Publications by authors named "Marvin Lerousseau"
Novel individual biomarkers are needed to guide therapeutic decisions for patients with head and neck cancer. We report for the first time, granulomas of TREM2-expressing multinucleated giant macrophages in keratin-rich tumor niches, as a biomarker of favorable prognosis and developed a deep-learning model to automate its quantification on routinely stained pathological slides.
View Article and Find Full Text PDFRecent advances in the field of immuno-oncology have brought transformative changes in the management of cancer patients. The immune profile of tumours has been found to have key value in predicting disease prognosis and treatment response in various cancers. Multiplex immunohistochemistry and immunofluorescence have emerged as potent tools for the simultaneous detection of multiple protein biomarkers in a single tissue section, thereby expanding opportunities for molecular and immune profiling while preserving tissue samples.
View Article and Find Full Text PDFThe clinical significance of the tumor-immune interaction in breast cancer is now established, and tumor-infiltrating lymphocytes (TILs) have emerged as predictive and prognostic biomarkers for patients with triple-negative (estrogen receptor, progesterone receptor, and HER2-negative) breast cancer and HER2-positive breast cancer. How computational assessments of TILs might complement manual TIL assessment in trial and daily practices is currently debated. Recent efforts to use machine learning (ML) to automatically evaluate TILs have shown promising results.
View Article and Find Full Text PDFModern histologic imaging platforms coupled with machine learning methods have provided new opportunities to map the spatial distribution of immune cells in the tumor microenvironment. However, there exists no standardized method for describing or analyzing spatial immune cell data, and most reported spatial analyses are rudimentary. In this review, we provide an overview of two approaches for reporting and analyzing spatial data (raster versus vector-based).
View Article and Find Full Text PDFArticle Synopsis
- The study investigates the use of a CD8 T-cell radiomics signature to predict lesion progression and overall survival in advanced melanoma patients receiving immunotherapy.
- Clinical data was analyzed from 136 patients, focusing on lesion characteristics and the association of radiomics scores with treatment outcomes.
- Findings revealed that a low radiomics score at baseline indicated higher risk for lesion progression and that certain lesions with lower scores were linked to better overall survival, suggesting the radiomics score could serve as a valuable biomarker in melanoma treatment.
COMBING: Clustering in Oncology for Mathematical and Biological Identification of Novel Gene Signatures.
IEEE/ACM Trans Comput Biol Bioinform
April 2023
Article Synopsis
- Precision medicine is evolving through genomics, but challenges like complex biological interactions and data analysis hinder its clinical use.
- This paper proposes a new unsupervised framework using the LP-Stability algorithm to identify low-dimensional gene biomarkers, enhancing flexibility and scalability in identifying clusters.
- The proposed method outperforms existing clustering techniques, showing significant improvements in mathematical and biological metrics, and effectively classifies tumor types and subtypes with high accuracy rates.
Purpose Of Review: Pathology is the cornerstone of cancer care. Pathomics, which represents the use of artificial intelligence in digital pathology, is an emerging and promising field that will revolutionize medical and surgical pathology in the coming years. This review provides an overview of pathomics, its current and future applications and its most relevant applications in Head and Neck cancer care.
View Article and Find Full Text PDFArticle Synopsis
- * The study examines the effects of three normalization methods and two discretization methods on radiomics features in brain MRI, establishing guidelines for consistent future research.
- * Using two datasets, results demonstrate that proper intensity normalization significantly enhances the stability of extracted features, which can improve the accuracy of machine learning algorithms in classifying tumor grades.
Article Synopsis
- The study evaluates how various factors affect the quality of pseudo computed tomography (pCT) generated from magnetic resonance imaging (MRI) using a 3D convolutional neural network (CNN).
- It includes analysis of 402 brain tumor cases, examining different MRI sequences and standardization approaches, while also comparing two specific neural network architectures (HighResNet and 3D UNet).
- Results show that larger training datasets improve pCT quality, with the best pCTs produced from >200 samples, and reveal that specific standardization methods (like white stripe) yield lower errors compared to others.
Article Synopsis
- The paper focuses on improving medical image analysis by addressing image registration and tumor segmentation simultaneously using a new deep learning algorithm.
- The proposed method utilizes the interdependence between registration and segmentation tasks, specifically adjusting similarity constraints within tumor regions for better results.
- The algorithm was tested on well-known datasets (BraTS 2018 and OASIS 3), showing competitive performance compared to state-of-the-art methods, especially in tumor areas, and is accessible for public use online.