In early 2017, data scientists from around the world came together in the Data Science Bowl presented by Booz Allen Hamilton and Kaggle to build open machine learning algorithms for early lung cancer detection.
Using CT scans already labeled by teams of radiologists, participants developed statistical models to classify whether a scan contains a cancerous lesion or not. The algorithms that were best at diagnosing new images won the challenge and were released under an open source license.
These algorithms provide a foundation for building the clinical application in the this Concept to Clinic challenge. The top 10 algorithms can be found through the following links:
|Leaderboard Ranking||Team Name||Link to open sourced version|
|2||Julian de Wit & Daniel Hammack||https://github.com/dhammack/DSB2017; https://github.com/juliandewit/kaggle_ndsb2017|
|5||Pierre Fillard (Therapixel)||https://github.com/pfillard/tpx-kaggle-dsb2017|
|8||Alex |Andre |Gilberto |Shize||https://github.com/astoc/kaggle_dsb2017|
In addition, several participants wrote about their approaches to working with the data and developing high-performing models. Here are a few resources:
The major machine learning tasks we’ll be working on in this challenge have a few differences from the problem in the Data Science Bowl. For more on how machine learning algorithms will feed into the Concept to Clinic application, check out the Challenge description. Ready to carry this work forward to the clinic? Check out the latest machine learning issues on Github.