Durval C. Costa

Differentiation of frontotemporal dementia from dementia with Lewy bodies using FP-CIT SPECT

Introduction There is increasing evidence that imaging with [123I]FP-CIT SPECT is helpful in differentiating dementia with Lewy bodies (DLB) from Alzheimers disease (AD) but it is not known how well the scan performs in differentiating DLB from frontotemporal dementia (FTD). Method We compared the striatal dopamine transporter (DAT) binding in FTD (n=12), DLB (n=10) and AD (n=9) by visually rating the caudate and putamen on [123I]FP-CIT SPECT scans. Results The majority (9/10) of DLB cases had an abnormal scan and a significant reduction of uptake of DAT binding in the putamen and the caudate. A third (4/12) of the FTD cases also had an abnormal scan and a significant reduction in uptake in the putamen and the caudate. In contrast, only one out of nine AD cases had an abnormal scan. Significant differences were found when comparisons were made between the groups for visual analysis of the entire scan (p=0.001) and the four regions of interest (p=0.001 – 0.013). In contrast to the AD group (specificity of scan 89%), the specificity of [123I]FP-CIT SPECT scans was reduced in the FTD group to 67%. Three quarters of the study population had at least one extrapyramidal motor sign (EPMS), with bradykinesia being the most common EPMS in both FTD (83%) and DLB (70%). Conclusions This study highlights to clinicians that a positive (abnormal) [123I]FP-CIT SPECT scan, even in a patient with an EPMS, does not exclude the diagnosis of FTD and emphasises the importance of a comprehensive clinical evaluation and a detailed cognitive assessment.

Predicting conversion from MCI to AD with FDG-PET brain images at different prodromal stages

Early diagnosis of Alzheimer disease (AD), while still at the stage known as mild cognitive impairment (MCI), is important for the development of new treatments. However, brain degeneration in MCI evolves with time and differs from patient to patient, making early diagnosis a very challenging task. Despite these difficulties, many machine learning techniques have already been used for the diagnosis of MCI and for predicting MCI to AD conversion, but the MCI group used in previous works is usually very heterogeneous containing subjects at different stages. The goal of this paper is to investigate how the disease stage impacts on the ability of machine learning methodologies to predict conversion. After identifying the converters and estimating the time of conversion (TC) (using neuropsychological test scores), we devised 5 subgroups of MCI converters (MCI-C) based on their temporal distance to the conversion instant (0, 6, 12, 18 and 24 months before conversion). Next, we used the FDG-PET images of these subgroups and trained classifiers to distinguish between the MCI-C at different stages and stable non-converters (MCI-NC). Our results show that MCI to AD conversion can be predicted as early as 24 months prior to conversion and that the discriminative power of the machine learning methods decreases with the increasing temporal distance to the TC, as expected. These findings were consistent for all the tested classifiers. Our results also show that this decrease arises from a reduction in the information contained in the regions used for classification and by a decrease in the stability of the automatic selection procedure.

Syllabus for Postgraduate Specialization in Nuclear Medicine – 2011/2012 Update

Nuclear medicine (NM) is a branch of medicine that uses unsealed radioactive substances for diagnosis and therapy. NM became an independent medical specialty under the European Directives in 1988. The minimum duration of the postgraduate specialized training in the European Union is 4 years, but may be extended beyond this period according to the requirements for training in other clinical disciplines. Candidates for specialized training should have a good general background in internal medicine. More detailed knowledge about those conditions which may need to be investigated or treated by NM techniques has to be acquired. Some complementary imaging and biological methods as far as they relate to NM procedures must be mastered. Training in basic sciences, such as pharmacokinetics, radiochemistry, instrumentation, image processing, dosimetry and quality control is required. The quality of training has to be objectively assessed, using a final examination on a national basis covering basic sciences and clinical skills, after satisfactory completion of a minimum number of courses and/or workshops and a formally organized and controlled practical training. Each training programme should contain a standard against which the progress of the trainee can be assessed for each element of the syllabus. The assessment may take the form of an interview, a written paper, an essay, a set of multiple-choice questions or an oral examination of displayed images of various NM techniques in clinical practice. Continuous assessment is an alternative. Each end of year or training programme assessment should carry a score that indicates how the candidate has progressed against the set target. Successful trainees are awarded with a final certificate, degree or diploma that is recognized by the government, local health authority and hospital as an assurance of specialist competence in NM. The clinical training of physicians specializing in NM should include: (1) a minimal theoretical foundation of the general principles of NM with active participation in clinical presentations, seminars and meetings and (2) in vivo diagnostic procedures performance. Personal responsibility (including indication, justification, performance and interpretation) must be taken for at least 3,000 in vivo NM diagnostic procedures, with a broad spectrum of the most currently used procedures. The list of the procedures published in the syllabus will be subject to revision. It is recommended that a period of training be spent away from the main department in at least one other On behalf of the Educational and Syllabus Committee andthe Executive Committee, Union Européenne des Médecins Spécialistes/ European Union of Medical Specialists, Section of Nuclear Medicine/ European Board of Nuclear Medicine (UEMS/EBNM). Other committee members actively participating in the planning, discussion and writing of the present syllabus update are for the UEMS/EBNM Educational and Syllabus Committee A.K.A. Ahonen (Finland), F. Brunotte (France), R. Hustinx (Belgium), H. Sayman (Turkey) and J. Pou Ucha (Spain) as young EANM member representative and for the UEMS/EBNM Executive Committee M. Bajc and L.S. Maffioli.

3D brain image-based diagnosis of Alzheimer's disease: Bringing medical vision into feature selection

Expert physicians are able to attain good Alzheimers Disease (AD) diagnostic accuracy, relying on visual inspection of Positron Emission Tomography (PET) images only. Nevertheless, computerized methods have been implemented with similar or even better performance. We investigate the potential of the physicians experienced visual inspection to guide feature selection, in an automatic classification procedure. Eye tracking methodology is employed to obtain a model of the physicians visual behavior, which allows for the sampling of voxel intensity features that are then fed to an SVM classifier. This approach is compared with commonly used automatic feature selection alternatives. Image data were taken from the Alzheimers Disease Neuroimaging Initiative database. The results show that the proposed approach marginally improves accuracy in AD vs. CN classification, but for MCI vs. CN and AD vs. MCI it presents lower performance.

Extraction, selection and comparison of features for an effective automated computer-aided diagnosis of Parkinson’s disease based on [123I]FP-CIT SPECT images

PurposeThis work aimed to assess the potential of a set of features extracted from [123I]FP-CIT SPECT brain images to be used in the computer-aided “in vivo” confirmation of dopaminergic degeneration and therefore to assist clinical decision to diagnose Parkinson’s disease.MethodsSeven features were computed from each brain hemisphere: five standard features related to uptake ratios on the striatum and two features related to the estimated volume and length of the striatal region with normal uptake. The features were tested on a dataset of 652 [123I]FP-CIT SPECT brain images from the Parkinson’s Progression Markers Initiative. The discrimination capacities of each feature individually and groups of features were assessed using three different machine learning techniques: support vector machines (SVM), k-nearest neighbors and logistic regression.ResultsCross-validation results based on SVM have shown that, individually, the features that generated the highest accuracies were the length of the striatal region (96.5%), the putaminal binding potential (95.4%) and the striatal binding potential (93.9%) with no statistically significant differences among them. The highest classification accuracy was obtained using all features simultaneously (accuracy 97.9%, sensitivity 98% and specificity 97.6%). Generally, slightly better results were obtained using the SVM with no statistically significant difference to the other classifiers for most of the features.ConclusionsThe length of the striatal region uptake is clinically useful and highly valuable to confirm dopaminergic degeneration “in vivo” as an aid to the diagnosis of Parkinson’s disease. It compares fairly well to the standard uptake ratio-based features, reaching, at least, similar accuracies and is easier to obtain automatically. Thus, we propose its day to day clinical use, jointly with the uptake ratio-based features, in the computer-aided diagnosis of dopaminergic degeneration in Parkinson’s disease.

The new UEMS-EACCME criteria for accreditation of live educational events (LEEs): another step forward to improve the quality of continuing medical education (CME) in Europe

Continuing medical education (CME) in Europe is a complex, multilevel, multilingual and multi-regulatory, rapidly growing learning system. An increasing number of countries are adopting voluntary or compulsory systems of CME participation for physicians under the stimulus of growing evidence that CME good quality systems are likely to improve both clinical practice and patient outcomes [1, 2]. Requirements of educational programmes are also rapidly growing in the effort to enhance CME quality and to unify CME principles and standards with the shared goal of “improved patient outcomes” beyond country borders. As the Good CME Practice Group published in its document to drive European CME, quality should be based upon four core principles: (1) adequate education, (2) productive education, (3) transparency and (4) fair balance.

Continuing Medical Education Committee and UEMS-EACCME

Continuing medical education (CME) and continuing professional development (CPD) are the mainstay for ensuring physicians’ competence and fitness to practice. At present, the rapidly evolving interplay among society, economy and technology along with rapid migration of patients and doctors within the EU are reshaping medical practice. Knowledge and skills acquired during undergraduate and postgraduate professional medical education are inadequate for ensuring competence and performance throughout a working career. Thorough organized continuing education programmes and individual learning activities are necessary. Health-care professionals are expected to keep their abilities up to date in through efficient knowledge management practices (evidence-informed practice) and self-directed learning strategies (life-long learning) [1]. For this reason the European Union of Medical Specialists (UEMS) has focused on CME-CPD, considering CPD a cornerstone of quality assurance in medical care [2]. In November 2011, Dr. Andrzey Rys, of the European Commission’s Directorate-General for Health and Consumers, addressing the first UEMS Conference on CME-CPD held in Brussels, highlighted the importance of health-care professionals updating their knowledge and skills in order to be properly trained to provide high-quality standards of care [3]. CME is fundamental to good medical practice and for delivery of high-quality patient care. Based upon the UEMS Charter on CME of Medical Specialists 1994, chapter 4, article 6, CME also represents a moral and ethical commitment for each medical specialist [4]. CME can be defined as “educational activities serving to maintain, develop or increase knowledge, skills and professional performance and relationships used by physicians to provide services to patients, the public, and the profession”. Therefore all continuing educational activities assisting medical professionals in carrying out their duties more effectively and efficiently are encompassed in the definition. Historically, the CME learning model holds that continuous learning is an adjunct to daily practice. As such, the goal of CME would be restricted to knowledge, rather than doing, changing practice, team management, social communication or research. The term CPD better reflects where CME is heading and covers the continuum of life-long medical education, at all stages of a career. In its 2001 policy paper (the Basel Declaration on CPD) the UEMS defines CPD as “the educative means of updating, developing and enhancing how doctors apply their knowledge, skills and attitudes required in their working lives” [5]. The goal of CPD is to improve all aspects of medical practitioners work performance, and the UEMS remains committed to this concept. This comprises educating medical specialists for the wider responsibilities required for specialty practice [6].

Analysis of gated myocardial perfusion spect images based on computational image registration

Myocardial perfusion is commonly studied based on the evaluation of the left ventricular function using stress-rest gated myocardial perfusion single photon emission computed tomography (GSPECT), which provides a suitable identification of the myocardial region, facilitating the localization and characterization of perfusion abnormalities. The prevalence and clinical predictors of myocardial ischemia and infarct can be assessed from GSPECT images. Here, techniques of image analysis, namely image segmentation and registration, are integrated to automatically extract a set of features from myocardial perfusion SPECT images that are automatically classified as related to myocardial perfusion disorders or not. The solution implemented can be divided into two main parts: 1) building of a template image, segmentation of the template image and computation of its dimensions; 2) registration of the image under study with the template image previously built, extraction of the image features, statistical analysis and classification. It should be noted that the first step just needs to be performed once for a particular population. Hence, algorithms of image segmentation, registration and classification were used, specifically of k-means clustering, rigid and deformable registration and classification. The computational solution developed was tested using 180 3D images from 48 patients with healthy cardiac condition and 72 3D images from 12 patients with cardiac diseases, which were reconstructed using the filtered back projection algorithm and a low pass Butterworth filter or iterative algorithms. The images were classified into two classes: “abnormality present” and “abnormality not present”. The classification was assessed using five parameters: sensitivity, specificity, precision, accuracy and mean error rate. The results obtained shown that the solution is effective, both for female and male cardiac SPECT images that can have very different structural dimensions. Particularly, the solution demonstrated reasonable robustness against the two major difficulties in SPECT image analysis: image noise and low resolution. Furthermore, the classifier used demonstrated good specificity and accuracy, Table 1.

Texton-based diagnosis of Alzheimer's disease

The textural content of FDG-PET brain images has been shown to be useful for the diagnosis of Alzheimers disease (AD) and Mild Cognitive Impairment (MCI). In this paper, we investigate the use of the textons method [1], a powerful texture extraction procedure that uses a full statistical representation of the response of the image to a set of filters. We also extend the MR8 filter bank used in [1] to 3D in order to match the dimensionality of FDG-PET images, while maintaining important properties such as invariance to rotation and a low dimensionality of the filter response space. We propose two methods to tackle difficulties inherent to the extraction and classification of texture from images whose appearance varies over space and to the fact that most regions of the image are not affected by AD or MCI. The first method selects only the voxels with the most discriminative filter responses, while the second method focuses on brain regions manually labeled by an expert physician. Experiments showed that the proposed approaches outperformed the more common one that uses voxel intensities directly as features both in the diagnosis of AD and MCI. It was also observed that the discriminative power of certain brain regions increased significantly when the texton based analysis was performed.

UEMS/EBNM endeavour – celebrations keep going!

The European Association of Nuclear Medicine web site states under “History” that “The EANM was founded on September 6, 1985 in London as the result of a merger between the Society of Nuclear Medicine Europe and the European Nuclear Medicine Society”. It was the last day of the 1985 European Nuclear Medicine Congress held in London [1]. I was one of the many lucky ones to see that happen. After completing nuclear medicine specialization training in Portugal (1984), I was in London (at the Institute of Nuclear Medicine, Middlesex Hospital and Medical School) finishing a course of studies to be awarded the MSc degree [2] in nuclear medicine and preparing to enter a PhD course of studies at the Faculty of Medical Sciences, UCL, University of London [3]. In Milan 2012 the nuclear medicine community was happily celebrating the “silver jubilee” of the EANM. All those interested in the use of radiopharmaceuticals for diagnosis, therapy and research joined in Milan to wish a happy future for nuclear medicine. The UEMS Section and the European Board of Nuclear Medicine (UEMS/EBNM) were present to demonstrate its importance in the practice of clinical nuclear medicine. Several events took place and the results were highly successful. Next year it is 25 years since nuclear medicine was recognized as a medical specialty in Europe (1988). Formal recognition as a separate medical specialty within the UEMS was achieved in 1989. We have, therefore, two years to celebrate the 25th Anniversary (“silver jubilee”) of the recognition of nuclear medicine as a mono-specialty in Europe and UEMS. But celebrations will continue into 2015, since it was in 1990 that the Section of Nuclear Medicine was created in the UEMS. The present outlook is therefore one of recurrent festivities. Outcome measures need to be implemented in order to assess performance, efficacy and determine the benefits for the specialty arising from our work. These have to focus around our main objectives: