▶
Medical Language Models for Data Scientists Training Day 2
In the final session of our training series, we explore the intersection of language and vision. Learn how to process medical images, perform advanced document parsing, and leverage the latest open-source Spark NLP features.
What we cover in this session:
- Visual NLP Classic Use Cases: Implementing OCR, object detection, and signature matching for medical document layout analysis.
= Visual Document Understanding with Small VLMs: Leveraging state-of-the-art Visual Language Models for advanced parsing at scale.
- De-identification of Medical Images: Anonymizing structured and unstructured medical images in DICOM, SVS, and pathology formats.
- Open Source Spark NLP: A deep dive into the latest features, including the Reader2X for faster data ingestion and new benchmarks.
