Illustration of transfer learning from breast cancer detection to risk prediction: adaptation to local data and local objectives.
Authors
Affiliations (5)
Affiliations (5)
- KU Leuven, Division of Medical Physics & Quality Assessment, Department of Imaging and Pathology, Leuven, Belgium.
- University of Ljubljana, Faculty of Mathematics and Physics, Ljubljana, Slovenia.
- UZ Leuven, Department of Radiology, Leuven, Belgium.
- Jožef Stefan Institute, Ljubljana, Slovenia.
- University of Wisconsin-Madison, Department of Medical Physics, Madison, Wisconsin, United States.
Abstract
We aim to investigate whether a breast cancer risk model can be trained with transfer learning from a breast cancer detection model. An existing open-source breast cancer detection model was used to extract the latent space representation of a local dataset composed of images from 17,878 breast cancer screening participants. An autoencoder network was used for dimensionality reduction. A final model training step mapped the reduced representation to 4-year breast cancer risk. Two experimental studies were performed: first, a local dataset was used to investigate the impact of transfer learning to local data. Second, the training was executed for breast cancer risk by excluding cases with obvious signs of cancer in the model training process, to avoid the influence of cancer signs. In addition, the Mirai model was evaluated. The open-source model achieved a baseline performance of 0.72 with 95%CI [0.66, 0.78] for 4-year risk prediction when applied to local test cases of breast cancer risk data. This performance was improved after training on local breast cancer detection data to 0.75 with 95%CI [0.69, 0.81], although not statistically significant ( <math xmlns="http://www.w3.org/1998/Math/MathML"><mrow><mi>p</mi> <mo>=</mo> <mn>0.09</mn></mrow> </math> ). Further training with local breast cancer risk data achieved an area under the curve (AUC) of 0.77 with 95%CI [0.71, 0.82], which is higher than the original model ( <math xmlns="http://www.w3.org/1998/Math/MathML"><mrow><mi>p</mi> <mo><</mo> <mn>0.01</mn></mrow> </math> ). The Mirai model demonstrated a lower performance after fine-tuning ( <math xmlns="http://www.w3.org/1998/Math/MathML"><mrow><mi>p</mi> <mo><</mo> <mn>0.01</mn></mrow> </math> ). Transfer learning enabled the creation of a breast cancer risk prediction model from a previously developed breast cancer detection model, demonstrating that a publicly available model can be adapted to local clinical needs.