Multiparametric MRI-derived Interpretable Habitat Radiomics for Preoperative Assessment of Tumor Budding Status in Breast Cancer.
Authors
Affiliations (7)
Affiliations (7)
- The Second Hospital of Hebei Medical University, Shijiazhuang, Hebei, China (M.S., H.Y., L.Z., D.G., Z.G.); Cangzhou Central Hospital, Cangzhou, Hebei, China (M.S., F.L.). Electronic address: [email protected].
- Cangzhou Central Hospital Affiliated to Hebei Medical University, Cangzhou, Hebei, China (W.Z., R.L.).
- Xiong'an Xuanwu Hospital, Xiong'an, Hebei, China (Y.W.).
- Cangzhou Central Hospital, Cangzhou, Hebei, China (M.S., F.L.).
- Hebei General Hospital, Shijiazhuang, Hebei, China (H.Z.).
- The Second Hospital of Hebei Medical University, Shijiazhuang, Hebei, China (M.S., H.Y., L.Z., D.G., Z.G.).
- The Second Hospital of Hebei Medical University, Shijiazhuang, Hebei, China (M.S., H.Y., L.Z., D.G., Z.G.). Electronic address: [email protected].
Abstract
Breast cancer exhibits high biological heterogeneity and variable invasion patterns. Tumor budding (TB) is a key histopathological marker of aggressive behavior and poor prognosis. However, preoperative TB assessment is limited by biopsy sampling issues. This study aims to develop a multiparametric magnetic Resonance Imaging (MRI)-based habitat radiomics model for noninvasive preoperative prediction of TB status, providing an imaging biomarker to support personalized surgical planning. This retrospective study included 281 breast cancer patients who underwent preoperative multiparametric MRI. Patients were divided into a training set (n = 175), an internal validation set (n = 76), and an external validation set (n = 30). Intratumoral habitats were generated by combining voxel-based K-means clustering with a 3 × 3 × 3 neighborhood expansion, resulting in 16 subregions per patient, from which radiomic features were extracted. Multiple TB prediction models were constructed using two machine learning algorithms and evaluated comprehensively. Furthermore, a nomogram was built by integrating key clinical factors and heterogeneity features to assess clinical utility, and the model was subjected to SHapley Additive exPlanations (SHAP) interpretability analysis. Multivariate analysis identified Ki-67 and enhancement pattern as independent predictors of TB. The combined model (logistic regression [LR]) achieved optimal performance, with area under the receiver operating characteristic curve values of 0.927, 0.858, and 0.858 in the training, internal validation, and external validation sets, respectively. SHAP analysis revealed that T2 habitat elongation, diffusion-weighted imaging habitat flatness, enhancement pattern, and Ki-67 were the core contributing features of the model. Higher elongation, lower flatness, and higher Ki-67 levels were associated with an increased risk of TB, providing potentially interpretable biological evidence for model decision-making. An interpretable, multiparametric MRI-based intratumoral habitat heterogeneity machine learning model can noninvasively predict TB status preoperatively, offering a reliable reference for individualized treatment planning in breast cancer patients.