Predicting pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in triple-negative breast cancer (TNBC) patients accurately is direly needed for clinical decision making. pCR is also regarded as a strong predictor of overall survival. In this work, we propose a deep learning system to predict pCR to NAC based on serial pathology images stained with hematoxylin and eosin and two immunohistochemical biomarkers (Ki67 and PHH3). To support human prior domain knowledge-based guidance and enhance interpretability of the deep learning system, we introduce a human knowledge-derived spatial attention mechanism to inform deep learning models of informative tissue areas of interest. For each patient, three serial breast tumor tissue sections from biopsy blocks were sectioned, stained in three different stains and integrated. The resulting comprehensive attention information from the image triplets is used to guide our prediction system for prognostic tissue regions. The experimental dataset consists of 26 419 pathology image patches of $1000×1000$ pixels from 73 TNBC patients treated with NAC. Image patches from randomly selected 43 patients are used as a training dataset and images patches from the rest 30 are used as a testing dataset. By the maximum voting from patch-level results, our proposed model achieves a 93% patient-level accuracy, outperforming baselines and other state-of-the-art systems, suggesting its high potential for clinical decision making. The codes, the documentation and example data are available on an open source at: https://github.com/jkonglab/PCR_Prediction_Serial_WSIs_biomarkers Supplementary data are available at Bioinformatics online.

Background: Pathological complete response (pCR) is associated with favorable prognosis in patients with triple-negative breast cancer (TNBC). However, only 30–40% of TNBC patients treated with neoadjuvant chemotherapy (NAC) show pCR, while the remaining 60–70% show residual disease (RD). The role of the tumor microenvironment in NAC response in patients with TNBC remains unclear. In this study, we developed a machine learning-based two-step pipeline to distinguish between various histological components in hematoxylin and eosin (H&E)-stained whole slide images (WSIs) of TNBC tissue biopsies and to identify histological features that can predict NAC response. Methods: H&E-stained WSIs of treatment-naïve biopsies from 85 patients (51 with pCR and 34 with RD) of the model development cohort and 79 patients (41 with pCR and 38 with RD) of the validation cohort were separated through a stratified eightfold cross-validation strategy for the first step and leave-one-out cross-validation strategy for the second step. A tile-level histology label prediction pipeline and four machine-learning classifiers were used to analyze 468,043 tiles of WSIs. The best-trained classifier used 55 texture features from each tile to produce a probability profile during testing. The predicted histology classes were used to generate a histology classification map of the spatial distributions of different tissue regions. A patient-level NAC response prediction pipeline was trained with features derived from paired histology classification maps. The top graph-based features capturing the relevant spatial information across the different histological classes were provided to the radial basis function kernel support vector machine (rbfSVM) classifier for NAC treatment response prediction. Results: The tile-level prediction pipeline achieved 86.72% accuracy for histology class classification, while the patient-level pipeline achieved 83.53% NAC response (pCR vs. RD) prediction accuracy of the model development cohort. The model was validated with an independent cohort with tile histology validation accuracy of 83.59% and NAC prediction accuracy of 81.01%. The histological class pairs with the strongest NAC response predictive ability were tumor and tumor tumor-infiltrating lymphocytes for pCR and microvessel density and polyploid giant cancer cells for RD. Conclusion: Our machine learning pipeline can robustly identify clinically relevant histological classes that predict NAC response in TNBC patients and may help guide patient selection for NAC treatment.

Understanding cellular remodeling in response to mechanical stimuli is a critical step in elucidating mechanical activation of biochemical signaling pathways. Experimental evidence indicates that external stress-induced subcellular adaptation is accomplished through dynamic cytoskeletal reorganization. To study the interactions between subcellular structures involved in transducing mechanical signals, we combined experimental data and computational simulations to evaluate real-time mechanical adaptation of the actin cytoskeletal network. Actin cytoskeleton was imaged at the same time as an external tensile force was applied to live vascular smooth muscle cells using a fibronectin-functionalized atomic force microscope probe. Moreover, we performed computational simulations of active cytoskeletal networks under an external tensile force. The experimental data and simulation results suggest that mechanical structural adaptation occurs before chemical adaptation during filament bundle formation: actin filaments first align in the direction of the external force by initializing anisotropic filament orientations, then the chemical evolution of the network follows the anisotropic structures to further develop the bundle-like geometry. Our findings present an alternative two-step explanation for the formation of actin bundles due to mechanical stimulation and provide new insights into the mechanism of mechanotransduction. Remodeling the cytoskeletal network in response to external force is key to cellular mechanotransduction. Despite much focus on cytoskeletal remodeling in recent years, a comprehensive understanding of actin remodeling in real-time in cells under mechanical stimuli is still lacking. We integrated tensile stress-induced 3D actin remodeling and 3D computational simulations of actin cytoskeleton to study how the actin cytoskeleton form bundles and how these bundles evolve over time upon external tensile stress. We found that actin network remodels through a two-step process in which rapid alignment of actin filaments is followed by slower actin bundling. Based on these results, we propose a “mechanics before chemistry” model of actin cytoskeleton remodeling under external tensile force.