Breast Multiparametric MRI for Prediction of Neoadjuvant Chemotherapy Response in Breast Cancer: The BMMR2 Challenge.

Purpose To describe the design, conduct, and results of the Breast Multiparametric MRI for prediction of neoadjuvant chemotherapy Response (BMMR2) challenge. Materials and Methods The BMMR2 computational challenge opened on May 28, 2021, and closed on December 21, 2021. The goal of the challenge was to identify image-based markers derived from multiparametric breast MRI, including diffusion-weighted imaging (DWI) and dynamic contrast-enhanced (DCE) MRI, along with clinical data for predicting pathologic complete response (pCR) following neoadjuvant treatment. Data included 573 breast MRI studies from 191 women (mean age [±SD], 48.9 years ± 10.56) in the I-SPY 2/American College of Radiology Imaging Network (ACRIN) 6698 trial (ClinicalTrials.gov: NCT01042379). The challenge cohort was split into training (60%) and test (40%) sets, with teams blinded to test set pCR outcomes. Prediction performance was evaluated by area under the receiver operating characteristic curve (AUC) and compared with the benchmark established from the ACRIN 6698 primary analysis. Results Eight teams submitted final predictions. Entries from three teams had point estimators of AUC that were higher than the benchmark performance (AUC, 0.782 [95% CI: 0.670, 0.893], with AUCs of 0.803 [95% CI: 0.702, 0.904], 0.838 [95% CI: 0.748, 0.928], and 0.840 [95% CI: 0.748, 0.932]). A variety of approaches were used, ranging from extraction of individual features to deep learning and artificial intelligence methods, incorporating DCE and DWI alone or in combination. Conclusion The BMMR2 challenge identified several models with high predictive performance, which may further expand the value of multiparametric breast MRI as an early marker of treatment response. Clinical trial registration no. NCT01042379 Keywords: MRI, Breast, Tumor Response Supplemental material is available for this article. © RSNA, 2024.

Segmentation of occluded hematopoietic stem cells from tracking.

Image sequences of live proliferating cells often contain visual ambiguities that are difficult even for human domain experts to resolve. Here we present a new approach to analyzing image sequences that capture the development of clones of hematopoietic stem cells (HSCs) from live cell time lapse microscopy. The HSCs cannot survive long term imaging unless they are cultured together with a secondary cell type, OP9 stromal cells. The HSCs frequently disappear under the OP9 cell layer, making segmentation difficult or impossible from a single image frame, even for a human domain expert. We have developed a new approach to the segmentation of HSCs that captures these occluded cells. Starting with an a priori segmentation that uses a Monte Carlo technique to estimate the number of cells in a clump of touching cells, we proceed to track and lineage the image data. Following user validation of the lineage information, an a posteriori resegmentation step utilizing tracking results delineates the HSCs occluded by the OP9 layer. Resegmentation has been applied to 3031 occluded segmentations from 77 tracks, correctly recovering over 84% of the occluded segmentations.