--- title: "Lakshmi Mahabaleshwara (@lakshmi-mahabalesh) | Hashnode" description: "Writing about healthcare AI, medical imaging, data engineering, and scalable ML. Read the latest articles by Lakshmi Mahabaleshwara on Hashnode." url: "https://hashnode.com/@lakshmi-mahabalesh" --- @lakshmi-mahabalesh # Lakshmi Mahabaleshwara @lakshmi-mahabalesh · Bengaluru, India · Joined May 2026 Writing about healthcare AI, medical imaging, data engineering, and scalable ML ### [How to Encrypt PII in Data Pipelines While Keeping It Searchable](https://freecodecamp.org/news/how-to-encrypt-pii-in-data-pipelines-while-keeping-it-searchable?utm_source=hashnode&utm_medium=feed) At Intuit, my team built a data pipeline that processed TurboTax e-filing data. This data needed to be made available for dashboards, analytics, and other downstream use cases. One of the biggest chal 16 min read · [freecodecamp.org](https://freecodecamp.org/news/how-to-encrypt-pii-in-data-pipelines-while-keeping-it-searchable?utm_source=hashnode&utm_medium=feed) [Oct 6](https://hashnode.com/posts/how-to-encrypt-pii-in-data-pipelines-while-keeping-it-searchable/6ac4810141f9b6b6ff5bf1cd) ### [How to Turn a RECIST Line into a 3D Tumor Segmentation Mask](https://freecodecamp.org/news/how-to-turn-a-recist-line-into-a-3d-tumor-segmentation-mask?utm_source=hashnode&utm_medium=feed) A radiologist can mark a tumor on a CT scan by drawing a straight line across it. Creating a complete 3D segmentation requires outlining the tumor across the slices where it appears, which is more tim 21 min read · [freecodecamp.org](https://freecodecamp.org/news/how-to-turn-a-recist-line-into-a-3d-tumor-segmentation-mask?utm_source=hashnode&utm_medium=feed) [Sep 18](https://hashnode.com/posts/how-to-turn-a-recist-line-into-a-3d-tumor-segmentation-mask/6aadae08b3c208add9878388) ### [What Happens to a Medical Image Before and After a Model Sees It](https://freecodecamp.org/news/what-happens-to-a-medical-image-before-and-after-a-model-sees-it?utm_source=hashnode&utm_medium=feed) Medical imaging papers are full of familiar-looking terms: normalization, labels, validation, annotation, and preprocessing. If you come from general machine learning, you may think you already know w 18 min read · [freecodecamp.org](https://freecodecamp.org/news/what-happens-to-a-medical-image-before-and-after-a-model-sees-it?utm_source=hashnode&utm_medium=feed) [Aug 24](https://hashnode.com/posts/what-happens-to-a-medical-image-before-and-after-a-model-sees-it/6a8cac4b80ffa6e1b9da795b) ### [How to Build a Privacy-First Medical Image De-Identification Agent with Claude and MCP](https://freecodecamp.org/news/build-a-privacy-first-medical-image-de-identification-agent?utm_source=hashnode&utm_medium=feed) Imagine asking an AI assistant to de-identify thousands of medical images. It runs the pipeline, tracks progress, summarizes every decision, and tells you which files need human review, all without ev 17 min read · [freecodecamp.org](https://freecodecamp.org/news/build-a-privacy-first-medical-image-de-identification-agent?utm_source=hashnode&utm_medium=feed) [Aug 6](https://hashnode.com/posts/build-a-privacy-first-medical-image-de-identification-agent/6a7450ad88b91c86871fa9de) ### [How to Train a Tumor Segmentation Model on Ultrasound Data with MONAI](https://freecodecamp.org/news/how-to-train-a-tumor-segmentation-model-on-ultrasound-data-with-monai?utm_source=hashnode&utm_medium=feed) Most segmentation tutorials begin by choosing a model, feeding images into it, and tuning hyperparameters until the metric improves. But this skips the step that often matters most: understanding the 16 min read · [freecodecamp.org](https://freecodecamp.org/news/how-to-train-a-tumor-segmentation-model-on-ultrasound-data-with-monai?utm_source=hashnode&utm_medium=feed) [Jul 22](https://hashnode.com/posts/how-to-train-a-tumor-segmentation-model-on-ultrasound-data-with-monai/6a60f5843dee1fe3a0faaca9)