Tissue Classification Research Articles

Cephalometric comparison of Eastman standards among caucasians and saudi population in the Najran region.

Caucasian norms derived from the European-American population are often applied in the diagnosis and treatment planning of Saudi orthodontic patients. Minor differences in cephalometric values can be considered routine and normal, but significant differences indicate a structural deviation. The objective of this study was to establish the cephalometric norms of normal and pleasant soft tissue profiles of adult Saudi living in the Najran region of Saudi Arabia and compare them with the Eastman standards derived from the Caucasian population. A total of 60 lateral cephalometric radiographs (30 males and 30 females) of Najran adults aged between 18-30 years with pleasing, acceptable, harmonious and well-balanced soft tissue profile and Class I molar relationship with no history of previous orthodontic treatment, no crowding or spacing, normal overjet and overbite were selected for the study. Descriptive analysis and Student t-test were performed to evaluate the male and female gender differences and compare the Najran mean with Eastman standards. On evaluating the gender differences, Najran females tend to have more ANB angle and L1 to A-Pog linear distance than Najran males(p<0.05). On comparing with the Eastman Caucasian standards, the Najran population tends to have more SNA, ANB, UI to MxP and L1 to A-Pog (p<0.05). The U1 to L1 angle tends to be less in Najran population than the Caucasians (p<0.05). The Najran population has more protrusive skeletal bases, bimaxillary protrusion, more proclined upper and lower incisors and reduced interincisal angle than Caucasians. The Najran females have more protrusive skeletal bases and more proclined lower incisors compared to Najran males. The cephalometric findings of this study can be useful in the diagnosis and treatment planning of orthodontic patients belonging to the Najran region of Saudi Arabia.

Is there a Need to Change the Basic Principles of Histology? Educational, Functional and Embryological Perspective

Although it is not an easy task to classify cells into different types, or in turn cell types into tissue types, a clear, understandable, didactically and clinically relevant tissue classification is indispensable for undergraduate medical education, expert discussions in biomedical research as well as for clinical practice. From the earliest discovery of the light microscope on, tissue classification has been a dynamic process. Historically, it was not a rare occurrence that different textbooks offered different tissue classifications. Nowadays, classifications have almost become uniform - the most common is the histological classification into four basic tissue types (epithelial, connective, muscle, nervous), which is recognized by the majority of modern histology and pathology textbooks. The reason is that, with some exceptions, this classification seems to be the most relevant not only for educational purposes but also from an embryological perspective and clinical-histopathological practice. Recently, attempts have been made to abandon this established classification and replace it with a new one. Any new classification, which would improve the presently used is welcomed. However, if the proposed innovation does not satisfy the needs of modern education and clinical practice, it should be handled with great caution or reconsidered.

Aggregation of Multimodal ICE-MS Data into Joint Classifier Increases Quality of Brain Cancer Tissue Classification

Mass spectrometry fingerprinting combined with multidimensional data analysis has been proposed in surgery to determine if a biopsy sample is a tumor. In the specific case of brain tumors, it is complicated to obtain control samples, leading to model overfitting due to unbalanced sample cohorts. Usually, classifiers are trained using a single measurement regime, most notably single ion polarity, but mass range and spectral resolution could also be varied. It is known that lipid groups differ significantly in their ability to produce positive or negative ions; hence, using only one polarity significantly restricts the chemical space available for sample discrimination purposes. In this work, we have developed an approach employing mass spectrometry data obtained by eight different regimes of measurement simultaneously. Regime-specific classifiers are trained, then a mixture of experts techniques based on voting or mean probability is used to aggregate predictions of all trained classifiers and assign a class to the whole sample. The aggregated classifiers have shown a much better performance than any of the single-regime classifiers and help significantly reduce the effect of an unbalanced dataset without any augmentation.

Classification of neck tissues in OCT images by using convolutional neural network

Identification and classification of surrounding neck tissues are very important in thyroid surgery. The advantages of optical coherence tomography (OCT), high resolution, non-invasion, and non-destruction make it have great potential in identifying different neck tissues during thyroidectomy. We studied the automatic classification for neck tissues in OCT images based on convolutional neural network in this paper. OCT images of five kinds of neck tissues were collected firstly by our home-made swept source (SS-OCT) system, and a dataset was built for neural network training. Three image classification neural networks: LeNet, VGGNet, and ResNet, were used to train and test the dataset. The impact of transfer learning on the classification of neck tissue OCT images was also studied. Through the comparison of accuracy, it was found that ResNet has the best classification accuracy among the three networks. In addition, transfer learning did not significantly improve the accuracy, but it can somewhat accelerate the convergence of the network and shorten the network training time.

Optimizing the classification of biological tissues using machine learning models based on polarized data.

Polarimetric data is nowadays used to build recognition models for the characterization of organic tissues or the early detection of some diseases. Different Mueller matrix-derived polarimetric observables, which allow a physical interpretation of a specific characteristic of samples, are proposed in literature to feed the required recognition algorithms. However, they are obtained through mathematical transformations of the Mueller matrix and this process may loss relevant sample information in search of physical interpretation. In this work, we present a thorough comparative between 12 classification models based on different polarimetric datasets to find the ideal polarimetric framework to construct tissues classification models. The study is conducted on the experimental Mueller matrices images measured on different tissues: muscle, tendon, myotendinous junction and bone; from a collection of 165 ex-vivo chicken thighs. Three polarimetric datasets are analyzed: (A) a selection of most representative metrics presented in literature; (B) Mueller matrix elements; and (C) the combination of (A) and (B) sets. Results highlight the importance of using raw Mueller matrix elements for the design of classification models.

World health organization classification of bone tumors (fifth edition): What a radiologist needs to know?

Since 1967, the World Health Organization (WHO) classification of tumors is regarded as a reference standard and practical guide and provides a precious resource not only for the histopathologists and oncosurgeons but also for the radiologists involved in cancer care. Primary bone tumors are a rare and heterogeneous group of neoplasms that have a broad spectrum of morphological, biological, genetic, and radiological features. Appropriate imaging workup and accurate histopathological diagnosis are crucial for appropriate management and prognostication. The fourth edition of the WHO classification of tumors of soft tissue and bone was introduced in 2013. In the past 7 years, there have been considerable advances in the understanding of this large and diverse group of tumors. With technological advances and the introduction of new molecular and genetic data about some bone tumors, there has been reorganization in the classification and introduction of a few new entities. The new WHO classification of soft tissue and bone tumors introduced in 2020 (fifth edition) has made essential refinements in the classification and has also introduced many new entities. Newly identified genetic alterations and corresponding immunohistochemical markers are included in the new classification, and this has helped in the reclassification of the existing tumor entities. These novel genetic alterations not only help in prognostication but are a target for potential therapeutic options which can bring a paradigm shift in the chemotherapeutic regimen for these entities in the future. The sole basis for the classification of bone tumors is histopathological. Although radiologists are not expected to know about the exquisite pathological details of bone tumors, a broad knowledge of the recent updates, including the reclassification of a few entities or the introduction of some, is vital for narrowing the differentials in imaging. A multidisciplinary approach including an orthopedic oncologist, radiologist, pathologist, surgical, and medical oncologist is required for accurate diagnosis and management of primary bone tumors. We hereby present a simplified review for the radiologists comprising the relevant details of the updates in bone tumors along with a simplified diagnostic algorithm to characterize these lesions.

Machine Learning-Based Classification of Abnormal Liver Tissues Using Relative Permittivity.

The search for non-invasive, fast, and low-cost diagnostic tools has gained significant traction among many researchers worldwide. Dielectric properties calculated from microwave signals offer unique insights into biological tissue. Material properties, such as relative permittivity (εr) and conductivity (σ), can vary significantly between healthy and unhealthy tissue types at a given frequency. Understanding this difference in properties is key for identifying the disease state. The frequency-dependent nature of the dielectric measurements results in large datasets, which can be postprocessed using artificial intelligence (AI) methods. In this work, the dielectric properties of liver tissues in three mouse models of liver disease are characterized using dielectric spectroscopy. The measurements are grouped into four categories based on the diets or disease state of the mice, i.e., healthy mice, mice with non-alcoholic steatohepatitis (NASH) induced by choline-deficient high-fat diet, mice with NASH induced by western diet, and mice with liver fibrosis. Multi-class classification machine learning (ML) models are then explored to differentiate the liver tissue groups based on dielectric measurements. The results show that the support vector machine (SVM) model was able to differentiate the tissue groups with an accuracy up to 90%. This technology pipeline, thus, shows great potential for developing the next generation non-invasive diagnostic tools.

Diffuse reflection spectroscopy at the fingertip: design and performance of a compact side-firing probe for tissue discrimination during colorectal cancer surgery.

Optical technologies are widely used for tissue sensing purposes. However, maneuvering conventional probe designs with flat-tipped fibers in narrow spaces can be challenging, for instance during pelvic colorectal cancer surgery. In this study, a compact side-firing fiber probe was developed for tissue discrimination during colorectal cancer surgery using diffuse reflectance spectroscopy. The optical behavior was compared to flat-tipped fibers using both Monte Carlo simulations and experimental phantom measurements. The tissue classification performance was examined using freshly excised colorectal cancer specimens. Using the developed probe and classification algorithm, an accuracy of 0.92 was achieved for discriminating tumor tissue from healthy tissue.

Ewing and Ewing-like sarcomas: A morphological guide through genetically-defined entities.

The fifth edition of the World Health Organization classification of soft tissue and bone tumors redefined Ewing sarcoma by fusions between EWSR1/FUS and ETS family of transcription factors, and recognized three tumor groups among Ewing-like sarcoma: CIC-rearranged sarcoma, sarcoma with BCOR genetic alterations, and round cell sarcoma with EWSR1::non-ETS fusions. Although this classification underscores the critical role of molecular genetics in the diagnosis of small round cell sarcoma, each entry is recognized as a specific entity not only because they have different genetics but because their phenotypes are distinct and reasonably robust to support the diagnosis. This review focuses on the morphological aspects of Ewing sarcoma and a subset of Ewing-like sarcomas (CIC-rearranged sarcoma, BCOR-associated sarcoma, and EWSR1::NFATC2 sarcoma) for which phenotypic characteristics have been well established. Classic histological findings, uncommon variations, and recurrent diagnostic pitfalls are addressed, along with the utility of recently developed immunohistochemical markers (NKX2.2, PAX7, ETV4, BCOR, CCNB3, and NKX3.1). Phenotypic expertise would significantly expedite the diagnostic process and complement (or sometimes outperform) genetic testing, even in well-resourced settings. Morphological knowledge plays an even more substantial role in facilities that do not have easy access to molecular testing.

Alzheimer’s Disease Detection with a 3D Convolutional Neural Network using Gray Matter Maps from T1‐weighted Brain MRI

AbstractBackgroundA practical screening tool to detect Alzheimer’s disease (AD) based on brain MRI would be valuable. Here we tested a deep learning method for subject‐wise AD classification; as gray matter (GM) is preferentially affected by AD, we also performed MRI tissue classification on the input data, to test the added value of these input features. We set out to compare different types of imaging data types1 as inputs to a 3D Convolutional Neural Network (CNN) for the AD classification task.MethodWe analyzed T1‐weighted brain MRI scans from 1123 subjects (596M/527F, 55.2 ‐ 95.8 years) from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). After registering the T1‐w MRI scans to a common brain template, GM was segmented as shown in Figure 1. We subdivided the dataset into training (3,302 scans/853 subjects), validation (413 scans/100 subjects) and test (170 scans/170 subjects) data for the CNN2. We also trained the CNN on different proportions (10%, 20%, 50% and 100%) of the overall ADNI training data. We further validated our results independently on 232 scans/232 subjects (78M/154F, 33‐96 years) from the Open Access Series of Imaging Studies (OASIS) dataset.ResultWe summarize our results in Table 1 in terms of the receiver‐operator characteristic curve‐area under the curve (ROC‐AUC). Results were aggregated over two separate runs to demonstrate the model’s stability. The CNN with GM segmented T1‐w MRI as input achieved an Average ROC‐AUC of 0.864, compared to 0.859 with the complete T1‐w MRI. The CNN performs better with gray matter segmented input; this performance boost was more pronounced with smaller training sets, i.e., 10% (330 scans) or 20% (660 scans) as seen in Figure 2. The models trained on gray matter maps from ADNI also yielded better performance on the OASIS test set.ConclusionIn this work, we found that using GM extracted from T1‐w MRI scans improves deep learning‐based AD diagnosis. Feature selection is improved by regulating the data input into the CNN.[1] Lu, B., et al., “A Practical Alzheimer’s Disease Classifier… on 85,721 Samples,” bioRxiv Prepr. (2021).[2] Dhinagar, N. J., et al., “3D CNNs for Classification of Alzheimer’s … with T1‐Weighted Brain MRI,” SIPAIM (2021).

DLA-H: A Deep Learning Accelerator for Histopathologic Image Classification.

It is more than a decade since machine learning and especially its leading subtype deep learning have become one of the most interesting topics in almost all areas of science and industry. In numerous contexts, at least one of the applications of deep learning is utilized or is going to be utilized. Using deep learning for image classification is now very popular and widely used in various use cases. Many types of research in medical sciences have been focused on the advantages of deep learning for image classification problems. Some recent researches show more than 90% accuracy for breast tissue classification which is a breakthrough. A huge number of computations in deep neural networks are considered a big challenge both from software and hardware point of view. From the architectural perspective, this big amount of computing operations will result in high power consumption and computation runtime. This led to the emersion of deep learning accelerators which are designed mainly for improving performance and energy efficiency. Data reuse and localization are two great opportunities for achieving energy-efficient computations with lower runtime. Data flows are mainly designed based on these important parameters. In this paper, DLA-H and BJS, a deep learning accelerator, and its data flow for histopathologic image classification are proposed. The simulation results with the MAESTRO tool showed 756 cycles for total runtime and [Formula: see text] GFLOPS roofline throughput that is an extreme performance improvement in comparison to current general-purpose deep learning accelerators and data flows.

Cancer Segmentation by Entropic Analysis of Ordered Gene Expression Profiles.

The availability of massive gene expression data has been challenging in terms of how to cure, process, and extract useful information. Here, we describe the use of entropic measures as discriminating criteria in cancer using the whole data set of gene expression levels. These methods were applied in classifying samples between tumor and normal type for 13 types of tumors with a high success ratio. Using gene expression, ordered by pathways, results in complexity-entropy diagrams. The map allows the clustering of the tumor and normal types samples, with a high success rate for nine of the thirteen, studied cancer types. Further analysis using information distance also shows good discriminating behavior, but, more importantly, allows for discriminating between cancer types. Together, our results allow the classification of tissues without the need to identify relevant genes or impose a particular cancer model. The used procedure can be extended to classification problems beyond the reported results.

Preoperative diagnosis of perineural invasion in patients with periampullary carcinoma by MSCT imaging: preliminary observations and clinical implications.

The aim of this study was to investigate the value of multi-slice computed tomography (MSCT) in preoperatively diagnosing perineural invasion (PNI) of periampullary carcinoma (PAC). Of 81 patients pathologically diagnosed as PAC, 73 patients were included. Their clinical documents and preoperative upper abdominal enhanced MSCT images were retrospectively reviewed to analyse clinical characteristics and MSCT features. MSCT features included tumor size, classification of fat tissue around celiac trunk and superior mesenteric artery. Chi-square test, Mann-Whitney U test or Fisher's exact test were used to compare the differences between PNI group and Non-PNI group. ROC analysis was performed to evaluate diagnostic efficiency for PAC PNI. There were significant differences in some clinical characteristics and MSCT features. PAC PNI patients had significantly higher CA19-9 levels, higher CEA levels, larger tumor size and higher classification of fat tissue around celiac trunk than Non-PNI patients (All P values < 0.05). In univariate analysis, tumor size had the highest AUC as 0.806, fat tissue around celiac trunk and CEA had the highest specificity as 100% (P < 0.001). In multivariate analysis, classification of fat tissue around celiac trunk incorporated with tumor size, CA19-9, CEA, age and sex, showed the highest AUC as 0.939, with specificity of 95.0% and sensitivity of 90.4% (P < 0.001). PAC PNI could be diagnosed preoperatively by evaluating abdominal enhanced MSCT images with high accuracy, combined with serum tumor marker could be more helpful.

Insights into Biochemical Sources and Diffuse Reflectance Spectral Features for Colorectal Cancer Detection and Localization.

Colorectal cancer (CRC) is the third most common and second most deadly type of cancer worldwide. Early detection not only reduces mortality but also improves patient prognosis by allowing the use of minimally invasive techniques to remove cancer while avoiding major surgery. Expanding the use of microsurgical techniques requires accurate diagnosis and delineation of the tumor margins in order to allow complete excision of cancer. We have used diffuse reflectance spectroscopy (DRS) to identify the main optical CRC biomarkers and to optimize parameters for the integration of such technologies into medical devices. A total number of 2889 diffuse reflectance spectra were collected in ex vivo specimens from 47 patients. Short source-detector distance (SDD) and long-SDD fiber-optic probes were employed to measure tissue layers from 0.5 to 1 mm and from 0.5 to 1.9 mm deep, respectively. The most important biomolecules contributing to differentiating DRS between tissue types were oxy- and deoxy-hemoglobin (Hb and HbO2), followed by water and lipid. Accurate tissue classification and potential DRS device miniaturization using Hb, HbO2, lipid and water data were achieved particularly well within the wavelength ranges 350-590 nm and 600-1230 nm for the short-SDD probe, and 380-400 nm, 420-610 nm, and 650-950 nm for the long-SDD probe.

Role of Histopathology in diagnosis of Soft Tissue Tumors at Tertiary Care Center

Introduction: Soft tissue tumors (STTs) are a diverse group of neoplasms. It varies from the most common benign tumors to some self-limited lesions and rare malignant soft tissue tumors. Because of the overlap in their clinical and radiological characteristics, histopathology is crucial in determining their diagnosis.&#x0D; Objectives: To study the relative frequencies of types of soft tissue tumors (benign, intermediate and malignant) as well as their histological pattern in relation to age, gender and site of distribution.&#x0D; Methodology: This was a retrospective study conducted over a period of three years from January 2018 to December 2020 in the Department of Pathology, Dhulikhel Hospital, Kavre Nepal. This study included STTs of all the anatomical sites excluding STTs of the female reproductive system. The tumors were classified as benign, intermediate, or malignant using the WHO 2013 classification of soft tissue and bone tumors. The sarcomas were further graded into grades 1, 2, and 3 using the FNCLCC (French Federation Nationale des Centres de Lutte Contre le Cancer) grading system. Immunohistochemistry (IHC) and special staining procedures were also performed as and when required. &#x0D; Result: A total of 198 STTs were studied, of which benign cases were 191 (96.45%), intermediate 03 (1.52%) and malignant 04 (2.03%) in number. The most common type of STTs was vascular tumors 77(38.89%) followed by adipocytic tumors 52(26.26%) and nerve sheath tumors 13(6.56%). STTs were most common in the third decade of life, with the head and neck region being the commonest site. All four malignant tumors were categorized using the FNCLCC grading system. There were three cases of Grade 2 sarcoma and one case of Grade 3 sarcoma.&#x0D; Conclusion: The most common benign tumors were vascular tumors followed by adipocytic tumors and nerve sheath tumors. STTs were most common in the third decade of life. Benign tumors were more common than malignant tumors. In comparison to malignant tumors, benign tumors were found at a younger age group. STTs were found mainly in the head and neck region followed by upper and lower limbs. Despite the fact that molecular diagnostics is gaining popularity in the field of soft tissue tumors, histopathology still remains the gold standard.

Harmonization of Rapid Evaporative Ionization Mass Spectrometry Workflows across Four Sites and Testing Using Reference Material and Local Food-Grade Meats.

Rapid evaporative ionization mass spectrometry (REIMS) is a direct tissue metabolic profiling technique used to accurately classify tissues using pre-built mass spectral databases. The reproducibility of the analytical equipment, methodology and tissue classification algorithms has yet to be evaluated over multiple sites, which is an essential step for developing this technique for future clinical applications. In this study, we harmonized REIMS methodology using single-source reference material across four sites with identical equipment: Imperial College London (UK); Waters Research Centre (Hungary); Maastricht University (The Netherlands); and Queen's University (Canada). We observed that method harmonization resulted in reduced spectral variability across sites. Each site then analyzed four different types of locally-sourced food-grade animal tissue. Tissue recognition models were created at each site using multivariate statistical analysis based on the different metabolic profiles observed in the m/z range of 600-1000, and these models were tested against data obtained at the other sites. Cross-validation by site resulted in 100% correct classification of two reference tissues and 69-100% correct classification for food-grade meat samples. While we were able to successfully minimize between-site variability in REIMS signals, differences in animal tissue from local sources led to significant variability in the accuracy of an individual site's model. Our results inform future multi-site REIMS studies applied to clinical samples and emphasize the importance of carefully-annotated samples that encompass sufficient population diversity.

Optical Characterization of Biological Tissues Based on Fluorescence, Absorption, and Scattering Properties.

Optical diagnostics methods are significantly appealing in biological applications since they are non-destructive, safe, and minimally invasive. Laser-induced fluorescence is a promising optical spectrochemical analytical technique widely employed for tissue classification through molecular analysis of the studied samples after excitation with appropriate short-wavelength laser light. On the other hand, diffuse optics techniques are used for tissue monitoring and differentiation based on their absorption and scattering characteristics in the red to the near-infrared spectra. Therefore, it is strongly foreseen to obtain promising results by combining these techniques. In the present work, tissues under different conditions (hydrated/dry skin and native/boiled adipose fat) were distinguished according to their fluorescence emission, absorption, and scattering properties. The selected tissues' optical absorption and scattering parameters were determined via Kubelka-Munk mathematical model according to the experimental tissue reflectance and transmittance measurements. Such measurements were obtained using an optical configuration of integrating sphere and spectrometer at different laser wavelengths (808, 830, and 980 nm). Moreover, the diffusion equation was solved for the fluence rate at the sample surface using the finite element method. Furthermore, the accuracy of the obtained spectroscopic measurements was evaluated using partial least squares regression statistical analysis with 0.87 and 0.89 R-squared values for skin and adipose fat, respectively.

What's new in soft tissue and bone pathology 2022-updates from the WHO classification 5th edition.

The 2020 release of the WHO Classification of Soft Tissue and Bone Tumors, 5th edition, contains several changes driven by new knowledge in the field. These include reclassification of some entities, refinement of risk classification systems, and the inclusion of novel disease processes, many of which are driven by recurrent gene fusions. The most notable changes are described here.

Update of pediatric bone tumors-notochordal tumors, chondrogenic tumors, and vascular tumors of the bone.

There are numerous bone tumors in the pediatric population, with imaging playing an essential role in diagnosis and management. Our understanding of certain bone tumors has rapidly evolved over the past decade with advancements in next-generation genetic sequencing techniques. This increased level of understanding has altered the nomenclature, management approach, and prognosis of certain lesions. We provide a detailed update of bone tumors that occur in the pediatric population with emphasis on the recently released nomenclature provided in the 5th edition of the World Health Organization Classification of Soft Tissue and Bone Tumours. In the current manuscript, we address notochordal tumors, chondrogenic tumors, and vascular tumors of the bone.

Diseased thyroid tissue classification in OCT images using deep learning: Towards surgical decision support.

Intraoperative guidance tools for thyroid surgery based on optical coherence tomography (OCT) could aid distinguish between normal and diseased tissue. However, OCT images are difficult to interpret, thus, real-time automatic analysis could support the clinical decision-making. In this study, several deep learning models were investigated for thyroid disease classification on 2D and 3D OCT data obtained from ex vivo specimens of 22 patients undergoing surgery and diagnosed with several thyroid pathologies. Additionally, two open-access datasets were used to evaluate the custom models. On the thyroid dataset, the best performance was achieved by the 3D vision transformer model with a Matthew's correlation coefficient (MCC) of 0.79 (accuracy=0.90) for the normal-versus-abnormal classification. On the open-access datasets, the custom models achieved the best performance (MCC > 0.88, accuracy > 0.96). Results obtained for the normal-versus-abnormal classification suggest OCT, complemented with deep learning-based analysis, as a tool for real-time automatic diseased tissue identification in thyroid surgery.