Neural network evaluation of PET scans of the liver: a potentially useful adjunct in clinical interpretation.

PURPOSE: To assess the performance of an artificial neural network in the evaluation of fluorine 18 fluorodeoxyglucose (FDG) uptake in the liver, compared with the results of expert interpretation of abdominal liver magnetic resonance (MR) images. MATERIALS AND METHODS: The study was approved by the institutional human research committee and was HIPAA compliant, with waiver of informed consent. Digital data from positron emission tomographic (PET)/computed tomographic (CT) examinations, along with patient demographics, were obtained from 98 consecutive patients who underwent both whole-body PET/CT examinations and liver MR imaging examinations within 2 months. Interpretations of the scans from PET/CT examinations by trained neural networks were cross-classified with expert interpretations of the findings on images from MR examinations for intrahepatic benignity or malignancy. Receiver operating characteristic (ROC) curves were obtained for the designed networks. The significance of the difference between neural network ROC curves and the ROC curves detailing the performance of two expert blinded observers in the interpretation of liver FDG uptake was determined. RESULTS: A neural network incorporating lesion data demonstrated an ROC curve with an area under the curve (AUC) of 0.905 (standard error, 0.0370). A network independent of lesion data demonstrated an ROC curve with an AUC of 0.896 (standard error, 0.0386). These results compare favorably with results of expert blinded observers 1 and 2 who demonstrated ROCs with AUCs of 0.786 (standard error, 0.0522) and 0.796 (standard error, 0.0514), respectively. Following unblinding to network data, the AUCs for readers 1 and 2 improved to 0.924 (standard error, 0.0335) and 0.881 (standard error, 0.0409), respectively. CONCLUSION: Computers running artificial neural networks employing PET/CT scan data are sensitive and specific in the designation of the presence of intrahepatic malignancy, with comparison with interpretation by expert observers. When used in conjunction with human expertise, network data improve accuracy of the human interpreter.

Atrioesophageal fistula after catheter pulmonary venous ablation for atrial fibrillation: imaging features.

Atrioesophageal fistula is a rare but highly morbid complication of catheter-mediated pulmonary vein ablation for the treatment of atrial fibrillation. Among patients who do not exsanguinate from upper gastrointestinal tract bleeding, presentation includes sepsis and embolic cerebrovascular disease. We present a case of atrioesophageal fistula after pulmonary venous ablation as a treatment for atrial fibrillation, focusing on the imaging features of this diagnosis.

Comparison of usefulness of inflammatory markers in patients with versus without peripheral arterial disease in predicting adverse cardiovascular outcomes (myocardial infarction, stroke, and death).

We tested the hypothesis that a combination of measurements of different aspects of atherosclerosis, including burden of atherosclerosis and levels of inflammation, would contain more predictive information than either alone in an outpatient population. We enrolled 110 patients (62 +/- 15 years of age) who were referred to the noninvasive vascular laboratory for sequential Doppler pressure measurements of the lower extremities. We measured ankle-brachial index (ABI) and serum markers of inflammation and followed subjects for a mean of 2.25 years. Fifty subjects did not have peripheral arterial disease (PAD; ABI > or =0.9), whereas 60 did (ABI <0.9). Markers of inflammation, including C-reactive protein (3.83 +/- 0.9 vs 2.11 +/- 1.1, p = 0.019), were higher in subjects who had PAD. During follow-up, 42% developed an event (myocardial infarction, stroke, unplanned coronary or lower extremity revascularization, or death). Decreasing ABI (chi-square 7.3, p = 0.026) and increasing C-reactive protein (chi-square 22.1, p <0.001) increased the risk of an event. Risk increased sixfold between the lowest and highest groups for all events and fourfold for hard events (myocardial infarction, stroke, and death) using both C-reactive protein and ABI. In conclusion, patients who have PAD and increased inflammation are at highest risk for adverse cardiovascular outcomes. Characterizing atherosclerosis on the basis of these parameters provides important prognostic information.