Different approaches for extracting information from the co-occurrence matrix

Deep Learning-Driven Transformation: A Novel Approach for Mitigating Batch Effects in Diffusion MRI Beyond Traditional Harmonization

BACKGROUND

"Batch effect" in MR images, due to vendor-specific features, MR machine generations, and imaging parameters, challenges image quality and hinders deep learning (DL) model generalizability.

PURPOSE

We aim to develop a DL model using contrast adjustment and super-resolution to reduce diffusion-weighted images (DWIs) diversity across magnetic field strengths and imaging parameters.

STUDY TYPE

Retrospective.

SUBJECTS

The DL model was built using an open dataset from one individual. The MR machine identification model was trained and validated on a dataset of 1134 adults (54% females, 46% males), with 1050 subjects showing no DWI abnormalities and 84 with conditions like stroke and tumors. The 21,000 images were divided into 80% for training, 20% for validation, and 3500 for testing.

FIELD STRENGTH/SEQUENCE

Seven MR scanners from four manufacturers with 1.5 T and 3 T magnetic field strengths. DWIs were acquired using spin-echo sequences and high-resolution T2WIs using the T2-SPACE sequence.

ASSESSMENT

An experienced, board-certified radiologist evaluated the effectiveness of restoring high-resolution T2WI and harmonizing diverse DWI with metrics such as PSNR and SSIM, and the texture and frequency attributes were further analyzed using gray-level co-occurrence matrix and 1-dimensional power spectral density. The model's impact on machine-specific characteristics was gauged through the performance metrics of a ResNet-50 model. Comprehensive statistical tests were employed for statistical robustness, including McNemar's test and the Dice index.

RESULTS

Our DL protocol reduced DWI contrast and resolution variation. ResNet-50 model's accuracy decreased from 0.9443 to 0.5786, precision from 0.9442 to 0.6494, recall from 0.9443 to 0.5786, and F1 score from 0.9438 to 0.5587. The t-SNE visualization indicated more consistent image features across multiple MR devices. Autoencoder halved learning iterations; Dice coefficient >0.74 confirmed signal reproducibility in 84 lesions.

CONCLUSION

This study presents a DL strategy to mitigate batch effects in diffusion MR images, improving their quality and generalizability.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 1.

Cyclic olefin copolymer (COC) as a promising biomaterial for affecting bacterial colonization: investigation on Vibrio campbellii

Cyclic olefin copolymer (COC) has emerged as an interesting biocompatible material for Organ-on-a-Chip (OoC) devices monitoring growth, viability, and metabolism of cells. Despite ISO 10993 approval, systematic investigation of bacteria grown onto COC is a still not documented issue. This study discusses biofilm formations of the canonical wild type BB120 Vibrio campbellii strain on a native COC substrate and addresses the impact of the physico-chemical properties of COC compared to conventional hydroxyapatite (HA) and poly(dimethylsiloxane) (PDMS) surfaces. An interdisciplinary approach combining bacterial colony counting, light microscopy imaging and advanced digital image processing remarks interesting results. First, COC can reduce biomass adhesion with respect to common biopolymers, that is suitable for tuning biofilm formations in the biological and medical areas. Second, remarkably different biofilm morphology (dendritic complex patterns only in the case of COC) was observed among the examined substrates. Third, the observed biofilm morphogenesis was related to the interaction of COC with the conditioning layer of the planktonic biological medium. Fourth, Level Co-occurrence Matrix (CGLM)-based analysis enabled quantitative assessment of the biomass textural fractal development under different coverage conditions. All of this is of key practical relevance in searching innovative biocompatible materials for pharmaceutical, implantable and medical products.

A deeply supervised adaptable neural network for diagnosis and classification of Alzheimer's severity using multitask feature extraction

Alzheimer's disease is the most prevalent form of dementia, which is a gradual condition that begins with mild memory loss and progresses to difficulties communicating and responding to the environment. Recent advancements in neuroimaging techniques have resulted in large-scale multimodal neuroimaging data, leading to an increased interest in using deep learning for the early diagnosis and automated classification of Alzheimer's disease. This study uses machine learning (ML) methods to determine the severity level of Alzheimer's disease using MRI images, where the dataset consists of four levels of severity. A hybrid of 12 feature extraction methods is used to diagnose Alzheimer's disease severity, and six traditional machine learning methods are applied, including decision tree, K-nearest neighbor, linear discrimination analysis, Naïve Bayes, support vector machine, and ensemble learning methods. During training, optimization is performed to obtain the best solution for each classifier. Additionally, a CNN model is trained using a machine learning system algorithm to identify specific patterns. The accuracy of the Naïve Bayes, Support Vector Machines, K-nearest neighbor, Linear discrimination classifier, Decision tree, Ensembled learning, and presented CNN architecture are 67.5%, 72.3%, 74.5%, 65.6%, 62.4%, 73.8% and, 95.3%, respectively. Based on the results, the presented CNN approach outperforms other traditional machine learning methods to find Alzheimer severity.

A hybridized feature extraction for COVID-19 multi-class classification on computed tomography images

COVID-19 has killed more than 5 million individuals worldwide within a short time. It is caused by SARS-CoV-2 which continuously mutates and produces more transmissible new different strains. It is therefore of great significance to diagnose COVID-19 early to curb its spread and reduce the death rate. Owing to the COVID-19 pandemic, traditional diagnostic methods such as reverse-transcription polymerase chain reaction (RT-PCR) are ineffective for diagnosis. Medical imaging is among the most effective techniques of respiratory disorders detection through machine learning and deep learning. However, conventional machine learning methods depend on extracted and engineered features, whereby the optimum features influence the classifier's performance. In this study, Histogram of Oriented Gradient (HOG) and eight deep learning models were utilized for feature extraction while K-Nearest Neighbour (KNN) and Support Vector Machines (SVM) were used for classification. A combined feature of HOG and deep learning feature was proposed to improve the performance of the classifiers. VGG-16 + HOG achieved 99.4 overall accuracy with SVM. This indicates that our proposed concatenated feature can enhance the SVM classifier's performance in COVID-19 detection.

Segmentation of Variants of Nuclei on Whole Slide Images by Using Radiomic Features

The histopathological segmentation of nuclear types is a challenging task because nuclei exhibit distinct morphologies, textures, and staining characteristics. Accurate segmentation is critical because it affects the diagnostic workflow for patient assessment. In this study, a framework was proposed for segmenting various types of nuclei from different organs of the body. The proposed framework improved the segmentation performance for each nuclear type using radiomics. First, we used distinct radiomic features to extract and analyze quantitative information about each type of nucleus and subsequently trained various classifiers based on the best input sub-features of each radiomic feature selected by a LASSO operator. Second, we inputted the outputs of the best classifier to various segmentation models to learn the variants of nuclei. Using the MoNuSAC2020 dataset, we achieved state-of-the-art segmentation performance for each category of nuclei type despite the complexity, overlapping, and obscure regions. The generalized adaptability of the proposed framework was verified by the consistent performance obtained in whole slide images of different organs of the body and radiomic features.

Two-photon microendoscope for label-free imaging in stereotactic neurosurgery

We demonstrate a gradient refractive index (GRIN) microendoscope with an outer diameter of ∼1.2 mm and a length of ∼186 mm that can fit into a stereotactic surgical cannula. Two photon imaging at an excitation wavelength of 900 nm showed a field of view of ∼180 microns and a lateral and axial resolution of 0.86 microns and 9.6 microns respectively. The microendoscope was tested by imaging autofluorescence and second harmonic generation (SHG) in label-free human brain tissue. Furthermore, preliminary image analysis indicates that image classification models can predict if an image is from the subthalamic nucleus or the surrounding tissue using conventional, bench-top two-photon autofluorescence.

Label-free liquid biopsy through the identification of tumor cells by machine learning-powered tomographic phase imaging flow cytometry

Image-based identification of circulating tumor cells in microfluidic cytometry condition is one of the most challenging perspectives in the Liquid Biopsy scenario. Here we show a machine learning-powered tomographic phase imaging flow cytometry system capable to provide high-throughput 3D phase-contrast tomograms of each single cell. In fact, we show that discrimination of tumor cells against white blood cells is potentially achievable with the aid of artificial intelligence in a label-free flow-cyto-tomography method. We propose a hierarchical machine learning decision-maker, working on a set of features calculated from the 3D tomograms of the cells' refractive index. We prove that 3D morphological features are adequately distinctive to identify tumor cells versus the white blood cell background in the first stage and, moreover, in recognizing the tumor type at the second decision step. Proof-of-concept experiments are shown, in which two different tumor cell lines, namely neuroblastoma cancer cells and ovarian cancer cells, are used against monocytes. The reported results allow claiming the identification of tumor cells with a success rate higher than 97% and with an accuracy over 97% in discriminating between the two cancer cell types, thus opening in a near future the route to a new Liquid Biopsy tool for detecting and classifying circulating tumor cells in blood by stain-free method.

Texture Analysis in Uterine Cervix Carcinoma: Primary Tumour and Lymph Node Assessment

The conventional magnetic resonance imaging (MRI) evaluation and staging of cervical cancer encounters several pitfalls, partially due to subjective evaluations of medical images. Fifty-six patients with histologically proven cervical malignancies (squamous cell carcinomas, n = 42; adenocarcinomas, n = 14) who underwent pre-treatment MRI examinations were retrospectively included. The lymph node status (non-metastatic lymph nodes, n = 39; metastatic lymph nodes, n = 17) was assessed using pathological and imaging findings. The texture analysis of primary tumours and lymph nodes was performed on T2-weighted images. Texture parameters with the highest ability to discriminate between the two histological types of primary tumours and metastatic and non-metastatic lymph nodes were selected based on Fisher coefficients (cut-off value > 3). The parameters' discriminative ability was tested using an k nearest neighbour (KNN) classifier, and by comparing their absolute values through an univariate and receiver operating characteristic analysis. Results: The KNN classified metastatic and non-metastatic lymph nodes with 93.75% accuracy. Ten entropy variations were able to identify metastatic lymph nodes (sensitivity: 79.17-88%; specificity: 93.48-97.83%). No parameters exceeded the cut-off value when differentiating between histopathological entities. In conclusion, texture analysis can offer a superior non-invasive characterization of lymph node status, which can improve the staging accuracy of cervical cancers.

Textbook outcome in hepato-pancreato-biliary surgery: systematic review

BACKGROUND

Textbook outcome (TO) is a multidimensional measure reflecting the ideal outcome after surgery. As a benchmarking tool, it provides an objective overview of quality of care. Uniform definitions of TO in hepato-pancreato-biliary (HPB) surgery are missing. This study aimed to provide a definition of TO in HPB surgery and identify obstacles and predictors for achieving it.

METHODS

A systematic literature search was conducted using PubMed, Embase, and Cochrane Database according to PRISMA guidelines. Studies published between 1993 and 2021 were retrieved. After selection, two independent reviewers extracted descriptive statistics and derived summary estimates of the occurrence of TO criteria and obstacles for achieving TO using co-occurrence maps.

RESULTS

Overall, 30 studies were included. TO rates ranged between 16-69 per cent. Commonly chosen co-occurring criteria to define TO included 'no prolonged length of stay (LOS)', 'no complications', 'no readmission', and 'no deaths'. Major obstacles for achieving TO in HPB surgery were prolonged LOS, complications, and readmission. On multivariable analysis, TO predicted better overall and disease-free survival in patients with cancer. Achievement of TO was more likely in dedicated centres and associated with procedural and structural indicators, including high case-mix index and surgical volume.

CONCLUSION

TO is a useful quality measure to benchmark surgical outcome. Future definitions of TO in HPB surgery should include 'no prolonged LOS', 'no complications', 'no readmission', and 'no deaths'.

MeQryEP: A Texture Based Descriptor for Biomedical Image Retrieval

Image texture analysis is a dynamic area of research in computer vision and image processing, with applications ranging from medical image analysis to image segmentation to content-based image retrieval and beyond. "Quinary encoding on mesh patterns (MeQryEP)" is a new approach to extracting texture features for indexing and retrieval of biomedical images, which is implemented in this work. An extension of the previous study, this research investigates the use of local quinary patterns (LQP) on mesh patterns in three different orientations. To encode the gray scale relationship between the central pixel and its surrounding neighbors in a two-dimensional (2D) local region of an image, binary and nonbinary coding, such as local binary patterns (LBP), local ternary patterns (LTP), and LQP, are used, while the proposed strategy uses three selected directions of mesh patterns to encode the gray scale relationship between the surrounding neighbors for a given center pixel in a 2D image. An innovative aspect of the proposed method is that it makes use of mesh image structure quinary pattern features to encode additional spatial structure information, resulting in better retrieval. On three different kinds of benchmark biomedical data sets, analyses have been completed to assess the viability of MeQryEP. LIDC-IDRI-CT and VIA/I-ELCAP-CT are the lung image databases based on computed tomography (CT), while OASIS-MRI is a brain database based on magnetic resonance imaging (MRI). This method outperforms state-of-the-art texture extraction methods, such as LBP, LQEP, LTP, LMeP, LMeTerP, DLTerQEP, LQEQryP, and so on in terms of average retrieval precision (ARP) and average retrieval rate (ARR).

Computer extracted features of nuclear morphology in hematoxylin and eosin images distinguish Stage II and IV colon tumors

We assessed the utility of quantitative features of colon cancer nuclei, extracted from digitized hematoxylin and eosin-stained whole slide images (WSIs), to distinguish between Stage II from Stage IV colon cancers. Our discovery cohort comprised 100 Stage II and Stage IV colon cancer cases sourced from the University Hospitals Cleveland Medical Center (UHCMC). We performed initial (independent) model validation on 51 (143) Stage II and 79 (54) Stage IV colon cancer cases from UHCMC (The Cancer Genome Atlas's Colon Adenocarcinoma, TCGA-COAD, cohort). Our approach comprised the following steps, (1) a fully convolutional deep neural network with VGG-18 architecture was trained to locate cancer on WSIs, (2) another deep-learning model based on Mask-RCNN with Resnet-50 architecture was used to segment all nuclei from within the identified cancer region, (3) a total of 26,641 quantitative morphometric features pertaining to nuclear shape, size, and texture were extracted from within and outside tumor nuclei, (4) a random forest classifier was trained to distinguish between Stage II and Stage IV colon cancers using the 5 most discriminatory features selected by the Wilcoxon rank-sum test. Our trained classifier using these top 5 features yielded an AUC of 0.81 and 0.78, respectively, on the held-out cases in UHCMC and TCGA validation sets. For 197 TCGA-COAD cases, the Cox-proportional hazards model yielded a hazard ratio of 2.20 (95% CI: 1.24-3.88) with a concordance index of 0.71 using only top-five features for risk stratification of overall survival. The Kaplan-Meier estimate also showed statistically significant separation between the low-risk and high-risk patients with a log-rank p-value of 0.0097. Finally, unsupervised clustering of the top-five features revealed that Stage IV colon cancers with peritoneal spread were morphologically more similar to Stage II colon cancers with no long-term metastases than Stage IV colon cancers with hematogenous spread. This article is protected by copyright. All rights reserved.

Assessing PD-L1 Expression Level via Preoperative MRI in HCC Based on Integrating Deep Learning and Radiomics Features

To assess if quantitative integrated deep learning and radiomics features can predict the PD-L1 expression level in preoperative MRI of hepatocellular carcinoma (HCC) patients. The data in this study consist of 103 hepatocellular carcinoma patients who received immunotherapy in a single center. These patients were divided into a high PD-L1 expression group (30 patients) and a low PD-L1 expression group (73 patients). Both radiomics and deep learning features were extracted from their MRI sequence of T2-WI, which were merged into an integrative feature space for machine learning for the prediction of PD-L1 expression. The five-fold cross-validation was adopted to validate the performance of the model, while the AUC was used to assess the predictive ability of the model. Based on the five-fold cross-validation, the integrated model achieved the best prediction performance, with an AUC score of 0.897 ± 0.084, followed by the deep learning-based model with an AUC of 0.852 ± 0.043 then the radiomics-based model with AUC of 0.794 ± 0.035. The feature set integrating radiomics and deep learning features is more effective in predicting PD-L1 expression level than only one feature type. The integrated model can achieve fast and accurate prediction of PD-L1 expression status in preoperative MRI of HCC patients.

Post-COVID-19 Symptom Burden: What is Long-COVID and How Should We Manage It?

The enduring impact of COVID-19 on patients has been examined in recent studies, leading to the description of Long-COVID. We report the lasting symptom burden of COVID-19 patients from the first wave of the pandemic. All patients with COVID-19 pneumonia discharged from a large teaching hospital trust were offered follow-up. We assessed symptom burden at follow-up using a standardised data collection technique during virtual outpatient clinic appointments. Eighty-six percent of patients reported at least one residual symptom at follow-up. No patients had persistent radiographic abnormalities. The presence of symptoms at follow-up was not associated with the severity of the acute COVID-19 illness. Females were significantly more likely to report residual symptoms including anxiety (p = 0.001), fatigue (p = 0.004), and myalgia (p = 0.022). The presence of long-lasting symptoms is common in COVID-19 patients. We suggest that the phenomenon of Long-COVID may not be directly attributable to the effect of SARS-CoV-2, and believe the biopsychosocial effects of COVID-19 may play a greater role in its aetiology.

Mapping images into ordinal networks

An increasing abstraction has marked some recent investigations in network science. Examples include the development of algorithms that map time series data into networks whose vertices and edges can have different interpretations, beyond the classical idea of parts and interactions of a complex system. These approaches have proven useful for dealing with the growing complexity and volume of diverse data sets. However, the use of such algorithms is mostly limited to one-dimensional data, and there has been little effort towards extending these methods to higher-dimensional data such as images. Here we propose a generalization for the ordinal network algorithm for mapping images into networks. We investigate the emergence of connectivity constraints inherited from the symbolization process used for defining the network nodes and links, which in turn allows us to derive the exact structure of ordinal networks obtained from random images. We illustrate the use of this new algorithm in a series of applications involving randomization of periodic ornaments, images generated by two-dimensional fractional Brownian motion and the Ising model, and a data set of natural textures. These examples show that measures obtained from ordinal networks (such as average shortest path and global node entropy) extract important image properties related to roughness and symmetry, are robust against noise, and can achieve higher accuracy than traditional texture descriptors extracted from gray-level co-occurrence matrices in simple image classification tasks.

Automated emergency paramedical response system

With the evolution of technology, the fields of medicine and science have also witnessed numerous advancements. In medical emergencies, a few minutes can be the difference between life and death. The obstacles encountered while providing medical assistance can be eliminated by ensuring quicker care and accessible systems. To this effect, the proposed end-to-end system-automated emergency paramedical response system (AEPRS) is semi-autonomous and utilizes aerial distribution by drones, for providing medical supplies on site in cases of paramedical emergencies as well as for patients with a standing history of diseases. Security of confidential medical information is a major area of concern for patients. Confidentiality has been achieved by using decentralised distributed computing to ensure security for the users without involving third-party institutions. AEPRS focuses not only on urban areas but also on semi-urban and rural areas. In urban areas where access to internet is widely available, a healthcare chatbot caters to the individual users and provides a diagnosis based on the symptoms provided by the patients. In semi-urban and rural areas, community hospitals have the option of providing specialised healthcare in spite of the absence of a specialised doctor. Additionally, object recognition and face recognition by using the concept of edge AI enables deep neural networks to run on the edge, without the need for GPU or internet connectivity to connect to the cloud. AEPRS is an airborne emergency medical supply delivery system. It uses the data entered by the user to deduce the best possible solution, in case of an alerted emergency situation and responds to the user accordingly.

A Bibliometric Analysis of Cleft Lip and Palate-Related Publication Trends From 2000 to 2017

OBJECTIVE

Cleft lip and palate (CLP) is the most common human cranial and maxillofacial birth defect. The aim of this bibliometric analysis was to provide an overview of the development of CLP-related research.

METHOD

Cleft lip and palate-related studies published from 2000 to 2017 were retrieved from the Science Citation Index Expanded core database. Publication date, journal, authors, first authors, keywords, and citations were extracted and quantitatively analyzed using Bibliographic Item Co-Occurrence Matrix Builder software. The word matrix and co-occurrence matrix were established, and the co-citation analysis, keyword clustering, and social network analysis (SNA) of highly cited papers were completed.

RESULTS

A total of 9040 articles were retrieved from the 18 years of publications that were searched. The number of documents steadily increased over the period of interest, with a slight decrease in 2016 and 2017. This article separately examined the top most cited papers and high-frequency keywords from 3 time periods: 2000 to 2005, 2006 to 2011, and 2011 to 2017. The strategy coordinates of citation reflect TGF-β3, MSX1 gene, technique for cleft lip repair, TTF2, P63, IRF6 gene, FGF signaling, PVRL1, TGFBR2, and BMP4 gene as areas of research interest in the field. Moreover, the SNA of keywords highlighted new research topics: meta-analysis, cone beam computed tomography, tooth agenesis, case-control study, association study, micrognathia, DiGeorge syndrome, NSCL/P, UCLP, GWAS, MTHFR, and CLPTM1L.

CONCLUSION

We conducted bibliometric research of CLP across an 18-year span. The results help to define an overall command of the latest topics in CLP and provide insight for launching new projects.

Thin Cap Fibroatheroma Detection in Virtual Histology Images Using Geometric and Texture Features

Atherosclerotic plaque rupture is the most common mechanism responsible for a majority of sudden coronary deaths. The precursor lesion of plaque rupture is thought to be a thin cap fibroatheroma (TCFA), or “vulnerable plaque”. Virtual Histology-Intravascular Ultrasound (VH-IVUS) images are clinically available for visualising colour-coded coronary artery tissue. However, it has limitations in terms of providing clinically relevant information for identifying vulnerable plaque. The aim of this research is to improve the identification of TCFA using VH-IVUS images. To more accurately segment VH-IVUS images, a semi-supervised model is developed by means of hybrid K-means with Particle Swarm Optimisation (PSO) and a minimum Euclidean distance algorithm (KMPSO-mED). Another novelty of the proposed method is fusion of different geometric and informative texture features to capture the varying heterogeneity of plaque components and compute a discriminative index for TCFA plaque, while the existing research on TCFA detection has only focused on the geometric features. Three commonly used statistical texture features are extracted from VH-IVUS images: Local Binary Patterns (LBP), Grey Level Co-occurrence Matrix (GLCM), and Modified Run Length (MRL). Geometric and texture features are concatenated in order to generate complex descriptors. Finally, Back Propagation Neural Network (BPNN), kNN (K-Nearest Neighbour), and Support Vector Machine (SVM) classifiers are applied to select the best classifier for classifying plaque into TCFA and Non-TCFA. The present study proposes a fast and accurate computer-aided method for plaque type classification. The proposed method is applied to 588 VH-IVUS images obtained from 10 patients. The results prove the superiority of the proposed method, with accuracy rates of 98.61% for TCFA plaque.

Robustness versus disease differentiation when varying parameter settings in radiomics features: application to nasopharyngeal PET/CT

OBJECTIVES

To investigate the impact of parameter settings as used for the generation of radiomics features on their robustness and disease differentiation (nasopharyngeal carcinoma (NPC) versus chronic nasopharyngitis (CN) in FDG PET/CT imaging).

METHODS

We studied 106 patients (69/37 NPC/CN, pathology confirmed), and extracted 57 radiomics features under different parameter settings. Robustness was assessed by the intra-class correlation coefficient (ICC). Logistic regression with leave-one-out cross validation was used to generate classification probabilities, and diagnostic performance was assessed by the area under the receiver operating characteristic curve (AUC).

RESULTS

Varying averaging strategies and symmetry, 4/26 GLCM features showed poor range of pairwise ICCs of 0.02-0.98, while depicting good AUCs of 0.82-0.91. Varying distances, 5/26 GLCM features showed ICCs of 0.82-0.99 while corresponding AUCs were 0.52-0.91. 6/13 GLRLM features showed both high AUC (0.81-0.89) and high ICC (0.85-0.99) regarding to averaging strategies. 7/13 GLSZM features showed AUCs of 0.81-0.90 while having ICCs of 0.01-0.99 under different neighbourhoods. 2/5 NGTDM features showed AUCs of 0.81-0.85 while having ICCs of 0.19-0.89 for different window sizes. Differentiating a subset of NPC (stages I-II) form CN, both SumEntropy and SZLGE achieved significantly higher AUCs than metabolically active tumour volume (AUC: 0.91 vs. 0.72, p<0.01).

CONCLUSIONS

Radiomics features depicting poor absolute-scale robustness regarding to parameter settings can still lead to good diagnostic performance. As such, robustness of radiomics features should not be overemphasized for removal of features towards assessment of clinical tasks. For differentiating NPC from CN, some radiomics features (e.g. SumEntropy, SZLGE, LGZE) outperformed conventional metrics.

KEY POINTS

• Poor robustness did not necessarily translate into poor differentiation performance. • Absolute-scale robustness of radiomics features should not be overemphasized. • Radiomics features SumEntropy, SZLGE and LGZE outperformed conventional metrics.

Monitoring Progression of Amyotrophic Lateral Sclerosis Using Ultrasound Morpho-Textural Muscle Biomarkers: A Pilot Study

The need is increasing for progression biomarkers that allow the loss of motor neurons in amyotrophic lateral sclerosis (ALS) to be monitored in clinical trials. In this prospective longitudinal study, muscle thickness, echointensity, echovariation and gray level co-occurrence matrix textural features are examined as possible progression ultrasound biomarkers in ALS patients during a 5-mo follow-up period. We subjected 13 patients to 3 measurements for 20 wk. They showed a significant loss of muscle, an evident tendency to loss of thickness and increased echointensity and echovariation. In regard to textural parameters, muscle heterogeneity tended to increase as a result of the neoformation of non-contractile tissue through denervation. Considering some limitations of the study, the quantitative muscle ultrasound biomarkers evaluated showed a promising ability to monitor patients affected by ALS.

Quantitative Muscle Ultrasonography Using Textural Analysis in Amyotrophic Lateral Sclerosis

The purpose of this study was to analyze differences in gray-level co-occurrence matrix (GLCM) parameters, as assessed by muscle ultrasound (MUS), between amyotrophic lateral sclerosis (ALS) patients and healthy controls, and to compare the diagnostic accuracy of these GLCM parameters with first-order MUS parameters (echointensity [EI], echovariation [EV], and muscle thickness [MTh]) in different muscle groups. Twenty-six patients with ALS and 26 healthy subjects underwent bilateral and transverse ultrasound of the biceps/brachialis, forearm flexor, quadriceps femoris, and tibialis anterior muscle groups. MTh was measured with electronic calipers, and EI, EV, and GLCM were obtained using Image J (v.1.48) software. Sensitivity, specificity, likelihood ratios, and area under the curve (AUC) were performed by logistic regression models and receiver operating characteristic curves. GLCM parameters showed reduced granularity in the muscles of ALS patients compared with the controls. Regarding the discrimination capacity, the best single diagnostic parameter in forearm flexors and quadriceps was GLCM and in biceps brachialis and tibialis anterior was EV. The respective combination of these two parameters with MTh resulted in the best AUC (over 90% in all muscle groups and close to the maximum combination model). The use of new textural parameters (EV and GLCM) combined with usual quantitative MUS variables is a promising biomarker in ALS.

Mining textural knowledge in biological images: Applications, methods and trends

Texture analysis is a major task in many areas of computer vision and pattern recognition, including biological imaging. Indeed, visual textures can be exploited to distinguish specific tissues or cells in a biological sample, to highlight chemical reactions between molecules, as well as to detect subcellular patterns that can be evidence of certain pathologies. This makes automated texture analysis fundamental in many applications of biomedicine, such as the accurate detection and grading of multiple types of cancer, the differential diagnosis of autoimmune diseases, or the study of physiological processes. Due to their specific characteristics and challenges, the design of texture analysis systems for biological images has attracted ever-growing attention in the last few years. In this paper, we perform a critical review of this important topic. First, we provide a general definition of texture analysis and discuss its role in the context of bioimaging, with examples of applications from the recent literature. Then, we review the main approaches to automated texture analysis, with special attention to the methods of feature extraction and encoding that can be successfully applied to microscopy images of cells or tissues. Our aim is to provide an overview of the state of the art, as well as a glimpse into the latest and future trends of research in this area.

Identification of Protein-Protein Interactions via a Novel Matrix-Based Sequence Representation Model with Amino Acid Contact Information

Identification of protein–protein interactions (PPIs) is a difficult and important problem in biology. Since experimental methods for predicting PPIs are both expensive and time-consuming, many computational methods have been developed to predict PPIs and interaction networks, which can be used to complement experimental approaches. However, these methods have limitations to overcome. They need a large number of homology proteins or literature to be applied in their method. In this paper, we propose a novel matrix-based protein sequence representation approach to predict PPIs, using an ensemble learning method for classification. We construct the matrix of Amino Acid Contact (AAC), based on the statistical analysis of residue-pairing frequencies in a database of 6323 protein–protein complexes. We first represent the protein sequence as a Substitution Matrix Representation (SMR) matrix. Then, the feature vector is extracted by applying algorithms of Histogram of Oriented Gradient (HOG) and Singular Value Decomposition (SVD) on the SMR matrix. Finally, we feed the feature vector into a Random Forest (RF) for judging interaction pairs and non-interaction pairs. Our method is applied to several PPI datasets to evaluate its performance. On the S.cerevisiae dataset, our method achieves 94.83% accuracy and 92.40% sensitivity. Compared with existing methods, and the accuracy of our method is increased by 0.11 percentage points. On the H.pylori dataset, our method achieves 89.06% accuracy and 88.15% sensitivity, the accuracy of our method is increased by 0.76%. On the Human PPI dataset, our method achieves 97.60% accuracy and 96.37% sensitivity, and the accuracy of our method is increased by 1.30%. In addition, we test our method on a very important PPI network, and it achieves 92.71% accuracy. In the Wnt-related network, the accuracy of our method is increased by 16.67%. The source code and all datasets are available at https://figshare.com/s/580c11dce13e63cb9a53.

Association of computerized texture features on MRI with early treatment response following laser ablation for neuropathic cancer pain: preliminary findings

Laser interstitial thermal therapy (LITT) has recently emerged as a new treatment modality for cancer pain management that targets the cingulum (pain center in the brain) and has shown promise over radio frequency (RF)-based ablation, due to magnetic resonance image (MRI) guidance that allows for precise ablation. Since laser ablation for pain management is currently exploratory and is only performed at a few centers worldwide, its short- and long-term effects on the cingulum are currently unknown. Traditionally, treatment effects for neurological conditions are evaluated by monitoring changes in intensities and/or volume of the ablation zone on post-treatment Gadolinium-contrast T1-w (Gd-T1) MRI. However, LITT introduces subtle localized changes corresponding to tissues response to treatment, which may not be appreciable on visual inspection of volumetric or intensity changes. Additionally, different MRI protocols [Gd-T1, T2w, gradient echo sequence (GRE), fluid-attenuated inversion recovery (FLAIR)] are known to capture complementary diagnostic information regarding the patient's response to treatment; the utility of these MRI protocols has so far not been investigated to evaluate early and localized response to LITT treatment in the context of neuropathic cancer pain. In this work, we present the first attempt at (a) examining early treatment-related changes on a per-voxel basis via quantitative comparison of computer-extracted texture descriptors across pre- and post-LITT multiparametric (MP-MRI) (Gd-T1, T2w, GRE, FLAIR), subtle microarchitectural texture changes that may not be appreciable on original MR intensities or volumetric differences, and (b) investigating the efficacy of different MRI protocols in accurately capturing immediate post-treatment changes reflected (1) within and (2) outside the ablation zone. A retrospective cohort of four patient studies comprising pre- and immediate (24 h) post-LITT 3 Tesla Gd-T1, T2w, GRE, and FLAIR acquisitions was considered. Our quantitative approach first involved intensity standardization to allow for grayscale MR intensities acquired pre- and post-LITT to have a fixed tissue-specific meaning within the same imaging protocol, the same body region, and within the same patient. An affine registration was then performed on individual post-LITT MRI protocols to a reference MRI protocol pre-LITT. A total of 78 computerized texture features (co-occurrence matrix homogeneity, neighboring gray-level dependence matrix, Gabor) are then extracted from pre- and post-LITT MP-MRI on a per-voxel basis. Quantitative, voxelwise comparison of the changes in MRI texture features between pre- and post-LITT MRI indicate that (a) Gabor texture features at specific orientations were highly sensitive as well as specific in predicting subtle microarchitectural changes within and around the ablation zone pre- and post-LITT, (b) FLAIR was identified as the most sensitive MRI protocol in identifying early treatment changes yielding a normalized percentage change of 360% within the ablation zone relative to its pre-LITT value, and (c) GRE was identified as the most sensitive MRI protocol in quantifying changes outside the ablation zone post-LITT. Our preliminary results thus indicate potential for noninvasive computerized MP-MRI features over volumetric features in determining localized microarchitectural early focal treatment changes post-LITT for neuropathic cancer pain treatment.

Identifying MRI markers to evaluate early treatment related changes post laser ablation for cancer pain management

Laser interstitial thermal therapy (LITT) has recently emerged as a new treatment modality for cancer pain management that targets the cingulum (pain center in the brain), and has shown promise over radio-frequency (RF) based ablation which is reported to provide temporary relief. One of the major advantages enjoyed by LITT is its compatibility with magnetic resonance imaging (MRI), allowing for high resolution in vivo imaging to be used in LITT procedures. Since laser ablation for pain management is currently exploratory and is only performed at a few centers worldwide, its short-, and long-term effects on the cingulum are currently unknown. Traditionally treatment effects are evaluated by monitoring changes in volume of the ablation zone post-treatment. However, this is sub-optimal since it involves evaluating a single global parameter (volume) to detect changes pre-, and post-MRI. Additionally, the qualitative observations of LITT-related changes on multi-parametric MRI (MP-MRI) do not specifically address differentiation between the appearance of treatment related changes (edema, necrosis) from recurrence of the disease (pain recurrence). In this work, we explore the utility of computer extracted texture descriptors on MP-MRI to capture early treatment related changes on a per-voxel basis by extracting quantitative relationships that may allow for an in-depth understanding of tissue response to LITT on MRI, subtle changes that may not be appreciable on original MR intensities. The second objective of this work is to investigate the efficacy of different MRI protocols in accurately capturing treatment related changes within and outside the ablation zone post-LITT. A retrospective cohort of studies comprising pre- and 24-hour post-LITT 3 Tesla T1-weighted (T1w), T2w, T2-GRE, and T2-FLAIR acquisitions was considered. Our scheme involved (1) inter-protocol as well as inter-acquisition affine registration of pre- and post-LITT MRI, (2) quantitation of MRI parameters by correcting for intensity drift in order to examine tissue-specific response, and (3) quantification of MRI maps via texture and intensity features to evaluate changes in MR markers pre- and post-LITT. A total of 78 texture features comprising of non-steerable and steerable gradient and second order statistical features were extracted from pre- and post-LITT MP-MRI on a per-voxel basis. Quantitative, voxel-wise comparison of the changes in MRI texture features between pre-, and post-LITT MRI indicate that (a) steerable and non-steerable gradient texture features were highly sensitive as well as specific in predicting subtle micro-architectural changes within and around the ablation zone pre- and post-LITT, (b) FLAIR was identified as the most sensitive MRI protocol in identifying early treatment changes yielding a normalized percentage change of 360% within the ablation zone relative to its pre-LITT value, and (c) GRE was identified as the most sensitive MRI protocol in quantifying changes outside the ablation zone post-LITT. Our preliminary results thus indicate great potential for non-invasive computerized MRI features in determining localized micro-architectural focal treatment related changes post-LITT.

Texture Descriptors to distinguish Radiation Necrosis from Recurrent Brain Tumors on multi-parametric MRI

Differentiating radiation necrosis (a radiation induced treatment effect) from recurrent brain tumors (rBT) is currently one of the most clinically challenging problems in care and management of brain tumor (BT) patients. Both radiation necrosis (RN), and rBT exhibit similar morphological appearance on standard MRI making non-invasive diagnosis extremely challenging for clinicians, with surgical intervention being the only course for obtaining definitive "ground truth". Recent studies have reported that the underlying biological pathways defining RN and rBT are fundamentally different. This strongly suggests that there might be phenotypic differences and hence cues on multi-parametric MRI, that can distinguish between the two pathologies. One challenge is that these differences, if they exist, might be too subtle to distinguish by the human observer. In this work, we explore the utility of computer extracted texture descriptors on multi-parametric MRI (MP-MRI) to provide alternate representations of MRI that may be capable of accentuating subtle micro-architectural differences between RN and rBT for primary and metastatic (MET) BT patients. We further explore the utility of texture descriptors in identifying the MRI protocol (from amongst T1-w, T2-w and FLAIR) that best distinguishes RN and rBT across two independent cohorts of primary and MET patients. A set of 119 texture descriptors (co-occurrence matrix homogeneity, neighboring gray-level dependence matrix, multi-scale Gaussian derivatives, Law features, and histogram of gradient orientations (HoG)) for modeling different macro and micro-scale morphologic changes within the treated lesion area for each MRI protocol were extracted. Principal component analysis based variable importance projection (PCA-VIP), a feature selection method previously developed in our group, was employed to identify the importance of every texture descriptor in distinguishing RN and rBT on MP-MRI. PCA-VIP employs regression analysis to provide an importance score to each feature based on their ability to distinguish the two classes (RN/rBT). The top performing features identified via PCA-VIP were employed within a random-forest classifier to differentiate RN from rBT across two cohorts of 20 primary and 22 MET patients. Our results revealed that, (a) HoG features at different orientations were the most important image features for both cohorts, suggesting inherent orientation differences between RN, and rBT, (b) inverse difference moment (capturing local intensity homogeneity), and Laws features (capturing local edges and gradients) were identified as important for both cohorts, and (c) Gd-C T1-w MRI was identified, across the two cohorts, as the best MRI protocol in distinguishing RN/rBT.

Different approaches for extracting information from the co-occurrence matrix

In 1979 Haralick famously introduced a method for analyzing the texture of an image: a set of statistics extracted from the co-occurrence matrix. In this paper we investigate novel sets of texture descriptors extracted from the co-occurrence matrix; in addition, we compare and combine different strategies for extending these descriptors. The following approaches are compared: the standard approach proposed by Haralick, two methods that consider the co-occurrence matrix as a three-dimensional shape, a gray-level run-length set of features and the direct use of the co-occurrence matrix projected onto a lower dimensional subspace by principal component analysis. Texture descriptors are extracted from the co-occurrence matrix evaluated at multiple scales. Moreover, the descriptors are extracted not only from the entire co-occurrence matrix but also from subwindows. The resulting texture descriptors are used to train a support vector machine and ensembles. Results show that our novel extraction methods improve the performance of standard methods. We validate our approach across six medical datasets representing different image classification problems using the Wilcoxon signed rank test. The source code used for the approaches tested in this paper will be available at: http://www.dei.unipd.it/wdyn/?IDsezione=3314&IDgruppo_pass=124&preview=.