Ugly Duckling Sign as a Major Factor of Efficiency in Melanoma Detection.

Importance: Understanding the contribution of the ugly duckling sign (a nevus that is obviously different from the others in a given individual) in intrapatient comparative analysis (IPCA) of nevi may help improve the detection of melanoma. Objectives: To assess the agreement of dermatologists on identification of the ugly duckling sign and estimate the contribution of IPCA to the diagnosis of melanoma. Design, Setting, and Participants: The same 2089 digital images of the nevi of a sample of 80 patients (mean age, 42 years [range, 19-80 years]; 33 men and 47 women), as well as 766 dermoscopic images from a subset of 30 patients (mean age, 40 years [range, 21-75 years]; 12 men and 18 women), were randomly presented to the same 9 dermatologists for blinded assessment from September 22, 2011, to April 1, 2013. The first experiment was designed to mimic an IPCA situation, with images of all nevi of each patient shown to the dermatologists, who were asked to identify ugly duckling nevi (UDN). The second experiment was designed to mimic a lesion-focused analysis to identify morphologically suspicious nevi. Data analysis was conducted from November 1, 2012, to June 1, 2013. Main Outcomes and Measures: Number of nevi labeled UDN and morphologically suspicious nevi, specificity of lesion-focused analysis and IPCA, and number of nevi identified for biopsy. Results: Of the 2089 clinical images of nevi from 80 patients (median number of nevi per patient, 26 [range, 8-81]) and 766 dermoscopic images (median number of nevi per patient, 19 [range, 8-81]), all melanomas were labeled UDN and as morphologically suspicious nevi by the 9 dermatologists. The median number of UDN detected per patient was 0.8 among the clinical images of nevi (mean, 1.0; range, 0.48-2.03) and 1.26 among the dermoscopic images (mean, 1.4; range, 1.00-2.06). The propensity to consider more or fewer nevi as having ugly duckling signs was independent of the presentation (clinical or dermoscopic). The agreement among the dermatologists regarding UDN was lower with dermoscopic images (mean pairwise agreement, 0.53 for clinical images and 0.50 for dermoscopic images). The specificity of IPCA was 0.96 for clinical images and 0.95 for dermoscopic images vs 0.88 and 0.85, respectively, for lesion-focused analysis. When both IPCA and lesion-focused analyses were used, the number of nevi considered for biopsy was reduced by a factor of 6.9 compared with lesion-focused analysis alone. Conclusions and Relevance: Intrapatient comparative analysis is of major importance to the effectiveness of the diagnosis of melanoma. Introducing IPCA using the ugly duckling sign in computer-assisted diagnosis systems would be expected to improve performance.

Evidence of a limited intra-individual diversity of nevi: intuitive perception of dominant clusters is a crucial step in the analysis of nevi by dermatologists.

Although nevi are highly polymorphous, it has been suggested that each individual is characterized by only a few dominant patterns of nevi. Therefore, a nevus that does not fit in with these patterns, the "ugly duckling" nevus, is suspicious. Our objective was to study the intra-individual diversity of nevi, using human ability to build "perceived similarity clusters" (PSCs). Nine dermatologists had to cluster all the nevi of 80 patients into PSCs, at the clinical scale (CS) and at the dermoscopic scale (DS) (subset of 30 patients). Nine novices did the same in a subset of 11 patients. The experts identified a mean of 2.8 PSCs/patient at CS. Concordance was higher between experts than between novices at CS and at DS. Despite a trend for more PSCs at DS than at CS, the number of nevus patterns per patient remained low, regardless of the number of nevi. Inter-expert concordance permits a consensus representation of nevus diversity in each individual. Nevus diversity is limited in each patient and constitutes an individual reference system, which we can intuitively perceive. This reference is probably crucial for nevus analysis and melanoma detection and opens perspectives for computer-aided diagnostics.

Structural analysis of fMRI data: a surface-based framework for multi-subject studies.

We present a method for fMRI data group analysis that makes the link between two distinct frameworks: surface-based techniques, which process data in the domain defined by the surface of the cortex, and structural techniques, which use object-based representations of the data as opposed to voxel-based ones. This work is a natural surface-based extension of the volume-based structural approach presented in a previous paper. A multi-scale surface-based representation of individual activation maps is first computed for each subject. Then the inter-subject matching and the activation detection decision are performed jointly by optimization of a Markovian model. Finally, a significance measure is computed in a non-parametric way for the results, in order to assess their relevance and control the risk of type I error. The method is applied on simulated and real data and the results are compared to those produced by standard analyses. The surface-based structural analysis is shown to be particularly robust to inter-subject spatial variability and to produce relevant results with good specificity and sensitivity. We also demonstrate the advantages of the surface-based approach by comparing with the results of a 3D structural analysis.

Brain perfusion SPECT with an automated quantitative tool can identify prodromal Alzheimer's disease among patients with mild cognitive impairment.

OBJECTIVE: To improve diagnosis of early Alzheimer's disease (AD), i.e., prodromal AD, by an automated quantitative tool combining brain perfusion single-photon emission computed tomography (SPECT) images and memory tests scores in order to be applied in clinical practice. PATIENTS AND METHODS: In this prospective, longitudinal, multi-centric study, a baseline (99m)Tc-ECD perfusion SPECT was performed in 83 patients with memory complaint and mild cognitive impairment (MCI). After a 3-year follow-up, 11 patients progressed to Alzheimer's disease (MCI-AD group), and 72 patients remained stable (MCI-S group), including 1 patient who developed mild vascular cognitive impairment. After comparison between the MCI-S and MCI-AD groups with a voxel-based approach, region masks were extracted from the statistically significant clusters and used alone or in combination with Free and Cued Selective Reminding Test (FCSRT) scores for the subject's categorization using linear discriminant analysis. Results were validated using the leave-one-out cross-validation method. RESULTS: Right parietal and hippocampal perfusion was significantly (p<0.05, corrected) decreased in the MCI-AD group as compared to the MCI-S group. The patients' classification in the MCI group using the mean activity in right and left parietal cortex and hippocampus yielded a sensitivity, specificity, and accuracy of 82%, 90%, and 89%, respectively. Combination of SPECT results and FCSRT free recall scores increased specificity to 93%. CONCLUSION: The combination of an automated quantitative tool for brain perfusion SPECT images and memory test scores was able to distinguish, in a group of amnestic MCI, patients at an early stage of AD from patients with stable MCI.

ColorPhylo: A Color Code to Accurately Display Taxonomic Classifications.

Color may be very useful to visualise complex data. As far as taxonomy is concerned, color may help observing various species' characteristics in correlation with classification. However, choosing the number of subclasses to display is often a complex task: on the one hand, assigning a limited number of colors to taxa of interest hides the structure imbedded in the subtrees of the taxonomy; on the other hand, differentiating a high number of taxa by giving them specific colors, without considering the underlying taxonomy, may lead to unreadable results since relationships between displayed taxa would not be supported by the color code. In the present paper, an automatic color coding scheme is proposed to visualise the levels of taxonomic relationships displayed as overlay on any kind of data plot. To achieve this goal, a dimensionality reduction method allows displaying taxonomic "distances" onto a Euclidean two-dimensional space. The resulting map is projected onto a 2D color space (the Hue, Saturation, Brightness colorimetric space with brightness set to 1). Proximity in the taxonomic classification corresponds to proximity on the map and is therefore materialised by color proximity. As a result, each species is related to a color code showing its position in the taxonomic tree. The so called ColorPhylo displays taxonomic relationships intuitively and can be combined with any biological result. A Matlab version of ColorPhylo is available at http://sy.lespi.free.fr/ColorPhylo-homepage.html. Meanwhile, an ad-hoc distance in case of taxonomy with unknown edge lengths is proposed.

Detection of melanoma from dermoscopic images of naevi acquired under uncontrolled conditions.

BACKGROUND AND OBJECTIVE: Several systems for the diagnosis of melanoma from images of naevi obtained under controlled conditions have demonstrated comparable efficiency with dermatologists. However, their robustness to analyze daily routine images was sometimes questionable. The purpose of this work is to investigate to what extent the automatic melanoma diagnosis may be achieved from the analysis of uncontrolled images of pigmented skin lesions. MATERIALS AND METHODS: Images were acquired during regular practice by two dermatologists using Reflex 24 x 36 cameras combined with Heine Delta 10 dermascopes. The images were then digitalized using a scanner. In addition, five senior dermatologists were asked to give the diagnosis and therapeutic decision (exeresis) for 227 images of naevi, together with an opinion about the existence of malignancy-predictive features. Meanwhile, a learning by sample classifier for the diagnosis of melanoma was constructed, which combines image-processing with machine-learning techniques. After an automatic segmentation, geometric and colorimetric parameters were extracted from images and selected according to their efficiency in predicting malignancy features. A diagnosis was subsequently provided based on selected parameters. An extensive comparison of dermatologists' and computer results was subsequently performed. RESULTS AND CONCLUSION: The KL-PLS-based classifier shows comparable performances with respect to dermatologists (sensitivity: 95% and specificity: 60%). The algorithm provides an original insight into the clinical knowledge of pigmented skin lesions.

Differential automatic diagnosis between Alzheimer's disease and frontotemporal dementia based on perfusion SPECT images.

OBJECTIVE: Alzheimer's disease (AD) and frontotemporal dementia (FTD) are among the most frequent neurodegenerative cognitive disorders, but their differential diagnosis is difficult. The aim of this study was to evaluate an automatic method returning the probability that a patient suffers from AD or FTD from the analysis of brain perfusion single photon emission computed tomography images. METHODS AND MATERIALS: A set of 116 descriptors corresponding to the average activity in regions of interest was calculated from the images of 82 AD and 91 FTD patients. A set of linear (logistic regression and linear discriminant analysis) and non-linear (support vector machines, k-nearest neighbours, multilayer perceptron and kernel logistic PLS) classification methods was subsequently used to ascertain diagnoses. Validation was carried out by means of the leave-one-out protocol. Diagnoses by the classifier and by four physicians (visual assessment) were compared. Since images were acquired in different hospitals, the impact of the medical centre on the diagnosis of both the classifier and the physicians was investigated. RESULTS: Best results were obtained with support vector machine and partial least squares regression coupled with k-nearest neighbours methods (PLS+K-NN), with an overall accuracy of 88%. PLS+K-NN was however considered as the best method since performances obtained with leave-one-out cross-validation were closer to whole-database learning. The performances of the classifier were higher than those of experts (accuracy ranged from 65 to 72%). Physicians found it more difficult to diagnose the images from centres other than their own, and it affected their performances. CONCLUSIONS: The performances obtained by the classifier for the differential diagnosis of AD and FTD were found convincing. It could help physicians in daily practice, particularly when visual assessment is inconclusive, or when dealing with multicentre data.

Low-dose hyper-radiosensitivity of progressive and regressive cells isolated from a rat colon tumour: impact of DNA repair.

PURPOSE: To ask whether highly metastatic sublines show more marked low-dose hyper-radiosensitivity (HRS) response than poorly metastatic ones. MATERIALS AND METHODS: The progressive (PRO) subline showing tumourigenicity and metastatic potential and the regressive (REG) subline showing neither tumourigenicity nor metastatic potential were both isolated from a parental rat colon tumour. Clonogenic survival, micronuclei and apoptosis, cell cycle distribution, DNA single- (SSB) and double-strand breaks (DSB) induction and repair were examined. RESULTS: HRS phenomenon was demonstrated in PRO subline. Before irradiation, PRO cells show more spontaneous damage than REG cells. After 0.1 Gy, PRO cells displayed: (i) More DNA SSB 15 min post-irradiation, (ii) more unrepaired DNA DSB processed by the non-homologous end-joining (NHEJ) and by the RAD51-dependent recombination pathways, (iii) more micronuclei, than REG cells while neither apoptosis nor p53 phosphorylation nor cell cycle arrest was observed in both sublines. CONCLUSIONS: HRS response of PRO subline may be induced by impairments in NHEJ repair that targets G(1) cells and RAD51-dependent repair that targets S-G(2)/M cells. The cellular consequences of such impairments are a failure to arrest in cell cycle, the propagation of damage through cell cycle, mitotic death but not p53-dependent apoptosis. Tumourigenic cells with high metastatic potential may preferentially show HRS response.

DD-HDS: A method for visualization and exploration of high-dimensional data.

Mapping high-dimensional data in a low-dimensional space, for example, for visualization, is a problem of increasingly major concern in data analysis. This paper presents data-driven high-dimensional scaling (DD-HDS), a nonlinear mapping method that follows the line of multidimensional scaling (MDS) approach, based on the preservation of distances between pairs of data. It improves the performance of existing competitors with respect to the representation of high-dimensional data, in two ways. It introduces (1) a specific weighting of distances between data taking into account the concentration of measure phenomenon and (2) a symmetric handling of short distances in the original and output spaces, avoiding false neighbor representations while still allowing some necessary tears in the original distribution. More precisely, the weighting is set according to the effective distribution of distances in the data set, with the exception of a single user-defined parameter setting the tradeoff between local neighborhood preservation and global mapping. The optimization of the stress criterion designed for the mapping is realized by "force-directed placement" (FDP). The mappings of low- and high-dimensional data sets are presented as illustrations of the features and advantages of the proposed algorithm. The weighting function specific to high-dimensional data and the symmetric handling of short distances can be easily incorporated in most distance preservation-based nonlinear dimensionality reduction methods.

Exploration of phylogenetic data using a global sequence analysis method.

BACKGROUND: Molecular phylogenetic methods are based on alignments of nucleic or peptidic sequences. The tremendous increase in molecular data permits phylogenetic analyses of very long sequences and of many species, but also requires methods to help manage large datasets. RESULTS: Here we explore the phylogenetic signal present in molecular data by genomic signatures, defined as the set of frequencies of short oligonucleotides present in DNA sequences. Although violating many of the standard assumptions of traditional phylogenetic analyses--in particular explicit statements of homology inherent in character matrices--the use of the signature does permit the analysis of very long sequences, even those that are unalignable, and is therefore most useful in cases where alignment is questionable. We compare the results obtained by traditional phylogenetic methods to those inferred by the signature method for two genes: RAG1, which is easily alignable, and 18S RNA, where alignments are often ambiguous for some regions. We also apply this method to a multigene data set of 33 genes for 9 bacteria and one archea species as well as to the whole genome of a set of 16 gamma-proteobacteria. In addition to delivering phylogenetic results comparable to traditional methods, the comparison of signatures for the sequences involved in the bacterial example identified putative candidates for horizontal gene transfers. CONCLUSION: The signature method is therefore a fast tool for exploring phylogenetic data, providing not only a pretreatment for discovering new sequence relationships, but also for identifying cases of sequence evolution that could confound traditional phylogenetic analysis.

GENSTYLE: exploration and analysis of DNA sequences with genomic signature.

GENSTYLE (http://Genstyle.imed.jussieu.fr) is a workspace designed for the characterization and classification of nucleotide sequences. Based on the genomic signature paradigm, GENSTYLE focuses on oligonucleotide frequencies in DNA sequences. Users can select sequences of interest in the GENSTYLE companion database, where the whole set of GenBank sequences is grouped per species, or upload their own sequences to work with. Tools for the exploration and analysis of signatures allow (i) identification of the origin of DNA segments (detection of rare species or species for which technical problems prevent fast characterization, such as micro-organisms with slow growth), (ii) analysis of the homogeneity of a genome and isolation of areas with novel functionality (horizontal transfers for example)--and (iii) molecular phylogeny and taxonomy.

Detection and characterization of horizontal transfers in prokaryotes using genomic signature.

Horizontal DNA transfer is an important factor of evolution and participates in biological diversity. Unfortunately, the location and length of horizontal transfers (HTs) are known for very few species. The usage of short oligonucleotides in a sequence (the so-called genomic signature) has been shown to be species-specific even in DNA fragments as short as 1 kb. The genomic signature is therefore proposed as a tool to detect HTs. Since DNA transfers originate from species with a signature different from those of the recipient species, the analysis of local variations of signature along recipient genome may allow for detecting exogenous DNA. The strategy consists in (i) scanning the genome with a sliding window, and calculating the corresponding local signature (ii) evaluating its deviation from the signature of the whole genome and (iii) looking for similar signatures in a database of genomic signatures. A total of 22 prokaryote genomes are analyzed in this way. It has been observed that atypical regions make up approximately 6% of each genome on the average. Most of the claimed HTs as well as new ones are detected. The origin of putative DNA transfers is looked for among approximately 12 000 species. Donor species are proposed and sometimes strongly suggested, considering similarity of signatures. Among the species studied, Bacillus subtilis, Haemophilus Influenzae and Escherichia coli are investigated by many authors and give the opportunity to perform a thorough comparison of most of the bioinformatics methods used to detect HTs.

Analysis of the compositional biases in Plasmodium falciparum genome and proteome using Arabidopsis thaliana as a reference.

Comparative genomic analysis of the malaria causative agent, Plasmodium falciparum, with other eukaryotes for which the complete genome is available, revealed that the genome from P. falciparum was more similar to the genome of a plant, Arabidopsis thaliana, than to other non-apicomplexan taxa. Plant-like sequences are thought to result from horizontal gene transfers after a secondary endosymbiosis involving an algal ancestor. The use of the A. thaliana genome and proteome as a reference gives an opportunity to refine our understanding of the extreme compositional bias in the P. falciparum genome that leads to a proteome-wide amino acid bias. A set of pairs of non-redundant protein homologues was selected owing to rigorous genome-wide sequence comparison methods. The introduction of A. thaliana as a reference was a mean to weight the magnitude of the protein evolutionary divergence in P. falciparum. The correlation of the amino acid proportions with evolutionary time supports the hypothesis that amino acids encoded by GC-rich codons are directionally substituted into amino acids encoded by AT-rich codons in the P. falciparum proteome. The long-term deviation of codons in malarial sequences appears as a possible consequence of a genome-wide tri-nucleotidic signature imprinting. Additionally, this study suggests possible working guidelines to improve the accuracy of P. falciparum sequence comparisons, for homology searches and phylogenetic studies.

A genomic schism in birds revealed by phylogenetic analysis of DNA strings.

The molecular systematics of vertebrates has been based entirely on alignments of primary structures of macromolecules; however, higher order features of DNA sequences not used in traditional studies also contain valuable phylogenetic information. Recent molecular data sets conflict over the phylogenetic placement of flightless birds (ratites - paleognaths), but placement of this clade critically influences interpretation of character change in birds. To help resolve this issue, we applied a new bioinformatics approach to the largest molecular data set currently available. We distilled nearly one megabase (1 million base pairs) of heterogeneous avian genomic DNA from 20 birds and an alligator into genomic signatures, defined as the complete set of frequencies of short sequence motifs (strings), thereby providing a way to directly compare higher order features of nonhomologous DNA sequences. Phylogenetic analysis and principal component analysis of the signatures strongly support the traditional hypothesis of basal ratites and monophyly of the nonratite birds (neognaths) and imply that ratite genomes are linguistically primitive within birds, despite their base compositional similarity to neognath genomes. Our analyses show further that the phylogenetic signal of genomic signatures are strongest among deep splits within vertebrates. Despite clear problems with phylogenetic analysis of genomic signatures, our study raises intriguing issues about the biological and genomic differences that fundamentally differentiate paleognaths and neognaths.