Description
This pipeline can be used to mask PHI information in Images. The output is an Image, similar to the one at the input, but with black bounding boxes on top of the targeted entities.
Predicted Entities
AGE, CITY, COUNTRY, DATE, DOCTOR, EMAIL, HOSPITAL, IDNUM, ORGANIZATION, PATIENT, PHONE, PROFESSION, STATE, STREET, USERNAME, ZIP, SIGNATURE.
Live Demo Open in Colab Download
How to use
from sparknlp.pretrained import PretrainedPipeline
deid_pipeline = PretrainedPipeline("image_deid_multi_model_context_pipeline_cpu", "en", "clinical/ocr")
import com.johnsnowlabs.ocr.pretrained.PretrainedPipeline
val deid_pipeline = PretrainedPipeline("image_deid_multi_model_context_pipeline_cpu", lang = "en", "clinical/ocr")
Example
Input:
Output:
Model Information
| Model Name: | image_deid_multi_model_context_pipeline |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 6.0.0+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 5.3 GB |
Included Models
- ImageToText
- DocumentAssembler
- SentenceDetectorDLModel
- Regex
- WordEmbeddingsModel
- MedicalNerModel
- NerConverter
- ContextualParserModel
- ContextualParserModel
- ContextualParserModel
- ContextualParserModel
- ContextualParserModel
- ContextualParserModel
- EntityExtractor
- ContextualParserModel
- RegexMatcher
- ContextualParserModel
- ContextualParserModel
- ContextualParserModel
- ContextualParserModel
- RegexMatcher
- ChunkMergeModel
- ChunkMergeModel
- XLMRobertaEmbeddings
- MedicalNerModel
- NerConverter
- PretrainedZeroShotNER
- NerConverter
- PretrainedZeroShotNER
- NerConverter
- ChunkMergeModel
- PositionFinder
- ImageDrawRegions