Fully neuromorphic vision and control for autonomous drone flight.

Biological sensing and processing is asynchronous and sparse, leading to low-latency and energy-efficient perception and action. In robotics, neuromorphic hardware for event-based vision and spiking neural networks promises to exhibit similar characteristics. However, robotic implementations have been limited to basic tasks with low-dimensional sensory inputs and motor actions because of the restricted network size in current embedded neuromorphic processors and the difficulties of training spiking neural networks. Here, we present a fully neuromorphic vision-to-control pipeline for controlling a flying drone. Specifically, we trained a spiking neural network that accepts raw event-based camera data and outputs low-level control actions for performing autonomous vision-based flight. The vision part of the network, consisting of five layers and 28,800 neurons, maps incoming raw events to ego-motion estimates and was trained with self-supervised learning on real event data. The control part consists of a single decoding layer and was learned with an evolutionary algorithm in a drone simulator. Robotic experiments show a successful sim-to-real transfer of the fully learned neuromorphic pipeline. The drone could accurately control its ego-motion, allowing for hovering, landing, and maneuvering sideways-even while yawing at the same time. The neuromorphic pipeline runs on board on Intel's Loihi neuromorphic processor with an execution frequency of 200 hertz, consuming 0.94 watt of idle power and a mere additional 7 to 12 milliwatts when running the network. These results illustrate the potential of neuromorphic sensing and processing for enabling insect-sized intelligent robots.

Aberrant patterns of PET response during treatment for DLBCL patients with MYC gene rearrangements.

PURPOSE: MYC gene rearrangements in diffuse large B-cell lymphoma (DLBCL) patients are associated with poor prognosis. Our aim was to compare patterns of 2[18F]fluoro-2-deoxy-D-glucose positron emission tomography computed tomography (PET/CT) response in MYC + and MYC- DLBCL patients. METHODS: Interim PET/CT (I-PET) and end of treatment PET/CT (EoT-PET) scans of 81 MYC + and 129 MYC- DLBCL patients from 2 HOVON trials were reviewed using the Deauville 5-point scale (DS). DS1-3 was regarded as negative and DS4-5 as positive. Standardized uptake values (SUV) and metabolic tumor volume (MTV) were quantified at baseline, I-PET, and EoT-PET. Negative (NPV) and positive predictive values (PPV) were calculated using 2-year overall survival. RESULTS: MYC + DLBCL patients had significantly more positive EoT-PET scans than MYC- patients (32.5 vs 15.7%, p = 0.004). I-PET positivity rates were comparable (28.8 vs 23.8%). In MYC + patients 23.2% of the I-PET negative patients converted to positive at EoT-PET, vs only 2% for the MYC- patients (p = 0.002). Nine (34.6%) MYC + DLBCL showed initially uninvolved localizations at EoT-PET, compared to one (5.3%) MYC- patient. A total of 80.8% of EoT-PET positive MYC + patients showed both increased lesional SUV and MTV compared to I-PET. In MYC- patients, 31.6% showed increased SUV and 42.1% showed increased MTV. NPV of I-PET and EoT-PET was high for both MYC subgroups (81.8-94.1%). PPV was highest at EoT-PET for MYC + patients (61.5%). CONCLUSION: MYC + DLBCL patients demonstrate aberrant PET response patterns compared to MYC- patients with more frequent progression during treatment after I-PET negative assessment and new lesions at sites that were not initially involved. TRIAL REGISTRATION NUMBER AND DATE OF REGISTRATION: HOVON-84: EudraCT: 2006-005,174-42, retrospectively registered 01-08-2008. HOVON-130: EudraCT: 2014-002,654-39, registered 26-01-2015.

Estimation of and correction for finite motion sampling errors in small animal PET rigid motion correction.

Motion tracking with finite time sampling causing an associated unknown residual motion between two motion measurements is one of the factors contributing to resolution loss in small animal PET motion correction. The aim of this work is (i) to provide a means to estimate the effect of the finite motion sampling on the spatial resolution of the motion correction reconstructions and (ii) to correct for this residual motion thereby minimizing resolution loss. We calculate a tailored spatially variant deconvolution kernel from the measured motion data which is then used to deconvolve the motion corrected image using a 3D Richardson-Lucy algorithm. A simulation experiment of numerical phantoms as well as a microDerenzo phantom experiment wherein the phantom was manually moved at different speeds was performed to assess the performance of our proposed method. In the motion corrected images of the microDerenzo phantom there was an average rod FWHM differences between the slow and fast motion cases of 9.7%. This difference was reduced to 5.8% after applying the residual motion deconvolution. In awake animal experiments, the proposed method can serve to mitigate the finite sampling factor degrading the spatial resolution as well as the resolution differences between fast-moving and slow-moving animals. Graphical abstract Motion correction of positron emission tomography (PET) scans of moving subjects can be performed by measuring the motion of the subject during the PET scan with an optical tracking camera. The motion tracking data obtained from the tracking camera is then used to correct the PET image reconstructions for motion. Due to finite time sampling of the motion data, the motion corrected reconstructions suffer from loss of spatial resolution. In the proposed method, a spatially variant deconvolution kernel is calculated from the motion tracking data, which is then used to correct the motion-corrected PET reconstructions for the blurring effect of the finite motion sampling through a Richardson-Lucy deconvolution.

Using PET for therapy monitoring in oncological clinical trials: challenges ahead.

Molecular imaging with PET has emerged as a powerful imaging tool in the clinical care of oncological patients. Assessing therapy response is a prime application of PET and so the integration of PET into multicentre trials can offer valuable scientific insights and shape future clinical practice. However, there are a number of logistic and methodological challenges that have to be dealt with. These range from availability and regulatory compliance of the PET radiopharmaceutical to availability of scan time for research purposes. Standardization of imaging and reconstruction protocols, quality control, image processing and analysis are of paramount importance. Strategies for harmonization of the final image and the quantification result are available and can be implemented within the scope of multicentre accreditation programmes. Data analysis can be performed either locally or by centralized review. Response assessment can be done visually or using more quantitative approaches, depending on the research question. Large-scale real-time centralized review can be achieved using web-based solutions. Specific challenges for the future are inclusion of PET/MRI scanners in multicentre trials and the incorporation of radiomic analyses. Inclusion of PET in multicentre trials is a necessity to guarantee the further development of PET for routine clinical care and may yield very valuable scientific insights.

Preclinical molecular imaging of glutamatergic and dopaminergic neuroreceptor kinetics in obsessive compulsive disorder.

BACKGROUND: Molecular neuroimaging was applied in the quinpirole rat model for compulsive checking in OCD to visualize the D2- and mGluR5-receptor occupancy with Raclopride and ABP-688 microPET/CT. METHODS: Animals (n=48) were exposed to either saline (CTRL; 1mL/kg) or quinpirole (QP; dopamine D2-agonist, 0.5mg/kg) in a single injection (RAC and ABP acute groups) or twice-weekly during 7weeks (chronic group). Animals underwent PET/CT after the 1st injection (acute) or before initial exposure and following the 10th injection in week 5 (chronic). For the latter, each injection was paired with an open field test and video tracking. RESULTS: The QP animals displayed a strong increase in visiting frequency (checking) in the chronic group (+699.29%) compared to the control animals. Acute administration of the drug caused significant (p<0.01) decreases in D2R occupancy in the CP (-42.03%±4.01%). Chronical exposure resulted in significantly stronger decreases in the CP (-52.29%±3.79%). Furthermore significant increases in mGluR5 occupancy were found in the CP (10.36%±4.09%), anterior cingulate cortex (13.26%±4.01%), amygdala (24.36%±6.86%), entorhinal cortex (18.49%±5.14%) and nucleus accumbens (13.8%±4.87%) of the chronic group, not present after acute exposure. CONCLUSIONS: Compared to acute exposure, sensitisation to QP as a model for OCD differs both on a dopaminergic and glutamateric level, indicating involvement of processes such as receptor internalization and changes in extracellular availability of both neurotransmitters.

Specific suppression of microgliosis cannot circumvent the severe neuropathology in peroxisomal ß-oxidation-deficient mice.

An important hallmark of various neurodegenerative disorders is the proliferation and activation of microglial cells, the resident immune cells of the central nervous system (CNS). Mice that lack multifunctional protein-2 (MFP2), the key enzyme in peroxisomal ß-oxidation, develop excessive microgliosis that positively correlates with behavioral deficits whereas no neuronal loss occurs. However, the precise contribution of neuroinflammation to the fatal neuropathology of MFP2 deficiency remains largely unknown. Here, we first attempted to suppress the inflammatory response by administering various anti-inflammatory drugs but they failed to reduce microgliosis. Subsequently, Mfp2-/- mice were treated with the selective colony-stimulating factor 1 receptor (CSF1R) inhibitor PLX5622 as microglial proliferation and survival is dependent on CSF1R signaling. This resulted in the elimination of >95% of microglia from control mice but only 70% of the expanded microglial population from Mfp2-/- mice. Despite microglial diminution in Mfp2-/- brain, inflammatory markers remained unaltered and residual microglia persisted in a reactive state. CSF1R inhibition did not prevent neuronal dysfunction, cognitive decline and clinical deterioration of Mfp2-/- mice. Collectively, the unaltered inflammatory profile despite suppressed microgliosis concurrent with persevering clinical decline strengthens our hypothesis that neuroinflammation importantly contributes to the Mfp2-/- phenotype.

Molecular imaging as a tool to investigate heterogeneity of advanced HER2-positive breast cancer and to predict patient outcome under trastuzumab emtansine (T-DM1): the ZEPHIR trial.

BACKGROUND: Only human epidermal growth factor receptor (HER)2 status determined by immunohistochemistry (IHC) and fluorescence in situ hybridization (FISH) has been validated to predict efficacy of HER2-targeting antibody-drug-conjugate trastuzumab emtansine (T-DM1). We propose molecular imaging to explore intra-/interpatient heterogeneity in HER2 mapping of metastatic disease and to identify patients unlikely to benefit from T-DM1. PATIENTS AND METHODS: HER2-positive mBC patients with IHC3+ or FISH ≥ 2.2 scheduled for T-DM1 underwent a pretreatment HER2-positron emission tomography (PET)/computed tomography (CT) with (89)Zr-trastuzumab. [(18)F]2-fluoro-2-deoxy-D-glucose (FDG)-PET/CT was performed at baseline and before T-DM1 cycle 2. Patients were grouped into four HER2-PET/CT patterns according to the proportion of FDG-avid tumor load showing relevant (89)Zr-trastuzumab uptake (>blood pool activity): patterns A and B were considered positive (>50% or all of the tumor load 'positive'); patterns C and D were considered negative (>50% or all of the tumor load 'negative'). Early FDG-PET/CT was defined as nonresponding when >50% of the tumor load showed no significant reduction of FDG uptake (<15%). Negative (NPV) and positive predictive values (PPV) of HER2-PET/CT, early FDG response and their combination were assessed to predict morphological response (RECIST 1.1) after three T-DM1 cycles and time-to-treatment failure (TTF). RESULTS: In the 56 patients analyzed, 29% had negative HER2-PET/CT while intrapatient heterogeneity (patterns B and C) was found in 46% of patients. Compared with RECIST1.1, respective NPV/PPV for HER2-PET/CT were 88%/72% and 83%/96% for early FDG-PET/CT. Combining HER2-PET/CT and FDG-PET/CT accurately predicted morphological response (PPV and NPV: 100%) and discriminated patients with a median TTF of only 2.8 months [n = 12, 95% confidence interval (CI) 1.4-7.6] from those with a TTF of 15 months (n = 25, 95% CI 9.7-not calculable). CONCLUSIONS: Pretreatment imaging of HER2 targeting, combined with early metabolic response assessment holds great promise for improving the understanding of tumor heterogeneity in mBC and for selecting patients who will/will not benefit from T-DM1. CLINICALTRIALSGOV IDENTIFIER: NCT01565200.

Small-animal repetitive transcranial magnetic stimulation combined with [¹8F]-FDG microPET to quantify the neuromodulation effect in the rat brain.

Repetitive transcranial magnetic stimulation (rTMS) is a non-invasive neurostimulation technique for the treatment of various neurological and psychiatric disorders. To investigate the working mechanism of this treatment approach, we designed a small-animal coil for dedicated use in rats and we combined this neurostimulation method with small-animal positron emission tomography (microPET or µPET) to quantify regional 2-deoxy-2-((18)F)fluoro-d-glucose ([(18)F]-FDG) uptake in the rat brain, elicited by a low- (1 Hz) and a high- (50 Hz) frequency paradigm. Rats (n=6) were injected with 1 mCi of [(18)F]-FDG 10 min after the start of 30 min of stimulation (1 Hz, 50 Hz or sham), followed by a 20-min µPET image acquisition. Voxel-based statistical parametric mapping (SPM) image analysis of 1-Hz and 50-Hz versus sham stimulation was performed. For both the 1-Hz and 50-Hz paradigms we found a large [(18)F]-FDG hypermetabolic cluster (2.208 mm(3) and 2.616 mm(3), resp.) (analysis of variance (ANOVA), p<0.05) located in the dentate gyrus complemented with an additional [(18)F]-FDG hypermetabolic cluster (ANOVA, p<0.05) located in the entorhinal cortex (2.216 mm(3)) for the 50-Hz stimulation. The effect on [(18)F]-FDG metabolism was 2.9 ± 0.8% at 1 Hz and 2.5 ± 0.8% at 50 Hz for the dentate gyrus clusters and 3.3 ± 0.5% for the additional cluster in the entorhinal cortex at 50 Hz. The maximal (4.19 vs. 2.58) and averaged (2.87 vs. 2.21) T-values are higher for 50 Hz versus 1 Hz. This experimental study demonstrates the feasibility to combine µPET imaging in rats stimulated with rTMS using a custom-made small-animal magnetic stimulation setup to quantify changes in the cerebral [(18)F]-FDG uptake as a measure for neuronal activity.

Integrated PET/CT in the staging of nonsmall cell lung cancer: technical aspects and clinical integration.

Lung cancer is a common disease and is a leading cause of death in many countries. The management of lung cancer is directed by an optimal staging of the tumour. Integrated positron emission tomography (PET)/computed tomography (CT) is an anatomo-metabolic imaging modality that has recently been introduced to clinical practice and combines two different techniques: CT, which provides very detailed anatomic information; and PET, which provides metabolic information. One of the advantages of PET/CT is the improved image interpretation. This improvement can result in the detection of lesions initially not seen on CT or PET, a more precise location of lesions, a better characterisation of the lesion as benign or malignant and a better differentiation between tumour and surrounding structures. Initial studies demonstrate better results for PET/CT in the staging of lung cancer in comparison with PET alone, CT alone or visual correlation of PET and CT. The purpose of the present article is to discuss technical aspects of integrated PET/CT and to attempt to outline how to introduce integrated PET/CT in clinical and daily practice.

Usefulness of FDG-PET to diagnose intravascular lymphoma with encephalopathy and renal involvement.

Intravascular lymphoma (IVL) is a rare subtype of extranodal diffuse large B-cell lymphoma. It is characterized by proliferation of neoplastic Lymphoid cells almost exclusively within the lumina of small blood vessels. It can affect virtually every organ system. Due to its rarity and its diverse and heterogeneous clinical presentation, diagnosis is difficult and often made post-mortem. When diagnosed early, it is, however, potentially treatable. We present a young woman with longstanding constitutional symptoms, positive antinuclear antibody, elevated LDH levels and rapidly progressive encephalopathy. FDG-PET scan showed intense uptake in the renal cortex, which prompted us to perform a kidney biopsy which was compatible with IVL. The value of PET in establishing the diagnosis of this rare disease will be discussed.

Relationship between fluorodeoxyglucose uptake in the large vessels and late aortic diameter in giant cell arteritis.

OBJECTIVE: GCA carries an increased risk of developing thoracic aortic aneurysms. Previous work with fluorodeoxyglucose (FDG)-PET has shown that the aorta is frequently involved in this type of vasculitis. We wanted to investigate whether there is a correlation between the extent of vascular FDG uptake during the acute phase of GCA and the aortic diameter at late follow-up. METHODS: All patients with biopsy-proven GCA who ever underwent an FDG-PET scan in our centre were asked to undergo a CT scan of the aorta. The diameter of the aorta was measured at six different levels (ascending aorta, aortic arch, descending aorta, abdominal suprarenal, juxtarenal and infrarenal aorta) and the volumes of the thoracic and of the abdominal aorta were calculated. RESULTS: Forty-six patients agreed to participate (32 females, 14 males). A mean of 46.7 +/- 29.9 months elapsed between diagnosis and CT scan. All aortic dimensions were significantly smaller in women than in men, except for the diameter of the ascending aorta. Patients who had an increased FDG uptake in the aorta at diagnosis of GCA, had a significantly larger diameter of the ascending aorta (P = 0.025) and descending aorta (P = 0.044) and a significantly larger volume of the thoracic aorta (P = 0.029). In multivariate analysis, FDG uptake at the thoracic aorta was associated with late volume of the thoracic aorta (P = 0.039). CONCLUSION: GCA-patients with increased FDG uptake in the aorta may be more prone to develop thoracic aortic dilatation than GCA patients without this sign of aortic involvement.

Non-Hodgkin lymphoma: retrospective study on the cost-effectiveness of early treatment response assessment by FDG-PET.

PURPOSE: Although lymphomas are very chemosensitive, 50% of patients with aggressive non-Hodgkin lymphoma (NHL) are not cured with standard first-line treatment. This consists of six cycles of doxorubicin, vincristine, prednisolone and cyclophosphamide (CHOP), recently complemented with rituximab. Preliminary studies show that PET mid-treatment is a good predictor of the remission status at the end of therapy. As patients with persistent FDG uptake after three cycles are unlikely to gain a complete remission, the remaining three cycles of chemotherapy are useless. We investigated the costs and benefits for the use of PET in this early treatment setting. METHODS: We conceived a model using a conventional arm where patients receive the full regimen of six cycles of CHOP [-rituximab] and an experimental algorithm where patients receive either six cycles (PET response) or only three cycles (PET non-response). Based on a patient sample (2004-2006), we calculated the costs for hospitalisation and treatment. We took into account all costs accrued (including overhead costs). We used a sensitivity analysis by varying the most important parameters. RESULTS: With a PET price of 700 euro and CHOP price (per cycle) of 1,829 euro , we can conclude to cost saving of 1,879 euro per patient. The PET price can increase up to 2,580 euro and the cost for one cycle of CHOP can decrease to 500 euro per cycle before cost savings are nil. The percentage of non-responders may be as low as 10%. The implementation of rituximab in first-line therapy only increases benefit (4,900 euro/pt). CONCLUSION: We conclude to substantial cost savings if management of NHL patients is based on mid-treatment PET scan. The economical data we used seem to be comparable to those published in other European studies. Implementation of Mabthera in first line only increases cost savings.

Laparoscopic para-aortic lymphadenectomy and positron emission tomography scan as staging procedures in patients with cervical carcinoma stage IB2-IIIB.

UNLABELLED: The objective of this study was to determine the role of laparoscopic lower para-aortic lymphadenectomy and positron emission tomography (PET) scan in the staging of cervical carcinoma. Ninety consecutive patients with FIGO stage IB2-IIIB were scheduled for laparoscopic para-aortic lymphadenectomy. EXCLUSION CRITERIA: obvious metastatic para-aortic nodes on computed tomography (CT)/PET or PET-CT. The procedure was stopped when a node was positive on frozen section. In ten patients, no para-aortic lymphadenectomy was performed as scheduled. Forty-seven patients were operated retroperitoneally, 22 transperitoneally, and 21 cases were converted from retroperitoneally to transperitoneally. Median number of removed nodes was 6 (1-24). In 10 of 80 patients, para-aortic metastases were diagnosed. Despite a nonsuspect PET result, 5 of 44 patients had positive para-aortic nodes. Two-year survival was 76% and 16% without and with para-aortic metastases, respectively (P = 0.0001). Laparoscopic para-aortic lymphadenectomy showed metastases in 13% of the patients. In the subgroup with negative PET scan, 11% had metastases. The procedure had a low morbidity and identified a group with an extremely poor prognosis.

Intravascular large B-cell lymphoma of the uterus presenting as fever of unknown origin (FUO) and revealed by FDG-PET.

Non-Hodgkin's lymphoma (NHL) is a common cause of Fever of Unknown Origin (FUO) but the presentation as a gynaecologic malignancy is exceedingly rare. To our knowledge, this represents the first report of an intravascular large B-cell lymphoma of the uterus presenting with fever of unknown origin. After a standard clinical work-up for FUO, the endometrial curettage directed by the finding of a localized fluoro-deoxyglucose Positron Emission Tomography (FDG-PET) hot spot in the pelvic area, yielded material revealing an intr avascular B-cell lymphoma. A total abdominal hysterectomy confirmed the presence of an intravascular large B-cell lymphoma in the lumina of small blood vessels of the uterus.

Integrated PET/CT in lung cancer imaging: history and technical aspects.

Integrated PET/CT is a new anatomo-metabolic imaging modality combining two different techniques: Computed Tomography (CT) that provides very detailed anatomic information and Positron Emission Tomography (PET) that provides metabolic information. Integrated PET/CT has several advantages. One of the advantages is the use of CT data for attenuation correction that is significantly faster compared to that in conventional PET systems. Due to the use of CT data for attenuation correction, artefacts can be generated on PET images related to the use of intravenous or oral CT contrast agents, CT beam-hardening artefacts due to metallic implants and motion artefacts (respiratory motion, physical bowel motion, cardiac motion). The purpose of this review is to discuss some technical considerations concerning the CT protocol that can be used for PET/CT in lung cancer imaging and to give a short overview of the initial results of staging of non-small cell lung cancer (NSCLC).

Detection of extrapulmonary lesions with integrated PET/CT in the staging of lung cancer.

The aim of the present study was to assess retrospectively the additional value of positron emission tomography (PET)/computed tomography (CT) in the detection of unexpected extrapulmonary lesions in the staging of patients with a malignant pulmonary lesion in comparison with CT and PET used alone. A total of 217 patients with a pathologically proven lung tumour underwent PET/CT. CT, PET and PET/CT were evaluated in the detection of extrapulmonary lesions. These abnormalities were compared with the final diagnosis obtained from the medical records and statistical analysis was carried out. In total, 108 lesions were clinically detected. PET/CT showed a sensitivity, specificity, positive and negative predictive values and accuracy of 100, 81, 71, 100 and 87%, respectively, for the detection of extrapulmonary lesions and 92, 98, 89, 98 and 97%, respectively, for the detection of malignant extrapulmonary lesions. PET/CT was significantly better than CT and PET used alone. Conventional staging work-up has a poor sensitivity in detecting second primary cancers or unexpected metastases. The detection of malignant extrapulmonary lesions is necessary for correct tumour staging. By combining both metabolic and anatomical information, positron emission tomography/computed tomography is able to depict more unexpected extrapulmonary lesions than computed tomography and positron emission tomography used alone, and positron emission tomography/computed tomography provides more additional information of malignancy or benignancy of lesions detected with one of the two imaging modalities alone.

Additional value of integrated PET-CT in the detection and characterization of lung metastases: correlation with CT alone and PET alone.

The purpose was evaluating retrospectively the additional value of integrated positron emission tomography (PET) and computed tomography (CT) in the detection of pulmonary metastases in comparison with CT and PET alone. Fifty-six lung nodules, divided into three groups according their size, detected in 24 consecutive patients with a known primary tumor were retrospectively evaluated with integrated PET-CT, CT and PET. The nature of these nodules was determined by either histopathology or a follow-up of at least 6 months. The CT and PET images of the integrated PET-CT were evaluated separately by a radiologist and a nuclear medicine physician, the integrated PET-CT images were evaluated by a chest radiologist and nuclear medicine physician in consensus. The investigators were asked to search lung nodules and to determine whether these nodules were metastases or not. Sensitivity and accuracy for CT, PET and integrated PET-CT for characterization of all pulmonary nodules were, respectively: 100%, 90%, 100% and 57%, 55%, 55%. There was no significant difference in the characterization of pulmonary nodules between integrated PET-CT and CT alone (P=1.000) and PET alone (P=0.1306). An accurate evaluation is only possible for lesions larger than 1 cm.

Additional value of PET-CT in the staging of lung cancer: comparison with CT alone, PET alone and visual correlation of PET and CT.

Integrated positron emission tomography (PET) and computed tomography (CT) is a new imaging modality offering anatomic and metabolic information. The purpose was to evaluate retrospectively the accuracy of integrated PET-CT in the staging of a suggestive lung lesion, comparing this with the accuracy of CT alone, PET alone and visually correlated PET-CT. Fifty patients undergoing integrated PET-CT for staging of a suggestive lung lesion were studied. Their tumor, node, metastasis (TNM) statuses were determined with CT, PET, visually correlated PET-CT and integrated PET-CT. These TNM stages were compared with the surgical TNM status. Integrated PET-CT was the most accurate imaging technique in the assessment of the TNM status. Integrated PET-CT predicted correctly the T status, N status, M status and TNM status in, respectively, 86%, 80%, 98%, 70% versus 68%, 66%,88%, 46% with CT, 46%, 70%, 96%, 30% with PET and 72%, 68%, 96%, 54% with visually correlated PET-CT. T status and N status were overstaged, respectively, in 8% and 16% with integrated PET-CT, in 20% and 28% with CT, in 16% and 20% with PET, in 12% and 20% with visually correlated PET-CT and understaged in 6% and 4% with integrated PET-CT, versus 12% and 6% with CT, 38% and 10% with PET and 12% with visually correlated PET-CT. Integrated PET-CT improves the staging of lung cancer through a better anatomic localization and characterization of lesions and is superior to CT alone and PET alone. If this technique is not available, visual correlation of PET and CT can be a valuable alternative.