Skip to content

Commit

Permalink
Merge 83c040d into fafcc55
Browse files Browse the repository at this point in the history
  • Loading branch information
@willgraf
willgraf committed May 5, 2021
2 parents fafcc55 + 83c040d commit 7d80691
Show file tree
Hide file tree
Showing 9 changed files with 151 additions and 172 deletions.
38 changes: 14 additions & 24 deletions src/About/About.js
View file
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@ import AccordionSummary from '@material-ui/core/AccordionSummary';
import AccordionDetails from '@material-ui/core/AccordionDetails';
import Container from '@material-ui/core/Container';
import Grid from '@material-ui/core/Grid';
import Link from '@material-ui/core/Link';
import Paper from '@material-ui/core/Paper';
import Typography from '@material-ui/core/Typography';
import { makeStyles } from '@material-ui/core/styles';
Expand Down Expand Up @@ -85,11 +86,7 @@ export default function About() {
(1) Data Annotation and Management, (2) Model Development, and (3) Deployment and Inference
</Typography>

<Grid
container
alignItems="stretch"
justify="space-evenly"
>
<Grid container alignItems="stretch" justify="space-evenly">

<Grid item xs={10}>
<Typography variant="h4" className={classes.sectionHeader}>
Expand All @@ -103,11 +100,10 @@ export default function About() {
id="panel-data-1-header"
>
<Typography className={classes.heading}>DeepCell Label</Typography>
{/* <Typography className={classes.secondaryHeading}>I am an accordion</Typography> */}
</AccordionSummary>
<AccordionDetails>
<Typography>
<a href="https://github.com/vanvalenlab/deepcell-label" target="_blank" rel="noreferrer">DeepCell Label</a> is our training data curation tool.
<Link href="https://github.com/vanvalenlab/deepcell-label" target="_blank" rel="noreferrer">DeepCell Label</Link> is our training data curation tool.
It provides an inutitive UI for users to create annotations from scratch or to correct model predictions, to faciliate the creation of large, high-quality datasets.
DeepCell Label can be deployed locally or on the cloud.
</Typography>
Expand All @@ -128,14 +124,13 @@ export default function About() {
id="panel-model-dev-1-header"
>
<Typography className={classes.heading}>deepcell-tf</Typography>
{/* <Typography className={classes.secondaryHeading}>I am an accordion</Typography> */}
</AccordionSummary>
<AccordionDetails>
<Typography>
<a href="https://github.com/vanvalenlab/deepcell-tf" target="_blank" rel="noreferrer">deepcell-tf</a> is our core deep learning library.
<Link href="https://github.com/vanvalenlab/deepcell-tf" target="_blank" rel="noreferrer">deepcell-tf</Link> is our core deep learning library.
Based on TensorFlow, it contains a suite of tools for building and training deep learning models.
The library has been constructed in a modular fashion to make it easy to mix and match different model architectures, prediction tasks, and post-processing functions.
For more information, check out the <a href="https://deepcell.readthedocs.io/en/master/" target="_blank" rel="noreferrer">documentation</a>.
For more information, check out the <Link href="https://deepcell.readthedocs.io/en/master/" target="_blank" rel="noreferrer">documentation</Link>.
</Typography>
</AccordionDetails>
</Accordion>
Expand All @@ -154,21 +149,16 @@ export default function About() {
id="panel-deployment-3-header"
>
<Typography className={classes.heading}>kiosk-console</Typography>
{/* <Typography className={classes.secondaryHeading}>I am an accordion</Typography> */}
</AccordionSummary>
<AccordionDetails>
<Typography component={'span'}>
The <a href="https://github.com/vanvalenlab/kiosk-console" target="_blank" rel="noreferrer">kiosk-console</a> is a turn-key cloud-based solution for deploying a scalable inference platform.
The platform includes <a href="https://deepcell.org/predict">a simple drag-and-drop interface</a> for segmenting a few images, and a <a href="https://github.com/vanvalenlab/kiosk-client" target="_blank" rel="noreferrer">robust API</a> capable of affordably processing millions of images.
The <Link href="https://github.com/vanvalenlab/kiosk-console" target="_blank" rel="noreferrer">kiosk-console</Link> is a turn-key cloud-based solution for deploying a scalable inference platform.
The platform includes a <Link href="/predict">simple drag-and-drop interface</Link> for segmenting a few images, and a <Link href="https://github.com/vanvalenlab/kiosk-client" target="_blank" rel="noreferrer">robust API</Link> capable of affordably processing millions of images.
<br /><br />
The platform comes out of the box with three distinct model types:
<ul>
<li>Segmentation: A nuclear prediction model for cell culture. The input to this model is a single nuclear image. The output of this model is a mask with the nuclear segmentation of each cell in the image.</li>
<li>Tracking: A live-cell tracking model. The input to this model is a time-lapse movie of a single nuclear channel. The output of this model is a segmentation mask for each frame in the time-lapse movie, with the cell ids linked across images such that the same cell always has the same label.</li>
<li>Multiplex: A multiplex imaging model. The input to this model is a 2-channel image consisting of a nuclear channel and a membrane or cytoplasm channel. The output of this model is a mask with the whole-cell segmentation of each cell in the image.</li>
</ul>
We use this platform to host DeepCell.org and <Link href="https://github.com/vanvalenlab/intro-to-deepcell/tree/master/pretrained_models#formatting-data-for-pre-trained-models" target="_blank" rel="noopener noreferrer"> currently deployed models</Link>.
However, it is built with extensibility in mind, and it is easy to deploy your own models.
To learn more about deploying your own instance of deepcell.org using the kiosk-console, <a href="https://deepcell-kiosk.readthedocs.io/" target="_blank" rel="noreferrer">read the docs</a>.

To learn more about deploying your own instance of DeepCell.org using the kiosk-console, <Link href="https://deepcell-kiosk.readthedocs.io/" target="_blank" rel="noreferrer">read the docs</Link>.
</Typography>
</AccordionDetails>
</Accordion>
Expand All @@ -184,7 +174,7 @@ export default function About() {
</AccordionSummary>
<AccordionDetails>
<Typography>
The <a href="https://github.com/vanvalenlab/kiosk-imagej-plugin" target="_blank" rel="noreferrer">kiosk-imagej-plugin</a> enables ImageJ to segment images with a deployed DeepCell Kiosk model without leaving the application.
The <Link href="https://github.com/vanvalenlab/kiosk-imagej-plugin" target="_blank" rel="noreferrer">kiosk-imagej-plugin</Link> enables ImageJ to segment images with a deployed DeepCell Kiosk model without leaving the application.
</Typography>
</AccordionDetails>
</Accordion>
Expand All @@ -200,7 +190,7 @@ export default function About() {
</AccordionSummary>
<AccordionDetails>
<Typography>
<a href="https://github.com/vanvalenlab/deepcell-applications" target="_blank" rel="noreferrer">deepcell-applications</a> contains a variety of trained deep learning models and post-processing functions for instance segmentation.
<Link href="https://github.com/vanvalenlab/deepcell-applications" target="_blank" rel="noreferrer">deepcell-applications</Link> contains a variety of trained deep learning models and post-processing functions for instance segmentation.
Each model can be imported and run locally from a Docker image, Jupyter notebook, or custom script.
</Typography>
</AccordionDetails>
Expand All @@ -217,9 +207,9 @@ export default function About() {
</AccordionSummary>
<AccordionDetails>
<Typography>
The <a href="https://github.com/angelolab/ark-analysis" target="_blank" rel="noreferrer">ark repository</a> is our integrated multiplex image analysis pipeline.
The <Link href="https://github.com/angelolab/ark-analysis" target="_blank" rel="noreferrer">ark repository</Link> is our integrated multiplex image analysis pipeline.
The input is multiplexed image data from any platform.
It runs the data through deepcell, extracts the counts of each marker in each cell, normalizes the data, and then creates a summary table with morphological information and marker intensity for every cell in each image.
It segments the data with <Link href="https://github.com/vanvalenlab/intro-to-deepcell/tree/master/pretrained_models#mesmer-segmentation-model" target="_blank" rel="noopener noreferrer">Mesmer</Link> using the <Link href="https://deepcell-kiosk.readthedocs.io" target="_blank" rel="noopener noreferrer">Kiosk</Link>, extracts the counts of each marker in each cell, normalizes the data, and then creates a summary table with morphological information and marker intensity for every cell in each image.
It also provides an easy way to run some standard spatial analysis functions on your data.
</Typography>
</AccordionDetails>
Expand Down
3 changes: 1 addition & 2 deletions src/App/App.js
View file
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@ const Footer = lazy(() => import('../Footer/Footer'));
const NavBar = lazy(() => import('../NavBar/NavBar'));
const Landing = lazy(() => import('../Landing/Landing'));
const Predict = lazy(() => import('../Predict/Predict'));
const Data = lazy(() => import('../Data/Data'));
// const Data = lazy(() => import('../Data/Data'));
const NotFound = lazy(() => import('../NotFound/NotFound'));

// If the mode is NOT production, then notify that we are in dev mode.
Expand Down Expand Up @@ -77,7 +77,6 @@ export default function App() {
<Route path='/about' component={withTracker(About)}/>
<Route path='/faq' component={withTracker(Faq)}/>
<Route path='/predict' component={withTracker(Predict)}/>
<Route path='/data' component={withTracker(Data)}/>
<SwaggerUI url='/api/swagger.json' />
<Route component={withTracker(NotFound)} />
</Switch>
Expand Down

0 comments on commit 7d80691

Please sign in to comment.