Papers by Daniel RACOCEANU
ArXiv, 2018
In this paper, we introduced a novel feature extraction approach, named exclusive autoencoder (XA... more In this paper, we introduced a novel feature extraction approach, named exclusive autoencoder (XAE), which is a supervised version of autoencoder (AE), able to largely improve the performance of nucleus detection and classification on hematoxylin and eosin (H&E) histopathological images. The proposed XAE can be used in any AE-based algorithm, as long as the data labels are also provided in the feature extraction phase. In the experiments, we evaluated the performance of an approach which is the combination of an XAE and a fully connected neural network (FCN) and compared with some AE-based methods. For a nucleus detection problem (considered as a nucleus/non-nucleus classification problem) on breast cancer H&E images, the F-score of the proposed XAE+FCN approach achieved 96.64% while the state-of-the-art was at 84.49%. For nucleus classification on colorectal cancer H&E images, with the annotations of four categories of epithelial, inflammatory, fibroblast and miscellaneous nuclei. ...
This article presents our vision about the next generation of challenges in computational/digital... more This article presents our vision about the next generation of challenges in computational/digital pathology. The key role of the domain ontology, developed in a sustainable manner (i.e. using reference checklists and protocols, as the living semantic repositories), opens the way to effective/sustainable traceability and relevance feedback concerning the use of existing machine learning algorithms, proven to be very performant in the latest digital pathology challenges (i.e. convolutional neural networks). Being able to work in an accessible web-service environment, with strictly controlled issues regarding intellectual property (image and data processing/analysis algorithms) and medical data/image confidentiality is essential for the future. Among the web-services involved in the proposed approach, the living yellow pages in the area of computational pathology seems to be very important in order to reach an operational awareness, validation, and feasibility. This represents a very p...
Applied Sciences
Deep neural networks represent, nowadays, the most effective machine learning technology in biome... more Deep neural networks represent, nowadays, the most effective machine learning technology in biomedical domain. In this domain, the different areas of interest concern the Omics (study of the genome—genomics—and proteins—transcriptomics, proteomics, and metabolomics), bioimaging (study of biological cell and tissue), medical imaging (study of the human organs by creating visual representations), BBMI (study of the brain and body machine interface) and public and medical health management (PmHM). This paper reviews the major deep learning concepts pertinent to such biomedical applications. Concise overviews are provided for the Omics and the BBMI. We end our analysis with a critical discussion, interpretation and relevant open challenges.
Maedica, 2017
The skin is a dynamic, visible organ, showing the most obvious signs of aging. The mechanisms of ... more The skin is a dynamic, visible organ, showing the most obvious signs of aging. The mechanisms of extrinsic aging, most of them presented in this paper, are currently well known and also the only ones that can be counteracted. Therefore, the transition of this knowledge in the general population is of the most importance, in order to introduce healthy aging strategies, to prevent the development of chronic or malignant diseases and psychological burden related to old age. A thorough review of the literature has been performed in order to identify the main factors involved in skin health and aging. This concept article represents a compilation of seven anti-ageing directions regarding major factors involved in health, aging and beauty, respectively sun, sugar, smoking, skin care, stress, sleep and second (the passage of time), easy to comprehend by the general public but sustained by a strong scientific documentation. Despite its final destination, every quality concept has to pass th...
Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society, 2018
Mitosis detection is one of the critical factors of cancer prognosis, carrying significant diagno... more Mitosis detection is one of the critical factors of cancer prognosis, carrying significant diagnostic information required for breast cancer grading. It provides vital clues to estimate the aggressiveness and the proliferation rate of the tumour. The manual mitosis quantification from whole slide images is a very labor-intensive and challenging task. The aim of this study is to propose a supervised model to detect mitosis signature from breast histopathology WSI images. The model has been designed using deep learning architecture with handcrafted features. We used handcrafted features issued from previous medical challenges MITOS @ ICPR 2012, AMIDA-13 and projects (MICO ANR TecSan) expertise. The deep learning architecture mainly consists of five convolution layers, four max-pooling layers, four rectified linear units (ReLU), and two fully connected layers. ReLU has been used after each convolution layer as an activation function. Dropout layer has been included after first fully co...
JAMA, Dec 12, 2017
Application of deep learning algorithms to whole-slide pathology images can potentially improve d... more Application of deep learning algorithms to whole-slide pathology images can potentially improve diagnostic accuracy and efficiency. Assess the performance of automated deep learning algorithms at detecting metastases in hematoxylin and eosin-stained tissue sections of lymph nodes of women with breast cancer and compare it with pathologists' diagnoses in a diagnostic setting. Researcher challenge competition (CAMELYON16) to develop automated solutions for detecting lymph node metastases (November 2015-November 2016). A training data set of whole-slide images from 2 centers in the Netherlands with (n = 110) and without (n = 160) nodal metastases verified by immunohistochemical staining were provided to challenge participants to build algorithms. Algorithm performance was evaluated in an independent test set of 129 whole-slide images (49 with and 80 without metastases). The same test set of corresponding glass slides was also evaluated by a panel of 11 pathologists with time constr...
Studies in health technology and informatics, 2017
With the wider acceptance of Whole Slide Images (WSI) in histopathology domain, automatic image a... more With the wider acceptance of Whole Slide Images (WSI) in histopathology domain, automatic image analysis algorithms represent a very promising solution to support pathologist's laborious tasks during the diagnosis process, to create a quantification-based second opinion and to enhance inter-observer agreement. In this context, reference vocabularies and formalization of the associated knowledge are especially needed to annotate histopathology images with labels complying with semantic standards. In this work, we elaborate a sustainable triptych able to bridge the gap between pathologists and image analysis scientists. The proposed paradigm is structured along three components: i) extracting a relevant semantic repository from the College of American Pathologists (CAP) organ-specific Cancer Checklists and associated Protocols (CC&P); ii) identifying imaging formalized knowledge issued from effective histopathology imaging methods highlighted by recent Digital Pathology (DP) conte...
Medical Imaging 2016: Digital Pathology, 2016
The morphology of intestinal glands is an important and significant indicator of the level of the... more The morphology of intestinal glands is an important and significant indicator of the level of the severity of an inflammatory bowel disease, and has also been used routinely by pathologists to evaluate the malignancy and the prognosis of colorectal cancers such as adenocarcinomas. The extraction of meaningful information describing the morphology of glands relies on an accurate segmentation method. In this work, we propose a novel technique based on mathematical morphology that characterizes the spatial positioning of nuclei for intestinal gland segmentation in histopathological images. According to their appearance, glands can be divided into two types: hallow glands and solid glands. Hallow glands are composed of lumen and/or goblet cells cytoplasm, or filled with abscess in some advanced stages of the disease, while solid glands are composed of bunches of cells clustered together and can also be filled with necrotic debris. Given this scheme, an efficient characterization of the spatial distribution of cells is sufficient to carry out the segmentation. In this approach, hallow glands are first identified as regions empty of nuclei and surrounded by thick layers of epithelial cells, then solid glands are identified by detecting regions crowded of people. First, cell nuclei are identified by color classification. Then, morphological maps are generated by the mean of advanced morphological operators applied to nuclei objects in order to interpret their spatial distribution and properties to identify candidates for glands central-regions and epithelial layers, that are combined to extract the glandular structures.
Background Recently, anatomic pathology (AP) has seen the introduction of such tools as slide sca... more Background Recently, anatomic pathology (AP) has seen the introduction of such tools as slide scanners and virtual slide technologies, creating the conditions for broader adoption of computer aided diagnosis based on whole slide images (WSI). This change brings up a number of scientific challenges such as the sustainable management of the semantic resources associated to the diagnostic interpretation of AP images by both humans (pathologists) and computers (image analysis algorithms). In order to reduce inter-observer variability between AP reports of malignant tumours, the College of American Pathologists (CAP) edited more than 60 organ-specific Cancer Checklists and associated Protocols (CC&P). Each checklist includes a set of AP observations that are expected to be reported by pathologists in organ-specific AP cancer reports. Our objectives were i) to identify the available histopathological formalized knowledge from the NCBO Bioportal in the scope of the CAP-CC&P for breast canc...
Recently, digital pathology (DP) has been largely improved due to the development of computer vis... more Recently, digital pathology (DP) has been largely improved due to the development of computer vision and machine learning. Automated detection of high-grade prostate carcinoma (HG-PCa) is an impactful medical use-case showing the paradigm of collaboration between DP and computer science: given a field of view (FOV) from a whole slide image (WSI), the computer-aided system is able to determine the grade by classifying the FOV. Various approaches have been reported based on this approach. However, there are two reasons supporting us to conduct this work: first, there is still room for improvement in terms of detection accuracy of HG-PCa; second, a clinical practice is more complex than the operation of simple image classification. FOV ranking is also an essential step. E.g., in clinical practice, a pathologist usually evaluates a case based on a few FOVs from the given WSI. Then, makes decision based on the most severe FOV. This important ranking scenario is not yet being well discussed. In this work, we introduce an automated detection and ranking system for PCa based on Gleason pattern discrimination. Our experiments suggested that the proposed system is able to perform high-accuracy detection (∼ 95.57% ± 2.1%) and excellent performance of ranking. Hence, the proposed system has a great potential to support the daily tasks in the medical routine of clinical pathology.
Breast carcinomas are cancers that arise from the epithelial cells of the breast, which are the c... more Breast carcinomas are cancers that arise from the epithelial cells of the breast, which are the cells that line the lobules and the lactiferous ducts. Breast carcinoma is the most common type of breast cancer and can be divided into different subtypes based on architectural features and growth patterns, recognized during a histopathological examination. Tumor microenvironment (TME) is the cellular environment in which tumor cells develop. Being composed of various cell types having different biological roles, TME is recognized as playing an important role in the progression of the disease. The architectural heterogeneity in breast carcinomas and the spatial interactions with TME are, to date, not well understood. Developing a spatial model of tumor architecture and spatial interactions with TME can advance our understanding of tumor heterogeneity. Furthermore, generating histological synthetic datasets can contribute to validating, and comparing analytical methods that are used in digital pathology. In this work, we propose a modeling method that applies to different breast carcinoma subtypes and TME spatial distributions based on mathematical morphology. The model is based on a few morphological parameters that give access to a large spectrum of breast tumor architectures and are able to differentiate in-situ ductal carcinomas (DCIS) and histological subtypes of invasive carcinomas such as ductal (IDC) and lobular carcinoma (ILC). In addition, a part of the parameters of the model controls the spatial distribution of TME relative to the tumor. The validation of the model has been performed by comparing morphological features between real and simulated images.
Exploring the spatial interactions between tumor and the inflammatory microenvironment using digi... more Exploring the spatial interactions between tumor and the inflammatory microenvironment using digital pathology image analysis can contribute to a better understanding of the immune function and tumor heterogeneity. We address this by providing tools able to reveal various metrics describing spatial relationships in the cancer ecosystem. The approach comprises nuclei segmentation and classification, using supervised learning algorithm, to detect lymphoid aggregates and tumor patterns, and spatial distribution quantification using sparse sets' mathematical morphology. Tumor patterns were classified into three groups: surrounded by lympho-cytes, close to lymphoid aggregates or distant and might be protected from immune attack. The approach provides statistical assessment and comprehensive visual representation of the inflammatory tumor microenvironment.
Previous studies have shown that Quantitative UltraSound (QUS) methods can provide tissue-microst... more Previous studies have shown that Quantitative UltraSound (QUS) methods can provide tissue-microstructure information and are able to successfully detect metastases in human lymph nodes (LNs) harvested from cancer patients. Nevertheless, the gold standard for diagnosis remains pathological evaluation of histology photomicrographs. The goal of the present study is to compare QUS-based and histology-based features which proved to be most valuable for metastatic classification in lymph nodes.
Prostate cancer (PCa) is one of the most common cancers in men, being also the second most deadly... more Prostate cancer (PCa) is one of the most common cancers in men, being also the second most deadly cancer after lung cancer. There is increasing interest in active surveillance and minimally invasive focal therapies in PCa to avoid morbidities associated with whole gland therapy. Tumor volume represents an essential prognostic factor of PCa and the definition of index lesion volume is critical for appropriate decision making, especially for image guide focal treatment or in case of active surveillance. Multi-parametric Magnetic Resonance Imaging (mp-MRI) is the modality of choice for the detection and the localization of PCa foci. However, little has been published on mp-MRI accuracy in determining PCa volume, especially at 3T. There is insufficient evidence and no consensus to determine which of the methods for measuring volume is optimal. The objective of this study concerns the elaboration of an algorithm for automatic interpretation of mp-MRI. We determine the accuracy of the proposed method by comparing the prostate tumor volume issued from the automated volumetric mp-MRI measurements of the tumoral region, with manual and semi-automated volumetric measurements done by and respectively with radiologists. Information issued from whole mount histopathology is used to validate the whole approach.
Besides going digital, with virtual slide technology demanding new workflows, Pathology must prep... more Besides going digital, with virtual slide technology demanding new workflows, Pathology must prepare for another coming revolution: semantic web technologies now enable the knowledge of experts to be stored in databases, shared through the Internet, and accessible by machines. Traceability, disambiguation of reports, quality monitoring , interoperability between health centers are some of the associated benefits that pathologists were seeking. However, major changes are also to be expected for the relation of human diagnosis to machine based procedures. Improving on a former imaging platform which used a local knowledge base and a reasoning engine to combine image processing modules into higher level tasks, we propose a framework where different actors of the histopathology imaging world can cooperate using web services-exchanging knowledge as well as imaging services-and where the results of such collaborations on diagnostic related tasks can be evaluated in international challenges such as those recently organized for mitosis detection, nuclear atypia, or tissue architecture in the context of cancer grading. In this first proposal, the participating imaging modules which use machine learning have no special status. In a second proposal, we address the issue of semantic input to learning modules from standard knowledge bases. The multi-task learning (MTL) paradigm is distinguished by its applicability to several different learning algorithms, its non-reliance on specialized architectures and the promising results demonstrated, in particular towards the problem of weak supervision, an issue found when direct links from pathology terms in reports to corresponding regions within images are missing. 1. TRACEABILITY AND MEDICAL FEEDBACK IN COMPUTATIONAL PATHOLOGY In the last decade, the virtual slide technology generated a real revolution in the use of image processing for diagnostic pathology. However, automation in Medicine has to be carefully validated by tests and clinical trials and further requires certification and official agreements not unlike requirements for drugs to go from development to market. Only partial task automation can find numerous enough homogeneous case samples to be practically validated, and even then, multicenter studies are often necessary, raising major interoperability issues. We started identifying such candidate tasks from the terms used in the standards for pathology reporting, restricting to cancer grading, and addressed the problems of semantic interoperability by using semantic web tools. In, 1 we used web services to map pathology terms used in cancer grading to UMLS semantic types and inferred the possibility of associating a quantitative entity to these terms, the computation of such quantitative traits from images being taken as an a priori candidate for image analysis algorithms. To refine that scheme, a more detailed
The fundamental role of vascular supply in tumor growth makes the evaluation of the angiogenesis ... more The fundamental role of vascular supply in tumor growth makes the evaluation of the angiogenesis crucial in assessing effect of anti-angiogenic therapies. Since many years, such therapies are designed to inhibit the vascular endothelial growth factor (VEGF). To contribute to the assessment of anti-angiogenic agent (Pazopanib) effect on vascular and cellular structures, we acquired data from tumors extracted from a murine tumor model using Multi-Fluorescence Scanning. In this paper, we implemented an unsupervised algorithm combining the Watershed segmentation and Markov Random Field model (MRF). This algorithm allowed us to quantify the proportion of apoptotic endothelial cells and to generate maps according to cell density. Stronger association between apoptosis and endothelial cells was revealed in the tumors receiving anti-angiogenic therapy (n = 4) as compared to those receiving placebo (n = 4). The percentage of apoptotic cells on tumor area is mostly endothelial. Lower density cells were detected in tumor slices presenting higher apoptotic endothelial areas.
Recherches en psychanalyse, 2005
... Spécialité Mathématiques Présentée `al'Université Aix-Marseille I par YVAN VELENIK Soute... more ... Spécialité Mathématiques Présentée `al'Université Aix-Marseille I par YVAN VELENIK Soutenue le 26 novembre 2003 devant le jury composé de Enrique ANDJEL Université Aix-Marseille I Rapporteur Erwin BOLTHAUSEN Université de Zürich Rapporteur ...
Histopathological examination is a powerful method for prognosis of major diseases such as breast... more Histopathological examination is a powerful method for prognosis of major diseases such as breast cancer. Analysis of medical images largely remains the work of human experts. Current virtual microscope systems are mainly an emulation of real microscopes with annotation and some image analysis capabilities. However, the lack of effective knowledge management prevents such systems from being computer-aided prognosis platforms. The cognitive virtual microscopic framework, through an extended modeling and use of medical knowledge, has the capacity to analyse histopathological images and to perform grading of breast cancer, providing pathologists with a robust and traceable second opinion.
Uploads
Papers by Daniel RACOCEANU