DICTORA.AI
This project uses publicly available anonymized ER CTs of abdominal traumas and uses Astra 3D capabilities to create a 3D rendering of the trauma.
Core trick
Renders anonymized CT slice stacks into a 3D trauma model, then maps detected injury to an embolization equipment list shown with part numbers.
Description
This project uses publicly available anonymized ER CTs of abdominal traumas and uses Astra 3D capabilities to create a 3D rendering of the trauma. It also detects the site of trauma and describes the findings. Using those detected abnormalities, it suggests a treatment method using interventional methodology, which is the standard of care. Further, it suggests a toolkit that describes the exact tools needed, from catheters to needles to wires to embolization tools such as coils, gels, and particles, showing them in 3D rendering and showing the name, part number, and manufacturer.
This project demonstrates to the emergency physician that this condition is treatable with embolization methods, allowing the emergency physician to send the patient immediately to the interventional suite. It allows the interventional radiology OR staff to have the toolkit ready so that when the on-call interventionalist arrives, there is a decrease in time to treatment of approximately 1 to 2 hours using this ablation.
README excerpt
# DICTORA · Trauma Workbench A four-case hackathon demo: choose a CT, scroll through its source slices, isolate the available anatomy in 3D, then play an illustrative interventional pathway with synchronized equipment cards. ## Run locally The interactive instrument lab runs directly from this public repository. It has no package dependencies, build step, API key, or backend requirement. ```sh git clone https://github.com/IRADXAI/dictora-trauma-workbench.git cd dictora-trauma-workbench python3 -m http.server 8080 --bind 127.0.0.1 --directory dist ``` Open **http://localhost:8080/lab.html?case=06&item=coil**. Select **Delivery demo**, then **Play delivery · 3s**. The CT workbench at `/index.html` additionally requires the local imaging assets described in [DATA.md](DATA.md). Dataset-derived images, meshes, videos and the Blender project are not bundled in this public repository. The existing [hosted demo](https://dictora-trauma-workbench.drfaizfrancis.chatgpt.site/) includes those assets and retains its current sign-in/access settings; publishing the source does not make that site public. ## Check the source With Node.js 18 or later: ```sh npm test ``` The checks generate all 17 instrument models, exercise seven delivery mechanisms, check finite geometry and animation resets, and validate application syntax and local code dependencies. The detailed historical demo validation is in [VALIDATION.md](VALIDATION.md). ## Interactive 3D instrument lab Open **3D toolkit**