Skip to content

Commit 44fa4cb

Browse files
Yousef Ashraf Hassan Kotb Hassanyousefkotp
Yousef Ashraf Hassan Kotb Hassan
authored and
yousefkotp
committed
chore: version 1.0.0.post1 for PyPI
1 parent 3c91267 commit 44fa4cb

5 files changed

Lines changed: 9 additions & 9 deletions

File tree

‎.gitignore‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -62,4 +62,4 @@ dmypy.json
6262
.cursor/rules/byterover-rules.mdc
6363
.kiro/steering/byterover-rules.md
6464
.qoder/rules/byterover-rules.md
65-
.augment/rules/byterover-rules.md
65+
.augment/rules/byterover-rules.mdPRE_RELEASE_CHECKLIST.md

‎README.md‎

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
<p align="center">
2-
<img src="assets/images/Logo.png" alt="AtlasPatch Logo" width="100%">
2+
<img src="https://raw.githubusercontent.com/AtlasAnalyticsLab/AtlasPatch/main/assets/images/Logo.png" alt="AtlasPatch Logo" width="100%">
33
</p>
44

55
# AtlasPatch: An Efficient and Scalable Tool for Whole Slide Image Preprocessing in Computational Pathology
@@ -152,7 +152,7 @@ AtlasPatch provides a flexible pipeline with **4 checkpoints** that you can use
152152
### Pipeline Checkpoints
153153

154154
<p align="center">
155-
<img src="assets/images/Checkouts.png" alt="AtlasPatch Pipeline Checkpoints" width="100%">
155+
<img src="https://raw.githubusercontent.com/AtlasAnalyticsLab/AtlasPatch/main/assets/images/Checkouts.png" alt="AtlasPatch Pipeline Checkpoints" width="100%">
156156
</p>
157157

158158
Quick overview of the checkpoint commands:
@@ -226,13 +226,13 @@ Pass a directory instead of a single file to process multiple WSIs; outputs land
226226
Below are some examples for the output masks and overlays (original image, predicted mask, overlay, contours, grid).
227227

228228
<p align="center">
229-
<img src="assets/images/VisualizationSamples.png" alt="AtlasPatch visualization samples" width="100%">
229+
<img src="https://raw.githubusercontent.com/AtlasAnalyticsLab/AtlasPatch/main/assets/images/VisualizationSamples.png" alt="AtlasPatch visualization samples" width="100%">
230230
</p>
231231

232232
Quantitative and qualitative analysis of AtlasPatch tissue detection against existing slide-preprocessing tools.
233233

234234
<p align="center">
235-
<img src="assets/images/Comparisons.jpg" alt="AtlasPatch method comparison" width="100%">
235+
<img src="https://raw.githubusercontent.com/AtlasAnalyticsLab/AtlasPatch/main/assets/images/Comparisons.jpg" alt="AtlasPatch method comparison" width="100%">
236236
</p>
237237

238238
Representative WSI thumbnails are shown from diverse tissue features and artifact conditions, with tissue masks predicted by thresholding methods (TIAToolbox, CLAM) and deep learning methods (pretrained "non-finetuned" SAM2 model, Trident-QC, Trident-Hest and AtlasPatch), highlighting differences in boundary fidelity, artifact suppression and handling of fragmented tissue (more tools are shown in the appendix). Tissue detection performance is also shown on the held-out test set for AtlasPatch and baseline pipelines, highlighting that AtlasPatch matches or exceeds their segmentation quality. The segmentation complexity–performance trade-off, plotting F1-score against segmentation runtime (on a random set of 100 WSIs), shows AtlasPatch achieves high performance with substantially lower wall-clock time than tile-wise detectors and heuristic pipelines, underscoring its suitability for large-scale WSI preprocessing.

‎atlas_patch/__init__.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2,5 +2,5 @@
22

33
from . import core, services
44

5-
__version__ = "1.0.0"
5+
__version__ = "1.0.0.post3"
66
__all__ = ["core", "services", "__version__"]

‎docs/index.html‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -47,7 +47,7 @@ <h2 class="abstract-title">Abstract</h2>
4747
heuristic thresholding for tissue detection, or adopt AI-based approaches trained on limited-diversity data that operate at the patch level,
4848
incurring substantial computational complexity. We present AtlasPatch, an efficient and scalable slide preprocessing framework for accurate
4949
tissue detection and high-throughput patch extraction with minimal computational overhead. AtlasPatch’s tissue detection module is trained
50-
on a heterogeneous and semi-manually annotated dataset of $\sim$35,000 WSI thumbnails, using efficient fine-tuning of the Segment Anything2
50+
on a heterogeneous and semi-manually annotated dataset of ~35,000 WSI thumbnails, using efficient fine-tuning of the Segment Anything2
5151
model. The tool extrapolates tissue masks from thumbnails to full-resolution slides to extract patch coordinates at user-specified magnifications,
5252
with options to stream patches directly into commonly used image encoders for embedding generation or export patch images for storage, all efficiently
5353
parallelized across CPUs and GPUs to maximize throughput. We assess AtlasPatch across segmentation accuracy, computational complexity, and downstream

‎pyproject.toml‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -4,13 +4,13 @@ build-backend = "setuptools.build_meta"
44

55
[project]
66
name = "atlas-patch"
7-
version = "1.0.0"
7+
version = "1.0.0.post3"
88
description = "A Python package for processing and handling whole slide images"
99
readme = "README.md"
1010
requires-python = ">=3.10"
1111
license = {text = "CC-BY-NC-SA-4.0"}
1212
authors = [
13-
{name = "Yousef Kotp", email = "yousefkotp@outlook.com"},
13+
{name = "Yousef Kotp"},
1414
{name = "Omar Metwally"},
1515
{name = "Ahmed Alagha"},
1616
]

0 commit comments

Comments
 (0)