Artificial intelligence strategy integrating morphologic and architectural biomarkers provides robust diagnostic accuracy for disease progression in chronic lymphocytic leukemia

AI system for diagnosing mucosa-associated lymphoid tissue lymphoma and diffuse large B cell lymphoma using ImageNet and hematoxylin and eosin-stained specimens

AI-assisted morphological analysis using whole-slide images (WSIs) shows promise in supporting complex pathological diagnosis. However, the implementation in clinical settings is costly and demands extensive data storage. This study aimed to develop a compact, practical classification model using patch images selected by pathologists from representative disease areas under a microscope. To evaluate the limits of classification performance, we applied multiple pretraining strategies and convolutional neural networks (CNNs) specifically for the diagnosis of particularly challenging malignant lymphomas and their subtypes. The EfficientNet CNN, pretrained with ImageNet, exhibited the highest classification performance among the tested models. Our model achieved notable accuracy in a four-class classification (normal lymph node and three B cell lymphoma subtypes) using only hematoxylin and eosin-stained specimens (AUC = 0.87), comparable to results from immunohistochemical and genetic analyses. This finding suggests that the proposed model enables pathologists to independently prepare image data and easily access the algorithm and enhances diagnostic reliability while significantly reducing costs and time for additional tests, offering a practical and efficient diagnostic support tool for general medical facilities.

Artificial Intelligence in Lymphoma Histopathology: Systematic Review

BACKGROUND

Artificial intelligence (AI) shows considerable promise in the areas of lymphoma diagnosis, prognosis, and gene prediction. However, a comprehensive assessment of potential biases and the clinical utility of AI models is still needed.

OBJECTIVE

Our goal was to evaluate the biases of published studies using AI models for lymphoma histopathology and assess the clinical utility of comprehensive AI models for diagnosis or prognosis.

METHODS

This study adhered to the Systematic Review Reporting Standards. A comprehensive literature search was conducted across PubMed, Cochrane Library, and Web of Science from their inception until August 30, 2024. The search criteria included the use of AI for prognosis involving human lymphoma tissue pathology images, diagnosis, gene mutation prediction, etc. The risk of bias was evaluated using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Information for each AI model was systematically tabulated, and summary statistics were reported. The study is registered with PROSPERO (CRD42024537394) and follows the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 reporting guidelines.

RESULTS

The search identified 3565 records, with 41 articles ultimately meeting the inclusion criteria. A total of 41 AI models were included in the analysis, comprising 17 diagnostic models, 10 prognostic models, 2 models for detecting ectopic gene expression, and 12 additional models related to diagnosis. All studies exhibited a high or unclear risk of bias, primarily due to limited analysis and incomplete reporting of participant recruitment. Most high-risk models (10/41) predominantly assigned high-risk classifications to participants. Almost all the articles presented an unclear risk of bias in at least one domain, with the most frequent being participant selection (16/41) and statistical analysis (37/41). The primary reasons for this were insufficient analysis of participant recruitment and a lack of interpretability in outcome analyses. In the diagnostic models, the most frequently studied lymphoma subtypes were diffuse large B-cell lymphoma, follicular lymphoma, chronic lymphocytic leukemia, and mantle cell lymphoma, while in the prognostic models, the most common subtypes were diffuse large B-cell lymphoma, follicular lymphoma, chronic lymphocytic leukemia, and Hodgkin lymphoma. In the internal validation results of all models, the area under the receiver operating characteristic curve (AUC) ranged from 0.75 to 0.99 and accuracy ranged from 68.3% to 100%. In models with external validation results, the AUC ranged from 0.93 to 0.99.

CONCLUSIONS

From a methodological perspective, all models exhibited biases. The enhancement of the accuracy of AI models and the acceleration of their clinical translation hinge on several critical aspects. These include the comprehensive reporting of data sources, the diversity of datasets, the study design, the transparency and interpretability of AI models, the use of cross-validation and external validation, and adherence to regulatory guidance and standardized processes in the field of medical AI.

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.

Artificial intelligence-based differential diagnosis of orbital MALT lymphoma and IgG4 related ophthalmic disease using hematoxylin-eosin images

PURPOSE

To investigate the possibility of distinguishing between IgG4-related ophthalmic disease (IgG4-ROD) and orbital MALT lymphoma using artificial intelligence (AI) and hematoxylin-eosin (HE) images.

METHODS

After identifying a total of 127 patients from whom we were able to procure tissue blocks with IgG4-ROD and orbital MALT lymphoma, we performed histological and molecular genetic analyses, such as gene rearrangement. Subsequently, pathological HE images were collected from these patients followed by the cutting out of 10 different image patches from the HE image of each patient. A total of 970 image patches from the 97 patients were used to construct nine different models of deep learning, and the 300 image patches from the remaining 30 patients were used to evaluate the diagnostic performance of the models. Area under the curve (AUC) and accuracy (ACC) were used for the performance evaluation of the deep learning models. In addition, four ophthalmologists performed the binary classification between IgG4-ROD and orbital MALT lymphoma.

RESULTS

EVA, which is a vision-centric foundation model to explore the limits of visual representation, was the best deep learning model among the nine models. The results of EVA were ACC = 73.3% and AUC = 0.807. The ACC of the four ophthalmologists ranged from 40 to 60%.

CONCLUSIONS

It was possible to construct an AI software based on deep learning that was able to distinguish between IgG4-ROD and orbital MALT. This AI model may be useful as an initial screening tool to direct further ancillary investigations.

Analysis by TeloView® Technology Predicts the Response of Hodgkin's Lymphoma to First-Line ABVD Therapy

Classic Hodgkin's lymphoma (cHL) is a curable cancer with a disease-free survival rate of over 10 years. Over 80% of diagnosed patients respond favorably to first-line chemotherapy, but few biomarkers exist that can predict the 15-20% of patients who experience refractory or early relapsed disease. To date, the identification of patients who will not respond to first-line therapy based on disease staging and traditional clinical risk factor analysis is still not possible. Three-dimensional (3D) telomere analysis using the TeloView® software platform has been shown to be a reliable tool to quantify genomic instability and to inform on disease progression and patients' response to therapy in several cancers. It also demonstrated telomere dysfunction in cHL elucidating biological mechanisms related to disease progression. Here, we report 3D telomere analysis on a multicenter cohort of 156 cHL patients. We used the cohort data as a training data set and identified significant 3D telomere parameters suitable to predict individual patient outcomes at the point of diagnosis. Multivariate analysis using logistic regression procedures allowed for developing a predictive scoring model using four 3D telomere parameters as predictors, including the proportion of t-stumps (very short telomeres), which has been a prominent predictor for cHL patient outcome in a previously published study using TeloView® analysis. The percentage of t-stumps was by far the most prominent predictor to identify refractory/relapsing (RR) cHL prior to initiation of adriamycin, bleomycin, vinblastine, and dacarbazine (ABVD) therapy. The model characteristics include an AUC of 0.83 in ROC analysis and a sensitivity and specificity of 0.82 and 0.78 respectively.

Automated tumor immunophenotyping predicts clinical benefit from anti-PD-L1 immunotherapy

Cancer immunotherapy has transformed the clinical approach to patients with malignancies, as profound benefits can be seen in a subset of patients. To identify this subset, biomarker analyses increasingly focus on phenotypic and functional evaluation of the tumor microenvironment to determine if density, spatial distribution, and cellular composition of immune cell infiltrates can provide prognostic and/or predictive information. Attempts have been made to develop standardized methods to evaluate immune infiltrates in the routine assessment of certain tumor types; however, broad adoption of this approach in clinical decision-making is still missing. We developed approaches to categorize solid tumors into 'desert', 'excluded', and 'inflamed' types according to the spatial distribution of CD8+ immune effector cells to determine the prognostic and/or predictive implications of such labels. To overcome the limitations of this subjective approach, we incrementally developed four automated analysis pipelines of increasing granularity and complexity for density and pattern assessment of immune effector cells. We show that categorization based on 'manual' observation is predictive for clinical benefit from anti-programmed death ligand 1 therapy in two large cohorts of patients with non-small cell lung cancer or triple-negative breast cancer. For the automated analysis we demonstrate that a combined approach outperforms individual pipelines and successfully relates spatial features to pathologist-based readouts and the patient's response to therapy. Our findings suggest that tumor immunophenotype generated by automated analysis pipelines should be evaluated further as potential predictive biomarkers for cancer immunotherapy. © 2024 The Pathological Society of Great Britain and Ireland.

Machine Learning Model with Texture Analysis for Automatic Classification of Histopathological Images of Ocular Adnexal Mucosa-associated Lymphoid Tissue Lymphoma of Two Different Origins

PURPOSE

The purpose of this study was to develop artificial intelligence algorithms that can distinguish between orbital and conjunctival mucosa-associated lymphoid tissue (MALT) lymphomas in pathological images.

METHODS

Tissue blocks with residual MALT lymphoma and data from histological and flow cytometric studies and molecular genetic analyses such as gene rearrangement were procured for 129 patients treated between April 2008 and April 2020. We collected pathological hematoxylin and eosin-stained (HE) images of lymphoma from these patients and cropped 10 different image patches at a resolution of 2048 × 2048 from pathological images from each patient. A total of 990 images from 99 patients were used to create and evaluate machine-learning models. Each image patch of three different magnification rates at ×4, ×20, and ×40 underwent texture analysis to extract features, and then seven different machine-learning algorithms were applied to the results to create models. Cross-validation on a patient-by-patient basis was used to create and evaluate models, and then 300 images from the remaining 30 cases were used to evaluate the average accuracy rate.

RESULTS

Ten-fold cross-validation using the support vector machine with linear kernel algorithm was identified as the best algorithm for discriminating between conjunctival mucosa-associated lymphoid tissue and orbital MALT lymphomas, with an average accuracy rate under cross-validation of 85%. There were ×20 magnification HE images that were more accurate in distinguishing orbital and conjunctival MALT lymphomas among ×4, ×20, and ×40.

CONCLUSION

Artificial intelligence algorithms can successfully distinguish HE images between orbital and conjunctival MALT lymphomas.

Pathomic Features Reveal Immune and Molecular Evolution From Lung Preneoplasia to Invasive Adenocarcinoma

Recent statistics on lung cancer, including the steady decline of advanced diseases and the dramatically increasing detection of early-stage diseases and indeterminate pulmonary nodules, mark the significance of a comprehensive understanding of early lung carcinogenesis. Lung adenocarcinoma (ADC) is the most common histologic subtype of lung cancer, and atypical adenomatous hyperplasia is the only recognized preneoplasia to ADC, which may progress to adenocarcinoma in situ (AIS) and minimally invasive adenocarcinoma (MIA) and eventually to invasive ADC. Although molecular evolution during early lung carcinogenesis has been explored in recent years, the progress has been significantly hindered, largely due to insufficient materials from ADC precursors. Here, we employed state-of-the-art deep learning and artificial intelligence techniques to robustly segment and recognize cells on routinely used hematoxylin and eosin histopathology images and extracted 9 biology-relevant pathomic features to decode lung preneoplasia evolution. We analyzed 3 distinct cohorts (Japan, China, and United States) covering 98 patients, 162 slides, and 669 regions of interest, including 143 normal, 129 atypical adenomatous hyperplasia, 94 AIS, 98 MIA, and 205 ADC. Extracted pathomic features revealed progressive increase of atypical epithelial cells and progressive decrease of lymphocytic cells from normal to AAH, AIS, MIA, and ADC, consistent with the results from tissue-consuming and expensive molecular/immune profiling. Furthermore, pathomics analysis manifested progressively increasing cellular intratumor heterogeneity along with the evolution from normal lung to invasive ADC. These findings demonstrated the feasibility and substantial potential of pathomics in studying lung cancer carcinogenesis directly from the low-cost routine hematoxylin and eosin staining.

Immunophenotypic and genomic landscape of Richter transformation diffuse large B-cell lymphoma

Integrated clinicopathological and molecular analyses of Richter transformation of diffuse large B-cell lymphoma subtype (RT-DLBCL) cases remain limited. This study group included 142 patients with RT-DLBCL. Morphological evaluation and immunophenotyping, using immunohistochemistry and/or multicolour flow cytometry, were performed. The results of conventional karyotyping, fluorescence in situ hybridisation analysis and mutation profiling performed using next generation sequencing were reviewed. Patients included 91 (64.1%) men and 51 (35.9%) women with a median age of 65.4 years (range 25.4-84.9 years) at the time of RT-DLBCL diagnosis. Patients had CLL for a median of 49.5 months (range 0-330 months) before onset of RT-DLBCL. Most cases (97.2%) of RT-DLBCL had immunoblastic (IB) morphology, the remainder had a high grade morphology. The most commonly expressed markers included: CD19 (100%), PAX5 (100%), BCL2 (97.5%), LEF1 (94.7%), CD22 (90.2%), CD5 (88.6%), CD20 (85.7%), CD38 (83.5%), MUM1 (83.3%), CD23 (77%) and MYC (46.3%). Most (51/65, 78.4%) cases had a non-germinal centre B-cell immunophenotype. MYC rearrangement was detected in 9/47 (19.1%) cases, BCL2 rearrangement was detected in 5/22 (22.7%) cases, and BCL6 rearrangement was detected in 2/15 (13.3%) cases. In comparison to CLL, RT-DLBCL had higher numbers of alterations involving chromosomes 6, 17, 21, and 22. The most common mutations detected in RT-DLBCL involved TP53 (9/14, 64.3%), NOTCH1 (4/14, 28.6%) and ATM (3/14, 21.4%). Among RT-DLBCL cases with mutant TP53, 5/8 (62.5%) had TP53 copy number loss, and among those, such loss was detected in the CLL phase of the disease in 4/8 (50%) cases. There was no significant difference in overall survival (OS) between patients with germinal centre B-cell (GCB) and non-GCB RT-DLBCL. Only CD5 expression correlated significantly with OS (HR=2.732; 95% CI 1.397-5.345; p=0.0374). RT-DLBCL has distinctive morphological and immunophenotypic features, characterised by IB morphology and common expression of CD5, MUM1 and LEF1. Cell-of-origin does not seem to have prognostic implications in RT-DLBCL.

Enhancing morphological analysis of peripheral blood cells in chronic lymphocytic leukemia with an artificial intelligence-based tool

BACKGROUND

Real-time monitoring is essential for the management of chronic lymphocytic leukemia (CLL) patients. Utilizing peripheral blood is advantageous due to its affordability and convenience. Existing methods of assessing peripheral blood films have limitations that include lack of automation, dependence on personal experience, and low repeatability and reproducibility. To overcome these challenges, we have designed an artificial intelligence-driven system that provides a clinical perspective to objectively evaluate morphologic features in CLL patients' blood cells.

METHODS

Based on our center's CLL dataset, we developed an automated algorithm using a deep convolutional neural network to precisely identify regions of interest on blood films and used the well-established Visual Geometry Group-16 as the encoder to segment cells and extract morphological features. This tool enabled us to extract morphological features of all lymphocytes for subsequent analysis.

RESULTS

Our study's lymphocyte identification had a recall of 0.96 and an F1 score of 0.97. Cluster analysis identified three clear, morphological groups of lymphocytes that reflect distinct stages of disease development to some extent. To investigate the longitudinal evolution of lymphocyte, we extracted cellular morphology parameters at various time points from the same patient. The results showed some similar trends to those observed in the aforementioned cluster analysis. Correlation analysis further supports the prognostic potential of cell morphology-based parameters.

CONCLUSION

Our study provides valuable insights and potential avenues for further exploration of lymphocyte dynamics in CLL. Investigating morphological changes may help in determining the optimal timing for intervening with CLL patients, but further research is needed.

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.

Artificial intelligence-assisted mapping of proliferation centers allows the distinction of accelerated phase from large cell transformation in chronic lymphocytic leukemia

Chronic lymphocytic leukemia/small lymphocytic lymphoma (CLL) is characterized morphologically by numerous small lymphocytes and pale nodules composed of prolymphocytes and paraimmunoblasts known as proliferation centers (PCs). Patients with CLL can undergo transformation to a more aggressive lymphoma, most often diffuse large B-cell lymphoma (DLBCL), known as Richter transformation (RT). An accelerated phase of CLL (aCLL) also may be observed which correlates with subsequent transformation to DLBCL, and may represent an early stage of transformation. Distinguishing PCs in CLL from aCLL or RT can be diagnostically challenging, particularly in small needle biopsy specimens. Available guidelines pertaining to distinguishing CLL from its' progressive forms are limited, subject to the morphologist's experience and are often not completely helpful in the assessment of scant biopsy specimens. To objectively assess the extent of PCs in aCLL and RT, and enhance diagnostic accuracy, we sought to design an artificial intelligence (AI)-based tool to identify and delineate PCs based on feature analysis of the combined individual nuclear size and intensity, designated here as the heat value. Using the mean heat value from the generated heat value image of all cases, we were able to reliably separate CLL, aCLL and RT with sensitive diagnostic predictive values.

Chronic Lymphocytic Leukemia Progression Diagnosis with Intrinsic Cellular Patterns via Unsupervised Clustering

Simple Summary

Distinguishing between chronic lymphocytic leukemia (CLL), accelerated CLL (aCLL), and full-blown transformation to diffuse large B-cell lymphoma (Richter transformation; RT) has significant clinical implications. Identifying cellular phenotypes via unsupervised clustering provides the most robust analytic performance in analyzing digitized pathology slides. This study serves as a proof of concept that using an unsupervised machine learning scheme can enhance diagnostic accuracy.

Abstract

Identifying the progression of chronic lymphocytic leukemia (CLL) to accelerated CLL (aCLL) or transformation to diffuse large B-cell lymphoma (Richter transformation; RT) has significant clinical implications as it prompts a major change in patient management. However, the differentiation between these disease phases may be challenging in routine practice. Unsupervised learning has gained increased attention because of its substantial potential in data intrinsic pattern discovery. Here, we demonstrate that cellular feature engineering, identifying cellular phenotypes via unsupervised clustering, provides the most robust analytic performance in analyzing digitized pathology slides (accuracy = 0.925, AUC = 0.978) when compared to alternative approaches, such as mixed features, supervised features, unsupervised/mixed/supervised feature fusion and selection, as well as patch-based convolutional neural network (CNN) feature extraction. We further validate the reproducibility and robustness of unsupervised feature extraction via stability and repeated splitting analysis, supporting its utility as a diagnostic aid in identifying CLL patients with histologic evidence of disease progression. The outcome of this study serves as proof of principle using an unsupervised machine learning scheme to enhance the diagnostic accuracy of the heterogeneous histology patterns that pathologists might not easily see.

Biology and Treatment of Richter Transformation

Richter transformation (RT), defined as the development of an aggressive lymphoma on a background of chronic lymphocytic leukemia/small lymphocytic lymphoma (CLL/SLL), represents a clinical unmet need because of its dismal prognosis. An increasing body of knowledge in the field of RT is arising from the recent development of preclinical models depicting the biology underlying this aggressive disease. Consistently, new therapeutic strategies based on a genetic rationale are exploring actionable pathogenic pathways to improve the outcome of patients in this setting. In this review, we summarize the current understandings on RT biology and the available treatment options.