Prediction of Upstaged Ductal Carcinoma In Situ Using Forced Labeling and Domain Adaptation

Abstract

Objective: The goal of this study is to use adjunctive classes to improve a predictive model whose performance is limited by the common problems of small numbers of primary cases, high feature dimensionality, and poor class separability. Specifically, our clinical task is to use mammographic features to predict whether ductal carcinoma in situ (DCIS) identified at needle core biopsy will be later upstaged or shown to contain invasive breast cancer.

Methods: To improve the prediction of pure DCIS (negative) versus upstaged DCIS (positive) cases, this study considers the adjunctive roles of two related classes: atypical ductal hyperplasia (ADH), a non-cancer type of breast abnormity, and invasive ductal carcinoma (IDC), with 113 computer vision based mammographic features extracted from each case. To improve the baseline Model A's classification of pure vs. upstaged DCIS, we designed three different strategies (Models B, C, D) with different ways of embedding features or inputs.

Results: Based on ROC analysis, the baseline Model A performed with AUC of 0.614 (95% CI, 0.496-0.733). All three new models performed better than the baseline, with domain adaptation (Model D) performing the best with an AUC of 0.697 (95% CI, 0.595-0.797).

Conclusion: We improved the prediction performance of DCIS upstaging by embedding two related pathology classes in different training phases.

Significance: The three new strategies of embedding related class data all outperformed the baseline model, thus demonstrating not only feature similarities among these different classes, but also the potential for improving classification by using other related classes.

Fig. 1.

Illustration of different pathology classes associated with breast cancer. ADH is benign but at high risk for being associated with cancer, DCIS is stage-0 cancer still confined within the milk duct, while IDC has invaded beyond the duct and can metastasize to lymph nodes or further.

Fig. 2.

Illustration of the Pipeline in Extraction MCs from Mammograms. First, the lesion ROI from original mammogram was annotated by a breast radiologist; Second, we applied some image enhancement algorithms to enhance the detectability of MCs; Third, MCs within the lesion ROI was detected; Last 113 features were extracted from both individual MCs and MC clusters.

Fig. 3.

Illustration of Four Models Designed with Traditional Way and Embedding ADH and IDC in Training

Fig. 4.

AUC of adding either ADH or IDC cases for training the classifier.

Fig. 5.

Heat-map of adding different number of ADH and IDC to training phase.

Fig. 6.

ROC Curves showing classification performances of different models: traditional classifier, forced labeling and domain adaptation.

Fig. 7.

Precision-Recall Curves showing classification performances of different models: traditional classifier, forced labeling and domain adaptation.

Fig. 8.

The Top Ranked Feature’s Distributions of Four Classes.