-
Notifications
You must be signed in to change notification settings - Fork 10
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
feat: add reading skew from czi files #1205
base: develop
Are you sure you want to change the base?
Conversation
Reviewer's Guide by SourceryThis pull request adds functionality to read and handle skew information from CZI files, and incorporates this information into the image processing pipeline. The changes primarily affect the image reading process, data structures, and how the image data is passed to layers in the visualization. Sequence diagram for reading and applying shear from CZI filessequenceDiagram
participant Reader as ImageReader
participant Metadata as Metadata
participant Image as Image
participant Layers as Layers
Reader->>Metadata: _read_shear(metadata)
Metadata->>Reader: return shear
Reader->>Image: create Image with shear
Image->>Layers: pass shear to layers
Layers->>Layers: apply shear to image layers
Updated class diagram for Image classclassDiagram
class Image {
+list[ChannelInfo | ChannelInfoFull] channel_info
+str axes_order
+Spacing shift
+np.ndarray shear
+str name
+dict metadata_dict
+np.ndarray | None shear()
}
File-Level Changes
Tips and commandsInteracting with Sourcery
Customizing Your ExperienceAccess your dashboard to:
Getting Help
|
WalkthroughThe changes include modifications to the Changes
Possibly related PRs
Poem
Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media? 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hey @Czaki - I've reviewed your changes and they look great!
Here's what I looked at during the review
- 🟢 General issues: all looks good
- 🟢 Security: all looks good
- 🟢 Testing: all looks good
- 🟢 Complexity: all looks good
- 🟢 Documentation: all looks good
Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.
@@ -85,14 +86,15 @@ def project_to_layers(project_info: typing.Union[ProjectTuple, MaskProjectTuple] | |||
res_layers = [] | |||
if project_info.image is not None and not isinstance(project_info.image, str): | |||
scale = project_info.image.normalized_scaling() |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
issue (code-quality): Extract code out into function (extract-method
)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Actionable comments posted: 4
🧹 Outside diff range and nitpick comments (3)
package/PartSegImage/image.py (1)
Line range hint
227-247
: LGTM! Consider adding parameter documentation.The addition of the
shear
parameter to the__init__
method is well-implemented. The new parameter is correctly added to the method signature and assigned to the_shear
instance variable.Consider adding a docstring or comment to explain the purpose and expected type of the
shear
parameter for better code documentation.package/PartSegImage/image_reader.py (2)
415-416
: Adjuststacklevel
inwarnings.warn
for correct warning location.Using
stacklevel=1
inwarnings.warn
may not display the warning at the expected location in the call stack. Settingstacklevel=2
will show the warning as originating from the caller of_read_skew
, providing clearer context.Apply this diff to adjust the
stacklevel
:if not shear_value.startswith("Skew"): - warnings.warn(f"Unknown shear value {shear_value}", stacklevel=1) + warnings.warn(f"Unknown shear value {shear_value}", stacklevel=2) continue
395-421
: Add docstrings to new methods for better documentation.Including docstrings for the
_read_shear
and_read_skew
methods will improve code readability and maintainability by explaining their purpose and usage.Apply this diff to add docstrings:
def _read_shear(self, metadata: dict): + """ + Compute the shear transformation matrix based on skew values extracted from metadata. + + Args: + metadata (dict): The metadata dictionary containing image information. + + Returns: + numpy.ndarray: A shear transformation matrix. + """ skew = self._read_skew(metadata) shear = np.diag([1.0] * len(skew)) for i, val in enumerate(skew): if val == 0: continue + if i + 1 < len(skew): shear[i, i + 1] = np.tan(np.radians(val)) return shear @staticmethod def _read_skew(metadata: dict): + """ + Extract skew values from the metadata for each dimension (T, Z, Y, X). + + Args: + metadata (dict): The metadata dictionary containing image information. + + Returns: + List[float]: A list of skew angles for each dimension. + """ dimensions = metadata["ImageDocument"]["Metadata"]["Information"]["Image"]["Dimensions"] res = [0.0] * 4 for i, dim in enumerate("TZYX"): if dim not in dimensions: continue if f"{dim}AxisShear" not in dimensions[dim]: continue shear_value = dimensions[dim][f"{dim}AxisShear"] if not shear_value.startswith("Skew"): warnings.warn(f"Unknown shear value {shear_value}", stacklevel=2) continue + try: res[i] = float(shear_value[4:]) + except ValueError: + warnings.warn(f"Invalid shear value '{shear_value}' cannot be converted to float.", stacklevel=2) + res[i] = 0.0 + continue return res
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
📒 Files selected for processing (3)
- package/PartSegCore/napari_plugins/loader.py (5 hunks)
- package/PartSegImage/image.py (3 hunks)
- package/PartSegImage/image_reader.py (2 hunks)
🧰 Additional context used
🔇 Additional comments (9)
package/PartSegImage/image.py (2)
374-377
: LGTM! Well-implemented property.The
shear
property is correctly implemented as a read-only property, providing access to the_shear
instance variable. The return type annotation is accurate and includes the possibility of returningNone
.
Line range hint
227-377
: Verify the usage of theshear
attribute in the codebase.The
shear
attribute has been added to theImage
class, but it's not yet used within the class itself. To ensure this addition is fully utilized:
- Check if there are any methods in this class that should be updated to use the
shear
attribute.- Verify if any subclasses or external code need to be updated to take advantage of this new attribute.
To help verify the usage of the
shear
attribute, you can run the following script:This script will help identify any current usage of 'shear' and places where the
Image
class is used or extended, which might need updates to incorporate the newshear
attribute.✅ Verification successful
Shear Attribute Usage Verified
The
shear
attribute added to theImage
class is actively used in other parts of the codebase, includingloader.py
andimage_reader.py
. This confirms that the addition is utilized as intended.
- Files using
shear
:
package/PartSegCore/napari_plugins/loader.py
package/PartSegImage/image_reader.py
🏁 Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash # Description: Check for potential usage or updates needed for the new 'shear' attribute # Search for 'shear' usage in Python files echo "Searching for 'shear' usage in Python files:" rg --type python 'shear' -C 3 # Search for 'Image' class usage echo "\nSearching for 'Image' class usage:" rg --type python 'class\s+\w+\(Image\)' -C 3 # Search for 'Image' instantiation echo "\nSearching for 'Image' instantiation:" rg --type python 'Image\(' -C 3Length of output: 490
Script:
#!/bin/bash # Description: Check for potential usage or updates needed for the new 'shear' attribute # Search for 'shear' usage in Python files echo "Searching for 'shear' usage in Python files:" rg --type py 'shear' -C 3 # Search for 'Image' class usage echo "\nSearching for 'Image' class usage:" rg --type py 'class\s+\w+\(Image\)' -C 3 # Search for 'Image' instantiation echo "\nSearching for 'Image' instantiation:" rg --type py 'Image\(' -C 3Length of output: 103085
package/PartSegCore/napari_plugins/loader.py (5)
60-60
: Verify thatshear
is accepted in labels layer propertiesYou've added
'shear': shear
to the layer properties for a labels layer. Ensure that the labels layer in napari accepts theshear
parameter and that it behaves as expected. Not all parameters are supported across different layer types.
74-74
: Confirmshear
parameter compatibility with image layersIncluding
'shear': shear
in the properties of image layers is a significant change. Make sure that the image layer in napari supports theshear
parameter and that it correctly applies the shear transformation to the displayed image.
97-97
: Checkshear
usage in ROI labels layerThe addition of
'shear': shear
to the ROI labels layer properties may affect how ROIs are rendered. Verify that including theshear
parameter is appropriate for labels layers representing ROIs and that it doesn't introduce any rendering issues.
110-110
: Ensureshear
is correctly applied to alternative ROI layersFor alternative ROIs, adding the
shear
parameter should be done cautiously. Confirm that each alternative ROI layer correctly interprets theshear
parameter and that it doesn't cause any unintended side effects.
121-121
: Verifyshear
parameter in Mask layer propertiesIncluding
'shear': shear
in the Mask layer properties is a meaningful update. Ensure that the Mask layer supports theshear
parameter and that it functions as intended without causing any errors.package/PartSegImage/image_reader.py (2)
4-4
: Importing 'warnings' module is appropriate.The 'warnings' module is required for issuing warnings in the
_read_skew
method.
392-392
: Adding 'shear' parameter to 'Image' object is appropriate.Including the 'shear' parameter enhances the
CziImageReader
to account for shear transformations in images.
@@ -51,13 +51,13 @@ def add_color(image: Image, idx: int) -> dict: # noqa: ARG001 | |||
return {} | |||
|
|||
|
|||
def _image_to_layers(project_info, scale, translate): | |||
def _image_to_layers(project_info, scale, translate, shear): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Ensure 'shear' parameter is compatible with all targeted napari versions
The addition of the shear
parameter to the _image_to_layers
function enhances functionality. However, it's important to verify that the shear
parameter is supported in all versions of napari that your application targets. Using unsupported parameters could lead to runtime errors in older versions of napari.
Consider adding a version check, similar to the one used for the add_color
function, to conditionally include the shear
parameter based on the napari version.
@@ -85,14 +86,15 @@ def project_to_layers(project_info: typing.Union[ProjectTuple, MaskProjectTuple] | |||
res_layers = [] | |||
if project_info.image is not None and not isinstance(project_info.image, str): | |||
scale = project_info.image.normalized_scaling() | |||
shear = project_info.image.shear |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Handle potential None
values for shear
When assigning shear = project_info.image.shear
, there's a possibility that project_info.image.shear
might be None
or not defined, especially if the image doesn't have shear information. Passing None
to layer properties could cause unexpected behavior or errors.
Consider adding a check to handle None
values or provide a default shear value to ensure robust code execution.
Apply this diff to handle possible None
values:
- shear = project_info.image.shear
+ shear = project_info.image.shear if project_info.image.shear is not None else np.zeros((ndim, ndim))
Replace ndim
with the appropriate number of dimensions for your shear matrix.
Committable suggestion was skipped due to low confidence.
if not shear_value.startswith("Skew"): | ||
warnings.warn(f"Unknown shear value {shear_value}", stacklevel=1) | ||
continue | ||
res[i] = float(shear_value[4:]) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Handle potential ValueError
when converting shear value to float.
Converting shear_value[4:]
to float may raise a ValueError
if the substring cannot be converted to a number. Adding error handling will prevent the program from crashing in such cases.
Apply this diff to add a try-except block:
if not shear_value.startswith("Skew"):
warnings.warn(f"Unknown shear value {shear_value}", stacklevel=2)
continue
+try:
res[i] = float(shear_value[4:])
+except ValueError:
+ warnings.warn(f"Invalid shear value '{shear_value}' cannot be converted to float.", stacklevel=2)
+ res[i] = 0.0
continue
📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
if not shear_value.startswith("Skew"): | |
warnings.warn(f"Unknown shear value {shear_value}", stacklevel=1) | |
continue | |
res[i] = float(shear_value[4:]) | |
if not shear_value.startswith("Skew"): | |
warnings.warn(f"Unknown shear value {shear_value}", stacklevel=2) | |
continue | |
try: | |
res[i] = float(shear_value[4:]) | |
except ValueError: | |
warnings.warn(f"Invalid shear value '{shear_value}' cannot be converted to float.", stacklevel=2) | |
res[i] = 0.0 | |
continue |
def _read_shear(self, metadata: dict): | ||
skew = self._read_skew(metadata) | ||
shear = np.diag([1.0] * len(skew)) | ||
for i, val in enumerate(skew): | ||
if val == 0: | ||
continue | ||
shear[i, i + 1] = np.tan(np.radians(val)) | ||
return shear | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Potential IndexError in _read_shear
due to out-of-bounds access.
In the _read_shear
method, the loop may attempt to access shear[i, i + 1]
when i + 1
equals the size of the matrix, resulting in an IndexError. This occurs when i
reaches the last index.
Apply this diff to prevent the IndexError by adjusting the loop:
def _read_shear(self, metadata: dict):
skew = self._read_skew(metadata)
shear = np.diag([1.0] * len(skew))
- for i, val in enumerate(skew):
+ for i, val in enumerate(skew[:-1]):
if val == 0:
continue
shear[i, i + 1] = np.tan(np.radians(val))
return shear
Alternatively, add a boundary check within the loop:
def _read_shear(self, metadata: dict):
skew = self._read_skew(metadata)
shear = np.diag([1.0] * len(skew))
for i, val in enumerate(skew):
if val == 0:
continue
+ if i + 1 >= len(skew):
+ continue
shear[i, i + 1] = np.tan(np.radians(val))
return shear
📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
def _read_shear(self, metadata: dict): | |
skew = self._read_skew(metadata) | |
shear = np.diag([1.0] * len(skew)) | |
for i, val in enumerate(skew): | |
if val == 0: | |
continue | |
shear[i, i + 1] = np.tan(np.radians(val)) | |
return shear | |
def _read_shear(self, metadata: dict): | |
skew = self._read_skew(metadata) | |
shear = np.diag([1.0] * len(skew)) | |
for i, val in enumerate(skew[:-1]): | |
if val == 0: | |
continue | |
shear[i, i + 1] = np.tan(np.radians(val)) | |
return shear |
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## develop #1205 +/- ##
===========================================
- Coverage 93.15% 93.12% -0.03%
===========================================
Files 210 210
Lines 33169 33198 +29
===========================================
+ Hits 30898 30916 +18
- Misses 2271 2282 +11 ☔ View full report in Codecov by Sentry. |
Quality Gate passedIssues Measures |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Actionable comments posted: 0
🧹 Outside diff range and nitpick comments (4)
package/PartSegImage/image.py (2)
227-227
: LGTM! Consider adding docstring for the newshear
parameter.The addition of the
shear
parameter is well-implemented. It allows for optional shear transformations to be specified for the image.Consider adding a brief description of the
shear
parameter in the method's docstring to improve documentation.Also applies to: 247-247
374-377
: LGTM! Consider adding a docstring to theshear
property.The
shear
property is correctly implemented, providing read-only access to the_shear
attribute.Consider adding a brief docstring to the
shear
property to describe its purpose and return value.package/PartSegImage/image_reader.py (2)
396-404
: Add a docstring to the_read_shear
method for better documentation.Including a descriptive docstring will clarify the purpose and functionality of the
_read_shear
method, improving code maintainability.
405-422
: Add a docstring to the_read_skew
method for enhanced clarity.Providing a docstring for the
_read_skew
method will help others understand its role in extracting skew values from metadata.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
📒 Files selected for processing (3)
- package/PartSegCore/napari_plugins/loader.py (5 hunks)
- package/PartSegImage/image.py (3 hunks)
- package/PartSegImage/image_reader.py (2 hunks)
🚧 Files skipped from review as they are similar to previous changes (1)
- package/PartSegCore/napari_plugins/loader.py
🧰 Additional context used
🔇 Additional comments (2)
package/PartSegImage/image_reader.py (2)
4-4
: Importing thewarnings
module is appropriate and necessary.The addition of
import warnings
allows the code to issue warnings for unexpected shear values, enhancing error reporting.
393-393
: Inclusion of theshear
parameter enhances image metadata handling.Passing the
shear
parameter to theImage
class ensures that shear transformations are properly incorporated into the image object.
Summary by Sourcery
Introduce the ability to read shear values from CZI file metadata and apply these transformations to images, enhancing the image processing capabilities by accounting for skew.
New Features:
Enhancements:
_image_to_layers
andproject_to_layers
functions to include shear transformations in the image layer metadata.Summary by CodeRabbit
New Features
shear
parameter for enhanced image layer construction and color adjustments.CziImageReader
class.Bug Fixes
adjust_color
function, ensuring better compatibility with different formats.Documentation