update pipelines (#1752)

Co-authored-by: Aymane Chilah <aymane.chilah@inetum.com>

Author: aymanechilah

docs/_posts/aymanechilah/2025-02-19-dicom_deid_full_anonymization_en_3_4.md

@@ -20,10 +20,9 @@ use_language_switcher: "Python-Scala-Java"
 
 ## Description
 
-This is a pretrained pipeline designed for DICOM De-identification, aimed at removing all text within the images as well as most of the sensitive metadata tags. The model effectively identifies and eliminates personal identifiers and other confidential information, ensuring the privacy and security of medical images.
-
-In addition to removing visible text within the image itself, the pipeline also processes and anonymizes the DICOM metadata, stripping out sensitive tags such as patient identifiers, physician information, and hospital details. This makes the pipeline an essential tool for preparing DICOM images for public sharing, research, or collaboration.
+This pipeline provides the highest level of anonymization by completely removing all identifying text from both the image and metadata. It is ideal for preparing DICOM files for public sharing, research, or regulatory compliance, ensuring that no traceable information remains.
 
+Comprehensive removal: Eliminates all visible text within images and removes or anonymizes most metadata fields, including patient identifiers, physician details, and hospital information.
 
 ## Predicted Entities
 

docs/_posts/aymanechilah/2025-02-19-dicom_deid_generic_augmented_minimal_en_3_4.md

@@ -20,8 +20,9 @@ use_language_switcher: "Python-Scala-Java"
 
 ## Description
 
-Pretrained pipeline for doing Dicom De-identification, attempting to remove the least possible amount of tags and image texts.
+This pipeline performs the least intrusive form of DICOM de-identification, removing only the most critical personal identifiers while preserving as much metadata as possible. It ensures that Protected Health Information (PHI) is stripped from both the image and metadata, but all non-sensitive details remain intact for research and analysis.
 
+Minimal removal: Eliminates only Personally Identifiable Information (PII) from images and the most essential metadata fields while keeping the majority of the DICOM tags untouched.
 
 ## Predicted Entities
 

docs/_posts/aymanechilah/2025-02-19-dicom_deid_generic_augmented_pseudonym_en_3_4.md

@@ -20,7 +20,9 @@ use_language_switcher: "Python-Scala-Java"
 
 ## Description
 
-This is a pretrained pipeline designed for DICOM De-identification, focused on replacing sensitive metadata values with pseudonyms while ensuring the privacy of Protected Health Information (PHI). The model carefully anonymizes the metadata by replacing personal identifiers, such as patient names, IDs, and other sensitive details, with pseudonyms.
+This pipeline anonymizes DICOM metadata by replacing personal identifiers with pseudonyms instead of removing them. It ensures that PHI is no longer traceable while maintaining data integrity for longitudinal studies and collaborations.
+
+Obfuscation mode: Removes PII from images and replaces sensitive metadata values (e.g., patient names, IDs) with randomized or pseudonymized data, preserving the overall structure and usability of the metadata.
 
 ## Predicted Entities