Breast Cancer Diagnosis in Digital Breast Tomosynthesis: Effects of Training Sample Size on Multi-Stage Transfer Learning Using Deep Neural Nets

Abstract

In this work we developed a deep convolutional neural network (CNN) for classification of malignant and benign masses in digital breast tomosynthesis (DBT) using a multi-stage transfer learning approach that utilized data from similar auxiliary domains for intermediate-stage finetuning. Breast imaging data from DBT and digitized screen-film mammography (SFM), digital mammography (DM) totaling 4,039 unique ROIs (1,797 malignant and 2,242 benign) were collected. Using cross-validation, we selected the best transfer network from six transfer networks by varying the level up to which the convolutional layers were frozen. In a single-stage transfer learning approach, knowledge from CNN trained on ImageNet data was fine-tuned directly with DBT data. In a multi-stage transfer learning approach, knowledge learned from ImageNet was first fine-tuned with the mammography data and then fine-tuned with the DBT data. Two transfer networks were compared for the second-stage transfer learning by freezing most of the CNN structure versus freezing only the first convolutional layer. We studied the dependence of the classification performance on training sample size for various transfer learning and fine-tuning schemes by varying the training data from 1% to 100% of the available sets. The area under the receiver operating characteristic curve (AUC) was used as a performance measure. The view-based AUC on the test set for single-stage transfer learning was 0.85±0.05 and improved significantly (p<0.05) to 0.91±0.03 for multi-stage learning. This study demonstrated that, when the training sample size from the target domain is limited, an additional stage of transfer-learning using data from a similar auxiliary domain is advantageous.

Quantifying Uncertainty in Machine Learning-Based Power Outage Prediction Model Training: A Tool for Sustainable Storm Restoration

“…iteration number or different training number of iterations for a given sample size), which shows a measure of predictive performance as a function of a varying number of training samples [18] or iterations [19]. The learning curves are used to search the optimal model performance by increased training sample sizes or iterations until the model performance converges at one given sample size or one iteration number [20].…”

“…We used learning curves for different models (DT, RF, BT, ENS, and OPT) and evaluation metrics to quantify the sample size dependence of OPT error [17]. In ML techniques, the learning curve characterizes the relationship of evaluation metrics and varying training amounts (that is, varying training sample sizes for a given iteration number or different training number of iterations for a given sample size), which shows a measure of predictive performance as a function of a varying number of training samples [18] or iterations [19]. The learning curves are used to search the optimal model performance by increased training sample sizes or iterations until the model performance converges at one given sample size or one iteration number [20].…”

Computer‐aided diagnosis in the era of deep learning

“…Stage 2 (DBT: C 1 ‐F 4 )” denotes stage 2 C 1 ‐to‐ F 4 ‐frozen transfer learning at a fixed (100%) DBT training set size after stage 1 transfer learning (curve A). [reprint with permission].…”

Deep Learning Assisted Efficient AdaBoost Algorithm for Breast Cancer Detection and Early Diagnosis

“…Samala et al [28] introduced Multi-Stage Transfer Learning for Digital Breast Tomosynthesis using deep neural networks (MSTL-DNN). The ImageNet knowledge first captured the mammography information and then optimized it in a multi-stages transfer process for digital Breast Tomosynthesis data.…”