Digital pathology in personalized cancer therapy

The development of small molecule inhibitors of growth factor receptors, and the discovery of somatic mutations of the tyrosine kinase domain, have resulted in new paradigms for cancer therapy. Digital microscopy is an important tool for surgical pathologists. The achievements in the digital pathology field have modified the workflow of pathomorphology labs, enhanced the pathologist's role in diagnostics, and increased their contribution to personalized targeted medicine. Digital image analysis is now available in a variety of platforms to improve quantification performance of diagnostic pathology. We here describe the state of digital microscopy as it applies to the field of quantitative immunohistochemistry of biomarkers related to the clinical personalized targeted therapy of breast cancer, non-small lung cancer and colorectal cancer: HER-2, EGFR, KRAS and BRAF genes. The information is derived from the experience of the authors and a review of the literature.     

Expanding application of digital pathology in Japan - from education,telepathology to autodiagnosis

Background

Digital pathology, i.e., applications of digital information technologies to pathology practice, has been expanding in the recent decades and the mode of pathology diagnostic practice is changing with enhanced precision. In the present study the changing processes of digital pathology in Japan were investigated and trends to future were discussed.

Methods

The changing status of digital pathology was investigated through reviewing the records of annual meetings of the Japanese Research Society of Telepathology and Pathology Informatics (JRST-PI) and of the Japanese pathology related medical and informatics journals. The results of the Japanese questionnaire survey conducted in 2008-2009 on telepathology and virtual slide were also reviewed. In addition effectiveness of an experimental automatic pathology diagnostic aid system using computer artificial intelligence was investigated by checking its rate of correct diagnosis for given prostate carcinoma digital images.

Results

Telepathology played a central role in the development of digital pathology in Japan. Both macroscopic and microscopic pathology digital images were routinely generated and used for diagnostic purposes in major hospitals. Virtual slide (VS) digital images were used first for education then for conference, consultation and also gradually for routine diagnosis and telepathology. The experimental automatic diagnostic aid system achieved the rate of correct diagnosis around 95% for prostate carcinoma and its use for automatic mapping of cancerous areas in a given tissue image was successful.

Conclusions

Advance in the digital information technologies gave revolutionary impacts on pathology education, conference, consultation, diagnosis, telepathology and also on pathology diagnostic procedures in Japan. The future will be bright for pathologists by the advanced digital pathology but we should pay attention to make the technologies and their effects under our control.

     

Optical and digital microscopic imaging techniques and applications in pathology

The conventional optical microscope has been the primary tool in assisting pathological examinations. The modern digital pathology combines the power of microscopy, electronic detection, and computerized analysis. It enables cellular-, molecular-, and genetic-imaging at high efficiency and accuracy to facilitate clinical screening and diagnosis. This paper first reviews the fundamental concepts of microscopic imaging and introduces the technical features and associated clinical applications of optical microscopes, electron microscopes, scanning tunnel microscopes, and fluorescence microscopes. The interface of microscopy with digital image acquisition methods is discussed. The recent developments and future perspectives of contemporary microscopic imaging techniques such as three-dimensional and in vivo imaging are analyzed for their clinical potentials.     

Web conferencing systems: Skype and MSN in telepathology

Virtual pathology is a very important tool that can be used in several ways, including interconsultations with specialists in many areas and for frozen sections. We considered in this work the use of Windows Live Messenger and Skype for image transmission. The conference was made through wide broad internet using Nikon E 200 microscope and Digital Samsung Colour SCC-131 camera. Internet speed for transmission varied from 400 Kb to 2.0 Mb. Both programs allow voice transmission concomitant to image, so the communication between the involved pathologists was possible using microphones and speakers. A live image could be seen by the receptor pathologist who was able to ask for moving the field or increase/diminish the augmentation. No phone call or typing required. The programs MSN and Skype can be used in many ways and with different operational systems installed in the computer. The capture system is simple and relatively cheap, what proves the viability of the system to be used in developing countries and in cities where do not exist pathologists. With the improvement of software and the improvement of digital image quality, associated to the use of the high speed broad band Internet this will be able to become a new modality in surgical pathology.     

Clustering methods applied in the detection of Ki67 hot-spots in whole tumor slide images: An efficient way to characterize heterogeneous tissue-based biomarkers

Whole-slide scanners allow the digitization of an entire histological slide at very high resolution. This new acquisition technique opens a wide range of possibilities for addressing challenging image analysis problems, including the identification of tissue-based biomarkers. In this study, we use whole-slide scanner technology for imaging the proliferating activity patterns in tumor slides based on Ki67 immunohistochemistry. Faced with large images, pathologists require tools that can help them identify tumor regions that exhibit high proliferating activity, called "hot-spots" (HSs). Pathologists need tools that can quantitatively characterize these HS patterns. To respond to this clinical need, the present study investigates various clustering methods with the aim of identifying Ki67 HSs in whole tumor slide images. This task requires a method capable of identifying an unknown number of clusters, which may be highly variable in terms of shape, size, and density. We developed a hybrid clustering method, referred to as Seedlink. Compared to manual HS selections by three pathologists, we show that Seedlink provides an efficient way of detecting Ki67 HSs and improves the agreement among pathologists when identifying HSs. ? 2012 International Society for Advancement of Cytometry.     

Computerized analysis of cellular features and biomarkers for cytologic diagnosis of early lung cancer

OBJECTIVE: To present a set of novel computerized analysis algorithms to construct a computer-aided cytologic diagnosis (CACD) system to differentiate lung cancer biomarkers and identify cancer cells in the tissue-based specimen images. STUDY DESIGN: Molecular methods, including application of cancer-specific markers, may prove to be complementary to cytology diagnosis, especially when they are combined with CACD system for biomarker assessment. We trained a novel CACD system to recognize expression of the cancer biomarkers histone H2AX in lung cancer cells and then tested the accuracy of this system to distinguish resected lung cancer from preneoplastic and normal tissues. The major characteristics of CACD algorithms is to adapt detection parameters according to cellular image contents. Our newly developed wavelet transform is able to adaptively select different resolution and orientation features based on image content requirements. RESULTS: Visual, statistical and quantitative results as CACD performance evaluation are presented in this paper. CONCLUSION: The presented algorithms and CACD system for cellular feature enhancement, segmentation and classification are very important in distinguishing benign and malignant lesions.     

Segmentation of Image Data from Complex Organotypic 3D Models of Cancer Tissues with Markov Random Fields

Organotypic, three dimensional (3D) cell culture models of epithelial tumour types such as prostate cancer recapitulate key aspects of the architecture and histology of solid cancers. Morphometric analysis of multicellular 3D organoids is particularly important when additional components such as the extracellular matrix and tumour microenvironment are included in the model. The complexity of such models has so far limited their successful implementation. There is a great need for automatic, accurate and robust image segmentation tools to facilitate the analysis of such biologically relevant 3D cell culture models. We present a segmentation method based on Markov random fields (MRFs) and illustrate our method using 3D stack image data from an organotypic 3D model of prostate cancer cells co-cultured with cancer-associated fibroblasts (CAFs). The 3D segmentation output suggests that these cell types are in physical contact with each other within the model, which has important implications for tumour biology. Segmentation performance is quantified using ground truth labels and we show how each step of our method increases segmentation accuracy. We provide the ground truth labels along with the image data and code. Using independent image data we show that our segmentation method is also more generally applicable to other types of cellular microscopy and not only limited to fluorescence microscopy.     

Closing the translation gap: AI applications in digital pathology

Recent advances in artificial intelligence show tremendous promise to improve the accuracy, reproducibility, and availability of medical diagnostics across a number of medical subspecialities. This is especially true in the field of digital pathology, which has recently witnessed a surge in publications describing state-of-the-art performance for machine learning models across a wide range of diagnostic applications. Nonetheless, despite this promise, there remain significant gaps in translating applications for any of these technologies into actual clinical practice. In this review, we will first give a brief overview of the recent progress in applying AI to digitized pathology images, focusing on how these tools might be applied in clinical workflows in the near term to improve the accuracy and efficiency of pathologists. Then we define and describe in detail the various factors that need to be addressed in order to successfully close the “translation gap” for AI applications in digital pathology.     

Automatic deep learning-based pleural effusion classification in lung ultrasound images for respiratory pathology diagnosis

Lung ultrasound (LUS) imaging as a point-of-care diagnostic tool for lung pathologies has been proven superior to X-ray and comparable to CT, enabling earlier and more accurate diagnosis in real-time at the patient’s bedside. The main limitation to widespread use is its dependence on the operator training and experience. COVID-19 lung ultrasound findings predominantly reflect a pneumonitis pattern, with pleural effusion being infrequent. However, pleural effusion is easy to detect and to quantify, therefore it was selected as the subject of this study, which aims to develop an automated system for the interpretation of LUS of pleural effusion. A LUS dataset was collected at the Royal Melbourne Hospital which consisted of 623 videos containing 99,209 2D ultrasound images of 70 patients using a phased array transducer. A standardized protocol was followed that involved scanning six anatomical regions providing complete coverage of the lungs for diagnosis of respiratory pathology. This protocol combined with a deep learning algorithm using a Spatial Transformer Network provides a basis for automatic pathology classification on an image-based level. In this work, the deep learning model was trained using supervised and weakly supervised approaches which used frame- and video-based ground truth labels respectively. The reference was expert clinician image interpretation. Both approaches show comparable accuracy scores on the test set of 92.4% and 91.1%, respectively, not statistically significantly different. However, the video-based labelling approach requires significantly less effort from clinical experts for ground truth labelling.     

The concept of structural entropy in tissue-based diagnosis

The concept of entropy is described and its characteristics discussed as applied in tissue-based diagnosis. The concept of entropy includes at least 2 points of view--thermodynamic and informatics perspectives. Entropy can be defined by various methods: a measure of nonreversible energy or of system heterogeneity or as information content of a message. It is a statistical measure and system feature composed of macrosystems and microsystems. The structural entropy of macrosystems relies on definition of individual events and built-in microsystems. It depends on interaction of events and probability distribution (e.g., Gibbs-Boltzmann). The more generalized q-entropy involves account interaction of neighboring events. The thermodynamic concept of structural entropy can be expanded according to the theorem of Prigogine, introducing entropy flow. In biology, cells usually serve for events in the thermodynamic entropy approach. Entropy has been successfully used to describe tissue sections, nuclei and nuclear substructures such as DNA content, chromosomes and AgNORs. The concept of entropy reveals a close relationship of structural entropy and prognosis-associated diagnosis of malignancies. It is useful in prognosis-associated, tissue-based diagnosis in breast, prostate, bladder and lung cancer and is a promising expansion of image analysis in diagnostic agnosis in breast, prostate, bladder and lung cancer and is a promising expansion of image analysis in diagnostic pathology.     

Digital cytology: current state of the art and prospects for the future

The growth of digital methods in pathology is accelerating. Digital images can be used for a variety of applications in cytology, including rapid interpretations, primary diagnosis and second opinions, continuing education and proficiency testing. All of these functions can be performed using small static digital images, real-time dynamic digital microscopy, or whole-slide images. This review will discuss the general principles of digital pathology, its methods and applications to cytologic specimens. As cytologic specimens have unique features compared to histopathology specimens, the key differences will be discussed. Technical and administrative issues in digital pathology applications and the outlook for the future of the field will be presented.     

Grid computing in image analysis

Diagnostic surgical pathology or tissue–based diagnosis still remains the most reliable and specific diagnostic medical procedure. The development of whole slide scanners permits the creation of virtual slides and to work on so-called virtual microscopes. In addition to interactive work on virtual slides approaches have been reported that introduce automated virtual microscopy, which is composed of several tools focusing on quite different tasks. These include evaluation of image quality and image standardization, analysis of potential useful thresholds for object detection and identification (segmentation), dynamic segmentation procedures, adjustable magnification to optimize feature extraction, and texture analysis including image transformation and evaluation of elementary primitives. Grid technology seems to possess all features to efficiently target and control the specific tasks of image information and detection in order to obtain a detailed and accurate diagnosis. Grid technology is based upon so-called nodes that are linked together and share certain communication rules in using open standards. Their number and functionality can vary according to the needs of a specific user at a given point in time. When implementing automated virtual microscopy with Grid technology, all of the five different Grid functions have to be taken into account, namely 1) computation services, 2) data services, 3) application services, 4) information services, and 5) knowledge services. Although all mandatory tools of automated virtual microscopy can be implemented in a closed or standardized open system, Grid technology offers a new dimension to acquire, detect, classify, and distribute medical image information, and to assure quality in tissue–based diagnosis.     

Mitotic figure recognition: agreement among pathologists and computerized detector

Despite the prognostic importance of mitotic count as one of the components of the Bloom-Richardson grade, several studies have found that pathologists' agreement on the mitotic grade is fairly modest. Collecting a set of more than 4,200 candidate mitotic figures, we evaluate pathologists' agreement on individual figures, and train a computerized system for mitosis detection, comparing its performance to the classifications of three pathologists. The system's and the pathologists' classifications are based on evaluation of digital micrographs of hematoxylin and eosin stained breast tissue. On figures where the majority of pathologists agree on a classification, we compare the performance of the trained system to that of the individual pathologists. We find that the level of agreement of the pathologists ranges from slight to moderate, with strong biases, and that the system performs competitively in rating the ground truth set. This study is a step towards automatic mitosis count to accelerate a pathologist's work and improve reproducibility.     

Online teaching of inflammatory skin pathology by a French-speaking International University Network

Introduction

Developments in technology, web-based teaching and whole slide imaging have broadened the teaching horizon in anatomic pathology. Creating online learning material including many types of media such as radiologic images, whole slides, videos, clinical and macroscopic photographs, is now accessible to most universities. Unfortunately, a major limiting factor to maintain and update the learning material is the amount of resources needed. In this perspective, a French-national university network was initiated in 2011 to build joint online teaching modules consisting of clinical cases and tests. The network has since expanded internationally to Québec, Switzerland and Ivory Coast.

Method

One of the first steps of the project was to build a learning module on inflammatory skin pathology for interns and residents in pathology and dermatology. A pathology resident from Québec spent 6 weeks in France and Switzerland to develop the contents and build the module on an e-learning Moodle platform under the supervision of two dermatopathologists. The learning module contains text, interactive clinical cases, tests with feedback, virtual slides, images and clinical photographs. For that module, the virtual slides are decentralized in 2 universities (Bordeaux and Paris 7). Each university is responsible of its own slide scanning, image storage and online display with virtual slide viewers.

Results

The module on inflammatory skin pathology includes more than 50 web pages with French original content, tests and clinical cases, links to over 45 virtual images and more than 50 microscopic and clinical photographs. The whole learning module is being revised by four dermatopathologists and two senior pathologists. It will be accessible to interns and residents in the spring of 2014. The experience and knowledge gained from that work will be transferred to the next international resident whose work will be aimed at creating lung and breast pathology learning modules.

Conclusion

The challenges of sustaining a project of this scope are numerous. The technical aspect of whole-slide imaging and storage needs to be developed by each university or group. The content needs to be regularly updated and its accuracy reviewed by experts in each individual domain. The learning modules also need to be promoted within the academic community to ensure maximal benefit for trainees. A collateral benefit of the project was the establishment of international partnerships between French-speaking universities and pathologists with the common goal of promoting pathology education through the use of multi-media technology including whole slide imaging.

     

Application of radiomics and machine learning in head and neck cancers

With the continuous development of medical image informatics technology, more and more high-throughput quantitative data could be extracted from digital medical images, which has resulted in a new kind of omics-Radiomics. In recent years, in addition to genomics, proteomics and metabolomics, radiomic has attracted the interest of more and more researchers. Compared to other omics, radiomics can be perfectly integrated with clinical data, even with the pathology and molecular biomarker, so that the study can be closer to the clinical reality and more revealing of the tumor development. Mass data will also be generated in this process. Machine learning, due to its own characteristics, has a unique advantage in processing massive radiomic data. By analyzing mass amounts of data with strong clinical relevance, people can construct models that more accurately reflect tumor development and progression, thereby providing the possibility of personalized and sequential treatment of patients. As one of the cancer types whose treatment and diagnosis rely on imaging examination, radiomics has a very broad application prospect in head and neck cancers (HNC). Until now, there have been some notable results in HNC. In this review, we will introduce the concepts and workflow of radiomics and machine learning and their current applications in head and neck cancers, as well as the directions and applications of artificial intelligence in the treatment and diagnosis of HNC.     

Autism spectrum disorder detection from semi-structured and unstructured medical data

Autism spectrum disorder (ASD) is a developmental disorder that significantly impairs patients’ ability to perform normal social interaction and communication. Moreover, the diagnosis procedure of ASD is highly time-consuming, labor-intensive, and requires extensive expertise. Although there exists no known cure for ASD, there is consensus among clinicians regarding the importance of early intervention for the recovery of ASD patients. Therefore, to benefit autism patients by enhancing their access to treatments such as early intervention, we aim to develop a robust machine learning-based system for autism detection by using Natural Language Processing techniques based on information extracted from medical forms of potential ASD patients. Our detecting framework involves converting semi-structured and unstructured medical forms into digital format, preprocessing, learning document representation, and finally, classification. Testing results are evaluated against the ground truth set by expert clinicians and the proposed system achieve a 83.4% accuracy and 91.1% recall, which is very promising. The proposed ASD detection framework could significantly simplify and shorten the procedure of ASD diagnosis.     

Virtual microscopy systems: analysis and perspectives

Microscopy has been constantly evolving since the end of the Twentieth Century, with the introduction of new resources which have improved its practice. For example, the use of the virtual microscope has reached a high level of maturity; it is a synergy among disciplines such as pathology, histology, medical informatics and image analysis. This technology has moved forward many paradigms in research, diagnosis, education and medical training. The virtual microscopy systems require the digitalization of a physical slide, using motorized microscopes, pre and post image processing, compression, transmission and visualization. This article provides an extensive analysis of each of these processes.? The main characteristics of virtual microscopy are presented as well as the impact of these systems in image interpretation and in diagnostic activities.     

Quantitative Imaging Network: Data Sharing and Competitive AlgorithmValidation Leveraging The Cancer Imaging Archive

The Quantitative Imaging Network (QIN), supported by the National Cancer Institute, is designed to promote research and development of quantitative imaging methods and candidate biomarkers for the measurement of tumor response in clinical trial settings. An integral aspect of the QIN mission is to facilitate collaborative activities that seek to develop best practices for the analysis of cancer imaging data. The QIN working groups and teams are developing new algorithms for image analysis and novel biomarkers for the assessment of response to therapy. To validate these algorithms and biomarkers and translate theminto clinical practice, algorithms need to be compared and evaluated on large and diverse data sets. Analysis competitions, or “challenges,” are being conducted within the QIN as a means to accomplish this goal. The QIN has demonstrated, through its leveraging of The Cancer Imaging Archive (TCIA), that data sharing of clinical images across multiple sites is feasible and that it can enable and support these challenges. In addition to Digital Imaging and Communications in Medicine (DICOM) imaging data, many TCIA collections provide linked clinical, pathology, and “ground truth” data generated by readers that could be used for further challenges. The TCIA-QIN partnership is a successful model that provides resources for multisite sharing of clinical imaging data and the implementation of challenges to support algorithm and biomarker validation.     

Evaluation of radiomic texture feature error due to MRI acquisition and reconstruction: A simulation study utilizing ground truth

The purpose of this study was to examine the dependence of image texture features on MR acquisition parameters and reconstruction using a digital MR imaging phantom. MR signal was simulated in a parallel imaging radiofrequency coil setting as well as a single element volume coil setting, with varying levels of acquisition noise, three acceleration factors, and four image reconstruction algorithms. Twenty-six texture features were measured on the simulated images, ground truth images, and clinical brain images. Subtle algorithm-dependent errors were observed on reconstructed phantom images, even in the absence of added noise. Sources of image error include Gibbs ringing at image edge gradients (tissue interfaces) and well-known artifacts due to high acceleration; two of the iterative reconstruction algorithms studied were able to mitigate these image errors. The difference of the texture features from ground truth, and their variance over reconstruction algorithm and parallel imaging acceleration factor, were compared to the clinical “effect size”, i.e., the feature difference between high- and low-grade tumors on T1- and T2-weighted brain MR images of twenty glioma patients. The measured feature error (difference from ground truth) was small for some features, but substantial for others. The feature variance due to reconstruction algorithm and acceleration factor were generally smaller than the clinical effect size. Certain texture features may be preserved by MR imaging, but adequate precautions need to be taken regarding their validity and reliability. We present a general simulation framework for assessing the robustness and accuracy of radiomic textural features under various MR acquisition/reconstruction scenarios.