In this study, a novel deep learning-based methodology was investigated to predict breast cancer response to neo-adjuvant chemotherapy (NAC) using the quantitative ultrasound (QUS) multi-parametric imaging at pre-treatment. QUS multi-parametric images of breast tumors were generated using the data acquired from 181 patients diagnosed with locally advanced breast cancer and planned for NAC followed by surgery. The ground truth response to NAC was identified for each patient after the surgery using the standard clinical and pathological criteria. Two deep convolutional neural network (DCNN) architectures including the residual network and residual attention network (RAN) were explored for extracting optimal feature maps from the parametric images, with a fully connected network for response prediction. In different experiments, the features maps were derived from the tumor core only, as well as the core and its margin. Evaluation results on an independent test set demonstrate that the developed model with the RAN architecture to extract feature maps from the expanded parametric images of the tumor core and margin had the best performance in response prediction with an accuracy of 88% and an area under the receiver operating characteristic curve of 0.86. Ten-year survival analyses indicate statistically significant differences between the survival of the responders and non-responders identified based on the model prediction at pre-treatment and the standard criteria at post-treatment. The results of this study demonstrate the promising capability of DCNNs with attention mechanisms in predicting breast cancer response to NAC prior to the start of treatment using QUS multi-parametric images.

Background A considerable proportion of metastatic brain tumors progress locally despite stereotactic radiation treatment, and it can take months before such local progression is evident on follow‐up imaging. Prediction of radiotherapy outcome in terms of tumor local failure is crucial for these patients and can facilitate treatment adjustments or allow for early salvage therapies. Purpose In this work, a novel deep learning architecture is introduced to predict the outcome of local control/failure in brain metastasis treated with stereotactic radiation therapy using treatment‐planning magnetic resonance imaging (MRI) and standard clinical attributes. Methods At the core of the proposed architecture is an InceptionResentV2 network to extract distinct features from each MRI slice for local outcome prediction. A recurrent or transformer network is integrated into the architecture to incorporate spatial dependencies between MRI slices into the predictive modeling. A visualization method based on prediction difference analysis is coupled with the deep learning model to illustrate how different regions of each lesion on MRI contribute to the model's prediction. The model was trained and optimized using the data acquired from 99 patients (116 lesions) and evaluated on an independent test set of 25 patients (40 lesions). Results The results demonstrate the promising potential of the MRI deep learning features for outcome prediction, outperforming standard clinical variables. The prediction model with only clinical variables demonstrated an area under the receiver operating characteristic curve (AUC) of 0.68. The MRI deep learning models resulted in AUCs in the range of 0.72 to 0.83 depending on the mechanism to integrate information from MRI slices of each lesion. The best prediction performance (AUC = 0.86) was associated with the model that combined the MRI deep learning features with clinical variables and incorporated the inter‐slice dependencies using a long short‐term memory recurrent network. The visualization results highlighted the importance of tumor/lesion margins in local outcome prediction for brain metastasis. Conclusions The promising results of this study show the possibility of early prediction of radiotherapy outcome for brain metastasis via deep learning of MRI and clinical attributes at pre‐treatment and encourage future studies on larger groups of patients treated with other radiotherapy modalities.

Objective: A noticeable proportion of larger brain metastases (BMs) are not locally controlled after stereotactic radiotherapy, and it may take months before local progression is apparent on standard follow-up imaging. This work proposes and investigates new explainable deep-learning models to predict the radiotherapy outcome for BM. Methods: A novel self-attention-guided 3D residual network is introduced for predicting the outcome of local failure (LF) after radiotherapy using the baseline treatment-planning MRI. The 3D self-attention modules facilitate capturing long-range intra/inter slice dependencies which are often overlooked by convolution layers. The proposed model was compared to a vanilla 3D residual network and 3D residual network with CBAM attention in terms of performance in outcome prediction. A training recipe was adapted for the outcome prediction models during pretraining and training the down-stream task based on the recently proposed big transfer principles. A novel 3D visualization module was coupled with the model to demonstrate the impact of various intra/peri-lesion regions on volumetric multi-channel MRI upon the network's prediction. Results: The proposed self-attention-guided 3D residual network outperforms the vanilla residual network and the residual network with CBAM attention in accuracy, F1-score, and AUC. The visualization results show the importance of peri-lesional characteristics on treatment-planning MRI in predicting local outcome after radiotherapy. Conclusion: This study demonstrates the potential of self-attention-guided deep-learning features derived from volumetric MRI in radiotherapy outcome prediction for BM. The insights obtained via the developed visualization module for individual lesions can possibly be applied during radiotherapy planning to decrease the chance of LF.

No abstract

Significantly affecting patients’ clinical course and quality of life, a growing number of cancer cases are diagnosed with brain metastasis (BM) annually. Stereotactic radiotherapy is now a major treatment option for patients with BM. However, it may take months before the local response of BM to stereotactic radiation treatment is apparent on standard follow-up imaging. While machine learning in conjunction with radiomics has shown great promise in predicting the local response of BM before or early after radiotherapy, further development and widespread application of such techniques has been hindered by their dependency on manual tumour delineation. In this study, we explored the impact of using less-accurate automatically generated segmentation masks on the efficacy of radiomic features for radiotherapy outcome prediction in BM. The findings of this study demonstrate that while the effect of tumour delineation accuracy is substantial for segmentation models with lower dice scores (dice score ≤ 0.85), radiomic features and prediction models are rather resilient to imperfections in the produced tumour masks. Specifically, the selected radiomic features (six shared features out of seven) and performance of the prediction model (accuracy of 80% versus 80%, AUC of 0.81 versus 0.78) were fairly similar for the ground-truth and automatically generated segmentation masks, with dice scores close to 0.90. The positive outcome of this work paves the way for adopting high-throughput automatically generated tumour masks for discovering diagnostic and prognostic imaging biomarkers in BM without sacrificing accuracy.