An official website of the United States government
Abstract Immunotherapies have shown promising results in treating patients with hematological malignancies like multiple myeloma, which is an incurable but treatable bone marrow-resident plasma cell cancer. Choosing the most efficacious treatment for a patient remains a challenge in such cancers. However, pre-clinical assays involving patient-derived tumor cells co-cultured in anex vivoreconstruction of immune-tumor micro-environment have gained considerable notoriety over the past decade. Such assays can characterize a patient’s response to several therapeutic agents including immunotherapies in a high-throughput manner, where bright-field images of tumor (target) cells interacting with effector cells (T cells, Natural Killer (NK) cells, and macrophages) are captured once every 30 minutes for upto six days. Cell detection, tracking, and classification of thousands of cells of two or more types in each frame is bound to test the limits of some of the most advanced computer vision tools developed to date and requires a specialized approach. We propose TLCellClassifier (time-lapse cell classifier) for live cell detection, cell tracking, and cell type classification, with enhanced accuracy and efficiency obtained by integrating convolutional neural networks (CNN), metric learning, and long short-term memory (LSTM) networks, respectively. State-of-the-art computer vision software like KTH-SE and YOLOv8 are compared with TLCellClassifier, which shows improved accuracy in detection (CNN) and tracking (metric learning). A two-stage LSTM-based cell type classification method is implemented to distinguish between multiple myeloma (tumor/target) cells and macrophages/monocytes (immune/effector cells). Validation of cell type classification was done both using synthetic datasets andex vivoexperiments involving patient-derived tumor/immune cells. Availability and implementationhttps://github.com/QibingJiang/cell classification ml
more »
« less
Cell-TRACTR: A transformer-based model for end-to-end segmentation and tracking of cells
Deep learning-based methods for identifying and tracking cells within microscopy images have revolutionized the speed and throughput of data analysis. These methods for analyzing biological and medical data have capitalized on advances from the broader computer vision field. However, cell tracking can present unique challenges, with frequent cell division events and the need to track many objects with similar visual appearances complicating analysis. Existing architectures developed for cell tracking based on convolutional neural networks (CNNs) have tended to fall short in managing the spatial and global contextual dependencies that are crucial for tracking cells. To overcome these limitations, we introduce Cell-TRACTR (Transformer withAttention forCellTracking andRecognition), a novel deep learning model that uses a transformer-based architecture. Cell-TRACTR operates in an end-to-end manner, simultaneously segmenting and tracking cells without the need for post-processing. Alongside this model, we introduce the Cell-HOTA metric, an extension of the Higher Order Tracking Accuracy (HOTA) metric that we adapted to assess cell division. Cell-HOTA differs from standard cell tracking metrics by offering a balanced and easily interpretable assessment of detection, association, and division accuracy. We test our Cell-TRACTR model on datasets of bacteria growing within a defined microfluidic geometry and mammalian cells growing freely in two dimensions. Our results demonstrate that Cell-TRACTR exhibits strong performance in tracking and division accuracy compared to state-of-the-art algorithms, while also meeting traditional benchmarks in detection accuracy. This work establishes a new framework for employing transformer-based models in cell segmentation and tracking.
more »
« less
- PAR ID:
- 10676389
- Editor(s):
- Mac_Gabhann, Feilim
- Publisher / Repository:
- PLOS Computational Biology
- Date Published:
- Journal Name:
- PLOS Computational Biology
- Volume:
- 21
- Issue:
- 5
- ISSN:
- 1553-7358
- Page Range / eLocation ID:
- e1013071
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Tracking plant cells in three-dimensional (3D) tissue captured through light microscopy presents significant challenge due to the large number of densely packed cells, non-uniform growth patterns, and variations in cell division planes across different cell layers. In addition, images of deeper tissue layers are often noisy, and systemic imaging errors further exacerbate the complexity of the task. In this paper, we propose a novel learning-based method DEGAST3D: Learning Deformable 3D GrAph Similarity to Track Plant Cells in Unregistered Time Lapse Images exploits the tightly packed 3D cell structure of plant cells to create a three-dimensional graph for accurate cell tracking. We also propose a novel algorithm for cell division detection and an effective three-dimensional registration, improving state-of-the-art algorithms. On a public dataset, our novel cell pair matching method outperforms the baseline by 6.83%, 5.96%, 6.40% in precision, recall, and F-1 score, respectively. On the same dataset, our proposed novel cell division technique improves the results of the baseline method by 15.38% and 14.78% in terms of recall and Fl-score, respectively.more » « less
-
The development of noninvasive methods for bladder cancer identification remains a critical clinical need. Recent studies have shown that atomic force microscopy (AFM), combined with pattern recognition machine learning, can detect bladder cancer by analyzing cells extracted from urine. However, these promising findings were limited by a relatively small patient cohort, resulting in modest statistical significance. In this study, we corroborated the AFM technique’s capability to identify bladder cancer cells with high accuracy using a controlled model system of genetically purified human bladder epithelial cell lines, comparing cancerous cells with nonmalignant controls. By processing AFM adhesion maps through machine learning algorithms, following previously established methods, we achieved an area under the ROC curve (AUC) of 0.97, with 91% accuracy in cancer cell identification. Furthermore, we enhanced cancer detection by incorporating multiple imaging channels recorded with AFM operating in Ringing mode, achieving an AUC of 0.99 and 93% accuracy. These results demonstrated strong statistical significance (p < 0.0001) in this well-defined model system. While this controlled study does not capture the biological variation present in clinical settings, it provides independent support for AFM-based detection methods and establishes a rigorous technical foundation for further clinical development of AFM imaging-based methods for bladder cancer detection.more » « less
-
ABSTRACT Agent-based models (ABMs) have become essential tools for simulating complex biological, ecological, and social systems where emergent behaviors arise from the interactions among individual agents. Quantifying uncertainty through global sensitivity analysis is crucial for assessing the robustness and reliability of ABM predictions. However, most global sensitivity methods demand substantial computational resources, making them impractical for highly complex models. Here, we introduce SMoRe GloS (SurrogateModeling forRecapitulatingGlobalSensitivity), a novel, computationally efficient method for performing global sensitivity analysis of ABMs. By leveraging explicitly formulated surrogate models, SMoRe GloS allows for comprehensive parameter space exploration and uncertainty quantification without sacrificing accuracy. We demonstrate our method’s flexibility by applying it to two biological ABMs: a simple 2D cell proliferation assay and a complex 3D vascular tumor growth model. Our results show that SMoRe GloS is compatible with simpler methods like the Morris one-at-a-time method, and more computationally intensive variance-based methods like eFAST. SMoRe GloS accurately recovered global sensitivity indices in each case while achieving substantial speedups, completing analyses in minutes. In contrast, direct implementation of eFAST amounted to several days of CPU time for the complex ABM. Remarkably, our method also estimates sensitivities for ABM parameters representing processes not explicitly included in the surrogate model, further enhancing its utility. By making global sensitivity analysis feasible for computationally expensive models, SMoRe GloS opens up new opportunities for uncertainty quantification in complex systems, allowing for more in depth exploration of model behavior, thereby increasing confidence in model predictions.more » « less
-
The microtubule cytoskeleton serves as a dynamic structural framework for mitosis in eukaryotic cells. TANGLED1 (TAN1) is a microtubule-binding protein that localizes to the division site and mitotic microtubules and plays a critical role in division plane orientation in plants. Here, in vitro experiments demonstrate that TAN1 directly binds microtubules, mediating microtubule zippering or end-on microtubule interactions, depending on their contact angle. Maize tan1 mutant cells improperly position the preprophase band (PPB), which predicts the future division site. However, cell shape–based modeling indicates that PPB positioning defects are likely a consequence of abnormal cell shapes and not due to TAN1 absence. In telophase, colocalization of growing microtubules ends from the phragmoplast with TAN1 at the division site suggests that TAN1 interacts with microtubule tips end-on. Together, our results suggest that TAN1 contributes to microtubule organization to ensure proper division plane orientation.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Journal Article:
- https://doi.org/10.1371/journal.pcbi.1013071
