Long-Term Optical Access to an Estimated One Million Neurons in the Live Mouse Cortex

Abstract

A major technological goal in neuroscience is to enable the interrogation of individual cells across the live brain. By creating a curved glass replacement to the dorsal cranium and surgical methods for its installation, we developed a chronic mouse preparation providing optical access to an estimated 800,000-1,100,000 individual neurons across the dorsal surface of neocortex. Post-surgical histological studies revealed comparable glial activation as in control mice. In behaving mice expressing a Ca²⁺ indicator in cortical pyramidal neurons, we performed Ca²⁺ imaging across neocortex using an epi-fluorescence macroscope and estimated that 25,000-50,000 individual neurons were accessible per mouse across multiple focal planes. Two-photon microscopy revealed dendritic morphologies throughout neocortex, allowed time-lapse imaging of individual cells, and yielded estimates of >1 million accessible neurons per mouse by serial tiling. This approach supports a variety of optical techniques and enables studies of cells across >30 neocortical areas in behaving mice.

Keywords: brain imaging; calcium imaging; dendrites; dendritic spines; fluorescence imaging; mouse behavior; neocortex; neural ensembles; two-photon microscopy.

Figure 1. The Crystal Skull Preparation Allows Long-Term Optical Access across the Live Mouse Cortex with Minimal Inflammation

(A) We made trapezoidal shaped windows from a standard (#0–#2) microscope cover glass (left). The resulting glass piece was heated and curved against a cylindrical mold (middle). The implant replaces the left and right parietal bones and parts of the frontal bone (right). Scale bar, 2 mm. (B) The implant is stable for months after implantation. There is limited to no skull re-growth under the glass, making the method compatible with longitudinal studies. SSS, superior sagittal sinus. Scale bar, 1 mm. (C) Histological analysis reveals comparable levels of cortical astrocytes in Crystal Skull mice as in mice that had no surgeries. We took tissue samples 2–5 weeks after surgery and stained them with DAPI, which labels nuclei of all cells (blue), and anti-glial fibrillary acidic protein (anti-GFAP; red). Scale bars represent 100 μm (top row) and 50 μm (bottom row). See also Figures S1–S3 and Table S1.

Figure 2. The Crystal Skull allows In Vivo Imaging of Sub-cellular Features across Cortex

(A) Epi-fluorescence image of a live Thy-1-YFP-H mouse, which expresses the yellow fluorescent protein (YFP) in a subset of layer 5 pyramidal neurons, with a Crystal Skull. Red and blue rectangles enclose regions shown in (B) and (E), respectively. Scale bar, 1 mm. (B) A tiling of two-photon image-stacks (two-dimensional projections of three-dimensional image stacks) acquired in the live mouse of (A) within the corresponding red-boxed area, visualized as a coronal section (1.8 mm × 8.9 mm). Pyramidal cell bodies are visible up to ~700 μm beneath the cortical surface. Dashed green box indicates the region shown in panel (C). Scale bar, 1 mm. (C) Magnified view of the green-boxed area in (B). Cell bodies and apical dendrites are visible ~300–700 μm beneath the cortical surface. Dashed yellow line marks the depth of the two-photon image shown in panel (D). Scale bar, 100 μm. (D) Two-photon image of YFP-labeled cell bodies and dendrites, acquired ~350 μm from the cortical surface. Scale bar, 100 μm. (E) A tiling of two-photon image-stacks (two-dimensional projections of three-dimensional image stacks) acquired in the live mouse of (A) within the corresponding blue-boxed area, visualized as a sagittal section (0.8 mm × 4.9 mm) Scale bar, 500 μm. (F) Epi-fluorescence macroscope image of a live Thy-1-GFP-M mouse, which expresses GFP in a sparse subset of layer 5 pyramidal neurons, with a Crystal Skull. Circles indicate locations where we took the two-photon images of (G)–(I) (marked in color-corresponding outlines). Scale bar, 1 mm. (G–I) Dendrites and dendritic spines imaged by two-photon microscopy in the areas enclosed in colored circles in (F). Scale bar, 10 μm.

Figure 3. An Estimated 25,000–50,000 GCaMP6f-Expressing Pyramidal Cells Are Optically Accessible through the Crystal Skull by One-Photon Ca²⁺ Imaging

(A) A maximum projection image, computed across a 20-s recording of neural Ca²⁺ activity. The video recording was acquired on an epi-fluorescence macroscope and reveals individual cells across the dorsal cortex of a GCaMP6f-tTA-dCre triple-transgenic mouse expressing GCaMP6f in cortical layer 2/3 pyramidal cells. Color overlay atop the left hemisphere is based on the Allen Brain Atlas (Oh et al., 2014) and shows a sampling of the >30 cortical areas that are accessible. 18 areas in the left hemisphere are marked. CC, cingulate cortex; MOp, primary motor area; MOs, secondary motor area; SSp-bfd, primary somatosensory area (barrel field); SSp-m, primary somatosensory area (mouth); SSp-ul, primary somatosensory area (upper limb); SSp-ll, primary somatosensory area (lower limb); SSp-tr, primary somatosensory area (trunk); SSs, secondary motor area; AUD, auditory area; PTLp, posterior parietal association area; RSP, retrosplenial area; VISal, anterolateral visual area; VISam, anteromedial visual area; VISp, primary visual area; VISpm, posteromedial visual area; TEa, temporal association area; ECT, ectorhinal area. Red box marks the area shown in (B) and used for computational sorting of cells based on their Ca²⁺ activity. Scale bar, 1 mm. (B) Top: map of 1,166 cells in the red-boxed area in (A) and identified computationally in epi-fluorescence Ca²⁺ videos. Bottom: 30 example Ca²⁺ activity traces. Locations of individual cells are marked with corresponding numerals in the map. Scale bar, 100 μm. (C) Trial structure of a simple behavioral protocol involving visual stimulation and reward delivery. At the start of each trial, the mouse saw five flashes of blue light (pulses 0.1 ms in duration, timed to start 0.2 ms apart) with its right eye. After a 1.7-s delay, the mouse received a water reward (~5–10 μL) from a spout. The inter-trial interval varied from 4 to 6 s. (D) A maximum projection image of the dorsal cortex, computed across a 3.5-min recording of neural Ca²⁺ activity in a mouse undergoing the protocol of (C). Colored boxes indicate cortical areas (red, visual; orange, retrosplenial; green, somatosensory; blue, motor) where we acquired additional Ca²⁺ imaging data at a higher magnification for computational extraction of individual cells. During Ca²⁺ imaging in each of these four areas, the mouse performed 24 behavioral trials. Scale bar, 1 mm. (E) Map of 262 cells in the red-boxed area in (D) (visual cortex) and identified computationally in epi-fluorescence Ca²⁺ videos as the mouse performed the protocol of (C). Activity traces for the numbered cells are shown in red in (G). Scale bar, 250 μm. (F) Map of 420 cells in the green-boxed area in (D) (somatosensory cortex) and identified computationally in epi-fluorescence Ca²⁺ videos as the mouse performed the protocol of (C). Activity traces for the numbered cells are shown in green in (G). Scale bar, 250 μm. (G) Left: example traces of neural Ca²⁺ activity acquired by epi-fluorescence imaging in the four color-corresponding areas in (D). The traces from visual and somatosensory cortex are those of the numbered cells in (E) and (F), respectively. Right: traces obtained by averaging each cell’s responses across all 24 trials. Yellow triangles mark the start of each trial. The blue triangle marks reward delivery.

Figure 4. Two-Photon Microscopy Makes a Million or More Neurons Optically Accessible through the Crystal Skull and Allows Time-Lapse Imaging of Individual Cells

(A) Mosaic of tiled two-photon images from the right hemisphere of a GCaMP6f-tTA-dCre mouse expressing GCaMP6f in cortical layer 2/3 pyramidal cells. Boundaries between tiles are apparent, because adjacent image tiles were acquired in different axial planes. The mouse is the same as in Figure 3A. Scale bar, 1 mm. Insets: magnified views of the color-corresponding boxed areas in the main panel. Scale bar, 100 μm (all insets). (B) Time-lapse imaging of individual cells in a tetO-GCaMP6s/CaMK2a-tTA mouse, which expresses GCaMP6s in a subset of pyramidal neurons. Individual cells can be tracked for multiple days. The day of imaging is indicated in the lower left of each image, starting with the first session on day 1. Scale bar, 100 μm. (C) Epi-fluorescence macroscope image of a tetO-GCaMP6s/CaMK2a-tTA mouse. Three regions of interest (ROIs) indicate locations where we took two-photon Ca²⁺ videos according to the protocol in (D) and at multiple tissue depths. Scale bar, 1 mm. (D) Protocol for two-photon Ca²⁺ imaging at the three ROI locations marked in (C). Within each ROI, we acquired 5-min movies at each of a series of tissue depths 100–500 μm from the cortical surface and spaced 10–20 μm apart. (E–G) Top: example cell maps determined by two-photon Ca²⁺ imaging in a tetO-GCaMP6s/CaMK2a-tTA mouse. Colors of the panel borders indicate the color-corresponding ROIs in (C). The tissue depth of each image is given above the panels. Bottom: for each panel, 15 Ca²⁺ activity traces are shown. Locations of individual cells are marked with numerals in the corresponding map. Scale bar, 100 μm.