{ "cells": [ { "cell_type": "markdown", "id": "da6d5a51-f8ac-4865-893e-10186189faa1", "metadata": {}, "source": [ "# From surface data to image data\n", "In this notebook we will turn surfaces into binary and label images." ] }, { "cell_type": "code", "execution_count": 1, "id": "2c16dfdc-32ff-43e9-a9df-56f0deecaf10", "metadata": {}, "outputs": [], "source": [ "import napari_process_points_and_surfaces as nppas\n", "import vedo" ] }, { "cell_type": "code", "execution_count": 2, "id": "b9048ddd-5930-46e4-bbf4-61f3ca985f41", "metadata": { "pycharm": { "is_executing": true } }, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "\n", "\n", "
\n", "\n", "\n", "nppas.SurfaceTuple
\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "
origin (z/y/x)[0. 0. 0.]
center of mass(z/y/x)50.000,46.575,42.589
scale(z/y/x)1.000,1.000,1.000
bounds (z/y/x)25.500...74.500
2.500...88.500
2.500...83.500
average size31.277
number of vertices19040
number of faces38076
\n", "\n", "
" ], "text/plain": [ "(array([[25.5, 44. , 47. ],\n", " [26. , 43.5, 47. ],\n", " [26. , 44. , 46.5],\n", " ...,\n", " [74.5, 56. , 51. ],\n", " [74.5, 56. , 52. ],\n", " [74.5, 56. , 53. ]], dtype=float32),\n", " array([[ 2, 1, 0],\n", " [ 4, 3, 0],\n", " [ 4, 0, 1],\n", " ...,\n", " [19038, 18870, 18872],\n", " [19038, 18872, 19039],\n", " [19039, 18872, 18852]], dtype=int64))" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "mesh = vedo.load(\"../../data/branchoid.ply\")\n", "surface = nppas.to_napari_surface_data(mesh)\n", "\n", "surface" ] }, { "cell_type": "markdown", "id": "ff91dc0c-d93f-4873-9e8f-3387fb0e27b1", "metadata": { "pycharm": { "is_executing": true } }, "source": [ "## Binary volumes\n", "A common task is to fill a volume to create a binary image stack." ] }, { "cell_type": "code", "execution_count": 3, "id": "bbc09181-568f-49de-b3e4-17f28e25b5b8", "metadata": { "pycharm": { "is_executing": true } }, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "\n", "\n", "
\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "
shape(49, 86, 81)
dtypeint32
size1.3 MB
min0
max1
\n", "\n", "
" ], "text/plain": [ "StackViewNDArray([[[0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " ...,\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0]],\n", "\n", " [[0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " ...,\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0]],\n", "\n", " [[0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " ...,\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0]],\n", "\n", " ...,\n", "\n", " [[0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " ...,\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0]],\n", "\n", " [[0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " ...,\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0]],\n", "\n", " [[0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " ...,\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0]]])" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "binary_image = nppas.surface_to_binary_volume(surface)\n", "binary_image" ] }, { "cell_type": "markdown", "id": "588d25bb", "metadata": {}, "source": [ "## Labeled surface voxels\n", "We can also sample points from the surface and turn these points into a label image." ] }, { "cell_type": "code", "execution_count": 4, "id": "79a81bc5-56f0-4a51-a06f-0f93294b1b1b", "metadata": { "pycharm": { "is_executing": true } }, "outputs": [ { "data": { "text/plain": [ "array([[26. , 44. , 46.5],\n", " [26. , 43.5, 48. ],\n", " [26. , 43.5, 50. ],\n", " ...,\n", " [74.5, 55. , 52. ],\n", " [74.5, 56. , 49. ],\n", " [74.5, 56. , 51. ]], dtype=float32)" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "point_cloud = nppas.sample_points_from_surface(surface, distance_fraction=0.01)\n", "point_cloud" ] }, { "cell_type": "code", "execution_count": 5, "id": "23c3fcd4-45bb-4d9e-a7df-2134942a4100", "metadata": { "pycharm": { "is_executing": true } }, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "\n", "\n", "
\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "
shape(76, 90, 85)
dtypeint32
size2.2 MB
min0
max5167
\n", "\n", "
" ], "text/plain": [ "StackViewNDArray([[[0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " ...,\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0]],\n", "\n", " [[0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " ...,\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0]],\n", "\n", " [[0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " ...,\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0]],\n", "\n", " ...,\n", "\n", " [[0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " ...,\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0]],\n", "\n", " [[0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " ...,\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0]],\n", "\n", " [[0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " ...,\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0]]])" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "point_labels = nppas.points_to_labels(point_cloud)\n", "point_labels" ] }, { "cell_type": "code", "execution_count": 6, "id": "427aa2f2-0140-4ca9-82c8-23fc314b3c52", "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "\n", "\n", "
\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "
shape(90, 85)
dtypeint32
size29.9 kB
min0
max2678
\n", "\n", "
" ], "text/plain": [ "StackViewNDArray([[0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " ...,\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0],\n", " [0, 0, 0, ..., 0, 0, 0]])" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "point_labels[50]" ] }, { "cell_type": "markdown", "id": "7e11ee27-22fa-4f17-b751-a017d3d2c1e7", "metadata": {}, "source": [ "These labels can also be turned into points again." ] }, { "cell_type": "code", "execution_count": 7, "id": "6a4939de-52e7-4e68-a78c-80490d444dc4", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[(26.0, 44.0, 47.0),\n", " (26.0, 44.0, 48.0),\n", " (26.0, 44.0, 50.0),\n", " (26.0, 44.0, 52.0),\n", " (26.0, 44.0, 54.0),\n", " (26.0, 45.0, 46.0),\n", " (26.0, 45.0, 48.0),\n", " (26.0, 45.0, 50.0),\n", " (26.0, 45.0, 52.0),\n", " (26.0, 45.0, 55.0)]" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "centroids = nppas.labels_to_centroids(point_labels)\n", "centroids[:10]" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.9.15" }, "vscode": { "interpreter": { "hash": "bffd3f721d7127ef2391d1b3b329910e3ca6998c35d437db3070140f7f84cfb6" } } }, "nbformat": 4, "nbformat_minor": 5 }