{"id":241,"date":"2016-08-13T11:03:56","date_gmt":"2016-08-13T15:03:56","guid":{"rendered":"https:\/\/sites.bu.edu\/tianlab\/?page_id=241"},"modified":"2026-10-20T20:14:16","modified_gmt":"2026-10-21T00:14:16","slug":"research","status":"publish","type":"page","link":"https:\/\/sites.bu.edu\/tianlab\/research\/","title":{"rendered":"Research"},"content":{"rendered":"<p>Our lab develops <strong>computational imaging systems<\/strong> by<em> jointly designing optics, devices, signal processing, and algorithms<\/em>. We combine <strong>optical engineering<\/strong>, <strong>physics<\/strong>, and <strong>computation<\/strong> to expand what imaging systems can measure. Our work spans biomedical imaging, neuroscience, and semiconductor metrology and inspection.<\/p>\n<hr \/>\n<h3><strong>Computational Fluorescence &amp; Neural Imaging<\/strong><\/h3>\n<p>We develop computational fluorescence microscopes for large-scale, three-dimensional imaging and fast measurements of biological and neural dynamics. Related publications are <a href=\"https:\/\/sites.bu.edu\/tianlab\/publications\/comp-fluo-imaging\/\">here<\/a>.<\/p>\n<h4 style=\"text-align: left;\"><span style=\"color: #752929;\"><strong><img loading=\"lazy\" src=\"\/tianlab\/files\/2026\/09\/biocm2-636x508.png\" alt=\"\" width=\"300\" height=\"240\" class=\"alignleft wp-image-2639\" srcset=\"https:\/\/sites.bu.edu\/tianlab\/files\/2026\/09\/biocm2-636x508.png 636w, https:\/\/sites.bu.edu\/tianlab\/files\/2026\/09\/biocm2-1024x818.png 1024w, https:\/\/sites.bu.edu\/tianlab\/files\/2026\/09\/biocm2-768x613.png 768w, https:\/\/sites.bu.edu\/tianlab\/files\/2026\/09\/biocm2-1536x1226.png 1536w, https:\/\/sites.bu.edu\/tianlab\/files\/2026\/09\/biocm2.png 1572w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/>Computational Miniature Mesoscope (CM<sup>2<\/sup>)<\/strong><\/span><\/h4>\n<p style=\"text-align: left;\">We develop compact computational fluorescence microscopes that combine distributed optics with model-based and learning-based reconstruction for single-shot 3D imaging across large fields of view. These platforms support studies of biological structure and dynamics at cellular scales.<\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Xue et al. <a href=\"https:\/\/doi.org\/10.1126\/sciadv.abb7508\"><strong>Single-Shot 3D Widefield Fluorescence Imaging with a Computational Miniature Mesoscope<\/strong><\/a>. <em><strong>Science Advances<\/strong><\/em> 6(43), eabb7508 (2020).<\/li>\n<li>Xue et al. <a href=\"https:\/\/opg.optica.org\/optica\/fulltext.cfm?uri=optica-9-9-1009&amp;id=497528\"><strong>Deep-learning-augmented computational miniature mesoscope<\/strong><\/a>. <em><strong>Optica<\/strong><\/em> 9, 1009\u20131021 (2022).<\/li>\n<li>Yang et al. <a href=\"https:\/\/opg.optica.org\/optica\/fulltext.cfm?uri=optica-11-6-860&amp;id=552177\"><strong>Wide-field, high-resolution reconstruction in computational multi-aperture miniscope using a Fourier neural network<\/strong><\/a>. <em><strong>Optica<\/strong><\/em> 11, 860\u2013871 (2024).<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<h4><\/h4>\n<p><img loading=\"lazy\" src=\"\/tianlab\/files\/2024\/06\/EventLFM-636x588.png\" alt=\"\" width=\"300\" height=\"277\" class=\"alignleft wp-image-2315\" srcset=\"https:\/\/sites.bu.edu\/tianlab\/files\/2024\/06\/EventLFM-636x588.png 636w, https:\/\/sites.bu.edu\/tianlab\/files\/2024\/06\/EventLFM-1024x947.png 1024w, https:\/\/sites.bu.edu\/tianlab\/files\/2024\/06\/EventLFM-768x710.png 768w, https:\/\/sites.bu.edu\/tianlab\/files\/2024\/06\/EventLFM-1536x1421.png 1536w, https:\/\/sites.bu.edu\/tianlab\/files\/2024\/06\/EventLFM-2048x1894.png 2048w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><\/p>\n<h4 style=\"text-align: left;\"><span style=\"color: #752929;\">Event-Driven Dynamic Microscopy<\/span><\/h4>\n<p>We combine event-based sensors, tailored illumination, and computational reconstruction to capture fast biological dynamics. Our approaches include volumetric light-field imaging and dual-channel fluorescence microscopy.<\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Guo et al. <a href=\"https:\/\/www.pnas.org\/doi\/10.1073\/pnas.2531386123\"><strong>Dual-channel event microscopy for ultrafast biological imaging<\/strong><\/a>. <em><strong>PNAS<\/strong><\/em> (2026).<\/li>\n<li>Guo et al. <a href=\"https:\/\/www.nature.com\/articles\/s41377-024-01502-5\"><strong>EventLFM: Event Camera integrated Fourier Light Field Microscopy for Ultrafast 3D imaging<\/strong><\/a>. <em><strong>Light: Science &amp; Applications<\/strong><\/em> (2024).<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<hr \/>\n<h3><strong>Computational Metrology &amp; Inspection<br \/>\n<\/strong><\/h3>\n<p>We develop computational imaging methods for surface measurement, three-dimensional material characterization, and semiconductor metrology and inspection. Related publications are <a href=\"https:\/\/sites.bu.edu\/tianlab\/publications\/computational-phase-microscopy\/\">here<\/a>.<\/p>\n<h4><span style=\"color: #752929;\"><strong><img loading=\"lazy\" src=\"\/tianlab\/files\/2026\/03\/mbs-636x489.jpeg\" alt=\"\" width=\"300\" height=\"231\" class=\"alignleft wp-image-2542\" srcset=\"https:\/\/sites.bu.edu\/tianlab\/files\/2026\/03\/mbs-636x489.jpeg 636w, https:\/\/sites.bu.edu\/tianlab\/files\/2026\/03\/mbs-1024x788.jpeg 1024w, https:\/\/sites.bu.edu\/tianlab\/files\/2026\/03\/mbs-768x591.jpeg 768w, https:\/\/sites.bu.edu\/tianlab\/files\/2026\/03\/mbs-1536x1182.jpeg 1536w, https:\/\/sites.bu.edu\/tianlab\/files\/2026\/03\/mbs-2048x1575.jpeg 2048w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/>Substrate-Enhanced Diffraction Tomography<\/strong><\/span><\/h4>\n<p><span>We develop reflection-mode tomography methods that use substrate-enhanced scattering and multiple-scattering models to recover three-dimensional refractive-index structure from intensity measurements.\u00a0<\/span><\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Li et al. <a href=\"https:\/\/opg.optica.org\/optica\/fulltext.cfm?uri=optica-13-4-661\"><strong>Transfer-function approach to substrate-enhanced diffraction tomography<\/strong><\/a>. <em><strong>Optica<\/strong><\/em> (2026).<\/li>\n<li>Zhu et al. <a href=\"https:\/\/ieeexplore.ieee.org\/abstract\/document\/11417435\"><strong>Reflection-mode Multi-slice Fourier Ptychographic Tomography<\/strong><\/a>. <em><strong>IEEE Transactions on Computational Imaging<\/strong><\/em> (2026).<\/li>\n<li>Li et al. <a href=\"https:\/\/opg.optica.org\/optica\/fulltext.cfm?uri=optica-12-3-406&amp;id=569159\"><strong>Reflection-mode diffraction tomography of multiple-scattering samples on a reflective substrate from intensity images<\/strong><\/a>. <em><strong>Optica<\/strong><\/em> (2025).<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<h4><span style=\"color: #752929;\"><strong><img loading=\"lazy\" src=\"\/tianlab\/files\/2023\/11\/FPT-494x636.png\" alt=\"\" width=\"300\" height=\"386\" class=\"alignleft wp-image-2233\" srcset=\"https:\/\/sites.bu.edu\/tianlab\/files\/2023\/11\/FPT-494x636.png 494w, https:\/\/sites.bu.edu\/tianlab\/files\/2023\/11\/FPT-795x1024.png 795w, https:\/\/sites.bu.edu\/tianlab\/files\/2023\/11\/FPT-768x989.png 768w, https:\/\/sites.bu.edu\/tianlab\/files\/2023\/11\/FPT-1193x1536.png 1193w, https:\/\/sites.bu.edu\/tianlab\/files\/2023\/11\/FPT.png 1246w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><\/strong><\/span><\/h4>\n<h4><\/h4>\n<h4><\/h4>\n<h4><span style=\"color: #752929;\"><strong>Fourier Ptychographic Topography<\/strong><\/span><\/h4>\n<p>We develop Fourier ptychographic topography (FPT) to recover surface height from reflection-mode measurements over wide fields of view. Single- and dual-wavelength approaches combine high lateral resolution with sensitive height measurements.<\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Shen et al. <a href=\"https:\/\/doi.org\/10.1109\/TCI.2026.3712486\"><strong>Dual-wavelength Fourier Ptychographic Topography<\/strong><\/a>. <em><strong>IEEE Transactions on Computational Imaging<\/strong><\/em> (2026).<\/li>\n<li>Wang et al. <a href=\"https:\/\/opg.optica.org\/oe\/fulltext.cfm?uri=oe-31-7-11007&amp;id=528271\"><strong>Fourier ptychographic topography<\/strong><\/a>. <em><strong>Optics Express<\/strong><\/em> 31, 11007\u201311018 (2023).<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<hr \/>\n<h3><strong>Physics-based AI<\/strong><\/h3>\n<p>We combine physical imaging models with neural networks, simulator-based learning, and structured priors to solve inverse problems. Explore our <a href=\"https:\/\/sites.bu.edu\/tianlab\/publications\/physics-based-ai\/\">Physics-based AI publications<\/a> and related work on <a href=\"https:\/\/sites.bu.edu\/tianlab\/publications\/physics-embedded-deep-learning\/\">imaging through scattering media<\/a>.<\/p>\n<h4><span style=\"color: #800000;\"><img loading=\"lazy\" src=\"\/tianlab\/files\/2025\/11\/WSD-636x450.png\" alt=\"\" width=\"300\" height=\"212\" class=\"wp-image-2501 alignleft\" srcset=\"https:\/\/sites.bu.edu\/tianlab\/files\/2025\/11\/WSD-636x450.png 636w, https:\/\/sites.bu.edu\/tianlab\/files\/2025\/11\/WSD-1024x725.png 1024w, https:\/\/sites.bu.edu\/tianlab\/files\/2025\/11\/WSD-768x544.png 768w, https:\/\/sites.bu.edu\/tianlab\/files\/2025\/11\/WSD-1536x1088.png 1536w, https:\/\/sites.bu.edu\/tianlab\/files\/2025\/11\/WSD.png 1870w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/>Diffusion models<\/span><\/h4>\n<p>We develop structured diffusion priors for image reconstruction, combining learned image statistics with measurement models.<\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Alido et al. <a href=\"https:\/\/arxiv.org\/abs\/2505.10311\"><strong>Whitened Score Diffusion: A Structured Prior for Imaging Inverse Problems<\/strong><\/a>. <em><strong>NeurIPS<\/strong><\/em> (2025).<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<p><img loading=\"lazy\" src=\"\/tianlab\/files\/2022\/09\/NF-IDT-636x363.png\" alt=\"\" width=\"300\" height=\"171\" class=\"alignleft wp-image-2008\" srcset=\"https:\/\/sites.bu.edu\/tianlab\/files\/2022\/09\/NF-IDT-636x363.png 636w, https:\/\/sites.bu.edu\/tianlab\/files\/2022\/09\/NF-IDT-1024x585.png 1024w, https:\/\/sites.bu.edu\/tianlab\/files\/2022\/09\/NF-IDT-768x439.png 768w, https:\/\/sites.bu.edu\/tianlab\/files\/2022\/09\/NF-IDT-1536x877.png 1536w, https:\/\/sites.bu.edu\/tianlab\/files\/2022\/09\/NF-IDT-2048x1169.png 2048w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><\/p>\n<h4><span style=\"color: #752929;\"><strong>Neural fields<\/strong><\/span><\/h4>\n<p>We use neural fields to represent continuous object structure and recover quantitative phase and three-dimensional refractive-index maps from optical measurements.<span style=\"text-decoration: underline;\"><em><\/em><\/span><\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Wang et al. <a href=\"https:\/\/doi.org\/10.1117\/1.APN.3.5.056005\"><strong>NeuPh: scalable and generalizable neural phase retrieval with local conditional neural fields<\/strong><\/a>. <em><strong>Advanced Photonics Nexus<\/strong><\/em> 3, 056005 (2024).<\/li>\n<li>Liu et al. <a href=\"https:\/\/www.nature.com\/articles\/s42256-022-00530-3\"><strong>Recovery of Continuous 3D Refractive Index Maps from Discrete Intensity-Only Measurements using Neural Fields<\/strong><\/a>. <em><strong>Nature Machine Intelligence<\/strong><\/em> 4, 781\u2013791 (2022).<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p><img loading=\"lazy\" src=\"\/tianlab\/files\/2022\/03\/Uncertainty-584x636.png\" alt=\"\" width=\"300\" height=\"327\" class=\"alignleft wp-image-1828\" srcset=\"https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/Uncertainty-584x636.png 584w, https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/Uncertainty-940x1024.png 940w, https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/Uncertainty-768x837.png 768w, https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/Uncertainty-1410x1536.png 1410w, https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/Uncertainty.png 1640w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><\/p>\n<h4><span style=\"color: #752929;\"><strong>Reliable Deep Learning with Uncertainty Quantification<\/strong><\/span><\/h4>\n<p>We develop uncertainty-aware learning methods that assess prediction confidence and improve the reliability of quantitative phase imaging and biomedical measurements.<\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Xue et al. <a href=\"https:\/\/doi.org\/10.1364\/OPTICA.6.000618\"><strong>Reliable deep learning-based phase imaging with uncertainty quantification<\/strong><\/a>. <em><strong>Optica<\/strong><\/em> 6, 618\u2013629 (2019).<\/li>\n<li>Liu et al. <a href=\"https:\/\/www.nature.com\/articles\/s41377-019-0216-0\"><strong>Deep spectral learning for label-free optical imaging oximetry with uncertainty quantification<\/strong><\/a>. <em><strong>Light: Science &amp; Applications<\/strong><\/em> 8, 102 (2019).<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<h3><\/h3>\n<hr \/>\n<h3>AI for Biomedicine<\/h3>\n<p>We develop AI methods for biomedical image reconstruction, denoising, digital staining, and quantitative analysis. Related publications are <a href=\"https:\/\/sites.bu.edu\/tianlab\/publications\/deep-learning-for-biomedical-imaging\/\">here<\/a>.<\/p>\n<h4><span style=\"color: #752929;\"><strong><img loading=\"lazy\" src=\"\/tianlab\/files\/2026\/09\/PINN-636x424.png\" alt=\"\" width=\"300\" height=\"200\" class=\"alignleft wp-image-2636\" srcset=\"https:\/\/sites.bu.edu\/tianlab\/files\/2026\/09\/PINN-636x424.png 636w, https:\/\/sites.bu.edu\/tianlab\/files\/2026\/09\/PINN-1024x683.png 1024w, https:\/\/sites.bu.edu\/tianlab\/files\/2026\/09\/PINN-768x512.png 768w, https:\/\/sites.bu.edu\/tianlab\/files\/2026\/09\/PINN.png 1536w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/>Physics-informed deep learning<\/strong><\/span><\/h4>\n<p>We integrate physical models with neural networks to estimate biological quantities from optical measurements, including vascular and tissue dynamics measured with laser speckle contrast imaging.<\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Li et al. <a href=\"https:\/\/doi.org\/10.1117\/1.NPh.13.3.035012\"><strong>Physics-informed neural network for mapping vascular and tissue dynamics using laser speckle contrast imaging<\/strong><\/a>. <em><strong>Neurophotonics<\/strong><\/em> 13, 035012 (2026).<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<p><img loading=\"lazy\" src=\"\/tianlab\/files\/2022\/03\/Neural-signal-630x636.png\" alt=\"\" width=\"300\" height=\"303\" class=\"alignleft wp-image-1824\" srcset=\"https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/Neural-signal-630x636.png 630w, https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/Neural-signal-1015x1024.png 1015w, https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/Neural-signal-768x775.png 768w, https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/Neural-signal-100x100.png 100w, https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/Neural-signal.png 1485w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><strong><\/strong><\/p>\n<h4><span style=\"color: #752929;\"><strong>Deep Learning for In Vivo Neural Signal Modeling &amp; Extraction<\/strong><\/span><\/h4>\n<p>We develop self-supervised denoising methods to recover neural signals from low-photon fluorescence measurements and support high-speed voltage imaging. Explore related <a href=\"https:\/\/sites.bu.edu\/tianlab\/publications\/comp-fluo-imaging\/\">neural-imaging publications<\/a>.<\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Liu et al. <a href=\"https:\/\/www.spiedigitallibrary.org\/journals\/neurophotonics\/volume-11\/issue-04\/045007\/DeepVID-v2--self-supervised-denoising-with-decoupled-spatiotemporal-enhancement\/10.1117\/1.NPh.11.4.045007.full\"><strong>DeepVID v2: self-supervised denoising with decoupled spatiotemporal enhancement for low-photon voltage imaging<\/strong><\/a>. <em><strong>Neurophotonics<\/strong><\/em> 11(4), 045007 (2024).<\/li>\n<li>Platisa et al. <a href=\"https:\/\/doi.org\/10.1038\/s41592-023-01820-3\"><strong>High-speed low-light in vivo two-photon voltage imaging of large neuronal populations<\/strong><\/a>. <em><strong>Nature Methods<\/strong><\/em> 20, 1095\u20131103 (2023).<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p><img loading=\"lazy\" src=\"\/tianlab\/files\/2022\/03\/digital_stain.png\" alt=\"\" width=\"300\" height=\"301\" class=\"wp-image-1826 alignleft\" srcset=\"https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/digital_stain.png 568w, https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/digital_stain-150x150.png 150w, https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/digital_stain-100x100.png 100w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><\/p>\n<h4><strong><span style=\"color: #752929;\">Digital Staining &amp; Cross-Modality Learning<\/span><\/strong><\/h4>\n<p>We learn relationships between imaging modalities to predict molecular and structural information from label-free measurements. Applications include multiplexed single-cell cytometry, digital staining, and computational tissue assessment.<\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Cheng et al. <a href=\"https:\/\/doi.org\/10.1126\/sciadv.abe0431\"><strong>Single-cell cytometry via multiplexed fluorescence prediction by label-free reflectance microscopy<\/strong><\/a>. <em><strong>Science Advances<\/strong><\/em> 7(3), eabe0431 (2021).<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<h4><\/h4>\n<hr \/>\n<h3>Quantitative Phase Imaging &amp; Tomography<\/h3>\n<p>We develop label-free methods to recover optical phase, refractive index, and three-dimensional sample structure. Explore our <a href=\"https:\/\/sites.bu.edu\/tianlab\/publications\/digital-holographic-imaging\/\">phase-imaging and tomography publications<\/a>.<\/p>\n<p><img loading=\"lazy\" src=\"\/tianlab\/files\/2022\/03\/IDT-636x490.png\" alt=\"\" width=\"300\" height=\"231\" class=\"wp-image-1825 alignleft\" srcset=\"https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/IDT-636x490.png 636w, https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/IDT-1024x789.png 1024w, https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/IDT-768x592.png 768w, https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/IDT.png 1200w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><\/p>\n<h4><span style=\"color: #752929;\"><strong>Intensity Diffraction Tomography<\/strong><\/span><\/h4>\n<p>We combine programmable illumination, scattering models, and reconstruction algorithms to recover three-dimensional refractive-index structure from intensity-only measurements.<\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Li et al. <a href=\"https:\/\/doi.org\/10.1117\/1.AP.1.6.066004\"><strong>High-speed in vitro intensity diffraction tomography<\/strong><\/a>. <em><strong>Advanced Photonics<\/strong><\/em> 1(6), 066004 (2019).<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<p><img loading=\"lazy\" src=\"\/tianlab\/files\/2022\/03\/FPM-636x481.png\" alt=\"\" width=\"300\" height=\"227\" class=\"wp-image-1864 alignleft\" srcset=\"https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/FPM-636x481.png 636w, https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/FPM-1024x775.png 1024w, https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/FPM-768x581.png 768w, https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/FPM-1536x1162.png 1536w, https:\/\/sites.bu.edu\/tianlab\/files\/2022\/03\/FPM-2048x1550.png 2048w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><\/p>\n<h4><span style=\"color: #800000;\">Fourier Ptychography\u00a0<\/span><\/h4>\n<p>We combine illumination diversity with computational reconstruction to achieve high-resolution phase imaging across wide fields of view.<\/p>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li>Tian et al. <a href=\"https:\/\/doi.org\/10.1364\/OPTICA.2.000904\"><strong>Computational illumination for high-speed in vitro Fourier ptychographic microscopy<\/strong><\/a>. <em><strong>Optica<\/strong><\/em> 2(10), 904\u2013911 (2015).<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Our lab develops computational imaging systems by jointly designing optics, devices, signal processing, and algorithms. We combine optical engineering, physics, and computation to expand what imaging systems can measure. Our work spans biomedical imaging, neuroscience, and semiconductor metrology and inspection. Computational Fluorescence &amp; Neural Imaging We develop computational fluorescence microscopes for large-scale, three-dimensional imaging and [&hellip;]<\/p>\n","protected":false},"author":12228,"featured_media":0,"parent":0,"menu_order":2,"comment_status":"closed","ping_status":"closed","template":"page-templates\/no-sidebars.php","meta":[],"_links":{"self":[{"href":"https:\/\/sites.bu.edu\/tianlab\/wp-json\/wp\/v2\/pages\/241"}],"collection":[{"href":"https:\/\/sites.bu.edu\/tianlab\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/sites.bu.edu\/tianlab\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/sites.bu.edu\/tianlab\/wp-json\/wp\/v2\/users\/12228"}],"replies":[{"embeddable":true,"href":"https:\/\/sites.bu.edu\/tianlab\/wp-json\/wp\/v2\/comments?post=241"}],"version-history":[{"count":50,"href":"https:\/\/sites.bu.edu\/tianlab\/wp-json\/wp\/v2\/pages\/241\/revisions"}],"predecessor-version":[{"id":2973,"href":"https:\/\/sites.bu.edu\/tianlab\/wp-json\/wp\/v2\/pages\/241\/revisions\/2973"}],"wp:attachment":[{"href":"https:\/\/sites.bu.edu\/tianlab\/wp-json\/wp\/v2\/media?parent=241"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}