Search

To evaluate random forests (RFs) as a supervised machine learning algorithm to classify amyloid brain PET as positive or negative for amyloid deposition and identify key regions of interest for stratification.The data set included 57 baseline F-florbetapir (Amyvid; Lilly, Indianapolis, IN) brain PET scans in participants with severe white matter disease, presenting with either transient ischemic attack/lacunar stroke or mild cognitive impairment from early Alzheimer disease, enrolled in a multicenter prospective observational trial. Scans were processed using the MINC toolkit to generate SUV ratios, normalized to cerebellar gray matter, and clinically read by 2 nuclear medicine physicians with interpretation based on consensus (35 negative, 22 positive). SUV ratio data and clinical reads were used for supervised training of an RF classifier programmed in MATLAB.A 10,000-tree RF, each tree using 15 randomly selected cases and 20 randomly selected features (SUV ratio per region of interest), with 37 cases for training and 20 cases for testing, had sensitivity = 86% (95% confidence interval [CI], 42%-100%), specificity = 92% (CI, 64%-100%), and classification accuracy = 90% (CI, 68%-99%). The most common features at the root node (key regions for stratification) were (1) left posterior cingulate (1039 trees), (2) left middle frontal gyrus (1038 trees), (3) left precuneus (857 trees), (4) right anterior cingulate gyrus (655 trees), and (5) right posterior cingulate (588 trees).Random forests can classify brain PET as positive or negative for amyloid deposition and suggest key clinically relevant, regional features for classification.

Purpose The aim of this study was to evaluate random forests (RFs) to identify ROIs on F-florbetapir and F-FDG PET associated with Montreal Cognitive Assessment (MoCA) score. Materials and methods Fifty-seven subjects with significant white matter disease presenting with either transient ischemic attack/lacunar stroke or mild cognitive impairment from early Alzheimer disease, enrolled in a multicenter prospective observational trial, had MoCA and F-florbetapir PET; 55 had F-FDG PET. Scans were processed using the MINC toolkit to generate SUV ratios, normalized to cerebellar gray matter (F-florbetapir PET), or pons (F-FDG PET). SUV ratio data and MoCA score were used for supervised training of RFs programmed in MATLAB. Results F-Florbetapir PETs were randomly divided into 40 training and 17 testing scans; 100 RFs of 1000 trees, constructed from a random subset of 16 training scans and 20 ROIs, identified ROIs associated with MoCA score: right posterior cingulate gyrus, right anterior cingulate gyrus, left precuneus, left posterior cingulate gyrus, and right precuneus. Amyloid increased with decreasing MoCA score. F-FDG PETs were randomly divided into 40 training and 15 testing scans; 100 RFs of 1000 trees, each tree constructed from a random subset of 16 training scans and 20 ROIs, identified ROIs associated with MoCA score: left fusiform gyrus, left precuneus, left posterior cingulate gyrus, right precuneus, and left middle orbitofrontal gyrus. F-FDG decreased with decreasing MoCA score. Conclusions Random forests help pinpoint clinically relevant ROIs associated with MoCA score; amyloid increased and F-FDG decreased with decreasing MoCA score, most significantly in the posterior cingulate gyrus.

PURPOSE Operculoinsular epilepsy (OIE) can be challenging to diagnose. While the value of SPECT cerebral blood flow and PET F-FDG studies for presurgical evaluation of patients with medial temporal lobe epilepsy (MTLE) is well established, it remains unclear whether they can help identify an operculoinsular epileptic focus. This study assesses the value of interictal/ictal regional cerebral blood flow (rCBF) SPECT and FDG PET for OIE diagnosis. METHODS Eighteen patients with proven OIE who underwent interictal/ictal rCBF SPECT and/or FDG-PET prior to epilepsy surgery were identified from our clinical database and were compared with a group of 18 patients who underwent MTLE surgery. Regional cerebral blood flow SPECT and FDG PET images were reevaluated visually by an expert reader blind to clinical data. RESULTS Interictal/ictal rCBF SPECT correctly identified an operculoinsular focus in 11 (65%) of 17 OIE patients and was misleading in 3 cases (18%). Secondary activation in areas connected to the insula was often observed. In the MTLE group, the area of maximal increased perfusion was congruent in 12 (75%) of 16 patients and extended to the ipsilateral insula in 1 patient. FDG PET findings were concordant with the epileptic focus in 8 (47%) of 17 OIE patients and were misleading in 4 (24%), whereas they were concordant in all MTLE patients. CONCLUSIONS Interictal/ictal rCBF SPECT can identify a concordant operculoinsular focus in a significant proportion of OIE patients and offers a valuable diagnostic tool in nonlesional cases. By contrast, the value of interictal FDG PET in this population is more equivocal.

The Tc-99m HMPAO brain imaging confirmed marked hypoperfusion secondary to anomalous cerebral venous drainage of the Sturge-Weber syndrome. Until now, this had been a hypothesis suggested by results obtained from conventional brain scans and cerebral arteriography.

The authors report a case of intestinal lymphangiectasia that was clearly demonstrated during abdominal lymphoscintigraphy using Tc-99m Sb colloid. Although lymphoscintigraphy has been used in many different clinical situations, this is, to our knowledge, the first scintigraphic description of this disease. Clinical and pathologic presentations of intestinal lymphangiectasia are briefly reviewed. Some possible approaches to the confirmation of the presence of a protein-losing gastroenteropathy are mentioned.