skip to main content
Idioma:
Primo Search
Clear Search Box
Search in: Busca Geral
Busca Avançada
Busca por Índices

A spatial attention guided deep learning system for prediction of pathological complete response using breast cancer histopathology images

Duanmu, Hongyi ; Bhattarai, Shristi ; Li, Hongxiao ; Shi, Zhan ; Wang, Fusheng ; Teodoro, George ; Gogineni, Keerthi ; Subhedar, Preeti ; Kiraz, Umay ; Janssen, Emiel A M ; Aneja, Ritu ; Kong, Jun Peng, Hanchuan

Bioinformatics (Oxford, England), 2022-09, Vol.38 (19), p.4605-4612 [Periódico revisado por pares]

England: Oxford University Press

Texto completo disponível

Citações Citado por
  • Título:
    A spatial attention guided deep learning system for prediction of pathological complete response using breast cancer histopathology images
  • Autor: Duanmu, Hongyi ; Bhattarai, Shristi ; Li, Hongxiao ; Shi, Zhan ; Wang, Fusheng ; Teodoro, George ; Gogineni, Keerthi ; Subhedar, Preeti ; Kiraz, Umay ; Janssen, Emiel A M ; Aneja, Ritu ; Kong, Jun
  • Peng, Hanchuan
  • Assuntos: Breast Neoplasms - diagnostic imaging ; Breast Neoplasms - pathology ; Deep Learning ; Female ; Humans ; Neoadjuvant Therapy ; Original Papers ; Triple Negative Breast Neoplasms - diagnostic imaging
  • É parte de: Bioinformatics (Oxford, England), 2022-09, Vol.38 (19), p.4605-4612
  • Descrição: 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.
  • Editor: England: Oxford University Press
  • Idioma: Inglês
Links
Voltar para lista de resultados

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.