Standardized evaluation of algorithms for computer-aided diagnosis of dementia based on structural MRI: The CADDementia challenge

Algorithms for computer-aided diagnosis of dementia based on structural MRI have demonstrated high performance in the literature, but are difficult to compare as different data sets and methodology were used for evaluation. In addition, it is unclear how the algorithms would perform on previously unseen data, and thus, how they would perform in clinical practice when there is no real opportunity to adapt the algorithm to the data at hand. To address these comparability, generalizability and clinical applicability issues, we organized a grand challenge that aimed to objectively compare algorithms based on a clinically representative multi-center data set. Using clinical practice as the starting point, the goal was to reproduce the clinical diagnosis. Therefore, we evaluated algorithms for multi-class classification of three diagnostic groups: patients with probable Alzheimer's disease, patients with mild cognitive impairment and healthy controls. The diagnosis based on clinical criteria was used as reference standard, as it was the best available reference despite its known limitations. For evaluation, a previously unseen test set was used consisting of 354 T1-weighted MRI scans with the diagnoses blinded. Fifteen research teams participated with a total of 29 algorithms. The algorithms were trained on a small training set (n = 30) and optionally on data from other sources (e.g., the Alzheimer's Disease Neuroimaging Initiative, the Australian Imaging Biomarkers and Lifestyle flagship study of aging). The best performing algorithm yielded an accuracy of 63.0% and an area under the receiver-operating-characteristic curve (AUC) of 78.8%. In general, the best performances were achieved using feature extraction based on voxel-based morphometry or a combination of features that included volume, cortical thickness, shape and intensity. The challenge is open for new submissions via the web-based framework: http://caddementia.grand-challenge.org.

A Diagnostic Assessment Of Evolutionary Multiobjective Optimization For Water Resources Systems

This study contributes a rigorous diagnostic assessment of state-of-the-art multiobjective evolutionary algorithms (MOEAs) and highlights key advances that the water resources field can exploit to better discover the critical tradeoffs constraining our systems. This study provides the most comprehensive diagnostic assessment of MOEAs for water resources to date, exploiting more than 100,000 MOEA runs and trillions of design evaluations. The diagnostic assessment measures the effectiveness, efficiency, reliability, and controllability of ten benchmark MOEAs for a representative suite of water resources applications addressing rainfall-runoff calibration, long-term groundwater monitoring (LTM), and risk-based water supply portfolio planning. The suite of problems encompasses a range of challenging problem properties including (1) many-objective formulations with 4 or more objectives, (2) multi-modality (or false optima), (3) nonlinearity, (4) discreteness, (5) severe constraints, (6) stochastic objectives, and (7) non-separability (also called epistasis). The applications are representative of the dominant problem classes that have shaped the history of MOEAs in water resources and that will be dominant foci in the future. Recommendations are provided for which modern MOEAs should serve as tools and benchmarks in the future water resources literature.

Intestinal current measurement for diagnostic classification of patients with questionable cystic fibrosis: validation and reference data

In questionable cystic fibrosis (CF), mild or monosymptomatic phenotypes frequently cause diagnostic difficulties despite detailed algorithms. CF transmembrane conductance regulator (CFTR)-mediated ion transport can be studied ex vivo in rectal biopsies by intestinal current measurement (ICM).

High specificity of line-immunoassay based algorithms for recent HIV-1 infection independent of viral subtype and stage of disease

Background Serologic testing algorithms for recent HIV seroconversion (STARHS) provide important information for HIV surveillance. We have shown that a patient's antibody reaction in a confirmatory line immunoassay (INNO-LIATM HIV I/II Score, Innogenetics) provides information on the duration of infection. Here, we sought to further investigate the diagnostic specificity of various Inno-Lia algorithms and to identify factors affecting it. Methods Plasma samples of 714 selected patients of the Swiss HIV Cohort Study infected for longer than 12 months and representing all viral clades and stages of chronic HIV-1 infection were tested blindly by Inno-Lia and classified as either incident (up to 12 m) or older infection by 24 different algorithms. Of the total, 524 patients received HAART, 308 had HIV-1 RNA below 50 copies/mL, and 620 were infected by a HIV-1 non-B clade. Using logistic regression analysis we evaluated factors that might affect the specificity of these algorithms. Results HIV-1 RNA <50 copies/mL was associated with significantly lower reactivity to all five HIV-1 antigens of the Inno-Lia and impaired specificity of most algorithms. Among 412 patients either untreated or with HIV-1 RNA ≥50 copies/mL despite HAART, the median specificity of the algorithms was 96.5% (range 92.0-100%). The only factor that significantly promoted false-incident results in this group was age, with false-incident results increasing by a few percent per additional year. HIV-1 clade, HIV-1 RNA, CD4 percentage, sex, disease stage, and testing modalities exhibited no significance. Results were similar among 190 untreated patients. Conclusions The specificity of most Inno-Lia algorithms was high and not affected by HIV-1 variability, advanced disease and other factors promoting false-recent results in other STARHS. Specificity should be good in any group of untreated HIV-1 patients.

A computer-aided diagnostic system to characterize CT focal liver lesions: design and optimization of a neural network classifier

In this paper, a computer-aided diagnostic (CAD) system for the classification of hepatic lesions from computed tomography (CT) images is presented. Regions of interest (ROIs) taken from nonenhanced CT images of normal liver, hepatic cysts, hemangiomas, and hepatocellular carcinomas have been used as input to the system. The proposed system consists of two modules: the feature extraction and the classification modules. The feature extraction module calculates the average gray level and 48 texture characteristics, which are derived from the spatial gray-level co-occurrence matrices, obtained from the ROIs. The classifier module consists of three sequentially placed feed-forward neural networks (NNs). The first NN classifies into normal or pathological liver regions. The pathological liver regions are characterized by the second NN as cyst or "other disease." The third NN classifies "other disease" into hemangioma or hepatocellular carcinoma. Three feature selection techniques have been applied to each individual NN: the sequential forward selection, the sequential floating forward selection, and a genetic algorithm for feature selection. The comparative study of the above dimensionality reduction methods shows that genetic algorithms result in lower dimension feature vectors and improved classification performance.

Simple Estimation of Incident HIV Infection Rates in Notification Cohorts Based on Window Periods of Algorithms for Evaluation of Line-Immunoassay Result Patterns

Background Tests for recent infections (TRIs) are important for HIV surveillance. We have shown that a patient's antibody pattern in a confirmatory line immunoassay (Inno-Lia) also yields information on time since infection. We have published algorithms which, with a certain sensitivity and specificity, distinguish between incident (< = 12 months) and older infection. In order to use these algorithms like other TRIs, i.e., based on their windows, we now determined their window periods. Methods We classified Inno-Lia results of 527 treatment-naïve patients with HIV-1 infection < = 12 months according to incidence by 25 algorithms. The time after which all infections were ruled older, i.e. the algorithm's window, was determined by linear regression of the proportion ruled incident in dependence of time since infection. Window-based incident infection rates (IIR) were determined utilizing the relationship ‘Prevalence = Incidence x Duration’ in four annual cohorts of HIV-1 notifications. Results were compared to performance-based IIR also derived from Inno-Lia results, but utilizing the relationship ‘incident = true incident + false incident’ and also to the IIR derived from the BED incidence assay. Results Window periods varied between 45.8 and 130.1 days and correlated well with the algorithms' diagnostic sensitivity (R2 = 0.962; P<0.0001). Among the 25 algorithms, the mean window-based IIR among the 748 notifications of 2005/06 was 0.457 compared to 0.453 obtained for performance-based IIR with a model not correcting for selection bias. Evaluation of BED results using a window of 153 days yielded an IIR of 0.669. Window-based IIR and performance-based IIR increased by 22.4% and respectively 30.6% in 2008, while 2009 and 2010 showed a return to baseline for both methods. Conclusions IIR estimations by window- and performance-based evaluations of Inno-Lia algorithm results were similar and can be used together to assess IIR changes between annual HIV notification cohorts.

Patterns of care in recurrent glioblastoma in Switzerland: a multicentre national approach based on diagnostic nodes

Despite moderate improvements in outcome of glioblastoma after first-line treatment with chemoradiation recent clinical trials failed to improve the prognosis of recurrent glioblastoma. In the absence of a standard of care we aimed to investigate institutional treatment strategies to identify similarities and differences in the pattern of care for recurrent glioblastoma. We investigated re-treatment criteria and therapeutic pathways for recurrent glioblastoma of eight neuro-oncology centres in Switzerland having an established multidisciplinary tumour-board conference. Decision algorithms, differences and consensus were analysed using the objective consensus methodology. A total of 16 different treatment recommendations were identified based on combinations of eight different decision criteria. The set of criteria implemented as well as the set of treatments offered was different in each centre. For specific situations, up to 6 different treatment recommendations were provided by the eight centres. The only wide-range consensus identified was to offer best supportive care to unfit patients. A majority recommendation was identified for non-operable large early recurrence with unmethylated MGMT promoter status in the fit patients: here bevacizumab was offered. In fit patients with late recurrent non-operable MGMT promoter methylated glioblastoma temozolomide was recommended by most. No other majority recommendations were present. In the absence of strong evidence we identified few consensus recommendations in the treatment of recurrent glioblastoma. This contrasts the limited availability of single drugs and treatment modalities. Clinical situations of greatest heterogeneity may be suitable to be addressed in clinical trials and second opinion referrals are likely to yield diverging recommendations.

Decreasing Proportion of Recent Infections among Newly Diagnosed HIV-1 Cases in Switzerland, 2008 to 2013 Based on Line-Immunoassay-Based Algorithms.

BACKGROUND: HIV surveillance requires monitoring of new HIV diagnoses and differentiation of incident and older infections. In 2008, Switzerland implemented a system for monitoring incident HIV infections based on the results of a line immunoassay (Inno-Lia) mandatorily conducted for HIV confirmation and type differentiation (HIV-1, HIV-2) of all newly diagnosed patients. Based on this system, we assessed the proportion of incident HIV infection among newly diagnosed cases in Switzerland during 2008-2013. METHODS AND RESULTS: Inno-Lia antibody reaction patterns recorded in anonymous HIV notifications to the federal health authority were classified by 10 published algorithms into incident (up to 12 months) or older infections. Utilizing these data, annual incident infection estimates were obtained in two ways, (i) based on the diagnostic performance of the algorithms and utilizing the relationship 'incident = true incident + false incident', (ii) based on the window-periods of the algorithms and utilizing the relationship 'Prevalence = Incidence x Duration'. From 2008-2013, 3'851 HIV notifications were received. Adult HIV-1 infections amounted to 3'809 cases, and 3'636 of them (95.5%) contained Inno-Lia data. Incident infection totals calculated were similar for the performance- and window-based methods, amounting on average to 1'755 (95% confidence interval, 1588-1923) and 1'790 cases (95% CI, 1679-1900), respectively. More than half of these were among men who had sex with men. Both methods showed a continuous decline of annual incident infections 2008-2013, totaling -59.5% and -50.2%, respectively. The decline of incident infections continued even in 2012, when a 15% increase in HIV notifications had been observed. This increase was entirely due to older infections. Overall declines 2008-2013 were of similar extent among the major transmission groups. CONCLUSIONS: Inno-Lia based incident HIV-1 infection surveillance proved useful and reliable. It represents a free, additional public health benefit of the use of this relatively costly test for HIV confirmation and type differentiation.

Novel speech signal processing algorithms for high-accuracy classification of Parkinson's disease

There has been considerable recent research into the connection between Parkinson's disease (PD) and speech impairment. Recently, a wide range of speech signal processing algorithms (dysphonia measures) aiming to predict PD symptom severity using speech signals have been introduced. In this paper, we test how accurately these novel algorithms can be used to discriminate PD subjects from healthy controls. In total, we compute 132 dysphonia measures from sustained vowels. Then, we select four parsimonious subsets of these dysphonia measures using four feature selection algorithms, and map these feature subsets to a binary classification response using two statistical classifiers: random forests and support vector machines. We use an existing database consisting of 263 samples from 43 subjects, and demonstrate that these new dysphonia measures can outperform state-of-the-art results, reaching almost 99% overall classification accuracy using only ten dysphonia features. We find that some of the recently proposed dysphonia measures complement existing algorithms in maximizing the ability of the classifiers to discriminate healthy controls from PD subjects. We see these results as an important step toward noninvasive diagnostic decision support in PD.

Signposting for diagnosis of Autism Spectrum Disorder using the Diagnostic Interview for Social and Communication Disorders (DISCO)

Recent research has investigated the capability of the Diagnostic and Statistical Manual for Mental Disorders (DSM-5) descriptions to identify individuals who should receive a diagnosis of Autism Spectrum Disorder (ASD) using standardised diagnostic instruments. Building on previous research investigating behaviours essential for the diagnosis of DSM-5 ASD, the current study investigated the sensitivity and specificity of a set of 14 items derived from the Diagnostic Interview for Social and Communication Disorders (DISCO Signposting set) that have potential for signposting the diagnosis of autism according to both the new DSM-5 criteria for ASD and ICD-10 criteria for Childhood Autism. An algorithm threshold for the Signposting set was calculated in Sample 1 (n = 67), tested in an independent validation sample (Sample 2; n = 78), and applied across age and ability sub-groups in Sample 3 (n = 190). The algorithm had excellent predictive validity according to best estimate clinical diagnosis (Samples 1 and 2) and excellent agreement with established algorithms for both DSM-5 and ICD-10 (all samples). The signposting set has potential to inform our understanding of the profile of ASD in relation to other neurodevelopmental disorders and to form the basis of a Signposting Interview for use in clinical practice.

Implementation of a machine tool performance measurement and diagnostic system and its impact on parts verification

Five axis machine tools are increasing and becoming more popular as customers demand more complex machined parts. In high value manufacturing, the importance of machine tools in producing high accuracy products is essential. High accuracy manufacturing requires producing parts in a repeatable manner and precision in compliance to the defined design specifications. The performance of the machine tools is often affected by geometrical errors due to a variety of causes including incorrect tool offsets, errors in the centres of rotation and thermal growth. As a consequence, it can be difficult to produce highly accurate parts consistently. It is, therefore, essential to ensure that machine tools are verified in terms of their geometric and positioning accuracy. When machine tools are verified in terms of their accuracy, the resulting numerical values of positional accuracy and process capability can be used to define design for verification rules and algorithms so that machined parts can be easily produced without scrap and little or no after process measurement. In this paper the benefits of machine tool verification are listed and a case study is used to demonstrate the implementation of robust machine tool performance measurement and diagnostics using a ballbar system.

Advancing Bag-of-visual-words Representations For Lesion Classification In Retinal Images.

Diabetic Retinopathy (DR) is a complication of diabetes that can lead to blindness if not readily discovered. Automated screening algorithms have the potential to improve identification of patients who need further medical attention. However, the identification of lesions must be accurate to be useful for clinical application. The bag-of-visual-words (BoVW) algorithm employs a maximum-margin classifier in a flexible framework that is able to detect the most common DR-related lesions such as microaneurysms, cotton-wool spots and hard exudates. BoVW allows to bypass the need for pre- and post-processing of the retinographic images, as well as the need of specific ad hoc techniques for identification of each type of lesion. An extensive evaluation of the BoVW model, using three large retinograph datasets (DR1, DR2 and Messidor) with different resolution and collected by different healthcare personnel, was performed. The results demonstrate that the BoVW classification approach can identify different lesions within an image without having to utilize different algorithms for each lesion reducing processing time and providing a more flexible diagnostic system. Our BoVW scheme is based on sparse low-level feature detection with a Speeded-Up Robust Features (SURF) local descriptor, and mid-level features based on semi-soft coding with max pooling. The best BoVW representation for retinal image classification was an area under the receiver operating characteristic curve (AUC-ROC) of 97.8% (exudates) and 93.5% (red lesions), applying a cross-dataset validation protocol. To assess the accuracy for detecting cases that require referral within one year, the sparse extraction technique associated with semi-soft coding and max pooling obtained an AUC of 94.2 ± 2.0%, outperforming current methods. Those results indicate that, for retinal image classification tasks in clinical practice, BoVW is equal and, in some instances, surpasses results obtained using dense detection (widely believed to be the best choice in many vision problems) for the low-level descriptors.

High Diagnostic Accuracy And Reproducibility Of Fine-needle Aspiration Cytology For Diagnosing Salivary Gland Tumors: Cytohistologic Correlation In 182 Cases.

The purpose of this study was to assess the efficacy and reproducibility of the cytologic diagnosis of salivary gland tumors (SGTs) using fine-needle aspiration cytology (FNAC). The study aimed to determine diagnostic accuracy, sensitivity, and specificity and to evaluate the extent of interobserver agreement. We retrospectively evaluated SGTs from the files of the Division of Pathology at the Clinics Hospital of São Paulo and Piracicaba Dental School between 2000 and 2006. We performed cytohistologic correlation in 182 SGTs. The sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy were 94%, 100%, 100%, 100%, and 99%, respectively. The interobserver cytologic reproducibility showed significant statistical concordance (P < .0001). FNAC is an effective tool for performing a reliable preoperative diagnosis in SGTs and shows high diagnostic accuracy and consistent interobserver reproducibility. Further FNAC studies analyzing large samples of malignant SGTs and reactive salivary lesions are needed to confirm their accuracy.

Newborn Hearing Screening And Early Diagnostic In The Nicu.

The aim was to describe the outcome of neonatal hearing screening (NHS) and audiological diagnosis in neonates in the NICU. The sample was divided into Group I: neonates who underwent NHS in one step and Group II: neonates who underwent a test and retest NHS. NHS procedure was automated auditory brainstem response. NHS was performed in 82.1% of surviving neonates. For GI, referral rate was 18.6% and false-positive was 62.2% (normal hearing in the diagnostic stage). In GII, with retest, referral rate dropped to 4.1% and false-positive to 12.5%. Sensorineural hearing loss was found in 13.2% of infants and conductive in 26.4% of cases. There was one case of auditory neuropathy spectrum (1.9%). Dropout rate in whole process was 21.7% for GI and 24.03% for GII. We concluded that it was not possible to perform universal NHS in the studied sample or, in many cases, to apply it within the first month of life. Retest reduced failure and false-positive rate and did not increase evasion, indicating that it is a recommendable step in NHS programs in the NICU. The incidence of hearing loss was 2.9%, considering sensorineural hearing loss (0.91%), conductive (1.83%) and auditory neuropathy spectrum (0.19%).