Correct the MONAI models' error in OrientationD pre-processing transforms from "RAS" to "LPS"

[MMelQin]

See detailed description in issue #557 .

The OrientationD in the Pre-processing transforms of the MONAI models that were trained with flipped DICOM CT images from Medical Decathlon contains error to transform the loaded DICOM images in LPS to RAS. Now, after the fix in monai v1.5.1 where input image's space metadata is properly parsed (MD App SDK sets it for loaded DICOM image as "LPS", but not labels) and affects the transform to RAS take effects, adverse that is, because before the image labels defaults to RAS and space not parsed.

Pull Request Overview
This PR corrects orientation transform parameters in MONAI-based medical imaging models to resolve compatibility issues with MONAI v1.5.1. The change addresses preprocessing errors that occurred after MONAI updated how image space metadata is parsed for DICOM CT images.

• Updates OrientationD transform parameter from "RAS" to "LPS" across multiple operators
• Fixes preprocessing pipeline compatibility with MONAI v1.5.1's improved space metadata parsing
• Ensures consistent image orientation handling for DICOM images that are loaded with LPS space metadata

Verification and Validation
The updated Jupyter notebook in the pull request was used to test the updates with input DICOM CT Series downloaded from TCIA.

[sonarqubecloud]

Quality Gate passed

Issues
0 New issues
0 Accepted issues

Measures
0 Security Hotspots
0.0% Coverage on New Code
0.0% Duplication on New Code

See analysis details on SonarQube Cloud

[Copilot]

Pull Request Overview

This PR corrects orientation transform parameters in MONAI-based medical imaging models to resolve compatibility issues with MONAI v1.5.1. The change addresses preprocessing errors that occurred after MONAI updated how image space metadata is parsed for DICOM CT images.

• Updates OrientationD transform parameter from "RAS" to "LPS" across multiple operators
• Fixes preprocessing pipeline compatibility with MONAI v1.5.1's improved space metadata parsing
• Ensures consistent image orientation handling for DICOM images that are loaded with LPS space metadata

Reviewed Changes

Copilot reviewed 4 out of 5 changed files in this pull request and generated no comments.

File	Description
platforms/nuance_pin/app/inference.py	Updated OrientationD axcodes parameter in preprocessing pipeline
examples/apps/cchmc_ped_abd_ct_seg_app/abdomen_seg_operator.py	Updated OrientationD axcodes parameter for pediatric abdomen segmentation
examples/apps/ai_unetr_seg_app/unetr_seg_operator.py	Updated OrientationD axcodes parameter for UNETR segmentation
examples/apps/ai_remote_infer_app/spleen_seg_operator.py	Updated OrientationD axcodes parameter for spleen segmentation

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}