An integrated texton and bag of words classifier for identifying anaplastic medulloblastomas

Artificial intelligence in histopathological image analysis of central nervous system tumours: A systematic review

The convergence of digital pathology and artificial intelligence could assist histopathology image analysis by providing tools for rapid, automated morphological analysis. This systematic review explores the use of artificial intelligence for histopathological image analysis of digitised central nervous system (CNS) tumour slides. Comprehensive searches were conducted across EMBASE, Medline and the Cochrane Library up to June 2023 using relevant keywords. Sixty-eight suitable studies were identified and qualitatively analysed. The risk of bias was evaluated using the Prediction model Risk of Bias Assessment Tool (PROBAST) criteria. All the studies were retrospective and preclinical. Gliomas were the most frequently analysed tumour type. The majority of studies used convolutional neural networks or support vector machines, and the most common goal of the model was for tumour classification and/or grading from haematoxylin and eosin-stained slides. The majority of studies were conducted when legacy World Health Organisation (WHO) classifications were in place, which at the time relied predominantly on histological (morphological) features but have since been superseded by molecular advances. Overall, there was a high risk of bias in all studies analysed. Persistent issues included inadequate transparency in reporting the number of patients and/or images within the model development and testing cohorts, absence of external validation, and insufficient recognition of batch effects in multi-institutional datasets. Based on these findings, we outline practical recommendations for future work including a framework for clinical implementation, in particular, better informing the artificial intelligence community of the needs of the neuropathologist.

High-Order Correlation-Guided Slide-Level Histology Retrieval With Self-Supervised Hashing

Histopathological Whole Slide Images (WSIs) play a crucial role in cancer diagnosis. It is of significant importance for pathologists to search for images sharing similar content with the query WSI, especially in the case-based diagnosis. While slide-level retrieval could be more intuitive and practical in clinical applications, most methods are designed for patch-level retrieval. A few recently unsupervised slide-level methods only focus on integrating patch features directly, without perceiving slide-level information, and thus severely limits the performance of WSI retrieval. To tackle the issue, we propose a High-Order Correlation-Guided Self-Supervised Hashing-Encoding Retrieval (HSHR) method. Specifically, we train an attention-based hash encoder with slide-level representation in a self-supervised manner, enabling it to generate more representative slide-level hash codes of cluster centers and assign weights for each. These optimized and weighted codes are leveraged to establish a similarity-based hypergraph, in which a hypergraph-guided retrieval module is adopted to explore high-order correlations in the multi-pairwise manifold to conduct WSI retrieval. Extensive experiments on multiple TCGA datasets with over 24,000 WSIs spanning 30 cancer subtypes demonstrate that HSHR achieves state-of-the-art performance compared with other unsupervised histology WSI retrieval methods.

Texture Analysis and its Applications in Biomedical Imaging: A Survey

Texture analysis describes a variety of image analysis techniques that quantify the variation in intensity and pattern. This paper provides an overview of several texture analysis approaches addressing the rationale supporting them, their advantages, drawbacks, and applications. This surveys emphasis is in collecting and categorising over five decades of active research on texture analysis. Brief descriptions of different approaches are presented along with application examples. From a broad range of texture analysis applications, this surveys final focus is on biomedical image analysis. An up-to-date list of biological tissues and organs in which disorders produce texture changes that may be used to spot disease onset and progression is provided. Finally, the role of texture analysis methods as biomarkers of disease is summarised.

CoMB-Deep: Composite Deep Learning-Based Pipeline for Classifying Childhood Medulloblastoma and Its Classes

Childhood medulloblastoma (MB) is a threatening malignant tumor affecting children all over the globe. It is believed to be the foremost common pediatric brain tumor causing death. Early and accurate classification of childhood MB and its classes are of great importance to help doctors choose the suitable treatment and observation plan, avoid tumor progression, and lower death rates. The current gold standard for diagnosing MB is the histopathology of biopsy samples. However, manual analysis of such images is complicated, costly, time-consuming, and highly dependent on the expertise and skills of pathologists, which might cause inaccurate results. This study aims to introduce a reliable computer-assisted pipeline called CoMB-Deep to automatically classify MB and its classes with high accuracy from histopathological images. This key challenge of the study is the lack of childhood MB datasets, especially its four categories (defined by the WHO) and the inadequate related studies. All relevant works were based on either deep learning (DL) or textural analysis feature extractions. Also, such studies employed distinct features to accomplish the classification procedure. Besides, most of them only extracted spatial features. Nevertheless, CoMB-Deep blends the advantages of textural analysis feature extraction techniques and DL approaches. The CoMB-Deep consists of a composite of DL techniques. Initially, it extracts deep spatial features from 10 convolutional neural networks (CNNs). It then performs a feature fusion step using discrete wavelet transform (DWT), a texture analysis method capable of reducing the dimension of fused features. Next, the CoMB-Deep explores the best combination of fused features, enhancing the performance of the classification process using two search strategies. Afterward, it employs two feature selection techniques on the fused feature sets selected in the previous step. A bi-directional long-short term memory (Bi-LSTM) network; a DL-based approach that is utilized for the classification phase. CoMB-Deep maintains two classification categories: binary category for distinguishing between the abnormal and normal cases and multi-class category to identify the subclasses of MB. The results of the CoMB-Deep for both classification categories prove that it is reliable. The results also indicate that the feature sets selected using both search strategies have enhanced the performance of Bi-LSTM compared to individual spatial deep features. CoMB-Deep is compared to related studies to verify its competitiveness, and this comparison confirmed its robustness and outperformance. Hence, CoMB-Deep can help pathologists perform accurate diagnoses, reduce misdiagnosis risks that could occur with manual diagnosis, accelerate the classification procedure, and decrease diagnosis costs.

Reimagining T Staging Through Artificial Intelligence and Machine Learning Image Processing Approaches in Digital Pathology

Tumor stage and grade, visually assessed by pathologists from evaluation of pathology images in conjunction with radiographic imaging techniques, have been linked to outcome, progression, and survival for a number of cancers. The gold standard of staging in oncology has been the TNM (tumor-node-metastasis) staging system. Though histopathological grading has shown prognostic significance, it is subjective and limited by interobserver variability even among experienced surgical pathologists. Recently, artificial intelligence (AI) approaches have been applied to pathology images toward diagnostic-, prognostic-, and treatment prediction-related tasks in cancer. AI approaches have the potential to overcome the limitations of conventional TNM staging and tumor grading approaches, providing a direct prognostic prediction of disease outcome independent of tumor stage and grade. Broadly speaking, these AI approaches involve extracting patterns from images that are then compared against previously defined disease signatures. These patterns are typically categorized as either (1) handcrafted, which involve domain-inspired attributes, such as nuclear shape, or (2) deep learning (DL)-based representations, which tend to be more abstract. DL approaches have particularly gained considerable popularity because of the minimal domain knowledge needed for training, mostly only requiring annotated examples corresponding to the categories of interest. In this article, we discuss AI approaches for digital pathology, especially as they relate to disease prognosis, prediction of genomic and molecular alterations in the tumor, and prediction of treatment response in oncology. We also discuss some of the potential challenges with validation, interpretability, and reimbursement that must be addressed before widespread clinical deployment. The article concludes with a brief discussion of potential future opportunities in the field of AI for digital pathology and oncology.

Classification of childhood medulloblastoma into WHO-defined multiple subtypes based on textural analysis

Childhood medulloblastoma is a case of a childhood brain tumour that requires close attention due to the low survival rate. Effective prognosis depends a lot on accurate detection of its subtype. The present study proposes a texture-based computer-aided categorization of childhood medulloblastoma samples. According to the World Health Organization, it has four subtypes (desmoplastic, classic, nodular and large). Classification is done in two levels: (i) normal and abnormal and (ii) its four subtypes. The system is evaluated on indigenous patient samples collected from the region. The main objective of database generation is to create a data set of childhood medulloblastoma samples since there exists no available benchmark data set. The proposed framework for automated classification is based on the architectural property and the distribution of cells. Five texture features were extracted for the feature set, namely: grey-level co-occurrence matrix, grey-level run length matrix, first-order histogram features, local binary pattern and Tamura features. The performance of each feature set was evaluated, both individually and in combinations, using five different classifiers. Fivefold cross-validation was used for training and testing the data set. Experiments on both individual feature sets and combinations (best-2, best-3, best-4 and all-5) of feature sets were evaluated based on the accuracy of performance. It was revealed that the combined best-4 feature set resulted in the highest accuracy of 91.3%. The precision, recall and specificity were 0.913, 0.913 and 0.97, respectively. Significantly, it implied that the all-5 feature set is not necessary to have a useful classification. Feature reduction by principal component analysis resulted in increased accuracy of 96.7%. LAY DESCRIPTION: Childhood medulloblastoma is a case of childhood brain tumour that requires high attention due to a low survival rate. Effective prognosis depends a lot on accurate detection of its subtype. The present study proposes a texture-based computer-aided categorization of childhood medulloblastoma samples. According to the World Health Organization (W.H.O), it has four subtypes (desmoplastic, classic, nodular, and large). Classification is done in two levels: i) normal and abnormal ii) its four subtypes. The system is evaluated on indigenous patient samples collected from the region. The main objective of database generation is to create a data set of childhood medulloblastoma samples since there exists no available benchmark data set. The proposed framework is a model for the automatic classification of the samples. The tissue samples obtained post-operation by doctors are converted into images, and then necessary algorithms are applied so that certain features describing each group of the image are known and studied for classification. Later these images are classified using the image features into the subtypes of abnormal samples.

Study on Contribution of Biological Interpretable and Computer-Aided Features Towards the Classification of Childhood Medulloblastoma Cells

Diagnosis and Prognosis of brain tumour in children is always a critical case. Medulloblastoma is that subtype of brain tumour which occurs most frequently amongst children. Post-operation, the classification of its subtype is most vital for further clinical management. In this paper a novel approach of pathological subtype classification using biological interpretable and computer-aided textural features is forwarded. The classifier for accurate features prediction is built purely on the feature set obtained by segmentation of the ground truth cells from the original histological tissue images, marked by an experienced pathologist. The work is divided into five stages: marking of ground truth, segmentation of ground truth images, feature extraction, feature reduction and finally classification. Kmeans colour segmentation is used to segment out the ground truth cells from histological images. For feature extraction we used morphological, colour and textural features of the cells followed by feature reduction using Principal Component Analysis. Finally both binary and multiclass classification is done using Support Vector Method (SVM). The classification was compared using six different classifiers and performance was evaluated employing five-fold cross-validation technique. The accuracy achieved for binary and multiclass classification before applying PCA were 95.4 and 62.1% and after applying PCA were 100 and 84.9% respectively. The run-time analysis are also shown. Results reveal that this technique of cell level classification can be successfully adopted as architectural view can be confusing. Moreover it conforms substantially to the pathologist's point of view regarding morphological and colour features, with the addition of computer assisted texture feature.

Medical Image Retrieval Using Multi-Texton Assignment

In this paper, we present a multi-texton representation method for medical image retrieval, which utilizes the locality constraint to encode each filter bank response within its local-coordinate system consisting of the k nearest neighbors in texton dictionary and subsequently employs spatial pyramid matching technique to implement feature vector representation. Comparison with the traditional nearest neighbor assignment followed by texton histogram statistics method, our strategies reduce the quantization errors in mapping process and add information about the spatial layout of texton distributions and, thus, increase the descriptive power of the image representation. We investigate the effects of different parameters on system performance in order to choose the appropriate ones for our datasets and carry out experiments on the IRMA-2009 medical collection and the mammographic patch dataset. The extensive experimental results demonstrate that the proposed method has superior performance.

Identification of Histological Correlates of Overall Survival in Lower Grade Gliomas Using a Bag-of-words Paradigm: A Preliminary Analysis Based on Hematoxylin & Eosin Stained Slides from the Lower Grade Glioma Cohort of The Cancer Genome Atlas

Background:

Glioma, the most common primary brain neoplasm, describes a heterogeneous tumor of multiple histologic subtypes and cellular origins. At clinical presentation, gliomas are graded according to the World Health Organization guidelines (WHO), which reflect the malignant characteristics of the tumor based on histopathological and molecular features. Lower grade diffuse gliomas (LGGs) (WHO Grade II–III) have fewer malignant characteristics than high-grade gliomas (WHO Grade IV), and a better clinical prognosis, however, accurate discrimination of overall survival (OS) remains a challenge. In this study, we aimed to identify tissue-derived image features using a machine learning approach to predict OS in a mixed histology and grade cohort of lower grade glioma patients. To achieve this aim, we used H and E stained slides from the public LGG cohort of The Cancer Genome Atlas (TCGA) to create a machine learned dictionary of “image-derived visual words” associated with OS. We then evaluated the combined efficacy of using these visual words in predicting short versus long OS by training a generalized machine learning model. Finally, we mapped these predictive visual words back to molecular signaling cascades to infer potential drivers of the machine learned survival-associated phenotypes.

Methods:

We analyzed digitized histological sections downloaded from the LGG cohort of TCGA using a bag-of-words approach. This method identified a diverse set of histological patterns that were further correlated with OS, histology, and molecular signaling activity using Cox regression, analysis of variance, and Spearman correlation, respectively. A support vector machine (SVM) model was constructed to discriminate patients into short and long OS groups dichotomized at 24-month.

Results:

This method identified disease-relevant phenotypes associated with OS, some of which are correlated with disease-associated molecular pathways. From these image-derived phenotypes, a generalized SVM model which could discriminate 24-month OS (area under the curve, 0.76) was obtained.

Conclusion:

Here, we demonstrated one potential strategy to incorporate image features derived from H and E stained slides into predictive models of OS. In addition, we showed how these image-derived phenotypic characteristics correlate with molecular signaling activity underlying the etiology or behavior of LGG.

Advancing Clinicopathologic Diagnosis of High-risk Neuroblastoma Using Computerized Image Analysis and Proteomic Profiling

A subset of patients with neuroblastoma are at extremely high risk for treatment failure, though they are not identifiable at diagnosis and therefore have the highest mortality with conventional treatment approaches. Despite tremendous understanding of clinical and biological features that correlate with prognosis, neuroblastoma at ultra-high risk for treatment failure remains a diagnostic challenge. As a first step towards improving prognostic risk stratification within the high-risk group of patients, we determined the feasibility of using computerized image analysis and proteomic profiling on single slides from diagnostic tissue specimens. After expert pathologist review of tumor sections to ensure quality and representative material input, we evaluated multiple regions of single slides as well as multiple sections from different patients' tumors using computational histologic analysis and semiquantitative proteomic profiling. We found that both approaches determined that intertumor heterogeneity was greater than intratumor heterogeneity. Unbiased clustering of samples was greatest within a tumor, suggesting a single section can be representative of the tumor as a whole. There is expected heterogeneity between tumor samples from different individuals with a high degree of similarity among specimens derived from the same patient. Both techniques are novel to supplement pathologist review of neuroblastoma for refined risk stratification, particularly since we demonstrate these results using only a single slide derived from what is usually a scarce tissue resource. Due to limitations of traditional approaches for upfront stratification, integration of new modalities with data derived from one section of tumor hold promise as tools to improve outcomes.

A Global Covariance Descriptor for Nuclear Atypia Scoring in Breast Histopathology Images

Nuclear atypia scoring is a diagnostic measure commonly used to assess tumor grade of various cancers, including breast cancer. It provides a quantitative measure of deviation in visual appearance of cell nuclei from those in normal epithelial cells. In this paper, we present a novel image-level descriptor for nuclear atypia scoring in breast cancer histopathology images. The method is based on the region covariance descriptor that has recently become a popular method in various computer vision applications. The descriptor in its original form is not suitable for classification of histopathology images as cancerous histopathology images tend to possess diversely heterogeneous regions in a single field of view. Our proposed image-level descriptor, which we term as the geodesic mean of region covariance descriptors, possesses all the attractive properties of covariance descriptors lending itself to tractable geodesic-distance-based k-nearest neighbor classification using efficient kernels. The experimental results suggest that the proposed image descriptor yields high classification accuracy compared to a variety of widely used image-level descriptors.

Lung nodule classification with multilevel patch-based context analysis

In this paper, we propose a novel classification method for the four types of lung nodules, i.e., well-circumscribed, vascularized, juxta-pleural, and pleural-tail, in low dose computed tomography scans. The proposed method is based on contextual analysis by combining the lung nodule and surrounding anatomical structures, and has three main stages: an adaptive patch-based division is used to construct concentric multilevel partition; then, a new feature set is designed to incorporate intensity, texture, and gradient information for image patch feature description, and then a contextual latent semantic analysis-based classifier is designed to calculate the probabilistic estimations for the relevant images. Our proposed method was evaluated on a publicly available dataset and clearly demonstrated promising classification performance.