Machine Learning Based on Morphological Features Enables Classification of Primary Intestinal T-Cell Lymphomas

Role of artificial intelligence in haematolymphoid diagnostics

The advent of digital pathology and the deployment of high-throughput molecular techniques are generating an unprecedented mass of data. Thanks to advances in computational sciences, artificial intelligence (AI) approaches represent a promising avenue for extracting relevant information from complex data structures. From diagnostic assistance to powerful research tools, the potential fields of application of machine learning techniques in pathology are vast and constitute the subject of considerable research work. The aim of this article is to provide an overview of the potential applications of AI in the field of haematopathology and to define the role that these emerging technologies could play in our laboratories in the short to medium term.

Deep Residual Learning-Based Classification with Identification of Incorrect Predictions and Quantification of Cellularity and Nuclear Morphological Features in Digital Pathological Images of Common Astrocytic Tumors

Interobserver variations in the pathology of common astrocytic tumors impact diagnosis and subsequent treatment decisions. This study leveraged a residual neural network-50 (ResNet-50) in digital pathological images of diffuse astrocytoma, anaplastic astrocytoma, and glioblastoma to recognize characteristic pathological features and perform classification at the patch and case levels with identification of incorrect predictions. In addition, cellularity and nuclear morphological features, including axis ratio, circularity, entropy, area, irregularity, and perimeter, were quantified via a hybrid task cascade (HTC) framework and compared between different characteristic pathological features with importance weighting. A total of 95 cases, including 15 cases of diffuse astrocytoma, 11 cases of anaplastic astrocytoma, and 69 cases of glioblastoma, were collected in Taiwan Hualien Tzu Chi Hospital from January 2000 to December 2021. The results revealed that an optimized ResNet-50 model could recognize characteristic pathological features at the patch level and assist in diagnosis at the case level with accuracies of 0.916 and 0.846, respectively. Incorrect predictions were mainly due to indistinguishable morphologic overlap between anaplastic astrocytoma and glioblastoma tumor cell area, zones of scant vascular lumen with compact endothelial cells in the glioblastoma microvascular proliferation area mimicking the glioblastoma tumor cell area, and certain regions in diffuse astrocytoma with too low cellularity being misrecognized as the glioblastoma necrosis area. Significant differences were observed in cellularity and each nuclear morphological feature among different characteristic pathological features. Furthermore, using the extreme gradient boosting (XGBoost) algorithm, we found that entropy was the most important feature for classification, followed by cellularity, area, circularity, axis ratio, perimeter, and irregularity. Identifying incorrect predictions provided valuable feedback to machine learning design to further enhance accuracy and reduce errors in classification. Moreover, quantifying cellularity and nuclear morphological features with importance weighting provided the basis for developing an innovative scoring system to achieve objective classification and precision diagnosis among common astrocytic tumors.

Artificial intelligence in digital pathology: a systematic review and meta-analysis of diagnostic test accuracy

Ensuring diagnostic performance of artificial intelligence (AI) before introduction into clinical practice is essential. Growing numbers of studies using AI for digital pathology have been reported over recent years. The aim of this work is to examine the diagnostic accuracy of AI in digital pathology images for any disease. This systematic review and meta-analysis included diagnostic accuracy studies using any type of AI applied to whole slide images (WSIs) for any disease. The reference standard was diagnosis by histopathological assessment and/or immunohistochemistry. Searches were conducted in PubMed, EMBASE and CENTRAL in June 2022. Risk of bias and concerns of applicability were assessed using the QUADAS-2 tool. Data extraction was conducted by two investigators and meta-analysis was performed using a bivariate random effects model, with additional subgroup analyses also performed. Of 2976 identified studies, 100 were included in the review and 48 in the meta-analysis. Studies were from a range of countries, including over 152,000 whole slide images (WSIs), representing many diseases. These studies reported a mean sensitivity of 96.3% (CI 94.1-97.7) and mean specificity of 93.3% (CI 90.5-95.4). There was heterogeneity in study design and 99% of studies identified for inclusion had at least one area at high or unclear risk of bias or applicability concerns. Details on selection of cases, division of model development and validation data and raw performance data were frequently ambiguous or missing. AI is reported as having high diagnostic accuracy in the reported areas but requires more rigorous evaluation of its performance.

White blood cell image analysis for infection detection based on virtual hexagonal trellis (VHT) by using deep learning

White blood cells (WBCs) are an indispensable constituent of the immune system. Efficient and accurate categorization of WBC is a critical task for disease diagnosis by medical experts. This categorization helps in the correct identification of medical problems. In this research work, WBC classes are categorized with the help of a transform learning model in combination with our proposed virtual hexagonal trellis (VHT) structure feature extraction method. The VHT feature extractor is a kernel-based filter model designed over a square lattice. In the first step, Graft Net CNN model is used to extract features of augmented data set images. Later, the VHT base feature extractor extracts useful features. The CNN-extracted features are passed to ant colony optimization (ACO) module for optimal features acquisition. Extracted features from the VHT base filter and ACO are serially merged to create a single feature vector. The merged features are passed to the support vector machine (SVM) variants for optimal classification. Our strategy yields 99.9% accuracy, which outperforms other existing methods.

Artificial Intelligence-Assisted Diagnostic Cytology and Genomic Testing for Hematologic Disorders

Artificial intelligence (AI) is a rapidly evolving field of computer science that involves the development of computational programs that can mimic human intelligence. In particular, machine learning and deep learning models have enabled the identification and grouping of patterns within data, leading to the development of AI systems that have been applied in various areas of hematology, including digital pathology, alpha thalassemia patient screening, cytogenetics, immunophenotyping, and sequencing. These AI-assisted methods have shown promise in improving diagnostic accuracy and efficiency, identifying novel biomarkers, and predicting treatment outcomes. However, limitations such as limited databases, lack of validation and standardization, systematic errors, and bias prevent AI from completely replacing manual diagnosis in hematology. In addition, the processing of large amounts of patient data and personal information by AI poses potential data privacy issues, necessitating the development of regulations to evaluate AI systems and address ethical concerns in clinical AI systems. Nonetheless, with continued research and development, AI has the potential to revolutionize the field of hematology and improve patient outcomes. To fully realize this potential, however, the challenges facing AI in hematology must be addressed and overcome.

Deep Learning-Based Nuclear Morphometry Reveals an Independent Prognostic Factor in Mantle Cell Lymphoma

Blastoid/pleomorphic morphology is associated with short survival in mantle cell lymphoma (MCL), but its prognostic value is overridden by Ki-67 in multivariate analysis. Herein, a nuclear segmentation model was developed using deep learning, and nuclei of tumor cells in 103 MCL cases were automatically delineated. Eight nuclear morphometric attributes were extracted from each nucleus. The mean, variance, skewness, and kurtosis of each attribute were calculated for each case, resulting in 32 morphometric parameters. Compared with those in classic MCL, 17 morphometric parameters were significantly different in blastoid/pleomorphic MCL. Using univariate analysis, 16 morphometric parameters (including 14 significantly different between classic and blastoid/pleomorphic MCL) emerged as significant prognostic factors. Using multivariate analysis, Biologic MCL International Prognostic Index (bMIPI) risk group (P = 0.025), low skewness of nuclear irregularity (P = 0.020), and high mean of nuclear irregularity (P = 0.047) emerged as independent adverse prognostic factors. Additionally, a morphometric score calculated from the skewness and mean of nuclear irregularity (P = 0.0038) was an independent prognostic factor in addition to bMIPI risk group (P = 0.025), and a summed morphometric bMIPI score was useful for risk stratification of patients with MCL (P = 0.000001). These results demonstrate, for the first time, that a nuclear morphometric score is an independent prognostic factor in MCL. It is more robust than blastoid/pleomorphic morphology and can be objectively measured.

The spectrum of intestinal mature T- and NK-cell neoplasms in a tertiary center in Taiwan with a high frequency of perforation

Primary intestinal T-cell lymphomas (PITLs) comprise enteropathy-associated T-cell lymphoma (EATL), monomorphic epitheliotropic intestinal T-cell lymphoma (MEITL), extranodal NK/T-cell lymphoma (ENKTL), anaplastic large cell lymphoma (ALCL), and intestinal T cell lymphoma, NOS (ITCL-NOS). MEITL is composed of monomorphic medium cells expressing CD8 and CD56, with a cytotoxic phenotype. We retrospectively analyzed 77 cases of intestinal T-cell lymphomas, 71 primary and six secondary, at a tertiary center in Taiwan from 2001 to 2021. Perforation occurred in 57 (74%) patients, including 56 (73%) at presentation and one after chemotherapy. The primary cases included MEITL (68%), ENKTL (14%), ITCL-NOS (13%), ALCL (4%), and EATL (1%). The perforation rate was 90%, 70%, and 22% in MEITL, ENKTL, and ITCL-NOS cases, respectively (p < 0.0001, Fisher's exact test). Most (75%; n = 36) MEITL cases were typical; while seven (15%) had atypical morphology and five (10%) exhibited atypical immunophenotype. The tumor cells of ITCL-NOS were pleomorphic, with various expression of CD8 or CD56. All METIL, ITCL-NOS and ALCL cases were negative for EBER; while all ENKTL cases, either primary or secondary, were positive for cytotoxic granules and EBER. The prognosis of PITL was poor, with a medium survival of 7.0, 3.3, and 3.7 months among patients with MEITL, ENKTL, and ITCL-NOS, respectively. Of the six secondary cases, the primary tumors orginated from nasal ENKTL (n = 5) and cutaneous PTCL-NOS (n = 1). We showed a wide spectrum of intestinal T-cell lymphomas in Taiwan, with MEITL as the most common PITL, a high rate of perforation, and a wider morphological and immunophenotypic spectrum.

Artificial Intelligence Predicted Overall Survival and Classified Mature B-Cell Neoplasms Based on Immuno-Oncology and Immune Checkpoint Panels

Artificial intelligence (AI) can identify actionable oncology biomarkers. This research integrates our previous analyses of non-Hodgkin lymphoma. We used gene expression and immunohistochemical data, focusing on the immune checkpoint, and added a new analysis of macrophages, including 3D rendering. The AI comprised machine learning (C5, Bayesian network, C&R, CHAID, discriminant analysis, KNN, logistic regression, LSVM, Quest, random forest, random trees, SVM, tree-AS, and XGBoost linear and tree) and artificial neural networks (multilayer perceptron and radial basis function). The series included chronic lymphocytic leukemia, mantle cell lymphoma, follicular lymphoma, Burkitt, diffuse large B-cell lymphoma, marginal zone lymphoma, and multiple myeloma, as well as acute myeloid leukemia and pan-cancer series. AI classified lymphoma subtypes and predicted overall survival accurately. Oncogenes and tumor suppressor genes were highlighted (MYC, BCL2, and TP53), along with immune microenvironment markers of tumor-associated macrophages (M2-like TAMs), T-cells and regulatory T lymphocytes (Tregs) (CD68, CD163, MARCO, CSF1R, CSF1, PD-L1/CD274, SIRPA, CD85A/LILRB3, CD47, IL10, TNFRSF14/HVEM, TNFAIP8, IKAROS, STAT3, NFKB, MAPK, PD-1/PDCD1, BTLA, and FOXP3), apoptosis (BCL2, CASP3, CASP8, PARP, and pathway-related MDM2, E2F1, CDK6, MYB, and LMO2), and metabolism (ENO3, GGA3). In conclusion, AI with immuno-oncology markers is a powerful predictive tool. Additionally, a review of recent literature was made.

Targeted Next-generation Sequencing Reveals a Wide Morphologic and Immunophenotypic Spectrum of Monomorphic Epitheliotropic Intestinal T-Cell Lymphoma

Primary intestinal T-cell lymphoma (PITL) is highly aggressive and includes celiac disease-related enteropathy-associated T-cell lymphoma (EATL), monomorphic epitheliotropic intestinal T-cell lymphoma (MEITL), and primary intestinal peripheral T-cell lymphoma, not otherwise specified (ITCL-NOS). MEITL is the most common PITL in Asia, comprising of monomorphic medium-sized cells typically expressing CD8, CD56, and cytotoxic granules. Occasional cases with intermediate features between MEITL and ITCL-NOS are difficult to be classified and warrant further investigation. We collected 54 surgically resected PITLs from Taiwan, with 80% presenting with bowel perforation. The overall outcome was poor with a median survival of 7 months. Based on histopathology (monomorphic vs. pleomorphic) and immunophenotype, we classified these cases into 4 groups: MEITL with typical immunophenotype (n=34), MEITL with atypical immunophenotype (n=5), pleomorphic PITL with MEITL-like immunophenotype (n=6), and ITCL-NOS (n=9). There was no EATL in our cohort. Targeted next-generation sequencing of the first 3 groups showed highly prevalent loss-of-function mutations for SETD2 (85%, 80%, and 83%, respectively) and frequent activating mutations for STAT5B (64%, 60%, and 50%, respectively) and JAK3 (38%, 20%, and 50%, respectively). In contrast, ITCL-NOS cases had less frequent mutations of SETD2 (56%) and STAT5B (11%) and rare JAK3 mutations (11%). Our results suggest that there is a wider morphologic and immunophenotypic spectrum of MEITL as currently defined in the 2017 WHO classification. MEITL with atypical immunophenotype and PITL with MEITL-like immunophenotype shared clinicopathologic and molecular features similar to MEITL but distinct from ITCL-NOS, indicating that such cases may be considered as immunophenotypic or histopathologic variants of MEITL.