Artificial intelligence image-based prediction models in IBD exhibit high risk of bias: A systematic review

BACKGROUND

There has been an increase in the development of both machine learning (ML) and deep learning (DL) prediction models in Inflammatory Bowel Disease. We aim in this systematic review to assess the methodological quality and risk of bias of ML and DL IBD image-based prediction studies.

METHODS

We searched three databases, PubMed, Scopus and Embase, to identify ML and DL diagnostic or prognostic predictive models using imaging data in IBD, to Dec 31, 2022. We restricted our search to include studies that primarily used conventional imaging data, were undertaken in human participants, and published in English. Two reviewers independently reviewed the abstracts. The methodological quality of the studies was determined, and risk of bias evaluated using the prediction risk of bias assessment tool (PROBAST).

RESULTS

Forty studies were included, thirty-nine developed diagnostic models. Seven studies utilized ML approaches, six were retrospective and none used multicenter data for model development. Thirty-three studies utilized DL approaches, ten were prospective, and twelve multicenter studies. Overall, all studies demonstrated high risk of bias. ML studies were evaluated in 4 domains all rated as high risk of bias: participants (6/7), predictors (1/7), outcome (3/7), and analysis (7/7), and DL studies evaluated in 3 domains: participants (24/33), outcome (10/33), and analysis (18/33). The majority of image-based studies used colonoscopy images.

CONCLUSION

The risk of bias was high in AI IBD image-based prediction models, owing to insufficient sample size, unreported missingness and lack of an external validation cohort. Models with a high risk of bias are unlikely to be generalizable and suitable for clinical implementation.

LungMAP Portal Ecosystem: Systems-level Exploration of the Lung

An improved understanding of the human lung necessitates advanced systems models informed by an ever-increasing repertoire of molecular omics, cellular imaging, and pathological datasets. To centralize and standardize information across broad lung research efforts, we expanded the LungMAP.net website into a new gateway portal. This portal connects a broad spectrum of research networks, bulk and single-cell multiomics data, and a diverse collection of image data that span mammalian lung development and disease. The data are standardized across species and technologies using harmonized data and metadata models that leverage recent advances, including those from the Human Cell Atlas, diverse ontologies, and the LungMAP CellCards initiative. To cultivate future discoveries, we have aggregated a diverse collection of single-cell atlases for multiple species (human, rhesus, and mouse) to enable consistent queries across technologies, cohorts, age, disease, and drug treatment. These atlases are provided as independent and integrated queryable datasets, with an emphasis on dynamic visualization, figure generation, reanalysis, cell-type curation, and automated reference-based classification of user-provided single-cell genomics datasets (Azimuth). As this resource grows, we intend to increase the breadth of available interactive interfaces, supported data types, data portals and datasets from LungMAP, and external research efforts.

MGS2AMR: a gene-centric mining of metagenomic sequencing data for pathogens and their antimicrobial resistance profile

BACKGROUND

Identification of pathogenic bacteria from clinical specimens and evaluating their antimicrobial resistance (AMR) are laborious tasks that involve in vitro cultivation, isolation, and susceptibility testing. Recently, a number of methods have been developed that use machine learning algorithms applied to the whole-genome sequencing data of isolates to approach this problem. However, making AMR assessments from more easily available metagenomic sequencing data remains a big challenge.

RESULTS

We present the Metagenomic Sequencing to Antimicrobial Resistance (MGS2AMR) pipeline, which detects antibiotic resistance genes (ARG) and their possible organism of origin within a sequenced metagenomics sample. This in silico method allows for the evaluation of bacterial AMR directly from clinical specimens, such as stool samples. We have developed two new algorithms to optimize and annotate the genomic assembly paths within the raw Graphical Fragment Assembly (GFA): the GFA Linear Optimal Path through seed segments (GLOPS) algorithm and the Adapted Dijkstra Algorithm for GFA (ADAG). These novel algorithms improve the sensitivity of ARG detection and aid in species annotation. Tests based on 1200 microbiome samples show a high ARG recall rate and correct assignment of the ARG origin. The MGS2AMR output can further be used in many downstream applications, such as evaluating AMR to specific antibiotics in samples from emerging intestinal infections. We demonstrate that the MGS2AMR-derived data is as informative for the entailing prediction models as the whole-genome sequencing (WGS) data. The performance of these models is on par with our previously published method (WGS2AMR), which is based on the sequencing data of bacterial isolates.

CONCLUSIONS

MGS2AMR can provide researchers with valuable insights into the AMR content of microbiome environments and may potentially improve patient care by providing faster quantification of resistance against specific antibiotics, thereby reducing the use of broad-spectrum antibiotics. The presented pipeline also has potential applications in other metagenome analyses focused on the defined sets of genes. Video Abstract.

Near Lossless Compression for 3D Radiological Images Using Optimal Multilinear Singular Value Decomposition (3D-VOI-OMLSVD)

Storage and transmission of high-compression 3D radiological images that create high-quality reconstruction upon decompression are critical necessities for effective and efficient teleradiology. To cater to this need, we propose a near lossless 3D image volume compression method based on optimal multilinear singular value decomposition called "3D-VOI-OMLSVD." The proposed strategy first eliminates any blank 2D image slices from the 3D image volume and uses the selective bounding volume (SBV) to identify and extract the volume of Interest (VOI). Following this, the VOI is decomposed with an optimal multilinear singular value decomposition (OMLSVD) to obtain the corresponding core tensor, factor matrices, and singular values that are compressed with adaptive binary range coder (ABRC), integrated as an entropy encoder. The compressed file can be transferred or transmitted and then decompressed in order to reconstruct the original image. The resultant decompressed VOI is acquired by reversing the above process and then fusing it with the background, using the bound volume coordinates associated with the compressed 3D image. The proposed method performance was tested on a variety of 3D radiological images with different imaging modalities and dimensions using quantitative evaluation metrics such as the compression rate (CR), bit rate (BR), peak signal to noise ratio (PSNR), and structural similarity index (SSIM). Furthermore, we also investigate the impact of VOI extraction on the model performance, before comparing it with two popular compression methods, namely JPEG and JPEG2000. Our proposed method, 3D-VOI-OMLSVD, displayed a high CR value, with a maximum of 37.31, and a low BR, with the lowest reported to be 0.21. The SSIM score was consistently high, with an average performance of 0.9868, while using < 1 second for decoding the image. We observe that with VOI extraction, the compression rate increases manifold, and bit rate drops significantly, and thus reduces the encoding and decoding time to a great extent. Compared to JPEG and JPEG2000, our method consistently performs better in terms of higher CR and lower BR. The results indicate that the proposed compression methodology performs consistently to create high-quality image compressions, and overall gives a better outcome when compared against two state-of-the-art and widely used methods, JPEG and JPEG2000.

Decision level integration of unimodal and multimodal single cell data with scTriangulate

Decisively delineating cell identities from uni- and multimodal single-cell datasets is complicated by diverse modalities, clustering methods, and reference atlases. We describe scTriangulate, a computational framework to mix-and-match multiple clustering results, modalities, associated algorithms, and resolutions to achieve an optimal solution. Rather than ensemble approaches which select the "consensus", scTriangulate picks the most stable solution through coalitional iteration. When evaluated on diverse multimodal technologies, scTriangulate outperforms alternative approaches to identify high-confidence cell-populations and modality-specific subtypes. Unlike existing integration strategies that rely on modality-specific joint embedding or geometric graphs, scTriangulate makes no assumption about the distributions of raw underlying values. As a result, this approach can solve unprecedented integration challenges, including the ability to automate reference cell-atlas construction, resolve clonal architecture within molecularly defined cell-populations and subdivide clusters to discover splicing-defined disease subtypes. scTriangulate is a flexible strategy for unified integration of single-cell or multimodal clustering solutions, from nearly unlimited sources.

maxATAC: Genome-scale transcription-factor binding prediction from ATAC-seq with deep neural networks

Transcription factors read the genome, fundamentally connecting DNA sequence to gene expression across diverse cell types. Determining how, where, and when TFs bind chromatin will advance our understanding of gene regulatory networks and cellular behavior. The 2017 ENCODE-DREAM in vivo Transcription-Factor Binding Site (TFBS) Prediction Challenge highlighted the value of chromatin accessibility data to TFBS prediction, establishing state-of-the-art methods for TFBS prediction from DNase-seq. However, the more recent Assay-for-Transposase-Accessible-Chromatin (ATAC)-seq has surpassed DNase-seq as the most widely-used chromatin accessibility profiling method. Furthermore, ATAC-seq is the only such technique available at single-cell resolution from standard commercial platforms. While ATAC-seq datasets grow exponentially, suboptimal motif scanning is unfortunately the most common method for TFBS prediction from ATAC-seq. To enable community access to state-of-the-art TFBS prediction from ATAC-seq, we (1) curated an extensive benchmark dataset (127 TFs) for ATAC-seq model training and (2) built "maxATAC", a suite of user-friendly, deep neural network models for genome-wide TFBS prediction from ATAC-seq in any cell type. With models available for 127 human TFs, maxATAC is the largest collection of high-performance TFBS prediction models for ATAC-seq. maxATAC performance extends to primary cells and single-cell ATAC-seq, enabling improved TFBS prediction in vivo. We demonstrate maxATAC's capabilities by identifying TFBS associated with allele-dependent chromatin accessibility at atopic dermatitis genetic risk loci.

CellDrift: inferring perturbation responses in temporally sampled single-cell data

Cells and tissues respond to perturbations in multiple ways that can be sensitively reflected in the alterations of gene expression. Current approaches to finding and quantifying the effects of perturbations on cell-level responses over time disregard the temporal consistency of identifiable gene programs. To leverage the occurrence of these patterns for perturbation analyses, we developed CellDrift (https://github.com/KANG-BIOINFO/CellDrift), a generalized linear model-based functional data analysis method that is capable of identifying covarying temporal patterns of various cell types in response to perturbations. As compared to several other approaches, CellDrift demonstrated superior performance in the identification of temporally varied perturbation patterns and the ability to impute missing time points. We applied CellDrift to multiple longitudinal datasets, including COVID-19 disease progression and gastrointestinal tract development, and demonstrated its ability to identify specific gene programs associated with sequential biological processes, trajectories and outcomes.

Data Augmentation Using Generative Adversarial Networks for Multi-Class Segmentation of Lung Confocal IF Images

The human lung is a complex organ with high cellular heterogeneity, and its development and maintenance require interactive gene networks and dynamic cross-talk among multiple cell types. We focus on the confocal immunofluorescent (IF) images of lung tissues from the LungMAP database to reveal lung development. Using the current state-of-the-art deep learning-based model, the authors consider obtaining accurate multi-class segmentation of lung confocal IF images. One of the primary bottlenecks in using deep Convolutional Neural Network (CNN) models is the lack of availability of large-scale training or ground-truth segmentation labels. Then, we implement the multi-class segmentation with Generative Adversarial Network (GAN) models to expand the training dataset, improve overall segmentation accuracy, and discuss the effectiveness of created synthetic images in the segmentation of IF images. Consequently, experimental results indicated that 15.1% increased the accuracy of six-class segmentation using Mask R-CNN. In particular, the accuracy of our few data was mainly improved by using our proposed method. Therefore, the synthetic dataset can moderate the imbalanced data and be used for expanding the dataset.

COMPUTATIONAL 2D and 3D MEDICAL IMAGE DATA COMPRESSION MODELS

In this world of big data, the development and exploitation of medical technology is vastly increasing and especially in big biomedical imaging modalities available across medicine. At the same instant, acquisition, processing, storing and transmission of such huge medical data requires efficient and robust data compression models. Over the last two decades, numerous compression mechanisms, techniques and algorithms were proposed by many researchers. This work provides a detailed status of these existing computational compression methods for medical imaging data. Appropriate classification, performance metrics, practical issues and challenges in enhancing the two dimensional (2D) and three dimensional (3D) medical image compression arena are reviewed in detail.

DeepImmuno: deep learning-empowered prediction and generation of immunogenic peptides for T-cell immunity

Cytolytic T-cells play an essential role in the adaptive immune system by seeking out, binding and killing cells that present foreign antigens on their surface. An improved understanding of T-cell immunity will greatly aid in the development of new cancer immunotherapies and vaccines for life-threatening pathogens. Central to the design of such targeted therapies are computational methods to predict non-native peptides to elicit a T-cell response, however, we currently lack accurate immunogenicity inference methods. Another challenge is the ability to accurately simulate immunogenic peptides for specific human leukocyte antigen alleles, for both synthetic biological applications, and to augment real training datasets. Here, we propose a beta-binomial distribution approach to derive peptide immunogenic potential from sequence alone. We conducted systematic benchmarking of five traditional machine learning (ElasticNet, K-nearest neighbors, support vector machine, Random Forest and AdaBoost) and three deep learning models (convolutional neural network (CNN), Residual Net and graph neural network) using three independent prior validated immunogenic peptide collections (dengue virus, cancer neoantigen and SARS-CoV-2). We chose the CNN as the best prediction model, based on its adaptivity for small and large datasets and performance relative to existing methods. In addition to outperforming two highly used immunogenicity prediction algorithms, DeepImmuno-CNN correctly predicts which residues are most important for T-cell antigen recognition and predicts novel impacts of SARS-CoV-2 variants. Our independent generative adversarial network (GAN) approach, DeepImmuno-GAN, was further able to accurately simulate immunogenic peptides with physicochemical properties and immunogenicity predictions similar to that of real antigens. We provide DeepImmuno-CNN as source code and an easy-to-use web interface.

On a hybrid lossless compression technique for three-dimensional medical images

In the last two decades, incredible progress in various medical imaging modalities and sensing techniques have been made, leading to the proliferation of three-dimensional (3D) imagery. Byproduct of such great progress is the production of huge volume of medical images and this big data place a burden on automatic image processing methods for diagnostic assistance processes. Moreover, large amount of medical imaging data needs to be transmitted with no loss of information for the purpose of telemedicine, remote diagnosis etc. In this work, we consider a hybrid lossless compression technique with object-based features for three-dimensional (3D) medical images. Our approach utilizes two phases as follows: first we determine the volume of interest (VOI) for a given 3D medical imagery using selective bounding volume (SBV) method, and second the obtained VOI is encoded using a hybrid lossless algorithm using Lembel-Ziv-Welch Coding (LZW) followed by arithmetic coding (L to A). Experimental results show that our proposed 3D medical image compression method is comparable with other existing standard lossless encoding methods such as Huffman Coding, Run Length Coding, LZW, and Arithmetic Coding and obtains superior results overall.

Machine Learning for Detection of Correct Peripherally Inserted Central Catheter Tip Position from Radiology Reports in Infants

BACKGROUND

In critically ill infants, the position of a peripherally inserted central catheter (PICC) must be confirmed frequently, as the tip may move from its original position and run the risk of hyperosmolar vascular damage or extravasation into surrounding spaces. Automated detection of PICC tip position holds great promise for alerting bedside clinicians to noncentral PICCs.

OBJECTIVES

This research seeks to use natural language processing (NLP) and supervised machine learning (ML) techniques to predict PICC tip position based primarily on text analysis of radiograph reports from infants with an upper extremity PICC.

METHODS

Radiographs, containing a PICC line in infants under 6 months of age, were manually classified into 12 anatomical locations based on the radiologist's textual report of the PICC line's tip. After categorization, we performed a 70/30 train/test split and benchmarked the performance of seven different (neural network, support vector machine, the naïve Bayes, decision tree, random forest, AdaBoost, and K-nearest neighbors) supervised ML algorithms. After optimization, we calculated accuracy, precision, and recall of each algorithm's ability to correctly categorize the stated location of the PICC tip.

RESULTS

A total of 17,337 radiographs met criteria for inclusion and were labeled manually. Interrater agreement was 99.1%. Support vector machines and neural networks yielded accuracies as high as 98% in identifying PICC tips in central versus noncentral position (binary outcome) and accuracies as high as 95% when attempting to categorize the individual anatomical location (12-category outcome).

CONCLUSION

Our study shows that ML classifiers can automatically extract the anatomical location of PICC tips from radiology reports. Two ML classifiers, support vector machine (SVM) and a neural network, obtained top accuracies in both binary and multiple category predictions. Implementing these algorithms in a neonatal intensive care unit as a clinical decision support system may help clinicians address PICC line position.

POCASUM : Policy Categorizer and Summarizer Based on Text Mining and Machine Learning

Having control over your data is a right and a duty that every citizen has in our digital society. It is often that users skip entire policies of applications or websites to save time and energy without realizing the potential sticky points in these policies. Due to obscure language and verbose explanations majority of users of hypermedia do not bother to read them. Further, sometimes digital media companies do not spend enough effort in stating their policies clearly which often time can also be incomplete. A summarized version of these privacy policies that can be categorized into the useful information can help the users. To solve this problem, in this work we propose to use machine learning based models for policy categorizer that classifies the policy paragraphs under the attributes proposed like security, contact etc. By benchmarking different machine learning based classifier models, we show that artificial neural network model performs with higher accuracy on a challenging dataset of textual privacy policies. We thus show that machine learning can help summarize the relevant paragraphs under the various attributes so that the user can get the gist of that topic within a few lines.

In situ mapping identifies distinct vascular niches for myelopoiesis

In contrast to nearly all other tissues, the anatomy of cell differentiation in the bone marrow remains unknown. This is owing to a lack of strategies for examining myelopoiesis-the differentiation of myeloid progenitors into a large variety of innate immune cells-in situ in the bone marrow. Such strategies are required to understand differentiation and lineage-commitment decisions, and to define how spatial organizing cues inform tissue function. Here we develop approaches for imaging myelopoiesis in mice, and generate atlases showing the differentiation of granulocytes, monocytes and dendritic cells. The generation of granulocytes and dendritic cells-monocytes localizes to different blood-vessel structures known as sinusoids, and displays lineage-specific spatial and clonal architectures. Acute systemic infection with Listeria monocytogenes induces lineage-specific progenitor clusters to undergo increased self-renewal of progenitors, but the different lineages remain spatially separated. Monocyte-dendritic cell progenitors (MDPs) map with nonclassical monocytes and conventional dendritic cells; these localize to a subset of blood vessels expressing a major regulator of myelopoiesis, colony-stimulating factor 1 (CSF1, also known as M-CSF)¹. Specific deletion of Csf1 in endothelium disrupts the architecture around MDPs and their localization to sinusoids. Subsequently, there are fewer MDPs and their ability to differentiate is reduced, leading to a loss of nonclassical monocytes and dendritic cells during both homeostasis and infection. These data indicate that local cues produced by distinct blood vessels are responsible for the spatial organization of definitive blood cell differentiation.

DeepImmuno: Deep learning-empowered prediction and generation of immunogenic peptides for T cell immunity

T-cells play an essential role in the adaptive immune system by seeking out, binding and destroying foreign antigens presented on the cell surface of diseased cells. An improved understanding of T-cell immunity will greatly aid in the development of new cancer immunotherapies and vaccines for life threatening pathogens. Central to the design of such targeted therapies are computational methods to predict non-native epitopes to elicit a T cell response, however, we currently lack accurate immunogenicity inference methods. Another challenge is the ability to accurately simulate immunogenic peptides for specific human leukocyte antigen (HLA) alleles, for both synthetic biological applications and to augment real training datasets. Here, we proposed a beta-binomial distribution approach to derive epitope immunogenic potential from sequence alone. We conducted systematic benchmarking of five traditional machine learning (ElasticNet, KNN, SVM, Random Forest, AdaBoost) and three deep learning models (CNN, ResNet, GNN) using three independent prior validated immunogenic peptide collections (dengue virus, cancer neoantigen and SARS-Cov-2). We chose the CNN model as the best prediction model based on its adaptivity for small and large datasets, and performance relative to existing methods. In addition to outperforming two highly used immunogenicity prediction algorithms, DeepHLApan and IEDB, DeepImmuno-CNN further correctly predicts which residues are most important for T cell antigen recognition. Our independent generative adversarial network (GAN) approach, DeepImmuno-GAN, was further able to accurately simulate immunogenic peptides with physiochemical properties and immunogenicity predictions similar to that of real antigens. We provide DeepImmuno-CNN as source code and an easy-to-use web interface.

DATA AVAILABILITY

DeepImmuno Python3 code is available at https://github.com/frankligy/DeepImmuno . The DeepImmuno web portal is available from https://deepimmuno.herokuapp.com . The data in this article is available in GitHub and supplementary materials.

Melanoma Skin Cancer Detection Method Based on Adaptive Principal Curvature, Colour Normalisation and Feature Extraction with the ABCD Rule

According to statistics of the American Cancer Society, in 2015, there are about 91,270 American adults diagnosed with melanoma of the skin. For the European Union, there are over 90,000 new cases of melanoma annually. Although melanoma only accounts for about 1% of all skin cancers, it causes most of the skin cancer deaths. Melanoma is considered one of the fastest-growing forms of skin cancer, and hence the early detection is crucial, as early detection is helpful and can provide strong recommendations for specific and suitable treatment regimens. In this work, we propose a method to detect melanoma skin cancer with automatic image processing techniques. Our method includes three stages: pre-process images of skin lesions by adaptive principal curvature, segment skin lesions by the colour normalisation and extract features by the ABCD rule. We provide experimental results of the proposed method on the publicly available International Skin Imaging Collaboration (ISIC) skin lesions dataset. The acquired results on melanoma skin cancer detection indicates that the proposed method has high accuracy, and overall, a good performance: for the segmentation stage, the accuracy, Dice, Jaccard scores are 96.6%, 93.9% and 88.7%, respectively; and for the melanoma detection stage, the accuracy is up to 100% for a selected subset of the ISIC dataset.

Automatic body mass index detection using correlation of face visual cues

Body mass index (BMI) is used widely as an indicator in general health. Determination of BMI using non-intrusive measurements are of interest and recent advancements in the availability of digital imaging sensors have paved the way for performing quick and automatic measurements. In this work, we consider automatic computation of BMI using correlation features from face images. We show that using face detection based facial fiducial points analysis provides good BMI prediction. Experimental results on comparing the correlation coefficients of facial ratios along with the colour feature has higher significance in BMI of a person.

Multiscale Structure Tensor for Improved Feature Extraction and Image Regularization

Regularization methods are used widely in image selective smoothing and edge preserving restoration of noisy images. Traditional methods utilize image gradients within regularization function for controlling the smoothing and can produce artifacts when noise levels are higher. In this paper, we consider a robust image adaptive exponent driven regularization for filtering noisy images with salient feature preservation. Our spatially adaptive variable exponent function depends on a continuous switch based on the eigenvalues of structure tensor which identifies noisy edges, and corners with higher accuracy. Structure tensor eigenvalues encode various image features and we consider a spatially varying continuous map which provides multiscale edge maps of natural images. By embedding the structure tensor-based exponent in a well-defined regularization model, we obtain denoising filters which are capable of obtaining good feature preserving image restoration. The GPU-based implementation computes the edge map in real time at 45-60 frames/s depending on the GPU card. Multiscale structure tensor-based spatially adaptive variable exponent provides reliable edge maps and compared with standard edge detectors it is robust under various noisy conditions. Moreover, filtering based on the multiscale variable exponent map method outperforms L0 sparse gradient-based image smoothing and related filters.

Effects of Distance Measure Choice on K-Nearest Neighbor Classifier Performance: A Review

The K-nearest neighbor (KNN) classifier is one of the simplest and most common classifiers, yet its performance competes with the most complex classifiers in the literature. The core of this classifier depends mainly on measuring the distance or similarity between the tested examples and the training examples. This raises a major question about which distance measures to be used for the KNN classifier among a large number of distance and similarity measures available? This review attempts to answer this question through evaluating the performance (measured by accuracy, precision, and recall) of the KNN using a large number of distance measures, tested on a number of real-world data sets, with and without adding different levels of noise. The experimental results show that the performance of KNN classifier depends significantly on the distance used, and the results showed large gaps between the performances of different distances. We found that a recently proposed nonconvex distance performed the best when applied on most data sets comparing with the other tested distances. In addition, the performance of the KNN with this top performing distance degraded only ∼20% while the noise level reaches 90%, this is true for most of the distances used as well. This means that the KNN classifier using any of the top 10 distances tolerates noise to a certain degree. Moreover, the results show that some distances are less affected by the added noise comparing with other distances.

Automatic disease stage classification of glioblastoma multiforme histopathological images using deep convolutional neural network

In the field of computational histopathology, computer-assisted diagnosis systems are important in obtaining patient-specific diagnosis for various diseases and help precision medicine. Therefore, many studies on automatic analysis methods for digital pathology images have been reported. In this work, we discuss an automatic feature extraction and disease stage classification method for glioblastoma multiforme (GBM) histopathological images. In this paper, we use deep convolutional neural networks (Deep CNNs) to acquire feature descriptors and a classification scheme simultaneously. Further, comparisons with other popular CNNs objectively as well as quantitatively in this challenging classification problem is undertaken. The experiments using Glioma images from The Cancer Genome Atlas shows that we obtain 96.5 % average classification accuracy for our network and for higher cross validation folds other networks perform similarly with a higher accuracy of 98.0 % . Deep CNNs could extract significant features from the GBM histopathology images with high accuracy. Overall, the disease stage classification of GBM from histopathological images with deep CNNs is very promising and with the availability of large scale histopathological image data the deep CNNs are well suited in tackling this challenging problem.

Confocal Vessel Structure Segmentation with Optimized Feature Bank and Random Forests

In this paper, we consider confocal microscopy based vessel segmentation with optimized features and random forest classification. By utilizing multi-scale vessel-specific features tuned to capture curvilinear structures such as Frobenius norm of the Hessian eigenvalues, Laplacian of Gaussians (LoG), oriented second derivative, line detector and intensity masked with LoG scale map. we obtain better segmentation results in challenging imaging conditions. We obtain binary segmentations using random forest classifier trained on physiologists marked ground-truth. Experimental results on mice dura mater confocal microscopy vessel segmentations indicate that we obtain better results compared to global segmentation approaches.

Random Forests for Dura Mater Microvasculature Segmentation Using Epifluorescence Images

Automatic segmentation of microvascular structures is a critical step in quantitatively characterizing vessel remodeling and other physiological changes in the dura mater or other tissues. We developed a supervised random forest (RF) classifier for segmenting thin vessel structures using multiscale features based on Hessian, oriented second derivatives, Laplacian of Gaussian and line features. The latter multiscale line detector feature helps in detecting and connecting faint vessel structures that would otherwise be missed. Experimental results on epifluorescence imagery show that the RF approach produces foreground vessel regions that are almost 20 and 25 percent better than Niblack and Otsu threshold-based segmentations respectively.

Multiquadric Spline-Based Interactive Segmentation of Vascular Networks

Commonly used drawing tools for interactive image segmentation and labeling include active contours or boundaries, scribbles, rectangles and other shapes. Thin vessel shapes in images of vascular networks are difficult to segment using automatic or interactive methods. This paper introduces the novel use of a sparse set of user-defined seed points (supervised labels) for precisely, quickly and robustly segmenting complex biomedical images. A multiquadric spline-based binary classifier is proposed as a unique approach for interactive segmentation using as features color values and the location of seed points. Epifluorescence imagery of the dura mater microvasculature are difficult to segment for quantitative applications due to challenging tissue preparation, imaging conditions, and thin, faint structures. Experimental results based on twenty epifluorescence images is used to illustrate the benefits of using a set of seed points to obtain fast and accurate interactive segmentation compared to four interactive and automatic segmentation approaches.

Methods on Skull Stripping of MRI Head Scan Images-a Review

The high resolution magnetic resonance (MR) brain images contain some non-brain tissues such as skin, fat, muscle, neck, and eye balls compared to the functional images namely positron emission tomography (PET), single photon emission computed tomography (SPECT), and functional magnetic resonance imaging (fMRI) which usually contain relatively less non-brain tissues. The presence of these non-brain tissues is considered as a major obstacle for automatic brain image segmentation and analysis techniques. Therefore, quantitative morphometric studies of MR brain images often require a preliminary processing to isolate the brain from extra-cranial or non-brain tissues, commonly referred to as skull stripping. This paper describes the available methods on skull stripping and an exploratory review of recent literature on the existing skull stripping methods.

Multiscale Tikhonov-Total Variation Image Restoration Using Spatially Varying Edge Coherence Exponent

Edge preserving regularization using partial differential equation (PDE)-based methods although extensively studied and widely used for image restoration, still have limitations in adapting to local structures. We propose a spatially adaptive multiscale variable exponent-based anisotropic variational PDE method that overcomes current shortcomings, such as over smoothing and staircasing artifacts, while still retaining and enhancing edge structures across scale. Our innovative model automatically balances between Tikhonov and total variation (TV) regularization effects using scene content information by incorporating a spatially varying edge coherence exponent map constructed using the eigenvalues of the filtered structure tensor. The multiscale exponent model we develop leads to a novel restoration method that preserves edges better and provides selective denoising without generating artifacts for both additive and multiplicative noise models. Mathematical analysis of our proposed method in variable exponent space establishes the existence of a minimizer and its properties. The discretization method we use satisfies the maximum-minimum principle which guarantees that artificial edge regions are not created. Extensive experimental results using synthetic, and natural images indicate that the proposed multiscale Tikhonov-TV (MTTV) and dynamical MTTV methods perform better than many contemporary denoising algorithms in terms of several metrics, including signal-to-noise ratio improvement and structure preservation. Promising extensions to handle multiplicative noise models and multichannel imagery are also discussed.