Skip to main content

Optical character recognition for Varian Real-Time Position Management System

Project description

Optical Character Recognition for Varian Real-time Position Management system

The Varian Real-time Position Management (RPM) system is a video-based system that compensates for target motion, enabling improved treatment in cancer by tracking the position of a reflective marker placed on the patient in three dimensions (vertical, longitudinal and lateral). The RPM system can detect unexpected motion, providing additional confidence that the target is always accurately positioned for treatment, so the planned dose is delivered to the tumor. If there is movement, the RPM system detects the interruption and instantly gates the beam off. The RPM system uses an infrared tracking camera and a reflective marker placed on the patient and measures the patient’s respiratory pattern and range of motion. It displays them as three waveforms (vertical, longitudinal, and lateral. 1 ) These will be smooth given that the beam is stopped if there is any patient movement.

In order to determine the position of the Varian Infrared Block on the true beam radiotherapy system when the couch is moving, we take a video of the signal coming from the Infrared tracking camera of the RPM system. The camera should be perpendicular to the system and taken with a tripod to minimize noise due to movement. From there, we use computer vision techniques, machine learning based optical character recognition (OCR), and develop anomaly detection techniques to reproduce the three waveforms described above. Due to FDA approval limitations, currently only 30 seconds of these waveforms can be extracted directly from the RPM system. With our method, an unlimited time period of movement can be analyzed and extracted.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ocr-varianrpm-0.0.1.tar.gz (2.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ocr_varianrpm-0.0.1-py3-none-any.whl (2.9 kB view details)

Uploaded Python 3

File details

Details for the file ocr-varianrpm-0.0.1.tar.gz.

File metadata

  • Download URL: ocr-varianrpm-0.0.1.tar.gz
  • Upload date:
  • Size: 2.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.1 importlib_metadata/4.6.1 pkginfo/1.5.0.1 requests/2.22.0 requests-toolbelt/0.9.1 tqdm/4.42.1 CPython/3.7.6

File hashes

Hashes for ocr-varianrpm-0.0.1.tar.gz
Algorithm Hash digest
SHA256 edb434f960c0f0428904e8be73303ef70952acab5a9a215304dc01f47fb2846a
MD5 b80b55abfb736b10c41a6071203cae35
BLAKE2b-256 75bfc278d3b7653a0309fb309723828f1d2178f1bbc4dd60b019f51ac42e493b

See more details on using hashes here.

File details

Details for the file ocr_varianrpm-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: ocr_varianrpm-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 2.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.1 importlib_metadata/4.6.1 pkginfo/1.5.0.1 requests/2.22.0 requests-toolbelt/0.9.1 tqdm/4.42.1 CPython/3.7.6

File hashes

Hashes for ocr_varianrpm-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 a336f620168843868c732f0b4f4a3c68da73783d6372c496fa44e341ad70e08e
MD5 b5827abedf4743b4487b5c0c7a6b8d00
BLAKE2b-256 696b8e5dd7042a8b62b66c5315bbdd6513e01137a6af90d41b7cdb5d1cf8ad41

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page