Small Methods

Uniform, reproducible blood smears are critical for reliable hematological evaluation. Manual smear preparation, however, is user-dependent and introduces variability that limits quantitative microscopy. Here we developed BUsmear, a low-cost, 3D-printed, motorized blood smear device that prepares two smears simultaneously from a printed stage and a micro-motor drive with tunable linear velocity, controlled through a joystick-operated driver module. By spreading two slides in parallel with fully repeatable slide-to-slide motion, the device doubles throughput while eliminating operator-dependent motion artifacts, and can be fabricated on any benchtop 3D printer in under one day. To validate smear quality, we analyzed blood films from three donors together with a manual smear prepared by an expert from the blood of one of the same donors, giving a matched device-versus-manual pair. Automated Cellpose segmentation of 14,046 red blood cells across 12 bright-field fields showed that cell diameter was preserved and closely matched the expert smear (6.7-7.8 um across groups, within the 6.2-8.2 um human reference range; 6.7 vs 6.9 um in the matched pair), and that all films formed non-aggregated monolayers (Clark-Evans index of aggregation 1.04-1.24). Critically, red blood cells in the device films were markedly more circular than in the expert manual smear (mean eccentricity 0.405 vs 0.502; 0.443 vs 0.502 in the matched pair), with complete separation between the two methods at the level of whole fields of view. Because eccentricity reports smear-induced cell distortion, this indicates that a constant, mechanically controlled spreading velocity preserves red blood cell morphology better than skilled manual technique. BUsmear offers an accessible route to standardized smear geometry for quantitative analysis, including AI-based morphometry, and its low cost may be particularly advantageous in low-income countries with a high prevalence of malaria.

The ultrastructure of endothelial cells (ECs) "in situ" is of great interest due to their involvement in many physiological processes. In some organs, these cells form transcellular pores or fenestrae, allowing for the rapid exchange of molecules between blood and interstitium. Despite their importance, no optical images of these dynamic morphological structures have yet been acquired in situ. Major obstacles to their in-situ imaging are the lack of specifical labels for fenestrae and their size well below the optical diffraction limit. Here, we report how we have overcome these challenges and managed to visualize the EC ultrastructure in situ in 25 {micro}m thick liver sections. To enable this, a lipophilic, fluorescent membrane dye was infused into the portal vein of murine livers to stain the sinusoidal ECs before the organ was harvested. Tissue sections were subsequently imaged using a novel, super-resolution optical-sectioning structured illumination microscope (OS-SIM), providing approx. 170 nm spatial resolution with significantly faster image acquisition compared to confocal microscopy.

Chimeric antigen receptor (CAR)-T cells and CAR-macrophages (or CAR-monocytes) offer complementary antitumor functions. CAR-T cells exert potent cytotoxicity against cancer cells, whereas CAR-macrophages can infiltrate solid tumors, phagocytose cancer cells and promote antigen spreading. Antibody-conjugated lipid nanoparticles (LNPs) have emerged as non-viral mRNA delivery platforms for generating CAR-immune cells. However, these systems have generally been optimized to target a single immune-cell type. Here, to enable the ex vivo generation of CAR-T cells and CAR-monocytes, we developed CLCM08, an anti-CD222 antibody, and co-displayed it with an anti-CD5 antibody on LNPs. CD222 is predominantly expressed by monocytes, macrophages and T cells, and facilitates the internalization of CD222-binding molecules. CD5 is primarily expressed by T cells and has previously been used to enable LNP-mediated mRNA delivery to these cells. Delivery of CAR mRNA by dual CD222/CD5 antibody-conjugated LNPs to primary monocytes and T cells substantially enhanced the ex vivo generation of CAR-monocytes and CAR-T cells compared with non-conjugated LNPs. Moreover, CD19 CAR-T cells and CAR-monocytes generated using dual CD222/CD5 antibody-conjugated LNPs showed enhanced cytotoxic and phagocytic activity, respectively, relative to cells generated using non-conjugated LNPs, with anti-CD222 LNPs producing the largest phagocytic gain in monocytes. These findings establish an adaptable antibody-conjugated LNP-mRNA platform for the ex vivo generation of CAR-T cells and CAR-monocytes.

Tissue monolayers are active living matter whose three-dimensional (3D) architecture and mechanical remodeling regulate tissue function, yet fast and continuous topographic monitoring remains difficult. Here, we present FLuorescence EXclusion microscopy fOr Monolayers (FLEXOM), a microfluidic platform that combines multilayer micropillar arrays with negative-staining optics to convert wide-field images into self-calibrated 3D height maps. Geometry-anchored reference cavities maintain in-frame calibration standards even in fully confluent monolayer fields, enabling continuous 3D profiling from isolated cells to confluent sheets with sub-second temporal resolution ([~]250 ms), sub-micrometer axial precision ([~]0.37 {micro}m), and multi-day biocompatibility and operational stability (>96 h). FLEXOM reveals two distinct anisotropic signatures in tissue monolayers. First, monolayers of different cell types show distinct vertical thickness profiles despite comparable lateral footprints. Only two vertical descriptors, mean height and height variability, distinguished cell types more accurately than nine 2D lateral descriptors, including area, circularity, and convexity (95% vs. 76%). Second, under acute osmotic shock, confluent monolayers exhibit geometrically anisotropic and temporally decoupled vertical-lateral remodeling: height changes dominate the overall volume response and precede lateral remodeling. Surprisingly, cyclic isotonic-hypotonic pulses every 3 min confine remodeling entirely to the vertical axis. Overall, our work provides a high-resolution 3D profiling tool and a framework for axis-resolved analysis of topographic responses in active living matter.

Treatment with chimeric antigen receptor (CAR) T cells has emerged as a promising immune therapy for relapsed and refractory hematologic malignancies. The CAR T cells are manufactured in a series of steps that involve isolating T cells from the patients leukapheresis product, genetically modifying them to express the CAR against the target antigen, and reinfusing them into the patient. Efficient T-cell enrichment from leukapheresis products is critical to the success of these therapies. Current methods for T-cell sorting on a clinical scale involve several washing steps to remove red blood cells and platelets, followed by T-cell selection and activation. These multi-step processes result in cell loss during processing and involve several handling steps. Here, we utilize fluidically assembled micromagnetic lenses to develop a high-throughput, continuous-flow microfluidic T-cell sorter, designated as the T-Chip, for sorting magnetic bead-labeled CD3+ T cells in a single step. Our approach allows direct sorting of T cells in expansion media from leukopaks without any washing steps, effectively removing 99.999% of RBCs and platelets from the leukapheresis product. A single 1-inch x 3-inch T-Chip can process leukapheresis product at a throughput of 60 mL/hr and 2.56 {+/-} 0.12 billion cells/hr. Using this optimized workflow, we demonstrate clinical-scale enrichment of highly pure CD3+ T cells (97.7 {+/-} 1.3%) with high viability (97.0 {+/-} 1.1%) and recovery (87.3 {+/-} 14.8%) in a functionally closed manner. Downstream processing of T cells isolated using the T-Chip yielded potent anti-mesothelin CAR T cells with demonstrated anti-tumor efficacy. Overall, by exploiting precisely engineered magnetic forces and laminar flow, the microfluidic T-Chip overcomes bottlenecks caused by low throughput and enables single-step large-scale T-cell purification for the rapid development of CAR T cells.

High-throughput droplet microfluidics can compartmentalize bacterial interactions, but recovering droplets displaying phenotypes of interest often requires custom fluorescence-activated droplet-sorting instrumentation. Here, we introduce post-assay photogelation to decouple the material requirements of bacterial coculture from those of commercial flow sorting. Bacteria are cocultured in initially aqueous water-in-oil droplets containing photoreactive polymer precursors. After interaction phenotypes develop, ultraviolet exposure converts the droplets into mechanically stable hydrogel particles that can be transferred to an aqueous carrier and sorted using a commercial benchtop cell sorter. The sorted particles can subsequently be degraded enzymatically to release the encapsulated bacteria. We show that the timing of gelation alters bacterial growth and spatial distribution within droplets, with post-assay gelation supporting greater and more uniformly distributed growth than culture in preformed hydrogels. Using two fluorescent bead-encoded hydrogel-particle populations, we demonstrate sorting to greater than 99% purity. As an end-to-end demonstration, we cocultured sfGFP-expressing Escherichia coli Nissle 1917 with a cultured human nasal bacterial community and found that E. coli Nissle became the predominant detectable population under the tested conditions with possible inhibition of the cultured nasal bacteriome. This liquid-to-solid transition provides an accessible interface between aqueous bacterial droplet assays, commercial particle sorting, and downstream microbial analysis.

Epithelial tissues continuously remodel their curvature during morphogenesis, homeostasis, regeneration, and disease, yet experimental access to time-varying curvature remains limited. Here, we introduce CurvoChip, a pneumatically actuated microsystem that reversibly deforms confluent epithelial monolayers cultured on a 20-m elastic membrane into concave or convex geometries. The device operates either in a standard incubator or on a microscope stage and provides programmable control over pressure amplitude, direction, and cycling. Analytical scaling, finite-element simulations, and confocal profilometry establish predictable membrane deformation across the operating range, whereas cycling between -400 and +400 mbar for 120 cycles produces stable deflection without detectable drift or residual deformation. We further implement a three-dimensional surface-reconstruction and segmentation workflow to quantify cell and nuclear morphology on curved monolayers. Acute curvature induction produces a marked polarity-dependent response: convex deformation causes greater cell spreading and epithelial thinning than concave deformation, while nuclear projected area, thickness, and volume change in a direction- and position-dependent manner. These results show that epithelial architecture is sensitive not only to curvature magnitude but also to its orientation relative to the apico-basal axis. CurvoChip therefore provides an accessible platform for dissecting how epithelial tissues integrate dynamic geometric cues.

Growth-induced pressure arises when proliferating cell populations are confined within rigid microenvironments and is increasingly recognized as a determinant of microbial physiology in soils, biofilms, and host tissues. We present two complementary microfluidic devices that confine microbes within polydimethylsiloxane (PDMS) chambers and apply defined, optically read-out growth-induced pressure of up to 1.5 MPa. The first, the self-closing (SC) chip, confines cells in multiple small chambers accommodating hundreds of cells; it provides excellent nutrient supply and rapid medium exchange, supports single-cell imaging, and allows multiplexing of cellular or chemical conditions. The second, the pressure-recovery (PR) chip, confines cells in a single 5 cm-long chamber accommodating hundreds of thousands of cells; a scalpel-cut step recovers live cells from the channel within minutes for bulk biochemical assays. The two devices share a single two-layer soft-lithography fabrication process and a common brightfield wall-displacement pressure readout. Together, they enable single-cell imaging and bulk biochemical analysis under matched, defined pressure conditions. We illustrate the protocol with two representative validations: rapid {beta}-estradiol-induced transcription in the SC chip, in which nascent transcription foci appear within 5 min independently of the applied pressure, and the PR chip, which produces uniform growth-induced pressure along the entire 5 cm channel and recovers between 0.1x10^6 and 1x10^6 cells per device in a pressure-tunable manner.

DNA-based technologies rely on short, transient hybridization events, but selecting sequences with desired kinetic properties remains largely empirical because hybridization kinetics are difficult to predict from sequence and slow to measure one sequence at a time. Here, we introduce SPARXS-Hyb, an implementation of SPARXS (Single-molecule Parallel Analysis for Rapid eXploration of Sequence space) for multiplexed sequence-resolved screening of DNA hybridization. Using a surface-immobilized docking-strand library and a quencher-labelled imager-strand library, we screened 128 different DNA sequences in a single kinetic measurement, exposing all sequences to identical experimental conditions. This multiplexed approach removes a major confounding factor of serial measurements, allowing sequence-dependent differences to be compared directly. The resulting dataset reveals sequence-dependent transient binding behaviours and enabled us to identify a sequence with which an order-of-magnitude higher sampling rate can be achieved in DNA-PAINT (DNA points accumulation for imaging in nanoscale topography), a super-resolution microscopy technique based on DNA hybridization. By enabling multiplexed screening across a sequence library, SPARXS-Hyb provides a route to kinetics-guided sequence selection for programmable transient interactions in DNA nanotechnology.

Cardiac blood flow is a regulator of several important developmental and remodelling processes in the heart, including through fluid shear forces sensed by the endothelial cells lining the heart. However, optically mapping these flow fields in the complex 3D geometry of the heart is challenging even in transparent animal models such as the zebrafish. One of the main challenges is the difficulty in measuring the out-of-plane (axial) velocity component, preventing accurate mapping of the complete 3-component-3-dimension (3C-3D) blood flow velocity field; image-based techniques such as microscopic particle image velocimetry ({micro}PIV) traditionally only provide the in-plane flow components. Here we present a computational approach to achieve full time-varying 3C-3D blood flow vector mapping using a standard selective plane illumination microscope (SPIM), based on robust cardiac phase assignment, precise measurement-driven registration of sequentially acquired z-stacks, and PIV data fusion from multiple sample orientations. Our approach holds the key to understanding the complex dynamic flow fields within the developing heart, and their role in shaping cardiac development.

Viral diagnostics during early phases of infection are often limited by target scarcity and the deployment tempo. We significantly advance both quantitative accuracy and diagnostic throughput of viral agglutination assays with Immuno-Janus Particle (IJP) aggregation behavior that "flicker" stochastically with size-dependent statistics. By scrutinizing microscale blinking patterns of time series fluorescent videos, we decipher Brownian dynamics of individual IJP-Virus conjugates and IJP aggregates via windowed Ito stochastic analysis (termed the Culsans method). High-frequency rotational fluctuation is deconvolved from corrupting drifts caused by gravitational sedimentation and Brownian translational motion. This methodology enables a non-linear mapping of angular positions of detected IJPs and IJP aggregates to extract rotational diffusivity (Dr) (and subsequently overall construct size) with superior linearity (R2[≥]0.85). The aggregation behavior exhibits a maximum when the IJP and viral particle concentrations are equal. The virion-bridged IJP-IJP conjugates significantly shift the detectable hydrodynamic diameter in the Poisson limit of reduced virus concentration with respect to IJPs, pushing the limit of detection (LOD) to 103 - 104 virions per mL in untreated human plasma. This tunable platform offers a rapid, low-volume, and scalable alternative to lab-based RT-PCR, bridging the gap between virion sensitivity and field-readiness.

Capturing fast hemodynamics in deep organs is essential for understanding microvascular regulation of organ responses to physiological demands and pathological stress. However, non-invasive three-dimensional (3D) imaging of these microscale processes remains challenging due to trade-offs between spatial resolution, imaging speed, and penetration depth. Here, we present fluctuation-based high-order super-resolution acoustic microscope (FLAME), a tracking-free 3D ultrasound imaging technology capable of fast microvascular angiography and flow measurement. Using as few as 30 volumes, FLAME improves 3D ultrasound resolution by 8-fold (~50 m) and shortens data acquisition time by over two orders of magnitude, from tens of seconds to tens of milliseconds, compared with conventional tracking-based super-resolution approaches1-6. This high-throughput capability supports high-fidelity imaging of tissue functions under flexible experimental settings. FLAME achieves an unprecedented 3D super-resolution frame rate of ~40 Hz, capturing transient hemodynamic responses to various physiological and pathological stimuli in different mouse organs, from the microvascular level to the whole-body scale. With open-sourced implementation, FLAME provides an accessible platform for real-time, in-depth hemodynamic monitoring across diverse biomedical applications and clinical translation.

Fluorescence microscopy is routinely used in the quantitative analysis of Giant Unilamellar Vesicles (GUVs) because it makes GUVs visible and easy to detect. Nonetheless, it requires fluorescence-equipped microscopes and, especially, the addition of tagged molecules that may introduce undesired and unaccounted variations compared to the pristine formulation. Alternatively, phase-contrast microscopy can be used to observe GUVs without labelling, yet the automatic detection of GUVs in phase-contrast images by standard image processing techniques is difficult. To overcome this limitation, we developed a framework for the automated detection and size characterization of label-free GUVs based on YOLOv11 model, a state-of-art lightweight Convolutional Neural Network (CNN) for object detection. Trained on 164 phase-contrast microscope images containing 4666 manually annotated vesicles, the model enables robust detection under low contrast-to-noise ratio and heterogeneous illumination. The trained model is implemented in a stand-alone desktop application supporting multiple analysis in a single run, pixel-to-micrometer calibration, and automated size distribution analysis. This approach achieves high detection accuracy and competitive cross-microscope generalization using YOLOv11 nano on greyscale image. Retraining scripts compatible with standard hardware are also provided to enhance adaptability. This tool enables fast and reliable analysis of GUVs without altering their composition, supporting experimental reproducibility.

Three-dimensional cellular models such as organoids and spheroids hold major promise for developmental biology, disease modelling and precision medicine, yet their large-scale production and analysis remain constrained by handling-induced shear stress, sample fragility, positional instability and limited compatibility with advanced imaging workflows. Here, we introduce Microdomes, dense arrays of open-top, dome-shaped microcavities. Each cavity holds a single specimen in its own miniature aquarium, accessed through a narrow apical opening that admits cells, medium, matrix and staining reagents while shielding it from the shear generated during routine pipetting. Each Microdomes chip accommodates more than 100 spheroids or organoids, supporting diverse cell types, co-culture formats and both matrix-free and matrix-embedded culture. All specimens are retained through prolonged culture, repeated medium exchange, fixation and immunostaining. Because every specimen occupies a fixed, addressable position against a thin transparent film, the same spheroid can be relocated and re-imaged over weeks of culture and across microscopes, from array-wide overviews to subcellular details, without transfer, embedding or other perturbation. Microdomes also support AI-based automated segmentation, from whole-spheroid outlines to individual nuclei in 3D, using common image analysis software. Microdomes thereby turn each array into a self-contained quality control unit, providing specimen-level traceability that organoid production pipelines currently lack.

In materials science, the integrity of scanning electron microscopy (SEM) images is paramount for quality control and validation of research outcomes. However, the introduction of sophisticated generative artificial intelligence, particularly Generative Adversarial Networks (GANs), has introduced a novel vulnerability: the potential for highly realistic, artificially synthesized SEM images to be used fraudulently in scientific literature. To address this challenge, we present a deep learning-based framework capable of distinguishing between authentic SEM images and those synthesized by Generative Adversarial Networks (GANs). Using FastGAN and StyleGAN2-ADA, two state-of-the-art GAN models, we generated synthetic SEM datasets to complement real imaging data. We fine-tuned a pre-trained Contrastive Language-Image Pre-training (CLIP) Vision Transformer (ViT-L-14) for binary classification. By unfreezing the final transformer blocks and appending a custom classification head, the model effectively captures the subtle, high-level artifacts inherent in GAN-generated upsampling. This work highlights the potential of deep learning to safeguard scientific imaging workflows and provides an important step toward detecting and mitigating image forgeries in materials science publications.

While geometric constraints shape tissue development, quantifying the resulting growth dynamics remains a central challenge in tissue engineering. Conventional methods often struggle to capture multi-scale kinetics without complex labeling or difficult single-cell tracking. Here, we analyze geometrically controlled growth of microtissues derived from human dermal fibroblasts using time-resolved, label-free brightfield microscopy, combined with optical flow and semi-automated deep learning mitosis detection. By extracting multi-scale flow fields and integrating them with tissue segmentation, we quantify directional tissue dynamics, separating flow into parallel and normal components relative to the local tissue contour. Applying this framework, we contrast the quiescent tissue interior with the advancing growth front where localized dynamics and cell proliferation drive expansion. Our results demonstrate that, compared to the bulk, the growth front exhibits higher fluctuations parallel to the tissue contour, positive mean normal flow, and significantly increased mitotic activity. Furthermore, evaluating flow divergence around mitotic events reveals distinct spatial behaviors: with the onset of mitosis, a contraction and subsequent expansion occurs in the vicinity of the dividing cells. Beyond the immediate cellular neighborhood, the broader regional dynamics remain consistent before and after mitosis onset, with net tissue expansion in proximity to the growth front and contraction within the tissue interior. By extracting continuous kinetic data from easily accessible, label-free brightfield imaging, this approach serves as a non-invasive, complementary tool for evaluating in vitro tissue morphogenesis and growth dynamics. This analytical framework can be expanded to study locally resolved tissue morphogenesis and growth kinetics in other microsystems, ranging from embryos to organoids. Statement of SignificanceUnderstanding how localized cellular forces drive tissue growth is critical for mechanobiology. However, mapping these dynamics traditionally requires complex, invasive fluorescent labeling. We present an accessible, label-free computational framework combining optical flow and deep learning-based mitosis detection to quantify continuous tissue kinematics directly from standard brightfield microscopy. Applying this to 3D microtissues, we reveal a distinct spatial coupling between cell division, local mechanical fluctuations, and directed tissue expansion at the active growth front. This non-invasive approach bridges the gap between single-cell mechanics and macroscopic morphogenesis, offering a versatile tool to monitor complex in vitro model systems-like organoids and bioengineered tissues-without disrupting their native state.

Preparing electron-transparent cryo-lamellae is inherently a serial, low-throughput process. During sample handling, milling, and transfer, cryo-fixed cells and their supporting films are subjected to mechanical forces as well as thermal stresses caused by temperature fluctuations. After milling, these extremely thin lamellae remain vulnerable to both mechanical and thermal stress, often leading to cracking or complete disintegration. Consequently, the loss of valuable lamellae is frequently an unavoidable aspect of working with such fragile specimens. In this work, we reconsider the conventional lamella geometry, which is typically a flat, thin cross-sectional slab. During milling, lamellae often become unintentionally bent, complicating the final polishing step required to achieve uniform thinning across their width. To address this limitation, we propose deliberately fabricating lamellae in a pre-bent configuration, i.e. specifically, adopting an arch-shaped profile instead of the traditional flat geometry. The arch shape is intrinsically more mechanically stable than a flat structure, thereby reducing lamella loss due to mechanical failure. Moreover, pre-bent milling patterns facilitate uniform thinning of bent lamellae, which is difficult to achieve using conventional flat milling approaches. In addition to the arch geometry, we investigate corrugated lamellae, characterised by a sinusoidal variation around the plane of a conventional flat lamella. Similarly to the arch shape, the corrugated design offers enhanced mechanical stability compared to traditional flat lamellae. We fabricated a series of test lamellae incorporating both arches and corrugations. High-resolution cryo-TEM imaging was performed to evaluate these structures, demonstrating that non-flat geometries do not compromise cryo-electron tomography performance. Furthermore, finite element method (FEM) simulations were conducted to provide insight into stress distributions within bent and corrugated lamellae.

Adoptive cellular therapies can be effective against solid tumors but rely on the identification and expansion of rare tumor-reactive T cells (TRTs). Here, we utilize antigen-presenting cell-mimetic scaffolds (APC-ms), a modular biomaterial platform that presents defined peptide-HLA and co-stimulatory ligands on a fluid lipid bilayer to selectively recover rare antigen-specific T cells from peripheral blood. Independent variation of peptide-HLA, co-stimulatory ligands, and cytokine support defined a formulation that enriched MART-1-specific T cells to above 2% of CD8+ T cells in 35 of 50 HLA-A*02:01+ healthy donors from low or undetectable baseline frequencies. Compared with mo-DCs, APC-ms achieved greater fold expansion of MART-1-specific T cells with increased functional avidity and preservation of an early differentiation phenotype, and generated a higher number of MART-1-specific clonotypes. In five of eight patients with treatment-naive melanoma, APC-ms could enrich MART-1-specific T cells to a median of 13.7% of CD8+ cells (range 0.30 - 57.2%) Moreover, APC-ms could expand T cells specific for an HLA-A*24:01-restricted personal neoantigen that were previously undetectable in peripheral blood of a patient with melanoma. These findings establish APC-ms as a tunable platform for the recovery of rare TRTs from peripheral blood, supporting its further development for therapeutic TCR discovery and personalized adoptive cell therapy.

Chronic, mechanically resilient thrombi remain difficult to remove rapidly and safely using existing therapies, which are limited by slow treatment speeds, reduced efficacy against aged clots and risks associated with embolic debris. Here we introduce Constrained Laser-Induced Cavitation (CLIC), a novel approach that confines laser-induced cavitation bubble generation and collapse within a miniaturized waveguide to enhance thrombolysis. Optimized CLIC removed retracted clots at a mass-loss rate of 393.5 mg/min, [~]40-fold higher than reported state-of-the-art sonothrombolysis under similar conditions. Systematic variation of channel length and laser parameters showed that CLIC efficacy depends strongly on treatment geometry and cavitation dynamics. Post-treatment analysis revealed cylindrical channels consistent with clot removal dominated by fluid jetting and suction-driven evacuation, with cavitation shockwaves likely contributing a secondary role. Debris fragment measurements remained predominantly below a 1 mm embolic-risk threshold, consistent with a promising embolic safety profile. These findings establish CLIC as a viable strategy for rapid thrombolysis of chronic, mechanically resistant thrombi.

The sea anemone Aiptasia is a model system for understanding cnidarian loss of symbiotic algae under heat stress (bleaching). While Aiptasia polyps have been widely used to study this process, accurate symbiosis phenotyping grapples with discordant length scales: fine spatial resolution (~100 um) is needed across a whole organism (~5 mm). To address this, we consider small (~100 um), optically transparent Aiptasia larvae as a bleaching model suitable for whole-organism phenotyping by fluorescence microscopy with larvae classified as symbiotic when algae are localized within gastrodermal cells. To expedite phenotyping, we introduce a machine-learning (ML) image-analysis pipeline (SYMPHONY) designed for single-larva resolution analysis of intact larvae. SYMPHONY efficiently identifies the cellular location of internalized algae (accuracy: 79%, precision: 82%, recall: 79%, F1 score: 79%; training dataset composed of 1611 total objects). Additionally, SYMPHONY reports statistically significant larval bleaching under heat stress and corroborates manual phenotyping results, while significantly reducing operator labor from hours to minutes. The combination of the Aiptasia larvae model and the SYMPHONY pipeline aims to accelerate our understanding of symbiosis breakdown.