biomedisa 24.8.8__tar.gz → 24.8.10__tar.gz

{biomedisa-24.8.8 → biomedisa-24.8.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: biomedisa
-Version: 24.8.8
+Version: 24.8.10
 Summary: Segmentation of 3D volumetric image data
 Author: Philipp Lösel
 Author-email: philipp.loesel@anu.edu.au
@@ -10,7 +10,7 @@ Project-URL: GitHub, https://github.com/biomedisa/biomedisa
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: European Union Public Licence 1.2 (EUPL 1.2)
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.10
+Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 
@@ -23,7 +23,6 @@ License-File: LICENSE
 - [Installation (browser based)](#installation-browser-based)
 - [Download Data](#download-data)
 - [Revisions](#revisions)
-- [Quickstart](#quickstart)
 - [Smart Interpolation](#smart-interpolation)
 - [Deep Learning](#deep-learning)
 - [Mesh Generator](#mesh-generator)
@@ -37,41 +36,26 @@ License-File: LICENSE
 Biomedisa (https://biomedisa.info) is a free and easy-to-use open-source application for segmenting large 3D volumetric images such as CT and MRI scans, developed at [The Australian National University CTLab](https://ctlab.anu.edu.au/). Biomedisa's smart interpolation of sparsely pre-segmented slices enables accurate semi-automated segmentation by considering the complete underlying image data. Additionally, Biomedisa enables deep learning for fully automated segmentation across similar samples and structures. It is compatible with segmentation tools like Amira/Avizo, ImageJ/Fiji, and 3D Slicer. If you are using Biomedisa or the data for your research please cite: Lösel, P.D. et al. [Introducing Biomedisa as an open-source online platform for biomedical image segmentation.](https://www.nature.com/articles/s41467-020-19303-w) *Nat. Commun.* **11**, 5577 (2020).
 
 ## Hardware Requirements
-+ One or more NVIDIA GPUs.
++ One or more NVIDIA GPUs
 
 ## Installation (command-line based)
 + [Ubuntu 22/24 + Smart Interpolation](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu_interpolation_cli.md)
 + [Ubuntu 22/24 + Deep Learning](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu_deeplearning_cli.md)
 + [Ubuntu 22/24 + Smart Interpolation + Deep Learning](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu_cli.md)
-+ [Windows 10/11 + Smart Interpolation + Deep Learning](https://github.com/biomedisa/biomedisa/blob/master/README/windows10_cuda_gpu_cli.md)
-+ [Windows (WSL) + Smart Interpolation + Deep Learning](https://github.com/biomedisa/biomedisa/blob/master/README/windows_wsl.md)
++ [Windows 10/11 + Smart Interpolation + Deep Learning](https://github.com/biomedisa/biomedisa/blob/master/README/windows_wsl.md)
 
 ## Installation (3D Slicer extension)
-+ [Ubuntu 22.04 + Smart Interpolation + Deep Learning](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu2204_cuda11.8_gpu_slicer.md)
-+ [Windows 10/11 + Smart Interpolation](https://github.com/biomedisa/biomedisa/blob/master/README/windows10_cuda_gpu_slicer.md)
++ [Ubuntu 22/24](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu_slicer.md)
++ [Windows 10/11](https://github.com/biomedisa/biomedisa/blob/master/README/windows_slicer.md)
 
 ## Installation (browser based)
-+ [Ubuntu 22.04](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu2204_cuda11.8.md)
++ [Ubuntu 22/24](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu_browser.md)
 
 ## Download Data
 + Download test data from our [gallery](https://biomedisa.info/gallery/)
 
 ## Revisions
-24.7.1
-+ 3D Slicer extension
-+ Prediction of large data block by block
-
-24.5.22
-+ Pip is the preferred installation method
-+ Commands, module names and imports have been changed to conform to the Pip standard
-+ For versions <=23.9.1 please check [README](https://github.com/biomedisa/biomedisa/blob/master/README/deprecated/README_2023.09.1.md)
-
-## Quickstart
-Install the Biomedisa package from the [Python Package Index](https://pypi.org/project/biomedisa/):
-```
-python -m pip install -U biomedisa
-```
-For smart interpolation and deep Learning modules, follow the installation instructions above.
++ [Revisions](https://github.com/biomedisa/biomedisa/blob/master/README/revisions.md)
 
 ## Smart Interpolation
 + [Parameters and Examples](https://github.com/biomedisa/biomedisa/blob/master/README/smart_interpolation.md)

{biomedisa-24.8.8 → biomedisa-24.8.10}/README.md

@@ -7,7 +7,6 @@
 - [Installation (browser based)](#installation-browser-based)
 - [Download Data](#download-data)
 - [Revisions](#revisions)
-- [Quickstart](#quickstart)
 - [Smart Interpolation](#smart-interpolation)
 - [Deep Learning](#deep-learning)
 - [Mesh Generator](#mesh-generator)
@@ -21,41 +20,26 @@
 Biomedisa (https://biomedisa.info) is a free and easy-to-use open-source application for segmenting large 3D volumetric images such as CT and MRI scans, developed at [The Australian National University CTLab](https://ctlab.anu.edu.au/). Biomedisa's smart interpolation of sparsely pre-segmented slices enables accurate semi-automated segmentation by considering the complete underlying image data. Additionally, Biomedisa enables deep learning for fully automated segmentation across similar samples and structures. It is compatible with segmentation tools like Amira/Avizo, ImageJ/Fiji, and 3D Slicer. If you are using Biomedisa or the data for your research please cite: Lösel, P.D. et al. [Introducing Biomedisa as an open-source online platform for biomedical image segmentation.](https://www.nature.com/articles/s41467-020-19303-w) *Nat. Commun.* **11**, 5577 (2020).
 
 ## Hardware Requirements
-+ One or more NVIDIA GPUs.
++ One or more NVIDIA GPUs
 
 ## Installation (command-line based)
 + [Ubuntu 22/24 + Smart Interpolation](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu_interpolation_cli.md)
 + [Ubuntu 22/24 + Deep Learning](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu_deeplearning_cli.md)
 + [Ubuntu 22/24 + Smart Interpolation + Deep Learning](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu_cli.md)
-+ [Windows 10/11 + Smart Interpolation + Deep Learning](https://github.com/biomedisa/biomedisa/blob/master/README/windows10_cuda_gpu_cli.md)
-+ [Windows (WSL) + Smart Interpolation + Deep Learning](https://github.com/biomedisa/biomedisa/blob/master/README/windows_wsl.md)
++ [Windows 10/11 + Smart Interpolation + Deep Learning](https://github.com/biomedisa/biomedisa/blob/master/README/windows_wsl.md)
 
 ## Installation (3D Slicer extension)
-+ [Ubuntu 22.04 + Smart Interpolation + Deep Learning](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu2204_cuda11.8_gpu_slicer.md)
-+ [Windows 10/11 + Smart Interpolation](https://github.com/biomedisa/biomedisa/blob/master/README/windows10_cuda_gpu_slicer.md)
++ [Ubuntu 22/24](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu_slicer.md)
++ [Windows 10/11](https://github.com/biomedisa/biomedisa/blob/master/README/windows_slicer.md)
 
 ## Installation (browser based)
-+ [Ubuntu 22.04](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu2204_cuda11.8.md)
++ [Ubuntu 22/24](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu_browser.md)
 
 ## Download Data
 + Download test data from our [gallery](https://biomedisa.info/gallery/)
 
 ## Revisions
-24.7.1
-+ 3D Slicer extension
-+ Prediction of large data block by block
-
-24.5.22
-+ Pip is the preferred installation method
-+ Commands, module names and imports have been changed to conform to the Pip standard
-+ For versions <=23.9.1 please check [README](https://github.com/biomedisa/biomedisa/blob/master/README/deprecated/README_2023.09.1.md)
-
-## Quickstart
-Install the Biomedisa package from the [Python Package Index](https://pypi.org/project/biomedisa/):
-```
-python -m pip install -U biomedisa
-```
-For smart interpolation and deep Learning modules, follow the installation instructions above.
++ [Revisions](https://github.com/biomedisa/biomedisa/blob/master/README/revisions.md)
 
 ## Smart Interpolation
 + [Parameters and Examples](https://github.com/biomedisa/biomedisa/blob/master/README/smart_interpolation.md)

{biomedisa-24.8.8 → biomedisa-24.8.10}/pyproject.toml

@@ -4,13 +4,13 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "biomedisa"
-version = "24.8.8"
+version = "24.8.10"
 authors = [
   { name="Philipp Lösel"}, {email="philipp.loesel@anu.edu.au" },
 ]
 description = "Segmentation of 3D volumetric image data"
 readme = "README.md"
-requires-python = ">=3.10"
+requires-python = ">=3.9"
 classifiers = [
     "Programming Language :: Python :: 3",
     "License :: OSI Approved :: European Union Public Licence 1.2 (EUPL 1.2)",

{biomedisa-24.8.8 → biomedisa-24.8.10}/src/biomedisa/deeplearning.py

@@ -95,6 +95,10 @@ def deep_learning(img_data, label_data=None, val_img_data=None, val_label_data=N
     # normalization
     bm.normalize = 1 if bm.normalization else 0
 
+    # patch normalization deactivates normalization of entire volume
+    if bm.patch_normalization:
+        bm.normalize = 0
+
     # use patch normalization instead of normalizing the entire volume
     if not bm.scaling:
         bm.normalize = 0

{biomedisa-24.8.8 → biomedisa-24.8.10}/src/biomedisa/features/DataGenerator.py

@@ -291,7 +291,7 @@ class DataGenerator(tf.keras.utils.Sequence):
 
                 # patch normalization
                 if self.patch_normalization:
-                    tmp_X = tmp_X.copy()
+                    tmp_X = tmp_X.copy().astype(np.float32)
                     for c in range(self.n_channels):
                         tmp_X[:,:,:,c] -= np.mean(tmp_X[:,:,:,c])
                         tmp_X[:,:,:,c] /= max(np.std(tmp_X[:,:,:,c]), 1e-6)

{biomedisa-24.8.8 → biomedisa-24.8.10}/src/biomedisa/features/crop_helper.py

@@ -153,19 +153,26 @@ def load_cropping_training_data(normalize, img_list, label_list, x_scale, y_scal
             img = np.append(img_z,img_y,axis=0)
             img = np.append(img,img_x,axis=0)
 
-            # normalize image data
+            # scale image data
             for c in range(channels):
                 img[:,:,:,c] -= np.amin(img[:,:,:,c])
                 img[:,:,:,c] /= np.amax(img[:,:,:,c])
-                if normalization_parameters is None:
-                    normalization_parameters = np.zeros((2,channels))
-                    normalization_parameters[0,c] = np.mean(img[:,:,:,c])
-                    normalization_parameters[1,c] = np.std(img[:,:,:,c])
-                elif normalize:
+
+            # normalize first validation image
+            if normalize and np.any(normalization_parameters):
+                for c in range(channels):
                     mean, std = np.mean(img[:,:,:,c]), np.std(img[:,:,:,c])
                     img[:,:,:,c] = (img[:,:,:,c] - mean) / std
                     img[:,:,:,c] = img[:,:,:,c] * normalization_parameters[1,c] + normalization_parameters[0,c]
 
+            # get normalization parameters from first image
+            if normalization_parameters is None:
+                normalization_parameters = np.zeros((2,channels))
+                if normalize:
+                    for c in range(channels):
+                        normalization_parameters[0,c] = np.mean(img[:,:,:,c])
+                        normalization_parameters[1,c] = np.std(img[:,:,:,c])
+
             # loop over list of images
             if any(img_list) or type(img_in) is list:
                 number_of_images = len(img_names) if any(img_list) else len(img_in)

{biomedisa-24.8.8 → biomedisa-24.8.10}/src/biomedisa/features/keras_helper.py

@@ -400,12 +400,6 @@ def load_training_data(bm, img_list, label_list, channels, img_in=None, label_in
                 label = label_in
                 label_names = ['label_1']
             label_dim = label.shape
-            # no-scaling for list of images needs negative values as it encodes padded areas as -1
-            label_dtype = label.dtype
-            if label_dtype==np.uint8:
-                label_dtype = np.int16
-            elif label_dtype in [np.uint16, np.uint32]:
-                label_dtype = np.int32
             label = set_labels_to_zero(label, bm.only, bm.ignore)
             if any([bm.x_range, bm.y_range, bm.z_range]):
                 if len(label_names)>1:
@@ -461,28 +455,44 @@ def load_training_data(bm, img_list, label_list, channels, img_in=None, label_in
             if any([bm.x_range, bm.y_range, bm.z_range]) or bm.crop_data:
                 img = img[argmin_z:argmax_z,argmin_y:argmax_y,argmin_x:argmax_x].copy()
 
-            # scale/resize image data
-            img = img.astype(np.float32)
+            # resize image data
             if bm.scaling:
+                img = img.astype(np.float32)
                 img = img_resize(img, bm.z_scale, bm.y_scale, bm.x_scale)
 
-            # normalize image data
-            for c in range(channels):
-                img[:,:,:,c] -= np.amin(img[:,:,:,c])
-                img[:,:,:,c] /= np.amax(img[:,:,:,c])
-                if normalization_parameters is None:
-                    normalization_parameters = np.zeros((2,channels))
-                    normalization_parameters[0,c] = np.mean(img[:,:,:,c])
-                    normalization_parameters[1,c] = np.std(img[:,:,:,c])
-                elif bm.normalize:
+            # scale data to the range from 0 to 1
+            if not bm.patch_normalization:
+                img = img.astype(np.float32)
+                for c in range(channels):
+                    img[:,:,:,c] -= np.amin(img[:,:,:,c])
+                    img[:,:,:,c] /= np.amax(img[:,:,:,c])
+
+            # normalize first validation image
+            if bm.normalize and np.any(normalization_parameters):
+                img = img.astype(np.float32)
+                for c in range(channels):
                     mean, std = np.mean(img[:,:,:,c]), np.std(img[:,:,:,c])
                     img[:,:,:,c] = (img[:,:,:,c] - mean) / std
                     img[:,:,:,c] = img[:,:,:,c] * normalization_parameters[1,c] + normalization_parameters[0,c]
 
+            # get normalization parameters from first image
+            if normalization_parameters is None:
+                normalization_parameters = np.zeros((2,channels))
+                if bm.normalize:
+                    for c in range(channels):
+                        normalization_parameters[0,c] = np.mean(img[:,:,:,c])
+                        normalization_parameters[1,c] = np.std(img[:,:,:,c])
+
             # pad data
             if not bm.scaling:
                 img_data_list = [img]
                 label_data_list = [label]
+                # no-scaling for list of images needs negative values as it encodes padded areas as -1
+                label_dtype = label.dtype
+                if label_dtype==np.uint8:
+                    label_dtype = np.int16
+                elif label_dtype in [np.uint16, np.uint32]:
+                    label_dtype = np.int32
 
             # loop over list of images
             if any(img_list) or type(img_in) is list:
@@ -530,13 +540,17 @@ def load_training_data(bm, img_list, label_list, channels, img_in=None, label_in
                         raise InputError()
                     if bm.crop_data:
                         a = np.copy(a[argmin_z:argmax_z,argmin_y:argmax_y,argmin_x:argmax_x], order='C')
-                    a = a.astype(np.float32)
                     if bm.scaling:
+                        a = a.astype(np.float32)
                         a = img_resize(a, bm.z_scale, bm.y_scale, bm.x_scale)
-                    for c in range(channels):
-                        a[:,:,:,c] -= np.amin(a[:,:,:,c])
-                        a[:,:,:,c] /= np.amax(a[:,:,:,c])
-                        if bm.normalize:
+                    if not bm.patch_normalization:
+                        a = a.astype(np.float32)
+                        for c in range(channels):
+                            a[:,:,:,c] -= np.amin(a[:,:,:,c])
+                            a[:,:,:,c] /= np.amax(a[:,:,:,c])
+                    if bm.normalize:
+                        a = a.astype(np.float32)
+                        for c in range(channels):
                             mean, std = np.mean(a[:,:,:,c]), np.std(a[:,:,:,c])
                             a[:,:,:,c] = (a[:,:,:,c] - mean) / std
                             a[:,:,:,c] = a[:,:,:,c] * normalization_parameters[1,c] + normalization_parameters[0,c]

{biomedisa-24.8.8 → biomedisa-24.8.10}/src/biomedisa.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: biomedisa
-Version: 24.8.8
+Version: 24.8.10
 Summary: Segmentation of 3D volumetric image data
 Author: Philipp Lösel
 Author-email: philipp.loesel@anu.edu.au
@@ -10,7 +10,7 @@ Project-URL: GitHub, https://github.com/biomedisa/biomedisa
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: European Union Public Licence 1.2 (EUPL 1.2)
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.10
+Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 
@@ -23,7 +23,6 @@ License-File: LICENSE
 - [Installation (browser based)](#installation-browser-based)
 - [Download Data](#download-data)
 - [Revisions](#revisions)
-- [Quickstart](#quickstart)
 - [Smart Interpolation](#smart-interpolation)
 - [Deep Learning](#deep-learning)
 - [Mesh Generator](#mesh-generator)
@@ -37,41 +36,26 @@ License-File: LICENSE
 Biomedisa (https://biomedisa.info) is a free and easy-to-use open-source application for segmenting large 3D volumetric images such as CT and MRI scans, developed at [The Australian National University CTLab](https://ctlab.anu.edu.au/). Biomedisa's smart interpolation of sparsely pre-segmented slices enables accurate semi-automated segmentation by considering the complete underlying image data. Additionally, Biomedisa enables deep learning for fully automated segmentation across similar samples and structures. It is compatible with segmentation tools like Amira/Avizo, ImageJ/Fiji, and 3D Slicer. If you are using Biomedisa or the data for your research please cite: Lösel, P.D. et al. [Introducing Biomedisa as an open-source online platform for biomedical image segmentation.](https://www.nature.com/articles/s41467-020-19303-w) *Nat. Commun.* **11**, 5577 (2020).
 
 ## Hardware Requirements
-+ One or more NVIDIA GPUs.
++ One or more NVIDIA GPUs
 
 ## Installation (command-line based)
 + [Ubuntu 22/24 + Smart Interpolation](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu_interpolation_cli.md)
 + [Ubuntu 22/24 + Deep Learning](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu_deeplearning_cli.md)
 + [Ubuntu 22/24 + Smart Interpolation + Deep Learning](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu_cli.md)
-+ [Windows 10/11 + Smart Interpolation + Deep Learning](https://github.com/biomedisa/biomedisa/blob/master/README/windows10_cuda_gpu_cli.md)
-+ [Windows (WSL) + Smart Interpolation + Deep Learning](https://github.com/biomedisa/biomedisa/blob/master/README/windows_wsl.md)
++ [Windows 10/11 + Smart Interpolation + Deep Learning](https://github.com/biomedisa/biomedisa/blob/master/README/windows_wsl.md)
 
 ## Installation (3D Slicer extension)
-+ [Ubuntu 22.04 + Smart Interpolation + Deep Learning](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu2204_cuda11.8_gpu_slicer.md)
-+ [Windows 10/11 + Smart Interpolation](https://github.com/biomedisa/biomedisa/blob/master/README/windows10_cuda_gpu_slicer.md)
++ [Ubuntu 22/24](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu_slicer.md)
++ [Windows 10/11](https://github.com/biomedisa/biomedisa/blob/master/README/windows_slicer.md)
 
 ## Installation (browser based)
-+ [Ubuntu 22.04](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu2204_cuda11.8.md)
++ [Ubuntu 22/24](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu_browser.md)
 
 ## Download Data
 + Download test data from our [gallery](https://biomedisa.info/gallery/)
 
 ## Revisions
-24.7.1
-+ 3D Slicer extension
-+ Prediction of large data block by block
-
-24.5.22
-+ Pip is the preferred installation method
-+ Commands, module names and imports have been changed to conform to the Pip standard
-+ For versions <=23.9.1 please check [README](https://github.com/biomedisa/biomedisa/blob/master/README/deprecated/README_2023.09.1.md)
-
-## Quickstart
-Install the Biomedisa package from the [Python Package Index](https://pypi.org/project/biomedisa/):
-```
-python -m pip install -U biomedisa
-```
-For smart interpolation and deep Learning modules, follow the installation instructions above.
++ [Revisions](https://github.com/biomedisa/biomedisa/blob/master/README/revisions.md)
 
 ## Smart Interpolation
 + [Parameters and Examples](https://github.com/biomedisa/biomedisa/blob/master/README/smart_interpolation.md)