Automated bone marrow cytology using deep learning to generate a histogram of cell types

Comparative analysis of feature-based ML and CNN for binucleated erythroblast quantification in myelodysplastic syndrome patients using imaging flow cytometry data

Myelodysplastic syndrome is primarily characterized by dysplasia in the bone marrow (BM), presenting a challenge in consistent morphology interpretation. Accurate diagnosis through traditional slide-based analysis is difficult, necessitating a standardized objective technique. Over the past two decades, imaging flow cytometry (IFC) has proven effective in combining image-based morphometric analyses with high-parameter phenotyping. We have previously demonstrated the effectiveness of combining IFC with a feature-based machine learning algorithm to accurately identify and quantify rare binucleated erythroblasts (BNEs) in dyserythropoietic BM cells. However, a feature-based workflow poses challenges requiring software-specific expertise. Here we employ a Convolutional Neural Network (CNN) algorithm for BNE identification and differentiation from doublets and cells with irregular nuclear morphology in IFC data. We demonstrate that this simplified AI workflow, coupled with a powerful CNN algorithm, achieves comparable BNE quantification accuracy to manual and feature-based analysis with substantial time savings, eliminating workflow complexity. This streamlined approach holds significant clinical value, enhancing IFC accessibility for routine diagnostic purposes.

Obesity paradox in uveal melanoma: high body mass index is associated with low metastatic risk

BACKGROUND

Metabolic factors and obesity may influence the development and progression of cancer. In this study, we examine their association with the risk of developing metastases of uveal melanoma.

METHODS

Data on metabolic factors, medications, serum leptin levels, tumour leptin receptor RNA expression and clinical outcomes were examined in three cohorts. HRs for metastasis and cumulative incidences of melanoma-related mortality were calculated, and the levels of tumour leptin receptor expression were compared with prognostic factors including BAP1 mutation, and tumour cell morphology.

RESULTS

Of 581 patients in the main cohort, 116 (20%) were obese and 7 (1 %) had metastatic disease at presentation. In univariate Cox regressions, tumour diameter, diabetes type II and use of insulin were associated with metastases, but patients with obesity had a lower risk. The beneficial prognostic implication of obesity was retained in multivariate regressions. In competing risk analyses, the incidence of melanoma-related mortality was significantly lower for patients with obesity. Serum leptin levels≥median were associated with a reduced risk for metastasis, independent of patient sex and cancer stage in a separate cohort (n=80). Similarly, in a third cohort (n=80), tumours with BAP1 mutation and epithelioid cells had higher leptin receptor RNA expression levels, which have a negative correlation with serum leptin levels.

CONCLUSION

Obesity and elevated serum leptin levels are associated with a lower risk for developing metastases and dying from uveal melanoma.

Digital Microscopy Augmented by Artificial Intelligence to Interpret Bone Marrow Samples for Hematological Diseases

Analysis of bone marrow aspirates (BMAs) is an essential step in the diagnosis of hematological disorders. This analysis is usually performed based on a visual examination of samples under a conventional optical microscope, which involves a labor-intensive process, limited by clinical experience and subject to high observer variability. In this work, we present a comprehensive digital microscopy system that enables BMA analysis for cell type counting and differentiation in an efficient and objective manner. This system not only provides an accessible and simple method to digitize, store, and analyze BMA samples remotely but is also supported by an Artificial Intelligence (AI) pipeline that accelerates the differential cell counting process and reduces interobserver variability. It has been designed to integrate AI algorithms with the daily clinical routine and can be used in any regular hospital workflow.

Challenges in developing cell culture media using machine learning

Microbial and mammalian cells are widely used in the food, pharmaceutical, and medical industries. Developing or optimizing culture media is essential to improve cell culture performance as a critical technology in cell culture engineering. Methodologies for media optimization have been developed to a great extent, such as the approaches of one-factor-at-a-time (OFAT) and response surface methodology (RSM). The present review introduces the emerging machine learning (ML) technology in cell culture engineering by combining high-throughput experimental technologies to develop highly efficient and effective culture media. The commonly used ML algorithms and the successful applications of employing ML in medium optimization are summarized. This review highlights the benefits of ML-assisted medium development and guides the selection of the media optimization method appropriate for various cell culture purposes.

How Artificial Intelligence Is Shaping Medical Imaging Technology: A Survey of Innovations and Applications

The integration of artificial intelligence (AI) into medical imaging has guided in an era of transformation in healthcare. This literature review explores the latest innovations and applications of AI in the field, highlighting its profound impact on medical diagnosis and patient care. The innovation segment explores cutting-edge developments in AI, such as deep learning algorithms, convolutional neural networks, and generative adversarial networks, which have significantly improved the accuracy and efficiency of medical image analysis. These innovations have enabled rapid and accurate detection of abnormalities, from identifying tumors during radiological examinations to detecting early signs of eye disease in retinal images. The article also highlights various applications of AI in medical imaging, including radiology, pathology, cardiology, and more. AI-based diagnostic tools not only speed up the interpretation of complex images but also improve early detection of disease, ultimately delivering better outcomes for patients. Additionally, AI-based image processing facilitates personalized treatment plans, thereby optimizing healthcare delivery. This literature review highlights the paradigm shift that AI has brought to medical imaging, highlighting its role in revolutionizing diagnosis and patient care. By combining cutting-edge AI techniques and their practical applications, it is clear that AI will continue shaping the future of healthcare in profound and positive ways.

Whole slide image representation in bone marrow cytology

One of the goals of AI-based computational pathology is to generate compact representations of whole slide images (WSIs) that capture the essential information needed for diagnosis. While such approaches have been applied to histopathology, few applications have been reported in cytology. Bone marrow aspirate cytology is the basis for key clinical decisions in hematology. However, visual inspection of aspirate specimens is a tedious and complex process subject to variation in interpretation, and hematopathology expertise is scarce. The ability to generate a compact representation of an aspirate specimen may form the basis for clinical decision-support tools in hematology. In this study, we leverage our previously published end-to-end AI-based system for counting and classifying cells from bone marrow aspirate WSIs, which enables the direct use of individual cells as inputs rather than WSI patches. We then construct bags of individual cell features from each WSI, and apply multiple instance learning to extract their vector representations. To evaluate the quality of our representations, we conducted WSI retrieval and classification tasks. Our results show that we achieved a mAP@10 of 0.58 ±0.02 in WSI-level image retrieval, surpassing the random-retrieval baseline of 0.39 ±0.1. Furthermore, we predicted five diagnostic labels for individual aspirate WSIs with a weighted-average F1 score of 0.57 ±0.03 using a k-nearest-neighbors (k-NN) model, outperforming guessing using empirical class prior probabilities (0.26 ±0.02). We present the first example of exploring trainable mechanisms to generate compact, slide-level representations in bone marrow cytology with deep learning. This method has the potential to summarize complex semantic information in WSIs toward improved diagnostics in hematology, and may eventually support AI-assisted computational pathology approaches.

An Intelligent Attention-Based Transfer Learning Model for Accurate Differentiation of Bone Marrow Stains to Diagnose Hematological Disorder

Bone marrow (BM) is an essential part of the hematopoietic system, which generates all of the body's blood cells and maintains the body's overall health and immune system. The classification of bone marrow cells is pivotal in both clinical and research settings because many hematological diseases, such as leukemia, myelodysplastic syndromes, and anemias, are diagnosed based on specific abnormalities in the number, type, or morphology of bone marrow cells. There is a requirement for developing a robust deep-learning algorithm to diagnose bone marrow cells to keep a close check on them. This study proposes a framework for categorizing bone marrow cells into seven classes. In the proposed framework, five transfer learning models-DenseNet121, EfficientNetB5, ResNet50, Xception, and MobileNetV2-are implemented into the bone marrow dataset to classify them into seven classes. The best-performing DenseNet121 model was fine-tuned by adding one batch-normalization layer, one dropout layer, and two dense layers. The proposed fine-tuned DenseNet121 model was optimized using several optimizers, such as AdaGrad, AdaDelta, Adamax, RMSprop, and SGD, along with different batch sizes of 16, 32, 64, and 128. The fine-tuned DenseNet121 model was integrated with an attention mechanism to improve its performance by allowing the model to focus on the most relevant features or regions of the image, which can be particularly beneficial in medical imaging, where certain regions might have critical diagnostic information. The proposed fine-tuned and integrated DenseNet121 achieved the highest accuracy, with a training success rate of 99.97% and a testing success rate of 97.01%. The key hyperparameters, such as batch size, number of epochs, and different optimizers, were all considered for optimizing these pre-trained models to select the best model. This study will help in medical research to effectively classify the BM cells to prevent diseases like leukemia.

Cell projection plots: A novel visualization of bone marrow aspirate cytology

Deep models for cell detection have demonstrated utility in bone marrow cytology, showing impressive results in terms of accuracy and computational efficiency. However, these models have yet to be implemented in the clinical diagnostic workflow. Additionally, the metrics used to evaluate cell detection models are not necessarily aligned with clinical goals and targets. In order to address these issues, we introduce novel, automatically generated visual summaries of bone marrow aspirate specimens called cell projection plots (CPPs). Encompassing relevant biological patterns such as neutrophil maturation, CPPs provide a compact summary of bone marrow aspirate cytology. To gauge clinical relevance, CPPs were inspected by 3 hematopathologists, who decided whether corresponding diagnostic synopses matched with generated CPPs. Pathologists were able to match CPPs to the correct synopsis with a matching degree of 85%. Our finding suggests CPPs can represent clinically relevant information from bone marrow aspirate specimens and may be used to efficiently summarize bone marrow cytology to pathologists. CPPs could be a step toward human-centered implementation of artificial intelligence (AI) in hematopathology, and a basis for a diagnostic-support tool for digital pathology workflows.

Digital assessment of peripheral blood and bone marrow aspirate smears

The diagnosis of benign and neoplastic hematologic disorders relies on analysis of peripheral blood and bone marrow aspirate smears. As demonstrated by the widespread laboratory adoption of hematology analyzers for automated assessment of peripheral blood, digital analysis of these samples provides many significant benefits compared to relying solely on manual review. Nonetheless, analogous instruments for digital bone marrow aspirate smear assessment have yet to be clinically implemented. In this review, we first provide a historical overview detailing the implementation of hematology analyzers for digital peripheral blood assessment in the clinical laboratory, including the improvements in accuracy, scope, and throughput of current instruments over prior generations. We also describe recent research in digital peripheral blood assessment, particularly in the development of advanced machine learning models that may soon be incorporated into commercial instruments. Next, we provide an overview of recent research in digital assessment of bone marrow aspirate smears and how these approaches could soon lead to development and clinical adoption of instrumentation for automated bone marrow aspirate smear analysis. Finally, we describe the relative advantages and provide our vision for the future of digital assessment of peripheral blood and bone marrow aspirate smears, including what improvements we can soon expect in the hematology laboratory.

CRISPR-based diagnostics detects invasive insect pests

Rapid identification of organisms is essential across many biological and medical disciplines, from understanding basic ecosystem processes and how organisms respond to environmental change, to disease diagnosis and detection of invasive pests. CRISPR-based diagnostics offers a novel and rapid alternative to other identification methods and can revolutionize our ability to detect organisms with high accuracy. Here we describe a CRISPR-based diagnostic developed with the universal cytochrome-oxidase 1 gene (CO1). The CO1 gene is the most sequenced gene among Animalia, and therefore our approach can be adopted to detect nearly any animal. We tested the approach on three difficult-to-identify moth species (Keiferia lycopersicella, Phthorimaea absoluta, and Scrobipalpa atriplicella) that are major invasive pests globally. We designed an assay that combines recombinase polymerase amplification (RPA) with CRISPR for signal generation. Our approach has a much higher sensitivity than other real time-PCR assays and achieved 100% accuracy for identification of all three species, with a detection limit of up to 120 fM for P. absoluta and 400 fM for the other two species. Our approach does not require a lab setting, reduces the risk of cross-contamination, and can be completed in less than one hour. This work serves as a proof of concept that has the potential to revolutionize animal detection and monitoring.

An improved Yolov5s based on transformer backbone network for detection and classification of bronchoalveolar lavage cells

Biological tissue information of the lung, such as cells and proteins, can be obtained from bronchoalveolar lavage fluid (BALF), through which it can be used as a complement to lung biopsy pathology. BALF cells can be confused with each other due to the similarity of their characteristics and differences in the way sections are handled or viewed. This poses a great challenge for cell detection. In this paper, An Improved Yolov5s Based on Transformer Backbone Network for Detection and Classification of BALF Cells is proposed, focusing on the detection of four types of cells in BALF: macrophages, lymphocytes, neutrophils and eosinophils. The network is mainly based on the Yolov5s network and uses Swin Transformer V2 technology in the backbone network to improve cell detection accuracy by obtaining global information; the C3Ghost module (a variant of the Convolutional Neural Network architecture) is used in the neck network to reduce the number of parameters during feature channel fusion and to improve feature expression performance. In addition, embedding intersection over union Loss (EIoU_Loss) was used as a bounding box regression loss function to speed up the bounding box regression rate, resulting in higher accuracy of the algorithm. The experiments showed that our model could achieve mAP of 81.29% and Recall of 80.47%. Compared to the original Yolov5s, the mAP has improved by 3.3% and Recall by 3.67%. We also compared it with Yolov7 and the newly launched Yolov8s. mAP improved by 0.02% and 2.36% over Yolov7 and Yolov8s respectively, while the FPS of our model was higher than both of them, achieving a balance of efficiency and accuracy, further demonstrating the superiority of our model.

DeepHeme: A generalizable, bone marrow classifier with hematopathologist-level performance

Morphology-based classification of cells in the bone marrow aspirate (BMA) is a key step in the diagnosis and management of hematologic malignancies. However, it is time-intensive and must be performed by expert hematopathologists and laboratory professionals. We curated a large, high-quality dataset of 41,595 hematopathologist consensus-annotated single-cell images extracted from BMA whole slide images (WSIs) containing 23 morphologic classes from the clinical archives of the University of California, San Francisco. We trained a convolutional neural network, DeepHeme, to classify images in this dataset, achieving a mean area under the curve (AUC) of 0.99. DeepHeme was then externally validated on WSIs from Memorial Sloan Kettering Cancer Center, with a similar AUC of 0.98, demonstrating robust generalization. When compared to individual hematopathologists from three different top academic medical centers, the algorithm outperformed all three. Finally, DeepHeme reliably identified cell states such as mitosis, paving the way for image-based quantification of mitotic index in a cell-specific manner, which may have important clinical applications.

An Automated Pipeline for Differential Cell Counts on Whole-Slide Bone Marrow Aspirate Smears

The pathologic diagnosis of bone marrow disorders relies in part on the microscopic analysis of bone marrow aspirate (BMA) smears and the manual counting of marrow nucleated cells to obtain a differential cell count (DCC). This manual process has significant limitations, including the analysis of only a small subset of optimal slide areas and nucleated cells, as well as interobserver variability due to differences in cell selection and classification. To address these shortcomings, we developed an automated machine learning-based pipeline for obtaining 11-component DCCs on whole-slide BMAs. This pipeline uses a sequential process of identifying optimal BMA regions with high proportions of marrow nucleated cells, detecting individual cells within these optimal areas, and classifying these cells into 1 of 11 DCC components. Convolutional neural network models were trained on 396,048 BMA region, 28,914 cell boundary, and 1,510,976 cell class images from manual annotations. The resulting automated pipeline produced 11-component DCCs that demonstrated a high statistical and diagnostic concordance with manual DCCs among a heterogeneous group of testing BMA slides with varying pathologies and cellularities. Additionally, we demonstrated that an automated analysis can reduce the intraslide variance in DCCs by analyzing the whole slide and marrow nucleated cells within all optimal regions. Finally, the pipeline outputs of region classification, cell detection, and cell classification can be visualized using whole-slide image analysis software. This study demonstrates the feasibility of a fully automated pipeline for generating DCCs on scanned whole-slide BMA images, with the potential for improving the current standard of practice for utilizing BMA smears in the laboratory analysis of hematologic disorders.

Circulating Cell-Free RNA in Blood as a Host Response Biomarker for the Detection of Tuberculosis

Tuberculosis (TB) remains a leading cause of death from an infectious disease worldwide. This is partly due to a lack of tools to effectively screen and triage individuals with potential TB. Whole blood RNA signatures have been extensively studied as potential biomarkers for TB, but they have failed to meet the World Health Organization's (WHOs) target product profiles (TPPs) for a non-sputum triage or diagnostic test. In this study, we investigated the utility of plasma cell-free RNA (cfRNA) as a host response biomarker for TB. We used RNA profiling by sequencing to analyze plasma samples from 182 individuals with a cough lasting at least two weeks, who were seen at outpatient clinics in Uganda, Vietnam, and the Philippines. Of these individuals, 100 were diagnosed with microbiologically-confirmed TB. Our analysis of the plasma cfRNA transcriptome revealed 541 differentially abundant genes, the top 150 of which were used to train 15 machine learning models. The highest performing model led to a 9-gene signature that had a diagnostic accuracy of 89.1% (95% CI: 83.6-93.4%) and an area under the curve of 0.934 (95% CI: 0.8674-1) for microbiologically-confirmed TB. This 9-gene signature exceeds the optimal WHO TPPs for a TB triage test (sensitivity: 96.2% [95% CI: 80.9-100%], specificity: 89.7% [95% CI: 72.4-100%]) and was robust to differences in sample collection, geographic location, and HIV status. Overall, our results demonstrate the utility of plasma cfRNA for the detection of TB and suggest the potential for a point-of-care, gene expression-based assay to aid in early detection of TB.

A study on the diagnosis of the Helicobacter pylori coccoid form with artificial intelligence technology

BACKGROUND

Helicobacter pylori (H. pylori) is an important pathogenic microorganism that causes gastric cancer, peptic ulcers and dyspepsia, and infects more than half of the world's population. Eradicating H. pylori is the most effective means to prevent and treat these diseases. H. pylori coccoid form (HPCF) causes refractory H. pylori infection and should be given more attention in infection management. However, manual HPCF recognition on slides is time-consuming and labor-intensive and depends on experienced pathologists; thus, HPCF diagnosis is rarely performed and often overlooked. Therefore, simple HPCF diagnostic methods need to be developed.

MATERIALS AND METHODS

We manually labeled 4,547 images from anonymized paraffin-embedded samples in the China Center for H. pylori Molecular Medicine (CCHpMM, Shanghai), followed by training and optimizing the Faster R-CNN and YOLO v5 models to identify HPCF. Mean average precision (mAP) was applied to evaluate and select the model. The artificial intelligence (AI) model interpretation results were compared with those of the pathologists with senior, intermediate, and junior experience levels, using the mean absolute error (MAE) of the coccoid rate as an evaluation metric.

RESULTS

For the HPCF detection task, the YOLO v5 model was superior to the Faster R-CNN model (0.688 vs. 0.568, mean average precision, mAP); the optimized YOLO v5 model had a better performance (0.803 mAP). The MAE of the optimized YOLO v5 model (3.25 MAE) was superior to that of junior pathologists (4.14 MAE, p < 0.05), no worse than intermediate pathologists (3.40 MAE, p > 0.05), and equivalent to a senior pathologist (3.07 MAE, p > 0.05).

CONCLUSION

HPCF identification using AI has the advantage of high accuracy and efficiency with the potential to assist or replace pathologists in clinical practice for HPCF identification.