Daniel Racoceanu

Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer

Importance Application of deep learning algorithms to whole-slide pathology images can potentially improve diagnostic accuracy and efficiency. Objective 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. Design, Setting, and Participants 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 (nu2009=u2009110) and without (nu2009=u2009160) 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 constraint (WTC) from the Netherlands to ascertain likelihood of nodal metastases for each slide in a flexible 2-hour session, simulating routine pathology workflow, and by 1 pathologist without time constraint (WOTC). Exposures Deep learning algorithms submitted as part of a challenge competition or pathologist interpretation. Main Outcomes and Measures The presence of specific metastatic foci and the absence vs presence of lymph node metastasis in a slide or image using receiver operating characteristic curve analysis. The 11 pathologists participating in the simulation exercise rated their diagnostic confidence as definitely normal, probably normal, equivocal, probably tumor, or definitely tumor. Results The area under the receiver operating characteristic curve (AUC) for the algorithms ranged from 0.556 to 0.994. The top-performing algorithm achieved a lesion-level, true-positive fraction comparable with that of the pathologist WOTC (72.4% [95% CI, 64.3%-80.4%]) at a mean of 0.0125 false-positives per normal whole-slide image. For the whole-slide image classification task, the best algorithm (AUC, 0.994 [95% CI, 0.983-0.999]) performed significantly better than the pathologists WTC in a diagnostic simulation (mean AUC, 0.810 [range, 0.738-0.884]; Pu2009<u2009.001). The top 5 algorithms had a mean AUC that was comparable with the pathologist interpreting the slides in the absence of time constraints (mean AUC, 0.960 [range, 0.923-0.994] for the top 5 algorithms vs 0.966 [95% CI, 0.927-0.998] for the pathologist WOTC). Conclusions and Relevance In the setting of a challenge competition, some deep learning algorithms achieved better diagnostic performance than a panel of 11 pathologists participating in a simulation exercise designed to mimic routine pathology workflow; algorithm performance was comparable with an expert pathologist interpreting whole-slide images without time constraints. Whether this approach has clinical utility will require evaluation in a clinical setting.

Gland segmentation in colon histology images: The glas challenge contest

&NA; Colorectal adenocarcinoma originating in intestinal glandular structures is the most common form of colon cancer. In clinical practice, the morphology of intestinal glands, including architectural appearance and glandular formation, is used by pathologists to inform prognosis and plan the treatment of individual patients. However, achieving good inter‐observer as well as intra‐observer reproducibility of cancer grading is still a major challenge in modern pathology. An automated approach which quantifies the morphology of glands is a solution to the problem. This paper provides an overview to the Gland Segmentation in Colon Histology Images Challenge Contest (GlaS) held at MICCAI2015. Details of the challenge, including organization, dataset and evaluation criteria, are presented, along with the method descriptions and evaluation results from the top performing methods. HighlightsThe Gland Segmentation in Colon Histology Images Challenge (GlaS) Contest at MICCAI15.The complete details of the challenge are presented.The descriptions of the top performing methods are presented.Evaluation results of the top performing methods are presented. Graphical abstract Figure. No caption available.

Multispectral band selection and spatial characterization: Application to mitosis detection in breast cancer histopathology

Breast cancer is the second most frequent cancer. The reference process for breast cancer prognosis is Nottingham grading system. According to this system, mitosis detection is one of the three important criteria required for grading process and quantifying the locality and prognosis of a tumor. Multispectral imaging, as relatively new to the field of histopathology, has the advantage, over traditional RGB imaging, to capture spectrally resolved information at specific frequencies, across the electromagnetic spectrum. This study aims at evaluating the accuracy of mitosis detection on histopathological multispectral images. The proposed framework includes: selection of spectral bands and focal planes, detection of candidate mitotic regions and computation of morphological and multispectral statistical features. A state-of-the-art of the methods for mitosis classification is also provided. This framework has been evaluated on MITOS multispectral dataset and achieved higher detection rate (67.35%) and F-Measure (63.74%) than the best MITOS contest results (Roux et al., 2013). Our results indicate that the selected multispectral bands have more discriminant information than a single spectral band or all spectral bands for mitotic figures, validating the interest of using multispectral images to improve the quality of the diagnostic in histopathology.

A structure-based approach for colon gland segmentation in digital pathology

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 nuclei. 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.

Towards semantic-driven high-content image analysis: an operational instantiation for mitosis detection in digital histopathology.

This study concerns a novel symbolic cognitive vision framework emerged from the Cognitive Microscopy (MICO(1)) initiative. MICO aims at supporting the evolution towards digital pathology, by studying cognitive clinical-compliant protocols involving routine virtual microscopy. We instantiate this paradigm in the case of mitotic count as a component of breast cancer grading in histopathology. The key concept of our approach is the role of the semantics as driver of the whole slide image analysis protocol. All the decisions being taken into a semantic and formal world, MICO represents a knowledge-driven platform for digital histopathology. Therefore, the core of this initiative is the knowledge representation and the reasoning. Pathologists knowledge and strategies are used to efficiently guide image analysis algorithms. In this sense, hard-coded knowledge, semantic and usability gaps are to be reduced by a leading, active role of reasoning and of semantic approaches. Integrating ontologies and reasoning in confluence with modular imaging algorithms, allows the emergence of new clinical-compliant protocols for digital pathology. This represents a promising way to solve decision reproducibility and traceability issues in digital histopathology, while increasing the flexibility of the platform and pathologists acceptance, the one always having the legal responsibility in the diagnosis process. The proposed protocols open the way to increasingly reliable cancer assessment (i.e. multiple slides per sample analysis), quantifiable and traceable second opinion for cancer grading, and modern capabilities for cancer research support in histopathology (i.e. content and context-based indexing and retrieval). Last, but not least, the generic approach introduced here is applicable for number of additional challenges, related to molecular imaging and, in general, to high-content image exploration.

Spectral band selection for mitosis detection in histopathology

This study aims at evaluating the accuracy of mitosis detection on multispectral histopathological images by developing a solution specifically designed to take advantage of multi-spectral information. The proposed framework includes a selection of spectral bands and focal plane, detection of candidate mitotic regions, computation of morphological & mul-tispectral statistical features (MMSF) and study of different state-of-the-art classification methods for mitosis classification. This framework achieved 74% TPR, 76% PPV and 74% F-Measure on MITOS dataset. Our results indicate that selected multispectral bands contain discriminant information for mitotic figures, being therefore a very promising exploration area to improve the quality of the diagnosis assistance in histopathology.

Reconstructing neuronal morphology from microscopy stacks using fast marching

Automated algorithms to build accurate models of 3D neuronal arborization is much in demand due to large volume of microscopy data. We present a tracking algorithm for automatic and reliable extraction of neuronal morphology. It is robust to ambiguous branch discontinuities, variability of intensity and curvature of fibres, arbitrary branch cross-sections, noise and irregular background illumination. We complete the presentation of our method with demonstration of its performance on synthetic data modeling challenging scenarios and on confocal microscopy data of Olfactory Projection fibres from DIADEM data set with promising results.

Neurite Tracing With Object Process

In this paper we present a pipeline for automatic analysis of neuronal morphology: from detection, modeling to digital reconstruction. First, we present an automatic, unsupervised object detection framework using stochastic marked point process. It extracts connected neuronal networks by fitting special configuration of marked objects to the centreline of the neurite branches in the image volume giving us position, local width and orientation information. Semantic modeling of neuronal morphology in terms of critical nodes like bifurcations and terminals, generates various geometric and morphology descriptors such as branching index, branching angles, total neurite length, internodal lengths for statistical inference on characteristic neuronal features. From the detected branches we reconstruct neuronal tree morphology using robust and efficient numerical fast marching methods. We capture a mathematical model abstracting out the relevant position, shape and connectivity information about neuronal branches from the microscopy data into connected minimum spanning trees. Such digital reconstruction is represented in standard SWC format, prevalent for archiving, sharing, and further analysis in the neuroimaging community. Our proposed pipeline outperforms state of the art methods in tracing accuracy and minimizes the subjective variability in reconstruction, inherent to semi-automatic methods.

Breakthrough Technologies in Digital Pathology

The 12th European Congress on Digital Pathology (ECDP 2014) was held from 18 to 21 June 2014 at the College des Bernardins in Paris, thanks to the support of the French Pathology Society, and with the collaboration of the Association for Developing Informatics in Cytology and Anatomic Pathology, ADICAP and the French Cellular Haematology Group, GFHC. By bringing along pathologists, scientists and industrials, this conference highlighted the dynamics of the communities involved in the evolution towards digital pathology. Among the challenges raised by this evolution, being able to bring justified and traceable responses has become an ethical priority for the patients and the healthcare professionals. From this perspective, the digital pathology will certainly bring an important increase in the quality of healthcare. In order to assess this evolution, seven journal papers have been selected from the ECDP 2014 presentations, for their pertinence and their originality, from the information and imaging technologies perspective. We entitled this special issue “Breakthrough Technologies in Digital Pathology”, as a stimulus to new challenges for the future of digital pathology. New perspectives about the use of semantics at the helm for a knowledgeable Whole Slide Image (WSI) exploration are presented. Indeed, in the perspective of a traceable ethical healthcare as the rise of big data challenges, semantic technologies will play a fundamental role in the future of digital as the integrative pathology. The modelling of visual appearance, very close to the cognitive and perceptual points of view, is considered as a key point for an ergonomic interface between WSI and the pathologist. In the continuation of the perceptive problems, the modelling of the visual appearance as a comparative study between frequential and spatial colour textons is presented followed by an interesting approach using Fourier ptychography. Coming close to computer-aided diagnosis, we selected an interesting weak supervision approach. Finally, promising advances in heterogeneity and precise localisation problems complete the range of the selected papers, coming closer and closer to daily routine in histopathology. We believe that the digital pathology will be a bridge for a smoother integration of all these challenges and viewpoints in the future of the pathology and we hope being able to participate to the on-going revolution of digital pathology by bringing them to your attention.

A model of tumor architecture and spatial interactions with tumor microenvironment in breast carcinoma

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.