Deep Learning‐Based Segmentation of Locally Advanced Breast Cancer on MRI in Relation to Residual Cancer Burden: A Multi‐Institutional Cohort Study

Abstract

BackgroundWhile several methods have been proposed for automated assessment of breast‐cancer response to neoadjuvant chemotherapy on breast MRI, limited information is available about their performance across multiple institutions.PurposeTo assess the value and robustness of deep learning‐derived volumes of locally advanced breast cancer (LABC) on MRI to infer the presence of residual disease after neoadjuvant chemotherapy.Study TypeRetrospective.SubjectsTraining cohort: 102 consecutive female patients with LABC scheduled for neoadjuvant chemotherapy (NAC) from a single institution (age: 25–73 years). Independent testing cohort: 55 consecutive female patients with LABC from four institutions (age: 25–72 years).Field Strength/SequenceTraining cohort: single vendor 1.5 T or 3.0 T. Testing cohort: multivendor 3.0 T. Gradient echo dynamic contrast‐enhanced sequences.AssessmentA convolutional neural network (nnU‐Net) was trained to segment LABC. Based on resulting tumor volumes, an extremely randomized tree model was trained to assess residual cancer burden (RCB)‐0/I vs. RCB‐II/III. An independent model was developed using functional tumor volume (FTV). Models were tested on an independent testing cohort and response assessment performance and robustness across multiple institutions were assessed.Statistical TestsThe receiver operating characteristic (ROC) was used to calculate the area under the ROC curve (AUC). DeLong's method was used to compare AUCs. Correlations were calculated using Pearson's method. P values <0.05 were considered significant.ResultsAutomated segmentation resulted in a median (interquartile range [IQR]) Dice score of 0.87 (0.62–0.93), with similar volumetric measurements (R = 0.95, P < 0.05). Automated volumetric measurements were significantly correlated with FTV (R = 0.80). Tumor volume‐derived from deep learning of DCE‐MRI was associated with RCB, yielding an AUC of 0.76 to discriminate between RCB‐0/I and RCB‐II/III, performing similar to the FTV‐based model (AUC = 0.77, P = 0.66). Performance was comparable across institutions (IQR AUC: 0.71–0.84).Data ConclusionDeep learning‐based segmentation estimates changes in tumor load on DCE‐MRI that are associated with RCB after NAC and is robust against variations between institutions.Evidence Level2.Technical EfficacyStage 4.

Deep Learning for Fully Automatic Tumor Segmentation on Serially Acquired Dynamic Contrast-Enhanced MRI Images of Triple-Negative Breast Cancer

“…First, nnU-Net_3tpt produced increasingly better segmentation results for tumors with larger sizes, which may explain the better performance at BL than at C2 and C4 because tumors at BL are untreated and tend to be larger. A similar trend was noticed in other studies [45,49,51]. The performance of our model on smaller tumors could be improved by including a more diverse range of samples, and the generalizability of the model could be validated by including public datasets for more comprehensive training and independent testing.…”

“…For instance, when Yue et al evaluated model performance on a dataset of 1000 subjects (n_training = 800, n_testing = 200), their own model, Res-UNet, achieved a DSC of 0.894, and their implementation of nnU-Net achieved a DSC of 0.887 [45], whereas our nnU-Net_3tpt model achieved a DSC of 0.93 in the BL test set. Other notable studies include one in which an nnU-Net trained on a training dataset of 102 subjects achieved a DSC of 0.87 (median value, mean was not reported) on a test set of 55 subjects [49]. Additionally, a regional convolutional neural network model trained on a dataset of 241 patients, including over 10,000 slices, achieved a DSC of 0.79 on a test set of 98 patients, including approximately 9000 slices, by splitting the 3D dataset into 2D space to increase dataset size [3].…”

Predicting response to neoadjuvant chemotherapy with liquid biopsies and multiparametric MRI in patients with breast cancer

“…For automated analysis of the MRI series, tumors were first automatically segmented using the method described by ref. 31 . A set of multiparametric MRI features previously used for computer-aided diagnosis by ref.…”

An Optical Sensory System for Assessment of Residual Cancer Burden in Breast Cancer Patients Undergoing Neoadjuvant Chemotherapy

“…[ 29 ] highlights the potential of machine learning with multiparametric MRI (mpMRI) to predict the complete pathological response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer patients. In another study [ 30 ], deep-learning-derived volumes of locally advanced breast cancer on MRI showed comparable performance to functional tumor volume in predicting residual disease after chemotherapy (AUC = 0.76). These findings suggest the potential of deep-learning-based segmentation for accurate assessment of tumor load and residual cancer burden in breast cancer patients.…”