期刊
JOURNAL OF MEDICAL IMAGING
卷 10, 期 2, 页码 -出版社
SPIE-SOC PHOTO-OPTICAL INSTRUMENTATION ENGINEERS
DOI: 10.1117/1.JMI.10.2.024502
关键词
deep learning; mammography; breast density; transfer learning; cancer risk
This study aims to build automated models using deep learning based on the scores given by radiologists to predict mammographic breast density accurately and consistently. The approach involves using pretrained deep networks to generate feature vectors for regression analysis, and the results show that the model performs at a similar level to human experts in estimating cancer risk. The study also demonstrates the high consistency and potential of the model.
Purpose: Mammographic breast density is one of the strongest risk factors for cancer. Density assessed by radiologists using visual analogue scales has been shown to provide better risk predictions than other methods. Our purpose is to build automated models using deep learning and train on radiologist scores to make accurate and consistent predictions. Approach: We used a dataset of almost 160,000 mammograms, each with two independent density scores made by expert medical practitioners. We used two pretrained deep networks and adapted them to produce feature vectors, which were then used for both linear and nonlinear regression to make density predictions. We also simulated an optimal method, which allowed us to compare the quality of our results with a simulated upper bound on performance. Results: Our deep learning method produced estimates with a root mean squared error (RMSE) of 8.79 +/- 0.21. The model estimates of cancer risk perform at a similar level to human experts, within uncertainty bounds. We made comparisons between different model variants and demonstrated the high level of consistency of the model predictions. Our modeled optimal method produced image predictions with a RMSE of between 7.98 and 8.90 for cranial caudal images. Conclusion: We demonstrated a deep learning framework based upon a transfer learning approach to make density estimates based on radiologists' visual scores. Our approach requires modest computational resources and has the potential to be trained with limited quantities of data. (c) 2023 Society of Photo-Optical Instrumentation Engineers (SPIE)
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据