Label-free automated neutropenia detection and grading using deep-ultraviolet microscopy

Ojaghi, Ashkan; Costa, Paloma Casteleiro; Caruso, Christina M.; Lam, Wilbur A.; Robles, Francisco E.

doi:10.1364/boe.434465

Cited by 11 publications

(8 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While several virtual staining techniques based on a variety of label-free imaging techniques have been presented [29][30][31][32], they are mostly geared toward the staining of tissues for histopathology and are not designed to digitally stain and analyze blood smears. Further, our segmentation method is robust and achieves comparable or even better performance than methods based on stained or pseudocolorized images, without the need for fix-ing and staining the sample [36][37][38] or the need for multispectral imaging [24]. We have presented a simple and robust classification and counting procedure that utilizes cellular and nuclear segmentation masks along with the grayscale images to first exclude dead WBCs and then classify healthy WBCs into five subtypes.…”

Section: Discussionmentioning

confidence: 99%

Virtual Staining, Segmentation, and Classification of Blood Smears for Label-Free Hematology Analysis

2022

Self Cite

View full text Add to dashboard Cite

Objective and Impact Statement. We present a fully automated hematological analysis framework based on single-channel (single-wavelength), label-free deep-ultraviolet (UV) microscopy that serves as a fast, cost-effective alternative to conventional hematology analyzers. Introduction. Hematological analysis is essential for the diagnosis and monitoring of several diseases but requires complex systems operated by trained personnel, costly chemical reagents, and lengthy protocols. Label-free techniques eliminate the need for staining or additional preprocessing and can lead to faster analysis and a simpler workflow. In this work, we leverage the unique capabilities of deep-UV microscopy as a label-free, molecular imaging technique to develop a deep learning-based pipeline that enables virtual staining, segmentation, classification, and counting of white blood cells (WBCs) in single-channel images of peripheral blood smears. Methods. We train independent deep networks to virtually stain and segment grayscale images of smears. The segmented images are then used to train a classifier to yield a quantitative five-part WBC differential. Results. Our virtual staining scheme accurately recapitulates the appearance of cells under conventional Giemsa staining, the gold standard in hematology. The trained cellular and nuclear segmentation networks achieve high accuracy, and the classifier can achieve a quantitative five-part differential on unseen test data. Conclusion. This proposed automated hematology analysis framework could greatly simplify and improve current complete blood count and blood smear analysis and lead to the development of a simple, fast, and low-cost, point-of-care hematology analyzer.

show abstract

Section: Discussionmentioning

confidence: 99%

Virtual Staining, Segmentation, and Classification of Blood Smears for Label-Free Hematology Analysis

2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Blood samples were collected from 23 individuals (4 healthy donors, 4 patients suffering from sickle cell disease, 4 patients with thrombocytopenia, and 11 patients with neutropenia). 26 All protocols were approved by the Institutional Review Boards of Georgia Institute of Technology and Emory University, and informed consent was obtained from the donors. Imaging was performed after drying the samples in air for five minutes.…”

Section: Data Acquisitionmentioning

confidence: 99%

“…20 We were also able to obtain a five-part WBC differential by leveraging structural and molecular information from segmented cells at 260 nm alone (having inherent nuclear contrast due to the absorption peak of nucleic acids). 20,26 Motivated by this, we developed a deep learning-based automated hematology analysis framework that operates on single-channel UV images acquired at 260 nm, enabling simpler instrumentation and a factor of three improvement in imaging speed without sacrificing accuracy. 22 Our automated pipeline consists of semantic segmentation of WBCs in grayscale images followed by 5-class WBC classification with an accuracy 94.02% on unseen test data.…”

Section: Introductionmentioning

confidence: 99%

Deep learning-based analysis of deep ultraviolet (UV) microscopy images for label-free, point-of-care hematological analysis

Kaza,

Chiou,

Lenk

et al. 2024

Optical Diagnostics and Sensing XXIV: Toward Point-of-Care Diagnostics

Self Cite

View full text Add to dashboard Cite

Hematological analysis is based on assessing changes in the numbers of different blood cells and their morphological, molecular, and cytogenetic properties via a complete blood count. It is integral to diagnose and monitor a range of blood conditions and diseases, ranging from allergies and infections to different types of cancers. The conventional approach to hematology analysis requires time-consuming protocols, multiple expensive chemical reagents, complex equipment, and highly trained personnel for operation, and presents a significant burden to patients and healthcare systems. There is a need for simple, fast, low-cost alternatives such as label-free techniques that eliminate the need for staining or exogenous labels. We recently demonstrated label-free hematology analysis using deep-ultraviolet (UV) microscopy, a high-resolution imaging technique that yields quantitative molecular and structural information from biological samples. In this work, we present a fast, automated analysis pipeline to classify and count the different blood cell types in single-channel UV microscopy images using a low-cost, compact deep-UV microscope. Our previous work focused primarily on white blood cells; here, we further add platelets and red blood cells. We train a YOLOv7-style network to identify and count different blood cells in smear images acquired from a deep-UV microscopy system. Our deep-UV microscope in an LEDbased, compact, and portable configuration and single-step analysis pipeline could be further combined with UV-transparent PDMS-based microfluidic devices to develop a fully automated, low-cost, label-free hematology analyzer.

show abstract

“…Early studies demonstrated UV microscopy for biomolecular mass-mapping in live cells without observable photodamage [7,9,10]. Recently applications of UV microscopy have included hematology analysis of whole blood samples and label-free histopathology of prostate cancer sections and fresh brain tissue [11][12][13][14][15][16][17]. In addition, live single-cell imaging with UV microscopy has been demonstrated for analysis of intracellular dynamics in cancer cells and T-cell phenotyping [18].…”

Section: Introductionmentioning

confidence: 99%

Characterizing UV-induced photo-damage to improve long-term, dynamic live cell imaging with UV microscopy

Gorti,

Robles

2024

Label-Free Biomedical Imaging and Sensing (LBIS) 2024

Self Cite

View full text Add to dashboard Cite

Ultraviolet (UV) microscopy of live cells has been challenging due to phototoxicity, with UV radiation affecting cellular components leading to irreversible cell death. Despite this challenge, recent advances in UV light sources and detectors have renewed interest in UV microscopy due to its high resolution and label-free molecular imaging capabilities. Indeed, UV microscopy has been recently demonstrated for a wide variety of cellular imaging applications, including multispectral imaging of cancer tissue sections, cells at varying time scales, and hematological analysis of whole blood cells. While these studies have leveraged UV microscopy to image static samples and cellular dynamics over short periods of time, UV phototoxicity remains a problem during live cell imaging sessions lasting over several hours and longitudinal imaging of a single sample. In this work, we characterize UV-induced photodamage by quantifying the flux required for cell death at notable wavelengths in the deep-UV region. We demonstrate how this flux can vary with cell adherence type using adherent and non-adherent cell lines. We then present fractionation studies conducted over time scales ranging from several hours to days and discuss the ability of cell populations to recover in each case. Finally, we provide viable live-cell imaging frameworks for UV microscopy applications ranging from single multispectral imaging sessions to long-term observation of samples.

show abstract

Label-free automated neutropenia detection and grading using deep-ultraviolet microscopy

Cited by 11 publications

References 26 publications

Virtual Staining, Segmentation, and Classification of Blood Smears for Label-Free Hematology Analysis

Virtual Staining, Segmentation, and Classification of Blood Smears for Label-Free Hematology Analysis

Deep learning-based analysis of deep ultraviolet (UV) microscopy images for label-free, point-of-care hematological analysis

Characterizing UV-induced photo-damage to improve long-term, dynamic live cell imaging with UV microscopy

Contact Info

Product

Resources

About