Deep learning-based model found to be capable of estimating breast density
Experts say that breast cancer is the most common cancer to affect women worldwide. According to the American Cancer Society, about 1 in 8 women in the United States will develop breast cancer in their lifetime. Various medical organizations advise regular screening to detect and treat cases at the early stage.
The breast density, defined as the proportion of fibro-glandular tissue within the breast, is often used to assess the risk of developing breast cancer, researchers say. While various methods are available to estimate this measure, studies have shown that subjective assessments conducted by radiologists based on visual analogue scales are more accurate than any other method.
Researchers, led by Susan M. Astley, PhD, from the University of Manchester, United Kingdom, recently developed and tested a new deep learning-based model capable of estimating breast density with high precision. Their findings are published in the Journal of Medical Imaging.
“The advantage of the deep learning-based approach is that it enables automatic feature extraction from the data itself,” says Astley. “This is appealing for breast density estimations since we do not completely understand why subjective expert judgments outperform other methods.”
According to the researchers, training deep learning models for medical image analysis is typically a challenging task owing to limited datasets. However, they say they found a solution to this problem: instead of building the model from the ground up, the researchers used two independent deep learning models that were initially trained on ImageNet, a non-medical imaging dataset with over a million images. This approach, known as “transfer learning,” allowed them to train the models more efficiently with fewer medical imaging data.
Using nearly 160,000 full-field digital mammogram images that were assigned density values on a visual analogue scale by experts (radiologists, advanced practitioner radiographers, and breast physicians) from 39,357 women, the researchers developed a procedure for estimating the density score for each mammogram image. The objective was to take in a mammogram image as input and churn out a density score as output.
They explained that the procedure involved preprocessing the images to make the training process computationally less intensive, extracting features from the processed images with the deep learning models, mapping the features to a set of density scores, and then combining the scores using an ensemble approach to produce a final density estimate.
With this approach, the researchers say they developed accurate models for estimating breast density and its correlation with cancer risk, while conserving the computation time and memory.
“The model’s performance is comparable to those of human experts within the bounds of uncertainty,” Astley explained. “Moreover, it can be trained much faster and on small datasets or subsets of the large dataset.”
Experts noted that the deep transfer learning framework is useful not only for estimating breast cancer risk in the absence of a radiologist, but also for training other medical imaging models based on its breast tissue density estimations. They explained that this can enable improved performance in tasks such as cancer risk prediction or image segmentation.