Welcome to PD-DWI documentation!

PD-DWI is a physiologically-decomposed Diffusion-Weighted MRI machine-learning model for predicting response to neoadjuvant chemotherapy in invasive breast cancer.

PD-DWI was developed by TCML group.

TCML

If you publish any work which uses this package, please cite the following publication: Gilad, M., Freiman, M. (2022). PD-DWI: Predicting Response to Neoadjuvant Chemotherapy in Invasive Breast Cancer with Physiologically-Decomposed Diffusion-Weighted MRI Machine-Learning Model. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds) Medical Image Computing and Computer Assisted Intervention – MICCAI 2022. MICCAI 2022. Lecture Notes in Computer Science, vol 13433. Springer, Cham. https://doi.org/10.1007/978-3-031-16437-8_4

Note

This work was developed as part of the BMMR2 challenge using ACRIN-6698 dataset.

Warning

Not intended for clinical use.

BMMR2 Challenge

{ "data": [ { "x": [ "Benchmark", "Team C", "Team B", "Team A", "PD-DWI" ], "y": [ 0.782, 0.803, 0.838, 0.840, 0.885 ], "marker": { "color": ["rgba(136,204,238,1)", "rgba(136,204,238,1)", "rgba(136,204,238,1)", "rgba(136,204,238,1)", "rgba(204,102,119,1)"] }, "type": "bar" } ], "layout": { "title": "Model Performance", "xaxis": { "title": "Best Performing Models" }, "yaxis": { "title": "AUC Score", "range": [ 0.75, 0.9 ] } } }