Skip to content

Commit c24bd8c

Browse files
authored
Merge pull request #106 from PytorchConnectomics/leander/update-docs
updated the readme, providing the latest demo link
2 parents 92a00c1 + ecdc93c commit c24bd8c

2 files changed

Lines changed: 18 additions & 18 deletions

File tree

README.md

Lines changed: 17 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -1,15 +1,15 @@
11
# SynAnno
22

33
## Live Demo
4-
A demo is available [here](http://16.170.214.77/)
4+
A demo is available [here](http://16.170.214.77/reset)
55

66
## Table of Contents
77

8-
SynAnno is a tool designed for proofreading and correcting synaptic polarity annotation from electron microscopy (EM) volumes - specifically the [H01](https://h01-release.storage.googleapis.com/landing.html) dataset. SynAnno is aimed for integration with CAVE (Connectome Annotation Versioning Engine).
8+
SynAnno is a tool designed for proofreading and correcting synaptic annotations from electron microscopy (EM) volumes - specifically the [H01](https://h01-release.storage.googleapis.com/landing.html) dataset. SynAnno is aimed for integration with CAVE (Connectome Annotation Versioning Engine).
99

1010
- [Key Components and Subjects](#key-components-and-subjects)
1111
- [H01](#h01)
12-
- [Synaptic Polarity Annotation](#synaptic-polarity-annotation)
12+
- [Direction of information flow](#direction-of-information-flow)
1313
- [CAVE (Connectome Annotation Versioning Engine)](#cave-connectome-annotation-versioning-engine)
1414
- [Neuroglancer Integration](#neuroglancer-integration)
1515
- [Cloud Volume](#cloud-volume)
@@ -24,10 +24,10 @@ SynAnno is a tool designed for proofreading and correcting synaptic polarity ann
2424
- [Navigating SynAnno](#navigating-synanno)
2525
- [Landing Page](#landing-page)
2626
- [Open Data](#open-data)
27-
- [Annotate](#annotate)
28-
- [Categorize](#categorize)
27+
- [Error Detection](#error-detection)
28+
- [Error Categorization](#error-categorization)
2929
- [Export Annotations](#export-annotations)
30-
- [Draw](#draw)
30+
- [Error Correction](#error-correction)
3131
- [Export Masks](#export-masks)
3232
- [Contributing](#contributing)
3333

@@ -37,9 +37,9 @@ SynAnno is a tool designed for proofreading and correcting synaptic polarity ann
3737

3838
Harvard's Lichtman laboratory and Google's Connectomics team released the [H01](https://h01-release.storage.googleapis.com/landing.html) dataset, a 1.4 petabyte view of human brain tissue via nanoscale EM. It covers a volume of ~1mm³, featuring tens of thousands of neurons, millions of neuron fragments, 183 million annotated synapses, and 100 proofread cells.
3939

40-
### Synaptic Polarity Annotation
40+
### Direction of information flow
4141

42-
Synaptic polarity refers to the directionality of information flow between two neurons at a synapse, the junction where they communicate. In this context, we classify synapses as pre-synaptic (information senders) or post-synaptic (information receivers). A pre-synaptic neuron sends neurotransmitter signals across the synaptic cleft to the post-synaptic neuron, which receives these signals and processes the information. While the segmentation masks highlight the synaptic clefts between neurons, the pre-/post-synaptic IDs are coordinates placed into the associated neurons, identifying the specific sender and receiver. Identifying these key elements is crucial for creating accurate structural and functional neural maps. SynAnno assists in proofreading, correcting, and identifying these segmentation masks and synaptic IDs.
42+
We classify synapses as pre-synaptic (information senders) or post-synaptic (information receivers). A pre-synaptic neuron sends neurotransmitter signals across the synaptic cleft to the post-synaptic neuron, which receives these signals and processes the information. While the segmentation masks highlight the synaptic clefts between neurons, the pre-/post-synaptic IDs are coordinates placed into the associated neurons, identifying the specific sender and receiver. Identifying these key elements is crucial for creating accurate structural and functional neural maps. SynAnno assists in proofreading, correcting, and identifying these segmentation masks and synaptic IDs.
4343

4444
### CAVE (Connectome Annotation Versioning Engine)
4545
[CAVE](https://www.biorxiv.org/content/10.1101/2023.07.26.550598v1) is a computational infrastructure to host petabyte connectomes for distributed proofreading and dynamic spatial annotation. Soon, we will provide support to use SynAnno together with CAVE-hosted datasets.
@@ -118,13 +118,13 @@ Repository includes a Dockerfile that enables you to build and run the applicati
118118
3. **Build the Docker image**: Build the Docker image using the provided Dockerfile.
119119

120120
```bash
121-
docker build -t synanno .
121+
docker build -t synanno/uwsgi -f Dockerfile_uwsgi .
122122
```
123123

124124
4. **Run the Docker container**: Run the Docker container using the image you just built.
125125

126126
```bash
127-
docker run -d --name synanno -p 80:80 -p 9015:9015 synanno
127+
docker run -d --name synanno -p 80:80 -p 9015:9015 synanno/uwsgi
128128
```
129129

130130
5. **Access the application**: Open a web browser and go to `http://localhost` to access the application running in the Docker container.
@@ -230,7 +230,7 @@ python run.py
230230

231231
- URL: http://127.0.0.1:5000/
232232

233-
On the landing page you can choose between two workflows: "Revise Dataset" and "Proofread Annotation". The former allows you to redraw segmentation masks, assign pre-/post-synaptic IDs, and add missed false negatives. The latter allows you to review existing segmentations and pre-/post-synaptic IDs, mark incorrect instances, and assign error descriptions to those instances. After categorizing all erroneous instances in the "Proofread Annotation" workflow, you can automatically proceed with the "Revise Dataset" workflow.
233+
On the landing page you can choose between two workflows: "Error Correction" and "Error Detection". The former allows you to redraw segmentation masks, assign pre-/post-synaptic IDs, and add missed false negatives. The latter allows you to review existing segmentations and pre-/post-synaptic IDs, mark incorrect instances, and assign error descriptions to those instances. After categorizing all erroneous instances in the "Error Detection" workflow, you can automatically proceed with the "Error Correction" workflow.
234234

235235
Each page has three buttons: "Home", "Question Mark", and "Menu". The first returns you to the landing page. The second provides an explanation of the current view and its functionality. The third provides general information and contact details.
236236

@@ -240,7 +240,7 @@ Each page has three buttons: "Home", "Question Mark", and "Menu". The first retu
240240

241241
- URL: http://127.0.0.1:5000/open_data
242242

243-
This view is identical for both workflows. You'll be prompted to provide a source bucket and target bucket (both in Neuroglancer's precomputed format), a URL to a materialization table, bucket secrets (defaults to ~/.cloudvolume/secrets), and optionally a JSON file containing instance metadata. The JSON file can be used to save and restore sessions or start a "Revise Dataset" workflow with information from a "Proofread Annotation" workflow. If you wish to use "View-Centric" neuron selection in a "Proofread Annotation" workflow, you must also provide a neuropil segmentation bucket in Neuroglancer's precomputed format as well.
243+
This view is identical for both workflows. You'll be prompted to provide a source bucket and target bucket (both in Neuroglancer's precomputed format), a URL to a materialization table, bucket secrets (defaults to ~/.cloudvolume/secrets), and optionally a JSON file containing instance metadata. The JSON file can be used to save and restore sessions or start a "Error Correction" workflow with information from a "Error Detection" workflow. If you wish to use "View-Centric" neuron selection in a "Error Detection" workflow, you must also provide a neuropil segmentation bucket in Neuroglancer's precomputed format as well.
244244

245245
Opening the "Volume Parameters" tab, you will have two different options for the manner in which to select your instances, "View Centric" and "Neuron Centric".
246246

@@ -258,12 +258,12 @@ If you choose the 'Neuron Centric' approach. You'll need to specify the coordina
258258
259259
After providing the required information, click 'Submit' to prepare the data for the first page or revision. Then, click "Start Data Proofread"/"Start Drawing" to begin proofreading or revision.
260260
261-
### Annotate
261+
### Error Detection
262262
263263
- Workflow: Proofreading
264264
- URL: http://127.0.0.1:5000/annotation
265265
266-
Clicking `Start Data Proofread` directs you to a grid view of instances. Instance status is indicated by color: correct (green), incorrect (red), unsure (gray). Clicking on an instance changes its status: once for incorrect, twice for unsure, three times for correct.
266+
Clicking `Start Data Proofread` directs you to a grid view of instances. Instance status is indicated by color: correct (green), incorrect (red), unsure (yellow). Clicking on an instance changes its status: once for incorrect, twice for unsure, three times for correct.
267267
268268
[![Grid View][3]][3]
269269
@@ -277,7 +277,7 @@ Click `View in NG` to view the instance in Neuroglancer.
277277

278278
After evaluating the segmentation masks, click `->` to load and evaluate the page. When done, click `Error Processing` on the last proofreading page.
279279

280-
### Categorize
280+
### Error Categorization
281281

282282
- Workflow: Proofreading
283283
- URL: http://127.0.0.1:5000/categorize
@@ -295,11 +295,11 @@ If you marked instances as false positives, you'll be asked if they should be di
295295
- Workflow: Proofreading
296296
- URL: http://127.0.0.1:5000/export_annotate
297297
298-
After clicking `Submit and finish`, you can download the JSON file containing instance metadata by clicking `Download JSON`, redraw masks with the `Revise Dataset` workflow by clicking `Redraw Masks`, or start a new process by clicking `Start New Process`.
298+
After clicking `Submit and finish`, you can download the JSON file containing instance metadata by clicking `Download JSON`, redraw masks with the `Error Correction` workflow by clicking `Redraw Masks`, or start a new process by clicking `Start New Process`.
299299
300300
[![Export Annotations][8]][8]
301301
302-
### Draw
302+
### Error Correction
303303
304304
- Revision Workflow
305305
- http://127.0.0.1:5000/draw

synanno/templates/annotation.html

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -77,7 +77,7 @@
7777
</div>
7878

7979
<!-- Error Processing Button -->
80-
<div class="position-absolute" style="bottom: 1.5rem; right: 2.5rem;">
80+
<div class="position-absolute" style="bottom: 1.5rem; right: 2.5rem; z-index: 1000;">
8181
<a class="btn btn-secondary" href="{{ url_for('categorize.categorize') }}">Error Processing</a>
8282
</div>
8383
</div>

0 commit comments

Comments
 (0)