Neural network-based processing and reconstruction of compromised biophotonic image data.

In recent years, the integration of deep learning techniques with biophotonic setups has opened new horizons in bioimaging. A compelling trend in this field involves deliberately compromising certain measurement metrics to engineer better bioimaging tools in terms of e.g., cost, speed, and form-factor, followed by compensating for the resulting defects through the utilization of deep learning models trained on a large amount of ideal, superior or alternative data. This strategic approach has found increasing popularity due to its potential to enhance various aspects of biophotonic imaging. One of the primary motivations for employing this strategy is the pursuit of higher temporal resolution or increased imaging speed, critical for capturing fine dynamic biological processes. Additionally, this approach offers the prospect of simplifying hardware requirements and complexities, thereby making advanced imaging standards more accessible in terms of cost and/or size. This article provides an in-depth review of the diverse measurement aspects that researchers intentionally impair in their biophotonic setups, including the point spread function (PSF), signal-to-noise ratio (SNR), sampling density, and pixel resolution. By deliberately compromising these metrics, researchers aim to not only recuperate them through the application of deep learning networks, but also bolster in return other crucial parameters, such as the field of view (FOV), depth of field (DOF), and space-bandwidth product (SBP). Throughout this article, we discuss various biophotonic methods that have successfully employed this strategic approach. These techniques span a wide range of applications and showcase the versatility and effectiveness of deep learning in the context of compromised biophotonic data. Finally, by offering our perspectives on the exciting future possibilities of this rapidly evolving concept, we hope to motivate our readers from various disciplines to explore novel ways of balancing hardware compromises with compensation via artificial intelligence (AI).

Virtual birefringence imaging and histological staining of amyloid deposits in label-free tissue using autofluorescence microscopy and deep learning.

Systemic amyloidosis involves the deposition of misfolded proteins in organs/tissues, leading to progressive organ dysfunction and failure. Congo red is the gold-standard chemical stain for visualizing amyloid deposits in tissue, showing birefringence under polarization microscopy. However, Congo red staining is tedious and costly to perform, and prone to false diagnoses due to variations in amyloid amount, staining quality and manual examination of tissue under a polarization microscope. We report virtual birefringence imaging and virtual Congo red staining of label-free human tissue to show that a single neural network can transform autofluorescence images of label-free tissue into brightfield and polarized microscopy images, matching their histochemically stained versions. Blind testing with quantitative metrics and pathologist evaluations on cardiac tissue showed that our virtually stained polarization and brightfield images highlight amyloid patterns in a consistent manner, mitigating challenges due to variations in chemical staining quality and manual imaging processes in the clinical workflow.

Non-Invasive Label-free Analysis Pipeline for In Situ Characterization of Differentiation in 3D Brain Organoid Models.

Brain organoids provide a unique opportunity to model organ development in a system similar to human organogenesis in vivo. Brain organoids thus hold great promise for drug screening and disease modeling. Conventional approaches to organoid characterization predominantly rely on molecular analysis methods, which are expensive, time-consuming, labor-intensive, and involve the destruction of the valuable 3D architecture of the organoids. This reliance on end-point assays makes it challenging to assess cellular and subcellular events occurring during organoid development in their 3D context. As a result, the long developmental processes are not monitored nor assessed. The ability to perform non-invasive assays is critical for longitudinally assessing features of organoid development during culture. In this paper, we demonstrate a label-free high-content imaging approach for observing changes in organoid morphology and structural changes occurring at the cellular and subcellular level. Enabled by microfluidic-based culture of 3D cell systems and a novel 3D quantitative phase imaging method, we demonstrate the ability to perform non-destructive high-resolution imaging of the organoid. The highlighted results demonstrated in this paper provide a new approach to performing live, non-destructive monitoring of organoid systems during culture.

Real-time semantic segmentation and anomaly detection of functional images for cell therapy manufacturing.

BACKGROUND AIMS: Cell therapy is a promising treatment method that uses living cells to address a variety of diseases and conditions, including cardiovascular diseases, neurologic disorders and certain cancers. As interest in cell therapy grows, there is a need to shift to a more efficient, scalable and automated manufacturing process that can produce high-quality products at a lower cost. METHODS: One way to achieve this is using non-invasive imaging and real-time image analysis techniques to monitor and control the manufacturing process. This work presents a machine learning-based image analysis pipeline that includes semantic segmentation and anomaly detection capabilities. RESULTS/CONCLUSIONS: This method can be easily implemented even when given a limited dataset of annotated images, is able to segment cells and debris and can identify anomalies such as contamination or hardware failure.

Functional imaging with dynamic quantitative oblique back-illumination microscopy.

SIGNIFICANCE: Quantitative oblique back-illumination microscopy (qOBM) is a recently developed label-free imaging technique that enables 3D quantitative phase imaging of thick scattering samples with epi-illumination. Here, we propose dynamic qOBM to achieve functional imaging based on subcellular dynamics, potentially indicative of metabolic activity. We show the potential utility of this novel technique by imaging adherent mesenchymal stromal cells (MSCs) grown in bioreactors, which can help address important unmet needs in cell manufacturing for therapeutics. AIM: We aim to develop dynamic qOBM and demonstrate its potential for functional imaging based on cellular and subcellular dynamics. APPROACH: To obtain functional images with dynamic qOBM, a sample is imaged over a period of time and its temporal signals are analyzed. The dynamic signals display an exponential frequency response that can be analyzed with phasor analysis. Functional images of the dynamic signatures are obtained by mapping the frequency dynamic response to phasor space and color-coding clustered signals. RESULTS: Functional imaging with dynamic qOBM provides unique information related to subcellular activity. The functional qOBM images of MSCs not only improve conspicuity of cells in complex environments (e.g., porous micro-carriers) but also reveal two distinct cell populations with different dynamic behavior. CONCLUSIONS: In this work we present a label-free, fast, and scalable functional imaging approach to study and intuitively display cellular and subcellular dynamics. We further show the potential utility of this novel technique to help monitor adherent MSCs grown in bioreactors, which can help achieve quality-by-design of cell products, a significant unmet need in the field of cell therapeutics. This approach also has great potential for dynamic studies of other thick samples, such as organoids.

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

Neutropenia is a condition identified by an abnormally low number of neutrophils in the bloodstream and signifies an increased risk of severe infection. Cancer patients are particularly susceptible to this condition, which can be disruptive to their treatment and even life-threatening in severe cases. Thus, it is critical to routinely monitor neutrophil counts in cancer patients. However, the standard of care to assess neutropenia, the complete blood count (CBC), requires expensive and complex equipment, as well as cumbersome procedures, which precludes easy or timely access to critical hematological information, namely neutrophil counts. Here we present a simple, low-cost, fast, and robust technique to detect and grade neutropenia based on label-free multi-spectral deep-UV microscopy. Results show that the developed framework for automated segmentation and classification of live, unstained blood cells in a smear accurately differentiates patients with moderate and severe neutropenia from healthy samples in minutes. This work has significant implications towards the development of a low-cost and easy-to-use point-of-care device for tracking neutrophil counts, which can not only improve the quality of life and treatment-outcomes of many patients but can also be lifesaving.

Noninvasive white blood cell quantification in umbilical cord blood collection bags with quantitative oblique back-illumination microscopy.

BACKGROUND: Umbilical cord blood has become an important source of hematopoietic stem and progenitor cells for therapeutic applications. However, cord blood banking (CBB) grapples with issues related to economic viability, partially due to high discard rates of cord blood units (CBUs) that lack sufficient total nucleated cells for storage or therapeutic use. Currently, there are no methods available to assess the likelihood of CBUs meeting storage criteria noninvasively at the collection site, which would improve CBB efficiency and economic viability. MATERIALS AND METHODS: To overcome this limitation, we apply a novel label-free optical imaging method, called quantitative oblique back-illumination microscopy (qOBM), which yields tomographic phase and absorption contrast to image blood inside collection bags. An automated segmentation algorithm was developed to count white blood cells and red blood cells (RBCs) and assess hematocrit. Fifteen CBUs were measured. RESULTS: qOBM clearly differentiates between RBCs and nucleated cells. The cell-counting analysis shows an average error of 13% compared to hematology analysis, with a near-perfect, one-to-one relationship (slope = 0.94) and strong correlation coefficient (r = 0.86). Preliminary results to assess hematocrit also show excellent agreement with expected values. Acquisition times to image a statistically significant number of cells per CBU were approximately 1 minute. CONCLUSION: qOBM exhibits robust performance for quantifying blood inside collection bags. Because the approach is automated and fast, it can potentially quantify CBUs within minutes of collection, without breaching the CBUs' sterile environment. qOBM can reduce costs in CBB by avoiding processing expenses of CBUs that ultimately do not meet storage criteria.