The Promise of Semantic Segmentation in Detecting Actinic Keratosis Using Clinical Photography in the Wild.

AK is a common precancerous skin condition that requires effective detection and treatment monitoring. To improve the monitoring of the AK burden in clinical settings with enhanced automation and precision, the present study evaluates the application of semantic segmentation based on the U-Net architecture (i.e., AKU-Net). AKU-Net employs transfer learning to compensate for the relatively small dataset of annotated images and integrates a recurrent process based on convLSTM to exploit contextual information and address the challenges related to the low contrast and ambiguous boundaries of AK-affected skin regions. We used an annotated dataset of 569 clinical photographs from 115 patients with actinic keratosis to train and evaluate the model. From each photograph, patches of 512 × 512 pixels were extracted using translation lesion boxes that encompassed lesions in different positions and captured different contexts of perilesional skin. In total, 16,488 translation-augmented crops were used for training the model, and 403 lesion center crops were used for testing. To demonstrate the improvements in AK detection, AKU-Net was compared with plain U-Net and U-Net++ architectures. The experimental results highlighted the effectiveness of AKU-Net, improving upon both automation and precision over existing approaches, paving the way for more effective and reliable evaluation of actinic keratosis in clinical settings.

Image Perceptual Similarity Metrics for the Assessment of Basal Cell Carcinoma.

Efficient management of basal cell carcinomas (BCC) requires reliable assessments of both tumors and post-treatment scars. We aimed to estimate image similarity metrics that account for BCC's perceptual color and texture deviation from perilesional skin. In total, 176 clinical photographs of BCC were assessed by six physicians using a visual deviation scale. Internal consistency and inter-rater agreement were estimated using Cronbach's α, weighted Gwet's AC2, and quadratic Cohen's kappa. The mean visual scores were used to validate a range of similarity metrics employing different color spaces, distances, and image embeddings from a pre-trained VGG16 neural network. The calculated similarities were transformed into discrete values using ordinal logistic regression models. The Bray-Curtis distance in the YIQ color model and rectified embeddings from the 'fc6' layer minimized the mean squared error and demonstrated strong performance in representing perceptual similarities. Box plot analysis and the Wilcoxon rank-sum test were used to visualize and compare the levels of agreement, conducted on a random validation round between the two groups: 'Human-System' and 'Human-Human.' The proposed metrics were comparable in terms of internal consistency and agreement with human raters. The findings suggest that the proposed metrics offer a robust and cost-effective approach to monitoring BCC treatment outcomes in clinical settings.

Distance from Unimodality for the Assessment of Opinion Polarization.

Commonsense knowledge is often approximated by the fraction of annotators who classified an item as belonging to the positive class. Instances for which this fraction is equal to or above 50% are considered positive, including however ones that receive polarized opinions. This is a problematic encoding convention that disregards the potentially polarized nature of opinions and which is often employed to estimate subjectivity, sentiment polarity, and toxic language. We present the distance from unimodality (DFU), a novel measure that estimates the extent of polarization on a distribution of opinions and which correlates well with human judgment. We applied DFU to two use cases. The first case concerns tweets created over 9 months during the pandemic. The second case concerns textual posts crowd-annotated for toxicity. We specified the days for which the sentiment-annotated tweets were determined as polarized based on the DFU measure and we found that polarization occurred on different days for two different states in the USA. Regarding toxicity, we found that polarized opinions are more likely by annotators originating from different countries. Moreover, we show that DFU can be exploited as an objective function to train models to predict whether a post will provoke polarized opinions in the future.

Scanning X-ray Fluorescence Data Analysis for the Identification of Byzantine Icons' Materials, Techniques, and State of Preservation: A Case Study.

X-ray fluorescence (XRF) spectrometry has proven to be a core, non-destructive, analytical technique in cultural heritage studies mainly because of its non-invasive character and ability to rapidly reveal the elemental composition of the analyzed artifacts. Being able to penetrate deeper into matter than the visible light, X-rays allow further analysis that may eventually lead to the extraction of information that pertains to the substrate(s) of an artifact. The recently developed scanning macroscopic X-ray fluorescence method (MA-XRF) allows for the extraction of elemental distribution images. The present work aimed at comparing two different analysis methods for interpreting the large number of XRF spectra collected in the framework of MA-XRF analysis. The measured spectra were analyzed in two ways: a merely spectroscopic approach and an exploratory data analysis approach. The potentialities of the applied methods are showcased on a notable 18th-century Greek religious panel painting. The spectroscopic approach separately analyses each one of the measured spectra and leads to the construction of single-element spatial distribution images (element maps). The statistical data analysis approach leads to the grouping of all spectra into distinct clusters with common features, while afterward dimensionality reduction algorithms help reduce thousands of channels of XRF spectra in an easily perceived dataset of two-dimensional images. The two analytical approaches allow extracting detailed information about the pigments used and paint layer stratigraphy (i.e., painting technique) as well as restoration interventions/state of preservation.

Characterizing Malignant Melanoma Clinically Resembling Seborrheic Keratosis Using Deep Knowledge Transfer.

Malignant melanomas resembling seborrheic keratosis (SK-like MMs) are atypical, challenging to diagnose melanoma cases that carry the risk of delayed diagnosis and inadequate treatment. On the other hand, SK may mimic melanoma, producing a 'false positive' with unnecessary lesion excisions. The present study proposes a computer-based approach using dermoscopy images for the characterization of SΚ-like MMs. Dermoscopic images were retrieved from the International Skin Imaging Collaboration archive. Exploiting image embeddings from pretrained convolutional network VGG16, we trained a support vector machine (SVM) classification model on a data set of 667 images. SVM optimal hyperparameter selection was carried out using the Bayesian optimization method. The classifier was tested on an independent data set of 311 images with atypical appearance: MMs had an absence of pigmented network and had an existence of milia-like cysts. SK lacked milia-like cysts and had a pigmented network. Atypical MMs were characterized with a sensitivity and specificity of 78.6% and 84.5%, respectively. The advent of deep learning in image recognition has attracted the interest of computer science towards improved skin lesion diagnosis. Open-source, public access archives of skin images empower further the implementation and validation of computer-based systems that might contribute significantly to complex clinical diagnostic problems such as the characterization of SK-like MMs.

Late fusion of deep and shallow features to improve discrimination of actinic keratosis from normal skin using clinical photography.

BACKGROUND: Actinic keratosis (AK) is a common premalignant skin lesion that can potentially progress to squamous cell carcinoma. Appropriate long-term management of AK requires close patient monitoring in addition to therapeutic interventions. Computer-aided diagnostic systems based on clinical photography might evolve in the future into valuable adjuncts to AK patient management. The present study proposes a late fusion approach of color-texture features (shallow features) and deep features extracted from pre-trained convolutional neural networks (CNN) to boost AK detection accuracy on clinical photographs. MATERIALS AND METHODS: System uses a sliding rectangular window of 50 × 50 pixels and a classifier that assigns the window region to either the AK or the healthy skin class. 6010 and 13 915 cropped regions of interest (ROI) of 50 × 50 pixels of AK and healthy skin, respectively, from 22 patients were used for system implementation. Different support vector machine (SVM) classifiers employing shallow or deep features and their late fusion using the max rule at decision level were compared with the McNemar test and Yule's Q-statistic. RESULTS: Support vector machine classifiers based on deep and shallow features exhibited overall competitive performances with complementary improvements in detection accuracy. Late fusion yielded significant improvement (6%) in both sensitivity (87%) and specificity (86%) compared to single classifier performance. CONCLUSION: The parallel improvement of sensitivity and specificity is encouraging, demonstrating the potential use of our system in evaluating AK burden. The latter might be of value in future clinical studies for the comparison of field-directed treatment interventions.

Automatic discrimination of actinic keratoses from clinical photographs.

BACKGROUND AND OBJECTIVE: Actinic keratoses (AK) are common premalignant skin lesions that can progress to invasive skin squamous cell carcinoma (sSCC). The subtle accumulation of multiple AK in aging individuals increases the risk of sSCC development, and this underscores the need for efficient treatment and patient follow-up. Our objectives were to develop a method based on color texture analysis of standard clinical photographs for the discrimination of AK from healthy skin and subsequently to test the developed approach in the quantification of field-directed treatment interventions. METHODS: AK and healthy skin in clinical photographs of 22 patients were demarcated by experts and regions of interest (ROIs) of 50 × 50 pixels were cropped. The data set comprised 6010 and 13915 ROIs from AK and healthy skin, respectively. Color texture features were extracted using local binary patterns (LBP) or texton frequency histograms and evaluated employing a support vector machine (SVM) classifier. Classifier evaluation was performed using a leave-one-patient-out scheme in RGB, YIQ and CIE-Lab color spaces. The best configuration of the SVM model was tested using 157 AK and 216 healthy skin rectangular regions of arbitrary size. AK treatment outcome was evaluated in an additional group of eight patients with 32 skin lesions. RESULTS: The best configuration of the discrimination model was achieved by employing LBP color texture descriptors estimated from the Y and I components of the YIQ color space. The sensitivity and specificity of the SVM model were 80.1% and 81.1% at ROI level and 89.8% and 91.7% at region level, respectively. Based on the classifier results the quantitative AK reduction was 83.6%. CONCLUSIONS: It is important that patients with AK seek evaluation for treatment to reduce the risk of disease progression. Efficient patient follow-up and treatment evaluation require cost-effective and easy to use approaches. The proposed SVM discrimination model based on LBP color texture analysis renders clinical photography a practical, widely available and cost-effective tool for the evaluation of AK burden and treatment efficacy.

PRESS: PRotEin S-Sulfenylation server.

MOTIVATION: Transient S-sulfenylation of cysteine thiols mediated by reactive oxygen species plays a critical role in pathology, physiology and cell signaling. Therefore, discovery of new S-sulfenylated sites in proteins is of great importance towards understanding how protein function is regulated upon redox conditions. RESULTS: We developed PRESS (PRotEin S-Sulfenylation) web server, a server which can effectively predict the cysteine thiols of a protein that could undergo S-sulfenylation under redox conditions. We envisage that this server will boost and facilitate the discovery of new and currently unknown functions of proteins triggered upon redox conditions, signal regulation and transduction, thus uncovering the role of S-sulfenylation in human health and disease. AVAILABILITY AND IMPLEMENTATION: The PRESS web server is freely available at http://press-sulfenylation.cse.uoi.gr/ CONTACTS: agtzakos@gmail.com or gtzortzi@cs.uoi.gr SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Fully unsupervised M-FISH chromosome image characterization.

Chromosome analysis is an important and difficult task for clinical diagnosis and biological research. A color imaging technique, multiplex fluorescent in situ hybridization (M-FISH), has been developed to ease the analysis of the process. Using an M-FISH technique each chromosome class (1,2, …,22,X,Y) is stained with a unique color. However, significant variations between images are observed due to a number of factors such as uneven hybridization and spectral overlap among channels. These types of variations influence the pixel classification accuracy of image classification methods which are supervised and require a set of annotated images for training. In this paper, we present a fully unsupervised M-FISH chromosome image classification methodology. Our main contributions are 1) the assumption that the intensity of a chromosome pixel is sampled from multiple Gaussian components [Gaussian mixture model (GMM)] such that each component corresponds to one chromosome class, and 2) the initialization of the GMM model using the emission information of each chromosome class. This is feasible since prior to the M-FISH image acquirement, we already know which chromosome class is emitting to each of the five M-FISH image channels. The method has been tested on a large number of M-FISH images and an overall accuracy of 89.85% is reported. Our method is unsupervised and presents higher classification accuracy even when it is compared with common supervised based methods. Since the developed classification method does not require training data, it is highly convenient when ground truth does not exist.

Combining magnetic resonance spectroscopy and molecular genomics offers better accuracy in brain tumor typing and prediction of survival than either methodology alone.

Recent advents in magnetic resonance spectroscopy (MRS) techniques permit subsequent microarray analysis over the entire human transcriptome in the same tissue biopsies. However, extracting information from such immense quantities of data is limited by difficulties in recognizing and evaluating the relevant patterns of apparent gene expression in the context of the existing knowledge of phenotypes by histopathology. Using a quantitative approach derived from a knowledge base of pathology findings, we present a novel methodology used to process genome-wide transcription and MRS data. This methodology was tested to examine metabolite and genome-wide profiles in MRS and RNA in 55 biopsies from human subjects with brain tumors with ~100% certainty. With the guidance of histopathology and clinical outcome, 15 genes with the assistance of 15 MRS metabolites were able to be distinguished by tumor categories and the prediction of survival was better than when either method was used alone. This new method, combining MRS, genomics, statistics and biological content, improves the typing and understanding of the complexity of human brain tumors, and assists in the search for novel tumor biomarkers. It is an important step for novel drug development, it generates testable hypotheses regarding neoplasia and promises to guide human brain tumor therapy provided improved in vivo methods for monitoring response to therapy are developed.

Multiple view clustering using a weighted combination of exemplar-based mixture models.

Multiview clustering partitions a dataset into groups by simultaneously considering multiple representations (views) for the same instances. Hence, the information available in all views is exploited and this may substantially improve the clustering result obtained by using a single representation. Usually, in multiview algorithms all views are considered equally important, something that may lead to bad cluster assignments if a view is of poor quality. To deal with this problem, we propose a method that is built upon exemplar-based mixture models, called convex mixture models (CMMs). More specifically, we present a multiview clustering algorithm, based on training a weighted multiview CMM, that associates a weight with each view and learns these weights automatically. Our approach is computationally efficient and easy to implement, involving simple iterative computations. Experiments with several datasets confirm the advantages of assigning weights to the views and the superiority of our framework over single-view and unweighted multiview CMMs, as well as over another multiview algorithm which is based on kernel canonical correlation analysis.

A Bayesian framework for image segmentation with spatially varying mixtures.

A new Bayesian model is proposed for image segmentation based upon Gaussian mixture models (GMM) with spatial smoothness constraints. This model exploits the Dirichlet compound multinomial (DCM) probability density to model the mixing proportions (i.e., the probabilities of class labels) and a Gauss-Markov random field (MRF) on the Dirichlet parameters to impose smoothness. The main advantages of this model are two. First, it explicitly models the mixing proportions as probability vectors and simultaneously imposes spatial smoothness. Second, it results in closed form parameter updates using a maximum a posteriori (MAP) expectation-maximization (EM) algorithm. Previous efforts on this problem used models that did not model the mixing proportions explicitly as probability vectors or could not be solved exactly requiring either time consuming Markov Chain Monte Carlo (MCMC) or inexact variational approximation methods. Numerical experiments are presented that demonstrate the superiority of the proposed model for image segmentation compared to other GMM-based approaches. The model is also successfully compared to state of the art image segmentation methods in clustering both natural images and images degraded by noise.

The global kernel k-means algorithm for clustering in feature space.

Kernel k-means is an extension of the standard k -means clustering algorithm that identifies nonlinearly separable clusters. In order to overcome the cluster initialization problem associated with this method, we propose the global kernel k-means algorithm, a deterministic and incremental approach to kernel-based clustering. Our method adds one cluster at each stage, through a global search procedure consisting of several executions of kernel k-means from suitable initializations. This algorithm does not depend on cluster initialization, identifies nonlinearly separable clusters, and, due to its incremental nature and search procedure, locates near-optimal solutions avoiding poor local minima. Furthermore, two modifications are developed to reduce the computational cost that do not significantly affect the solution quality. The proposed methods are extended to handle weighted data points, which enables their application to graph partitioning. We experiment with several data sets and the proposed approach compares favorably to kernel k -means with random restarts.

Sparse Bayesian modeling with adaptive kernel learning.

Sparse kernel methods are very efficient in solving regression and classification problems. The sparsity and performance of these methods depend on selecting an appropriate kernel function, which is typically achieved using a cross-validation procedure. In this paper, we propose an incremental method for supervised learning, which is similar to the relevance vector machine (RVM) but also learns the parameters of the kernels during model training. Specifically, we learn different parameter values for each kernel, resulting in a very flexible model. In order to avoid overfitting, we use a sparsity enforcing prior that controls the effective number of parameters of the model. We present experimental results on artificial data to demonstrate the advantages of the proposed method and we provide a comparison with the typical RVM on several commonly used regression and classification data sets.

Variational Bayesian sparse kernel-based blind image deconvolution with Student's-t priors.

In this paper, we present a new Bayesian model for the blind image deconvolution (BID) problem. The main novelty of this model is the use of a sparse kernel-based model for the point spread function (PSF) that allows estimation of both PSF shape and support. In the herein proposed approach, a robust model of the BID errors and an image prior that preserves edges of the reconstructed image are also used. Sparseness, robustness, and preservation of edges are achieved by using priors that are based on the Student's-t probability density function (PDF). This pdf, in addition to having heavy tails, is closely related to the Gaussian and, thus, yields tractable inference algorithms. The approximate variational inference methodology is used to solve the corresponding Bayesian model. Numerical experiments are presented that compare this BID methodology to previous ones using both simulated and real data.

Variational Bayesian image restoration based on a product of t-distributions image prior.

Image priors based on products have been recognized to offer many advantages because they allow simultaneous enforcement of multiple constraints. However, they are inconvenient for Bayesian inference because it is hard to find their normalization constant in closed form. In this paper, a new Bayesian algorithm is proposed for the image restoration problem that bypasses this difficulty. An image prior is defined by imposing Student-t densities on the outputs of local convolutional filters. A variational methodology, with a constrained expectation step, is used to infer the restored image. Numerical experiments are shown that compare this methodology to previous ones and demonstrate its advantages.

Bayesian kernel methods for analysis of functional neuroimages.

We propose an approach to analyzing functional neuroimages in which 1) regions of neuronal activation are described by a superposition of spatial kernel functions, the parameters of which are estimated from the data and 2) the presence of activation is detected by means of a generalized likelihood ratio test (GLRT). Kernel methods have become a staple of modern machine learning. Herein, we show that these techniques show promise for neuroimage analysis. In an on-off design, we model the spatial activation pattern as a sum of an unknown number of kernel functions of unknown location, amplitude, and/or size. We employ two Bayesian methods of estimating the kernel functions. The first is a maximum a posteriori (MAP) estimation method based on a Reversible-Jump Markov-chain Monte-Carlo (RJMCMC) algorithm that searches for both the appropriate model complexity and parameter values. The second is a relevance vector machine (RVM), a kernel machine that is known to be effective in controlling model complexity (and thus discouraging overfitting). In each method, after estimating the activation pattern, we test for local activation using a GLRT. We evaluate the results using receiver operating characteristic (ROC) curves for simulated neuroimaging data and example results for real fMRI data. We find that, while RVM and RJMCMC both produce good results, RVM requires far less computation time, and thus appears to be the more promising of the two approaches.

Combination of high-resolution magic angle spinning proton magnetic resonance spectroscopy and microscale genomics to type brain tumor biopsies.

Advancements in the diagnosis and prognosis of brain tumor patients, and thus in their survival and quality of life, can be achieved using biomarkers that facilitate improved tumor typing. We introduce and implement a combinatorial metabolic and molecular approach that applies state-of-the-art, high-resolution magic angle spinning (HRMAS) proton (1H) MRS and gene transcriptome profiling to intact brain tumor biopsies, to identify unique biomarker profiles of brain tumors. Our results show that samples as small as 2 mg can be successfully processed, the HRMAS 1H MRS procedure does not result in mRNA degradation, and minute mRNA amounts yield high-quality genomic data. The MRS and genomic analyses demonstrate that CNS tumors have altered levels of specific 1H MRS metabolites that directly correspond to altered expression of Kennedy pathway genes; and exhibit rapid phospholipid turnover, which coincides with upregulation of cell proliferation genes. The data also suggest Sonic Hedgehog pathway (SHH) dysregulation may play a role in anaplastic ganglioglioma pathogenesis. That a strong correlation is seen between the HRMAS 1H MRS and genomic data cross-validates and further demonstrates the biological relevance of the MRS results. Our combined metabolic/molecular MRS/genomic approach provides insights into the biology of anaplastic ganglioglioma and a new potential tumor typing methodology that could aid neurologists and neurosurgeons to improve the diagnosis, treatment, and ongoing evaluation of brain tumor patients.

Unsupervised learning of gaussian mixtures based on variational component splitting.

In this paper, we present an incremental method for model selection and learning of Gaussian mixtures based on the recently proposed variational Bayes approach. The method adds components to the mixture using a Bayesian splitting test procedure: a component is split into two components and then variational update equations are applied only to the parameters of the two components. As a result, either both components are retained in the model or one of them is found to be redundant and is eliminated from the model. In our approach, the model selection problem is treated locally, in a region of the data space, so we can set more informative priors based on the local data distribution. A modified Bayesian mixture model is presented to implement this approach, along with a learning algorithm that iteratively applies a splitting test on each mixture component. Experimental results and comparisons with two other techniques testify for the adequacy of the proposed approach.

A class-adaptive spatially variant mixture model for image segmentation.

We propose a new approach for image segmentation based on a hierarchical and spatially variant mixture model. According to this model, the pixel labels are random variables and a smoothness prior is imposed on them. The main novelty of this work is a new family of smoothness priors for the label probabilities in spatially variant mixture models. These Gauss-Markov random field-based priors allow all their parameters to be estimated in closed form via the maximum a posteriori (MAP) estimation using the expectation-maximization methodology. Thus, it is possible to introduce priors with multiple parameters that adapt to different aspects of the data. Numerical experiments are presented where the proposed MAP algorithms were tested in various image segmentation scenarios. These experiments demonstrate that the proposed segmentation scheme compares favorably to both standard and previous spatially constrained mixture model-based segmentation.