Screening Mammogram Classification with Prior Exams
This addresses breast cancer diagnosis for radiologists by improving classification accuracy, though it is incremental as it builds on existing neural network methods.
The paper tackled the problem of predicting malignancy in screening mammograms by comparing pairs of exams from the same patient, achieving an AUC of 0.866 and reducing error rates compared to a baseline.
Radiologists typically compare a patient's most recent breast cancer screening exam to their previous ones in making informed diagnoses. To reflect this practice, we propose new neural network models that compare pairs of screening mammograms from the same patient. We train and evaluate our proposed models on over 665,000 pairs of images (over 166,000 pairs of exams). Our best model achieves an AUC of 0.866 in predicting malignancy in patients who underwent breast cancer screening, reducing the error rate of the corresponding baseline.