Guillaume Thibault

Merck · Department of Oncology

Machine learning approaches have the potential for meaningful impact in the biomedical field. However, there are often challenges unique to biomedical data that prohibits the adoption of these innovations. For example, limited data, data volatility, and data shifts all compromise model robustness and generalizability. Without proper tuning and data...

Electron microscopy (EM) enables imaging at nanometer resolution and can shed light on how cancer evolves to develop resistance to therapy. Acquiring these images has become a routine task; however, analyzing them is now the bottleneck, as manual structure identification is very time-consuming and can take up to several months for a single sample....

Mapping spatial interactions of cancer, immune and stromal cells present novel opportunities for patient stratification and for advancing immunotherapy. While single-cell studies revealed significant molecular heterogeneity in prostate tumors, there is currently no understanding of how immune cell heterogeneity impacts spatial coordination between...

New developments in electron microscopy technology, improved efficiency of detectors, and artificial intelligence applications for data analysis over the past decade have increased the use of volume electron microscopy (vEM) in the life sciences field. Moreover, sample preparation methods are continuously being modified by investigators to improve...

Mechanisms of therapeutic resistance and vulnerability evolve in metastatic cancers as tumor cells and extrinsic microenvironmental influences change during treatment. To support the development of methods for identifying these mechanisms in individual people, here we present an omic and multidimensional spatial (OMS) atlas generated from four seri...

Ensemble of predictions is known to perform better than individual predictions taken separately. However, for tasks that require heavy computational resources, \textit{e.g.} semantic segmentation, creating an ensemble of learners that needs to be trained separately is hardly tractable. In this work, we propose to leverage the performance boost offe...

Objective and quantifiable assessment of tissue pathology is necessary to study mechanistic disease progression; however, current quantification methods based on tissue staining have many drawbacks including cost, time, labor, batch effects, as well as uneven staining which can result in misinterpretation and investigator bias. Here we present VIST...

Background Functional interactions between immune cells and neoplastic cells in the tumor immune microenvironment have been actively pursued for both biomarker discovery for patient stratification, as well as therapeutic anti-cancer targets to improve clinical outcomes. Although accumulating evidence indicates that intratumoral infiltration of immu...

The emergence of megascale single-cell multiplex tissue imaging (MTI) datasets necessitates reproducible, scalable, and robust tools for cell phenotyping and spatial analysis. We developed open-source, graphics processing unit (GPU)-accelerated tools for intensity normalization, phenotyping, and microenvironment characterization. We deploy the tool...

Accurate diagnosis of metastatic cancer is essential for prescribing optimal control strategies to halt further spread of metastasizing disease. While pathological inspection aided by immunohistochemistry staining provides a valuable gold standard for clinical diagnostics, deep learning methods have emerged as powerful tools for identifying clinica...

The drivers of ductal carcinoma in situ (DCIS) to invasive ductal carcinoma (IDC) transition are poorly understood. Here, we conducted an integrated genomic, transcriptomic, and whole-slide image analysis to evaluate changes in copy-number profiles, mutational profiles, expression, neoantigen load, and topology in 6 cases of matched pure DCIS and r...

The emergence of megascale single-cell multiplex tissue imaging (MTI) datasets necessitates reproducible, scalable, and robust tools for cell phenotyping and spatial analysis. We developed open-source, graphics processing unit (GPU)-accelerated tools for intensity nor-malization, phenotyping, and microenvironment characterization. We deploy the too...

Metastatic cancers often respond to treatment initially but almost universally escape therapeutic control through molecular mechanisms intrinsic to tumor cells, as well as extrinsic influences from immune cells, stroma, and structural microenvironments. We explore the extent to which we can learn these mechanisms and associated therapeutic vulnerab...

Mechanistic disease progression studies using animal models require objective and quantifiable assessment of tissue pathology. Currently quantification relies heavily on staining methods which can be expensive, labor/time-intensive, inconsistent across laboratories and batch, and produce uneven staining that is prone to misinterpretation and invest...

Pancreatic ductal adenocarcinoma (PDAC) patients, who often present with stage III or IV disease, face a dismal prognosis as the 5-year survival rate remains below 10%. Recent studies have revealed that CD4 + T, CD8 + T, and/or B cells in specific spatial arrangements relative to intratumoral regions correlate with clinical outcome for patients, bu...

Background: The transition from ductal carcinoma in situ (DCIS) to invasive ductal carcinoma (IDC) is an evolutionary bottleneck where progression occurs only in 30% of patients. Whilst the genetic drivers of this transition remain poorly understood, we have previously shown that immune escape is a key event. In this study, we profile the evolution...

Abstract Spatially-resolved molecular profiling by immunostaining tissue sections is a key feature in cancer diagnosis, subtyping, and treatment, where it complements routine histopathological evaluation by clarifying tumor phenotypes. In this work, we present a deep learning-based method called speedy histological-to-immunofluorescent translation...

Most deep learning segmentation architectures require a large amount of training data, comprised of thousands of manually annotated images. Despite being time consuming to create, manual annotations are more accurate than algorithmic segmentations and, therefore, result in better training. Here we describe a strategy that utilizes iterative learnin...

Mechanistic studies of pancreatic disease progression using animal models require objective and quantifiable assessment of tissue changes among animal cohorts. Disease state quantification, however, relies heavily on tissue immunostaining, which can be expensive, labor-and time-intensive, and all too often produces uneven staining that is prone to...

Recent advances in multiplexed imaging technologies promise to improve the understanding of the functional states of individual cells and the interactions between the cells in tissues. This often requires compilation of results from multiple samples. However, quantitative integration of information between samples is complicated by variations in st...

Predicting primary site of secondary liver cancer with a neural estimator of metastatic origin," Abstract Purpose: Pathologists rely on relevant clinical information, visual inspection of stained tissue slide morphology, and sophisticated molecular diagnostics to accurately infer the biological origin of secondary metastatic cancer. While highly ef...

Immunotherapy harnesses the power of the adaptive immune system and has revolutionized the field of oncotherapy, as novel therapeutic strategies have been introduced into clinical use. The development of immune checkpoint inhibitors has led to durable control of disease in a subset of advanced cancer patients, such as those with melanoma and non-sm...

Recent advances in multiplexed staining and imaging technologies promise to significantly improve the understanding of the functional states of individual cells and the interactions between the cells that comprise complex tissues. This often requires compilation of results from multiple samples. Quantitative integration of information between sampl...

KEY POINTS • Spatially-resolved molecular profiling is an essential complement to histopathological evaluation of cancer tissues. • Information obtained by immunofluorescence imaging is encoded by features in histological images. • SHIFT leverages previously unappreciated features in histological images to facilitate virtual immunofluorescence s...

Computer Vision Techniques for Cancerous Cells Analysis in FIB-SEM Images - Volume 25 Supplement - Guillaume Thibault, Jessica Riesterer, Kevin Stoltz, Kevin Loftis, Geoffrey Schau, Erin Stempinski, Claudia López, Young Hwan Chang, Joe W. Gray

Correlation Of Imaging Technologies: Methodologies. - Volume 25 Supplement - Claudia S. López, Kevin Loftis, Guillaume Thibault, Sunjong Kwon, Erin Stempinski, Jessica L. Riesterer, Joe W. Gray

Pathologists rely on clinical information, tissue morphology, and sophisticated molecular diagnostics to accurately infer the metastatic origin of secondary liver cancer. In this paper, we introduce a deep learning approach to identify spatially localized regions of cancerous tumor within hematoxylin and eosin stained tissue sections of liver cance...

This work applies deep variational autoencoder learning architecture to study multi-cellular growth characteristics of human mammary epithelial cells in response to diverse microenvironment perturbations. Our approach introduces a novel method of visualizing learned feature spaces of trained variational autoencoding models that enables visualizatio...

We aimed to determine whether multiresolution fractal analysis of voxel-based dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) parametric maps can provide early prediction of breast cancer response to neoadjuvant chemotherapy (NACT). In total, 55 patients underwent 4 DCE-MRI examinations before, during, and after NACT. The shutter-spe...

AUTOMATIC NUCLEI SEGMENTATION IN HISTOPATHOLOGY IMAGES

Image cytometry enables quantitative cell characterization with preserved tissue architecture ; thus, it has been highlighted in the advancement of multiplex immunohisto-chemistry (IHC) and digital image analysis in the context of immune-based biomarker monitoring associated with cancer immunotherapy. However, one of the challenges in the current i...

As cell-cell interactions among tumor and immune cells are known to contribute to tumor progression, in depth evaluation of tumor-immune heterogeneity will enable biomarker-guided patient stratification and improvement of treatment response. Here we examined head and neck squamous cell carcinomas (HNSCC) to reveal the prognostic significance of leu...

Positive response to neoadjuvant chemotherapy (NACT) has been correlated to better long-term outcomes in breast cancer treatment. Early prediction of response to NACT can help modify the regimen for non-responding patients, sparing them of potential toxicities of ineffective therapies. It has been observed that tumor functions such as vascularizati...

Tumor specimens contain a variety of healthy cells as well as cancerous cells, and this heterogeneity underlies resistance to various cancer therapies. But this problem has not been thoroughly investigated until recently. Meanwhile, technological breakthroughs in imaging have led to an explosion of molecular and cellular profiling data from large n...

Graphical Abstract Highlights d Multiplex IHC and computational image analysis phenotypes tumor-immune complexity d In situ leukocyte density correlates with subclassification and prognosis in HNSCC d Immune complexity stratifies response to vaccination therapy in PDAC d CD8 + T cell and PD-L1 status correlate with outcomes of vaccinated PDAC patie...

While fluorescence microscopy provides tools for highly specific labeling and sensitive detection, its resolution limit and lack of general contrast has hindered studies of cellular structure and protein localization. Recent advances in correlative light and electron microscopy (CLEM), including the fully integrated CLEM workflow instrument, the FE...

The translation of genomic sequencing technology to the clinic has greatly advanced personalized medicine. However, the presence of normal cells in tumors is a confounding factor in genome sequence analysis. Tumor purity, or the percentage of cancerous cells in whole tissue section, is a correction factor that can be used to improve the clinical ut...

This study has brought together image processing, clustering and spatial pattern analysis to quantitatively analyze hematoxylin and eosin-stained (H&E) tissue sections. A mixture of tumor and normal cells (intratumoral heterogeneity) as well as complex tissue architectures of most samples complicate the interpretation of their cytological profiles....

This study investigates the effectiveness of hundreds of texture features extracted from voxel-based dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) parametric maps for early prediction of breast cancer response to neoadjuvant chemotherapy (NAC). In total, 38 patients with breast cancer underwent DCE-MRI before (baseline) and after t...

In this paper, we generalize image (texture) statistical descriptors and propose algorithms that improve their efficacy. Recently, a new method showed how the popular Co-Occurrence Matrix (COM) can be modified into a fuzzy version (FCOM) which is more effective and robust to noise. Here, we introduce new fuzzy versions of two additional higher orde...

The cellular heterogeneity and complex tissue architecture of most tumor samples is a major obstacle in image analysis on standard hematoxylin and eosin-stained (H&E) tissue sections. A mixture of cancer and normal cells complicates the interpretation of their cytological profiles. Furthermore , spatial arrangement and architectural organization of...

This paper presents the initial demonstration that changes in 3D texture features of DCE-MRI based parametric maps in the early phase of NAC can be effective predictors of eventual breast cancer RCB score, and thus, pathologic response to NAC. The use of powerful 3D statistical matrices produced high RCB score correlations and allowed automatic det...

The automatic detection of exudates in color eye fundus images is an important task in applications such as diabetic retinopathy screening. The presented work has been undertaken in the framework of the TeleOphta project, whose main objective is to automatically detect normal exams in a tele-ophthalmology network, thus reducing the burden on the re...

Quantifying concentrations of target molecules near cellular structures, within cells or tissues, requires identifying the gold particles in immunogold labelled images. In this paper, we address the problem of automatically detect them accurately and reliably across multiple scales and in noisy conditions. For this purpose, we introduce a new contr...

This paper presents new structural statistical matrices which are gray level Size Zone Matrix (SZM) texture descriptor variants. The SZM is based on the co-occurrences of size/intensity of each flat zone (connected pixels with the same gray level). The first improvement increases the information processed by merging multiple gray levels quantizatio...

A complete prototype for the automatic detection of normal examinations on a teleophthalmology network for diabetic retinopathy screening is presented. The system combines pathological pattern mining methods, with specific lesion detection methods, to extract information from the images. This information, plus patient and other contextual data, is...

This paper describes the sequence of construction of a cell nuclei classification model by the analysis, the characterization and the classification of shape and texture. We describe first the elaboration of dedicated shape indexes and second the construction of the associated classification submodel. Then we present a new method of texture charact...

This paper presents the different steps for an automatic fluorescence-labelled cell classification method. First a data features study is discussed in order to describe cell texture by means of morphological and statistical texture descriptors. Then, results on supervised classification using logistic regression, random forest and neural networks,...

This paper presents significant improvements of Gray Level Size Zone Matrix (GLSZM) which is a bivariate statistical representation of texture, based on the co-occurrences of size/intensity of each flat zone (connected pixels of the same gray level). The first improvement is a multi-scale extension of the matrix which merges various quantizations o...

In this paper, we present a study on the characterization and the classification of textures. This study is performed using a set of values obtained by the computation of indexes. To obtain these indexes, we extract a set of data with two techniques: the computation of matrices which are statistical representations of the texture and the computatio...

This paper present a study on the diagnoses of blood cell nuclei from patients affected by the Progeria disease. Nuclei are characterized with various methods that analyze them shape and texture, and subsequently classify them by learning techniques. These methods extract "measures" from nuclei, which are used for the computation of a set of values...

In this paper, we present a study on the characterization and the classification of binary digital objects. This study is performed using a set of values obtained by the computation of ”shape and texture indexes”. To get the shape indexes, we extract a set of data called ”measures” from 2D shapes, like for example surface and perimeter. These index...

In this paper, we present a study on the characterization and the classification of binary digital shapes. This study is performed using a set of values obtained by the computation of "shape indexes". To get these indexes, we extract a set of data called "measures" from the 2D shape, like for example a shape's surface and perimeter. Then these meas...

Numerous papers are describing methods for virtual sculpture which simulate real behaviours in a virtual environment. During the sculpture process, the artist does not have to be disturbed by the latency of an interaction between the object he works on and the tool he uses. Existing data structures or multiprocessing enhancements are first ways to...