Publications by authors named "C Boissin"
Background: In breast cancer, several gene expression assays have been developed to provide a more personalised treatment. This study focuses on the prediction of two molecular proliferation signatures: an 11-gene proliferation score and the MKI67 proliferation marker gene. The aim was to assess whether these could be predicted from digital whole slide images (WSIs) using deep learning models.
View Article and Find Full Text PDFArticle Synopsis
- The alignment of tissue in whole-slide images (WSI) is essential for both research and clinical purposes, and recent advancements in computing and deep learning have changed how these images are analyzed.
- The ACROBAT challenge was organized to evaluate various WSI registration algorithms using a large dataset of 4,212 WSIs from breast cancer patients, aiming to align tissue stained with different methods.
- The study found that various WSI registration methods can achieve high accuracy and identified specific clinical factors that affect their performance, helping researchers choose and improve their analysis techniques.
Article Synopsis
- Nottingham histological grade (NHG) is crucial for assessing breast cancer but shows variability in classifications, particularly for intermediate-grade tumors (NHG2).
- A study analyzed over 11 million image tiles from breast cancer biopsy specimens using the DeepGrade model, which aims to classify tumors into low- and high-risk categories by using preoperative images.
- The results showed DeepGrade accurately predicted tumor grades NHG1 and NHG3 with a high level of agreement (AUC of 0.908), and it successfully identified 65% of NHG2 tumors as low-risk, which may aid in better treatment planning for patients.
The analysis of FFPE tissue sections stained with haematoxylin and eosin (H&E) or immunohistochemistry (IHC) is essential for the pathologic assessment of surgically resected breast cancer specimens. IHC staining has been broadly adopted into diagnostic guidelines and routine workflows to assess the status of several established biomarkers, including ER, PGR, HER2 and KI67. Biomarker assessment can also be facilitated by computational pathology image analysis methods, which have made numerous substantial advances recently, often based on publicly available whole slide image (WSI) data sets.
View Article and Find Full Text PDF