059) almost reached the standard level of statistical significance. Lower baseline FLT PET uptake was significantly correlated with improved survival (p = 0.022). CONCLUSION: Baseline FLT uptake appears to be predictive of overall survival. Furthermore, changes in SUVmax over time showed a tendency to be associated with improved survival. However, further studies are necessary to investigate the ability of FLT PET imaging to discriminate between true progression and pseudoprogression in patients with glioblastoma.

99mTc-HDP bone scintigraphy and 18F-sodiumfluoride PET/CT in primary staging of patients with prostate cancer.

INTRODUCTION/AIM: Correct staging of patients with prostate cancer is important for treatment planning and prognosis. Although bone scintigraphy with 99mTc-phosphonates (BS) is generally advised for staging by guidelines in high risk prostate cancer, this imaging technique is hampered by a high rate of inconclusive results and moderate accuracy. Potentially better imaging techniques for detection of bone metastases such as 18F-sodiumfluoride PET/CT (NaF PET/CT) are therefore being evaluated. In this observational cohort study we evaluate the performance and clinical impact of both BS and NaF PET/CT in primary staging of patients with prostate cancer. METHODS: The first of two cohorts consisted of patients who received a BS while the second included patients who received a NaF PET/CT for primary staging of prostate cancer. For both cohorts the number of positive, negative and equivocal findings, calculated diagnostic performance of the imaging modality in terms of sensitivity and specificity, as well as the impact on clinical management were studied. The ranges of the diagnostic performance were calculated both assuming that equivocal findings were positive and assuming that they were negative for bone metastases. For the NaF PET/CT cohort the number of patients with signs of lymph node metastases on low dose CT were also recorded, including the impact of these findings on clinical management. RESULTS: One-hundred-and-four patients underwent NaF PET/CT, whereas 122 patients underwent BS. Sensitivities of 97-100 and 84-95% and specificities of 98-100 and 72-100% were found on a patient basis for detection of bone metastases with NaF PET/CT and BS, respectively. Equivocal findings warranted further diagnostic procedures in 2% of the patients in the NaF cohort and in 16% in the BS cohort. In addition NaF PET/CT demonstrated lymph node metastases in 50% of the included patients, of which 25% showed evidence of lymph node metastases only. CONCLUSION: Our data indicate better diagnostic performance of NaF PET/CT compared to BS for detection of bone metastases in primary staging of prostate cancer patients. Less equivocal findings are encountered with NaF PET/CT. Moreover, NaF PET/CT has additional value over BS since lymph node metastases are encountered frequently.

FDG PET/CT: EANM procedure guidelines for tumour imaging: version 2.0.

The purpose of these guidelines is to assist physicians in recommending, performing, interpreting and reporting the results of FDG PET/CT for oncological imaging of adult patients. PET is a quantitative imaging technique and therefore requires a common quality control (QC)/quality assurance (QA) procedure to maintain the accuracy and precision of quantitation. Repeatability and reproducibility are two essential requirements for any quantitative measurement and/or imaging biomarker. Repeatability relates to the uncertainty in obtaining the same result in the same patient when he or she is examined more than once on the same system. However, imaging biomarkers should also have adequate reproducibility, i.e. the ability to yield the same result in the same patient when that patient is examined on different systems and at different imaging sites. Adequate repeatability and reproducibility are essential for the clinical management of patients and the use of FDG PET/CT within multicentre trials. A common standardised imaging procedure will help promote the appropriate use of FDG PET/CT imaging and increase the value of publications and, therefore, their contribution to evidence-based medicine. Moreover, consistency in numerical values between platforms and institutes that acquire the data will potentially enhance the role of semiquantitative and quantitative image interpretation. Precision and accuracy are additionally important as FDG PET/CT is used to evaluate tumour response as well as for diagnosis, prognosis and staging. Therefore both the previous and these new guidelines specifically aim to achieve standardised uptake value harmonisation in multicentre settings.

Impact of total PSA, PSA doubling time and PSA velocity on detection rates of 11C-Choline positron emission tomography in recurrent prostate cancer.

PURPOSE: To evaluate the effect of total PSA (tPSA) and PSA kinetics on the detection rates of (11)C-Choline PET in patients with biochemical recurrence (BCR) after radical prostatectomy (RP) or external beam radiotherapy (EBRT). METHODS: We included 185 patients with BCR after RP (PSA >0.2 ng/ml) or after EBRT (ASTRO definition). After injection of 400 MBq 11C-Choline i.v., a scan was made using the ECAT HR + PET camera with CT fusion images or Siemens mCT PET/CT. Biopsy-proven histology, confirmative imaging (CT or bone scan) and/or clinical follow-up (PSA) were used as composite reference. Statistical analysis was performed using PASW Statistics 18. RESULTS: 11C-Choline PET was positive in 124/185 cases (65%) (in 22/61 (36%) after RP, 102/124 (82%) after EBRT). In 79 patients a local recurrence was identified, and 45 patients showed locoregional metastases on PET/CT. In 20 cases a proven false-negative PET scan was observed. Positive PET scans were confirmed by histology in 87/124 (70%) cases, by confirmatory imaging in 34/124 (28%) and by clinical follow-up after salvage treatment in 3 (2%) cases. The ROC analysis to detect a recurrence showed significant difference in area under the curve (AUC) of tPSA 0.721(p < 0.001) and PSA velocity 0.730 (p < 0.001). PSA doubling time showed no significant difference with an AUC of 0.542 (p = 0.354). Detection rates are <50% in tPSA <2 ng/ml and/or PSA velocity <1 ng/ml/year. CONCLUSIONS: Total serum PSA and PSA velocity have significant effect on the detection rates of 11C-Choline PET/CT in men with a BCR after RP or EBRT.

Alternative PET tracers in head and neck cancer. A review.

Positron emission tomography (PET) has become a standard in staging Head and Neck cancer. While (18)F-fluoro-2-deoxy-D-glucose (FDG) is the most frequently used radiopharmaceutical, glycolysis is not the only metabolic process that can be visualized. Different PET tracers can also be used to visualize other metabolic processes and in this manner, the disadvantages of FDG PET can be avoided. In this review, we describe a comprehensive overview of alternatives to FDG that can be used in identifying head and neck cancer. The potential advantages and disadvantages of these radiopharmaceuticals are discussed.

Plasma thymus and activation-regulated chemokine as an early response marker in classical Hodgkin's lymphoma.

BACKGROUND: Plasma thymus and activation-regulated chemokine is a potential biomarker for classical Hodgkin's lymphoma. To define its value as a marker to monitor treatment response, we correlated serial plasma thymus and activation-regulated chemokine levels with clinical response in newly diagnosed and relapsed classical Hodgkin's lymphoma patients. DESIGN AND METHODS: Plasma was collected from 60 (39 early stage and 21 advanced stage) newly diagnosed classical Hodgkin's lymphoma patients before, during, and after treatment, and from 12 relapsed patients before and after treatment. Plasma thymus and activation-regulated chemokine levels were determined by enzyme-linked immunosorbent assay and were related to pre-treatment metabolic tumor volume, as measured by quantification of 2-[18F]fluoro-2-deoxyglucose positron emission tomography images, and to treatment response. RESULTS: Baseline plasma thymus and activation-regulated chemokine levels correlated with stage of disease and bulky disease, and more closely with metabolic tumor volume. Response to treatment was observed among 38 of 39 early stage and 19 of 21 advanced stage patients. Reduction in plasma thymus and activation-regulated chemokine to normal range levels could be observed as early as after one cycle of chemotherapy in all responsive patients, while plasma levels remained elevated during and after treatment in the 3 non-responsive patients. Plasma thymus and activation-regulated chemokine was elevated in all 12 relapsed patients at time of relapse and remained elevated after salvage treatment in the 4 non-responsive patients. CONCLUSIONS: Baseline plasma thymus and activation-regulated chemokine levels correlate with classical Hodgkin's lymphoma tumor burden and serial levels correlate with response to treatment in patients with classical Hodgkin's lymphoma.

Fluorodeoxyglucose positron emission tomography for evaluating early response during neoadjuvant chemoradiotherapy in patients with potentially curable esophageal cancer.

BACKGROUND: Neoadjuvant chemoradiotherapy before surgery can improve survival in patients with potentially curable esophageal cancer, but not all patients respond. Fluorodeoxyglucose positron emission tomography (FDG-PET) has been proposed to identify nonresponders early during neoadjuvant chemoradiotherapy. The aim of the present study was to determine whether FDG-PET could differentiate between responding and nonresponding esophageal tumors early in the course of neoadjuvant chemoradiotherapy. METHODS: This clinical trial comprised serial FDG-PET before and 14 days after start of chemoradiotherapy in patients with potentially curable esophageal carcinoma. Histopathologic responders were defined as patients with no or less than 10% viable tumor cells (Mandard score on resection specimen). PET response was measured using the standardized uptake value (SUV). Receiver operating characteristic analysis was used to evaluate the ability of SUV in distinguishing between histopathologic responders and nonresponders. RESULTS: In 100 included patients, 64 were histopathologic responders. The median SUV decrease 14 days after the start of therapy was 30.9% for histopathologic responders and 1.7% for nonresponders (P = 0.001). In receiver operating characteristic analysis, the area under the curve was 0.71 (95% CI = 0.60-0.82). Using a 0% SUV decrease cutoff value, PET correctly identified 58 of 64 responders (sensitivity 91%) and 18 of 36 nonresponders (specificity 50%). The corresponding positive and negative predictive values were 76% and 75%, respectively. CONCLUSIONS: SUV decrease 14 days after the start of chemoradiotherapy was significantly associated with histopathologic tumor response, but its accuracy in detecting nonresponders was too low to justify the clinical use of FDG-PET for early discontinuation of neoadjuvant chemoradiotherapy in patients with potentially curable esophageal cancer.

Reduction of artefacts caused by hip implants in CT-based attenuation-corrected PET images using 2-D interpolation of a virtual sinogram on an irregular grid.

PURPOSE: Metallic prosthetic replacements, such as hip or knee implants, are known to cause strong streaking artefacts in CT images. These artefacts likely induce over- or underestimation of the activity concentration near the metallic implants when applying CT-based attenuation correction of positron emission tomography (PET) images. Since this degrades the diagnostic quality of the images, metal artefact reduction (MAR) prior to attenuation correction is required. METHODS: The proposed MAR method, referred to as virtual sinogram-based technique, replaces the projection bins of the sinogram that are influenced by metallic implants by a 2-D Clough-Tocher cubic interpolation scheme performed in an irregular grid, called Delaunay triangulated grid. To assess the performance of the proposed method, a physical phantom and 30 clinical PET/CT studies including hip prostheses were used. The results were compared to the method implemented on the Siemens Biograph mCT PET/CT scanner. RESULTS: Both phantom and clinical studies revealed that the proposed method performs equally well as the Siemens MAR method in the regions corresponding to bright streaking artefacts and the artefact-free regions. However, in regions corresponding to dark streaking artefacts, the Siemens method does not seem to appropriately correct the tracer uptake while the proposed method consistently increased the uptake in the underestimated regions, thus bringing it to the expected level. This observation is corroborated by the experimental phantom study which demonstrates that the proposed method approaches the true activity concentration more closely. CONCLUSION: The proposed MAR method allows more accurate CT-based attenuation correction of PET images and prevents misinterpretation of tracer uptake, which might be biased owing to the propagation of bright and dark streaking artefacts from CT images to the PET data following the attenuation correction procedure.

18F-FDG PET during stereotactic body radiotherapy for stage I lung tumours cannot predict outcome: a pilot study.

PURPOSE: (18)F-Fluorodeoxyglucose positron emission tomography (FDG PET) has been used to assess metabolic response several months after stereotactic body radiotherapy (SBRT) for early-stage non-small cell lung cancer. However, whether a metabolic response can be observed already during treatment and thus can be used to predict treatment outcome is undetermined. METHODS: Ten medically inoperable patients with FDG PET-positive lung tumours were included. SBRT consisted of three fractions of 20 Gy delivered at the 80% isodose at days 1, 6 and 11. FDG PET was performed before, on day 6 immediately prior to administration of the second fraction of SBRT and 12 weeks after completion of SBRT. Tumour metabolism was assessed semi-quantitatively using the maximum standardized uptake value (SUV(max)) and SUV(70%). RESULTS: After the first fraction, median SUV(max) increased from 6.7 to 8.1 (p = 0.07) and median SUV(70%) increased from 5.7 to 7.1 (p = 0.05). At 12 weeks, both median SUV(max) and median SUV(70%) decreased by 63% to 3.1 (p = 0.008) and to 2.5 (p = 0.008), respectively. CONCLUSION: SUV increased during treatment, possibly due to radiation-induced inflammation. Therefore, it is unlikely that (18)F-FDG PET during SBRT will predict treatment success.

FDG PET and PET/CT: EANM procedure guidelines for tumour PET imaging: version 1.0.

The aim of this guideline is to provide a minimum standard for the acquisition and interpretation of PET and PET/CT scans with [18F]-fluorodeoxyglucose (FDG). This guideline will therefore address general information about[18F]-fluorodeoxyglucose (FDG) positron emission tomography-computed tomography (PET/CT) and is provided to help the physician and physicist to assist to carrying out,interpret, and document quantitative FDG PET/CT examinations,but will concentrate on the optimisation of diagnostic quality and quantitative information.

18F-FDG PET in squamous cell carcinoma of the oral cavity and oropharynx: a study on inter- and intraobserver agreement.

PURPOSE: Good observer agreement is mandatory for an effective imaging technique. However, little is known about the observer agreement of fluorine-18 fluorodeoxyglucose ((18)F-FDG) positron emission tomography (PET) in head and neck squamous cell carcinoma. The aim of the present study was to evaluate the inter- and intraobserver agreement of interpretations of (18)F-FDG PET in head and neck SCC and to assess the influence of observer experience, tumor localizing, and tumor size on the agreement. PATIENTS AND METHODS: (18)F-FDG PET scans of 80 patients with oral and oropharyngeal SCC were reassessed twice by 2 experienced nuclear medicine physicians and 2 residents in nuclear medicine. The absolute agreement and Cohen's kappa were calculated by comparing the results of the 4 observers for the primary tumor, cervical metastases, and distant metastases/second primary tumor. To analyze the sensitivity and specificity, the results were compared with the findings from the histologic specimens or the follow-up data. RESULTS: The interobserver agreement of the nuclear medicine physicians revealed an absolute agreement and kappa of 0.91 and 0.58 for detecting the primary tumor, 0.94 and 0.83 for detecting cervical metastases, and 0.85 and 0.53 for detecting distant metastases/second primary tumors, respectively. The intraobserver agreement was greater overall than the interobserver agreement. Compared with the nuclear medicine physicians, the residents scored lower in interobserver agreement. The interobserver agreement decreased when localizing the malignancy more precisely. The agreement and sensitivity increased with tumor size. However, for small metastases, a high observer agreement was found owing to the nondetection of these malignancies. CONCLUSIONS: Good inter- and intraobserver agreement in SCC in the oral cavity or oropharynx with (18)F-FDG PET was found. Observer experience had limited influence on observer agreement. However, the agreement level decreased when a more precise anatomic tumor localization was required.

Improved selection of patients for hepatic surgery of colorectal liver metastases with (18)F-FDG PET: a randomized study.

UNLABELLED: With the increasing possibilities for surgical treatment of colorectal liver metastases, careful selection of patients who may benefit from surgical treatment becomes critical. The addition of PET to (18)F-FDG may significantly improve conventional staging by CT. Up to now, definitive evidence that the addition of (18)F-FDG PET to conventional staging leads to superior clinical results and improved clinical management in these patients has been lacking. In this randomized controlled trial in patients with colorectal liver metastases, we investigated whether the addition of (18)F-FDG PET is beneficial and reduces the number of futile laparotomies. METHODS: A total of 150 patients with colorectal liver metastases selected for surgical treatment by imaging with CT were randomly assigned to CT only (n = 75) or CT plus (18)F-FDG PET (n = 75). Patients were followed up for at least 3 y. The primary outcome measure was futile laparotomy, defined as any laparotomy that did not result in complete tumor treatment, that revealed benign disease, or that did not result in a disease-free survival period longer than 6 mo. RESULTS: Patient and tumor characteristics were similar for both groups. The number of futile laparotomies was 34 (45%) in the control arm without (18)F-FDG PET and 21 (28%) in the experimental arm with (18)F-FDG PET; the relative risk reduction was 38% (95% confidence interval, 4%-60%, P = 0.042). CONCLUSION: The number of futile laparotomies was reduced from 45% to 28%; thus, the addition of (18)F-FDG PET to the work-up for surgical resection of colorectal liver metastases prevents unnecessary surgery in 1 of 6 patients.

Phenylketonuria: High plasma phenylalanine decreases cerebral protein synthesis.

Left untreated, phenylketonuria biochemically results in high phenylalanine concentrations in blood and tissues, and clinically especially in severe mental retardation. Treatment consists of severe dietary restriction of phenylalanine with more or less normal intellectual outcome as result when started early enough. It is unclear whether treatment for life is necessary. A clear relationship between plasma phenylalanine concentrations and cerebral outcome exists, but the precise pathophysiological mechanism is not understood. In studies in mice with phenylketonuria, the cerebral protein synthesis rate is decreased when compared to controls. The aim of the present study was to determine the protein synthesis rate in relation to the plasma phenylalanine concentrations in-vivo in patients with phenylketonuria by positron emission tomography brain studies after an intravenous l-[1-(11)C]-tyrosine bolus. Results showed a significant negative relationship (R(2)=0.40, p<0.01) between plasma phenylalanine concentration and the cerebral protein synthesis rate in 19 patients with phenylketonuria. At increased plasma phenylalanine concentrations, i.e. above 600-800micromol/l, the cerebral protein synthesis rate is clearly decreased compared to lower phenylalanine concentrations. These data suggest that cerebral protein metabolism in untreated adults with phenylketonuria can be abnormal due to high plasma phenylalanine concentrations. Hence, we speculate that it is important to continue dietary treatment into adulthood, aiming at plasma phenylalanine concentrations <600-800micromol/l.

Haemodialysis is associated with a pronounced fall in myocardial perfusion.

BACKGROUND: Whereas haemodialysis (HD) is lifesaving by replacement of renal function, there are data to suggest that the HD procedure itself may contribute to the high cardiac risk in dialysis patients. The HD procedure is associated with an increased risk of sudden death, and there is accumulating evidence that HD can elicit myocardial ischaemia. In this study, we evaluated the effect of HD on global and regional myocardial blood flow (MBF) and left ventricular (LV) function in non-diabetic, non-cardiac compromised patients. METHODS: (13)N-NH(3) positron emission tomography (PET) was used to quantify changes in MBF, LV wall motion, cardiac output (CO), LV end-diastolic volume (LVEDV) and end-systolic volume (LVESV) in seven non-diabetic patients with uneventful cardiac histories. PET scans were performed before and at 30 and 220 min of HD. RESULTS: In all patients global MBF fell during HD. At 30 min of HD without ultrafiltration (UF), global MBF had fallen 13.5 +/- 11.5% (P < 0.05) while CO, LVEDV and LVESV were 4.6 +/- 5.3% (NS), 5.6 +/- 4.2% (P < 0.05) and 6.9 +/- 7.2% (P < 0.05) lower, respectively. At 220 min of HD, after UF of 2.5 +/- 0.9 l, global MBF had fallen 26.6 +/- 13.9% (P < 0.05) from baseline while CO, LVEDV and LVESV were 21.0 +/- 19.7%, 31.1 +/- 12.7% and 36.4 +/- 17.5% (all P < 0.05) lower, respectively. In two patients, new LV regional wall motion abnormalities (RWMA) developed at 220 min of HD. MBF was reduced to a greater extent in regions that developed LV RWMA compared to those that did not. CONCLUSIONS: Haemodialysis induced a pronounced fall in MBF. Since MBF fell already early during HD not only hypovolaemia but also acute dialysis-associated factors seem to play a role. Haemodialysis-associated reductions in MBF may contribute to the high cardiac event rate of dialysis patients.

Screening for distant metastases in head and neck cancer patients by chest CT or whole body FDG-PET: a prospective multicenter trial.

BACKGROUND AND PURPOSE: The aim of the study was to define the added value of whole body FDG-PET in screening for distant metastases in patients with head and neck squamous cell carcinoma and risk factors. MATERIALS AND METHODS: In a multi-center prospective study between 1998 and 2003, 145 consecutive HNSCC patients with risk factors for distant metastases underwent chest CT and whole body FDG-PET for screening of distant metastases. The data of 92 evaluable patients who developed distant metastases or who had a follow-up of at least 12 months were analyzed. Besides their performance in clinical practice, the operational characteristics of PET and CT using ROC analyses were investigated. RESULTS: Pretreatment screening identified distant metastases in 19 patients (21%). FDG-PET had a higher sensitivity (53% vs. 37%) and positive predictive value (80% vs. 75%) than CT. The combination of CT and FDG-PET had the highest sensitivity (63%). The ROC analyses of the five point ordinal scales revealed that the "area under the curve" (AUC) of FDG-PET was significantly higher as compared to CT. CONCLUSION: In HNSCC patients with risk factors, pretreatment screening for distant metastases by chest CT is improved by FDG-PET.