Digital image analysis and machine learning-assisted prediction of neoadjuvant chemotherapy response in triple-negative breast cancer

Abstract

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.

A more objective PD diagnostic model: integrating texture feature markers of cerebellar gray matter and white matter through machine learning

“…Medical image texture analysis is a quantification approach for assessing internal patterns and image structures, having demonstrated potential in disease quantitative analysis (Zwanenburg et al, 2020 ; Fisher et al, 2024 ). Machine learning, a pivotal tool in medical image texture analysis, offers numerous unique benefits to the medical domain.…”

“…By harnessing advanced technologies such as deep learning, machine learning can autonomously extract crucial texture information beneficial for disease diagnosis and prediction, thereby enhancing the sensitivity and accuracy of potential disease detection (Yang et al, 2023 ). Furthermore, machine learning personalizes medical image analysis, tailoring diagnosis and treatment to patients' unique conditions and medical histories, thus escalating treatment precision and reducing needless interventions, ultimately improving medical outcomes (Chen et al, 2023 ; Sheng et al, 2023 ; Fisher et al, 2024 ). Machine learning and deep learning have demonstrated their potential in assisting the diagnosis of Parkinson's disease, capable of characterizing disease stages and patient functional impairments to better understand the brain mechanisms of PD (Abós et al, 2017 ; Sivaranjini and Sujatha, 2019 ; Guo et al, 2022 ).…”