Automated Prediction of Breast Cancer Response to Neoadjuvant Chemotherapy from DWI Data
This addresses the need for non-invasive, automated surgical planning in breast cancer treatment, though it appears incremental as it builds on existing machine learning approaches with a specific improvement in segmentation.
The paper tackled the problem of predicting breast cancer response to neoadjuvant chemotherapy from DWI data by proposing a deep learning model with automatic tumor segmentation, achieving an AUC of 0.76 pre-NAC and 0.729 mid-NAC, matching or surpassing existing methods.
Effective surgical planning for breast cancer hinges on accurately predicting pathological complete response (pCR) to neoadjuvant chemotherapy (NAC). Diffusion-weighted MRI (DWI) and machine learning offer a non-invasive approach for early pCR assessment. However, most machine-learning models require manual tumor segmentation, a cumbersome and error-prone task. We propose a deep learning model employing "Size-Adaptive Lesion Weighting" for automatic DWI tumor segmentation to enhance pCR prediction accuracy. Despite histopathological changes during NAC complicating DWI image segmentation, our model demonstrates robust performance. Utilizing the BMMR2 challenge dataset, it matches human experts in pCR prediction pre-NAC with an area under the curve (AUC) of 0.76 vs. 0.796, and surpasses standard automated methods mid-NAC, with an AUC of 0.729 vs. 0.654 and 0.576. Our approach represents a significant advancement in automating breast cancer treatment planning, enabling more reliable pCR predictions without manual segmentation.