RESUMEN
We aimed to build a deep learning-based pathomics model to predict the early recurrence of non-muscle-infiltrating bladder cancer (NMIBC) in this work. A total of 147 patients from Xuzhou Central Hospital were enrolled as the training cohort, and 63 patients from Suqian Affiliated Hospital of Xuzhou Medical University were enrolled as the test cohort. Based on two consecutive phases of patch level prediction and WSI-level predictione, we built a pathomics model, with the initial model developed in the training cohort and subjected to transfer learning, and then the test cohort was validated for generalization. The features extracted from the visualization model were used for model interpretation. After migration learning, the area under the receiver operating characteristic curve for the deep learning-based pathomics model in the test cohort was 0.860 (95% CI 0.752-0.969), with good agreement between the migration training cohort and the test cohort in predicting recurrence, and the predicted values matched well with the observed values, with p values of 0.667766 and 0.140233 for the Hosmer-Lemeshow test, respectively. The good clinical application was observed using a decision curve analysis method. We developed a deep learning-based pathomics model showed promising performance in predicting recurrence within one year in NMIBC patients. Including 10 state prediction NMIBC recurrence group pathology features be visualized, which may be used to facilitate personalized management of NMIBC patients to avoid ineffective or unnecessary treatment for the benefit of patients.
Asunto(s)
Aprendizaje Profundo , Recurrencia Local de Neoplasia , Neoplasias Vesicales sin Invasión Muscular , Anciano , Femenino , Humanos , Masculino , Persona de Mediana Edad , Recurrencia Local de Neoplasia/epidemiología , Recurrencia Local de Neoplasia/patología , Neoplasias Vesicales sin Invasión Muscular/patología , Curva ROC , Medición de Riesgo/métodosRESUMEN
BACKGROUND: Recurrent bladder cancer is the most common type of urinary tract malignancy; nevertheless, the mechanistic basis for its recurrence is uncertain. Innovative technologies such as single-cell transcriptomics and spatial transcriptomics (ST) offer new avenues for studying recurrent tumour progression at the single-cell level while preserving spatial data. METHOD: This study integrated single-cell RNA (scRNA) sequencing and ST profiling to examine the tumour microenvironment (TME) of six bladder cancer tissues (three from primary tumours and three from recurrent tumours). FINDINGS: scRNA data-based ST deconvolution analysis revealed a much higher tumour heterogeneity along with TME in recurrent tumours than in primary tumours. High-resolution ST analysis further identified that while the overall natural killer/T cell and malignant cell count or the ratio of total cells was similar or even lower in the recurrent tumours, a higher interaction between epithelial and immune cells was detected. Moreover, the analysis of spatial communication reveals a marked increase in activity between cancer-associated fibroblasts (CAFs) and malignant cells, as well as other immune cells in recurrent tumours. INTERPRETATION: We observed an enhanced interplay between CAFs and malignant cells in bladder recurrent tumours. These findings were first observed at the spatial level.