Fixing some infinite slope bug

Author: Corentin

.gitignore

@@ -164,4 +164,5 @@ pid
 *.jpg
 *.csv
 *.png
-*.tif
+*.tif
+debug_data/

.vscode/launch.json

@@ -0,0 +1,16 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Python: Module",
+            "type": "python",
+            "request": "launch",
+            "module": "myoquant",
+            "justMyCode": true,
+            "args": ["he-analysis", "debug_data/tritc_16.tif", "--stardist-path", "debug_data/dapi_16_labels.tif", "--cellpose-path", "debug_data/tritc_16_cp_masks.tif"],
+        }
+    ]
+}

README.md

@@ -1,4 +1,4 @@
-![Twitter Follow](https://img.shields.io/twitter/follow/corentinm_py?style=social) ![Demo Version](https://img.shields.io/badge/Demo-https%3A%2F%2Flbgi.fr%2FMyoQuant%2F-9cf) ![PyPi](https://img.shields.io/badge/PyPi-https%3A%2F%2Fpypi.org%2Fproject%2Fmyoquant%2F-blueviolet) ![Pypi verison](https://img.shields.io/pypi/v/myoquant) ![PyPi Python Version](https://img.shields.io/pypi/pyversions/myoquant) ![PyPi Format](https://img.shields.io/pypi/format/myoquant) ![GitHub last commit](https://img.shields.io/github/last-commit/lambda-science/MyoQuant) ![GitHub](https://img.shields.io/github/license/lambda-science/MyoQuant) 
+![Twitter Follow](https://img.shields.io/twitter/follow/corentinm_py?style=social) ![Demo Version](https://img.shields.io/badge/Demo-https%3A%2F%2Flbgi.fr%2FMyoQuant%2F-9cf) ![PyPi](https://img.shields.io/badge/PyPi-https%3A%2F%2Fpypi.org%2Fproject%2Fmyoquant%2F-blueviolet) ![Pypi verison](https://img.shields.io/pypi/v/myoquant) ![PyPi Python Version](https://img.shields.io/pypi/pyversions/myoquant) ![PyPi Format](https://img.shields.io/pypi/format/myoquant) ![GitHub last commit](https://img.shields.io/github/last-commit/lambda-science/MyoQuant) ![GitHub](https://img.shields.io/github/license/lambda-science/MyoQuant)
 
 # MyoQuant🔬: a tool to automatically quantify pathological features in muscle fiber histology images
 
@@ -7,16 +7,17 @@
 </p>
 
 MyoQuant🔬 is a command-line tool to automatically quantify pathological features in muscle fiber histology images.  
-It is built using CellPose, Stardist, custom neural-network models and image analysis techniques to automatically analyze myopathy histology images. Currently MyoQuant is capable of quantifying centralization of nuclei in muscle fiber with HE staining and anomaly in the mitochondria distribution in muscle fibers with SDH staining.  
+It is built using CellPose, Stardist, custom neural-network models and image analysis techniques to automatically analyze myopathy histology images. Currently MyoQuant is capable of quantifying centralization of nuclei in muscle fiber with HE staining and anomaly in the mitochondria distribution in muscle fibers with SDH staining.
 
-An online demo with a web interface is available at [https://lbgi.fr/MyoQuant/](https://lbgi.fr/MyoQuant/). This project is free and open-source under the AGPL license, feel free to fork and contribute to the development. 
+An online demo with a web interface is available at [https://lbgi.fr/MyoQuant/](https://lbgi.fr/MyoQuant/). This project is free and open-source under the AGPL license, feel free to fork and contribute to the development.
 
-#### *Warning: This tool is still in early phases and active development.*
+#### _Warning: This tool is still in early phases and active development._
 
 ## How to install
 
 ### Installing from PyPi (Preferred)
-**MyoQuant package is officially available on PyPi (pip) repository. [https://pypi.org/project/myoquant/](https://pypi.org/project/myoquant/) ![Pypi verison](https://img.shields.io/pypi/v/myoquant)** 
+
+**MyoQuant package is officially available on PyPi (pip) repository. [https://pypi.org/project/myoquant/](https://pypi.org/project/myoquant/) ![Pypi verison](https://img.shields.io/pypi/v/myoquant)**
 
 Using pip, you can simply install MyoQuant in a python environment with a simple: `pip install myoquant`
 
@@ -42,10 +43,12 @@ Then you can perform SDH or HE analysis. You can use the command `myoquant --hel
 _If you're running into an issue such as `myoquant: command not found` please check if you activated your virtual environment with the package installed. And also you can try to run it with the full command: `python -m myoquant sdh-analysis --help`_
 
 ## Contact
-Creator and Maintainer: [**Corentin Meyer**, 3rd year PhD Student in the CSTB Team, ICube — CNRS — Unistra](https://cmeyer.fr)  <[email protected]>
+
+Creator and Maintainer: [**Corentin Meyer**, 3rd year PhD Student in the CSTB Team, ICube — CNRS — Unistra](https://cmeyer.fr) <[email protected]>
 
 ## Citing MyoQuant🔬
-[placeholder]  
+
+[placeholder]
 
 ## Examples
 
@@ -62,9 +65,15 @@ For SDH Staining analysis, you can download this sample image: [HERE](https://ww
 
 ## Advanced information
 
+### Model path and manual download
+
 For the SDH Analysis our custom model will be downloaded and placed inside the myoquant package directory. You can also download it manually here: [https://lbgi.fr/~meyer/SDH_models/model.h5](https://lbgi.fr/~meyer/SDH_models/model.h5) and then you can place it in the directory of your choice and provide the path to the model file using:  
 `myoquant sdh-analysis IMAGE_PATH --model_path /path/to/model.h5`
 
+### HuggingFace🤗 repositories for Data and Model
+
+In a effort to push for open-science, MyoQuant [SDH dataset](https://huggingface.co/datasets/corentinm7/MyoQuant-SDH-Data) and [model](https://huggingface.co/corentinm7/MyoQuant-SDH-Model) and availiable on HuggingFace🤗
+
 ## Partners
 
 <p align="center">

myoquant/HE_analysis.py

@@ -48,6 +48,12 @@ def single_cell_analysis(
     for _, value in df_nuc_single.iterrows():
         n_nuc += 1
         # Extend line and find closest point
+
+        # Handling of the case where the nucleus is at the exact center of the fiber
+        if x_fiber == value[3] and y_fiber == value[2]:
+            n_nuc_intern += 1
+            continue
+
         m, b = line_equation(x_fiber, y_fiber, value[3], value[2])
 
         intersections_lst = calculate_intersection(

myoquant/draw_line.py

@@ -1,6 +1,17 @@
+import math
+
+
 def line_equation(x1, y1, x2, y2):
-    m = (y2 - y1) / (x2 - x1)
+    # Poor man's handling of the case where the equation is infinite
+    if x2 - x1 == 0 and y2 > y1:
+        m = 9999
+    elif x2 - x1 == 0 and y1 > y2:
+        m = -9999
+    else:
+        m = (y2 - y1) / (x2 - x1)
     b = y1 - m * x1
+    if math.isinf(m) or math.isinf(b):
+        raise ValueError("Line equation is infinite")
     return m, b
 
 
@@ -16,6 +27,8 @@ def calculate_intersection(m, b, image_dim=(256, 256)):
         intersect = (i - b) / m
         if intersect >= 0 and intersect < image_dim[1]:
             results.append((intersect, i))
+    if results == []:
+        raise ValueError("No intersection found")
     return results
 
 

pyproject.toml

@@ -1,7 +1,7 @@
 [tool.poetry]
 name = "myoquant"
-version = "0.1.4"
-description = "Command line interface (CLI) for MyoQuant, my histology image quantification tool."
+version = "0.1.6"
+description = "MyoQuant🔬: a tool to automatically quantify pathological features in muscle fiber histology images."
 authors = ["Corentin Meyer <[email protected]>"]
 maintainers = ["Corentin Meyer <[email protected]>"]
 license = "AGPL-3.0-or-later"