Personalizable AI platform for universal access to research and diagnosis in digital pathology.

BACKGROUND AND MOTIVATION: Digital pathology has been evolving over the last years, proposing significant workflow advantages that have fostered its adoption in professional environments. Patient clinical and image data are readily available in remote data banks that can be consumed efficiently over standard communication technologies. The appearance of new imaging techniques and advanced artificial intelligence algorithms has significantly reduced the burden on medical professionals by speeding up the screening process. Despite these advancements, the usage of digital pathology in professional environments has been slowed down by poor interoperability between services resulting from a lack of standard interfaces and integrative solutions. This work addresses this issue by proposing a cloud-based digital pathology platform built on standard and open interfaces. METHODS: The work proposes and describes a vendor-neutral platform that provides interfaces for managing digital slides, and medical reports, and integrating digital image analysis services compatible with existing standards. The solution integrates the open-source plugin-based Dicoogle PACS for interoperability and extensibility, which grants the proposed solution great feature customization. RESULTS: The solution was developed in collaboration with iPATH research project partners, including the validation by medical pathologists. The result is a pure Web collaborative framework that supports both research and production environments. A total of 566 digital slides from different pathologies were successfully uploaded to the platform. Using the integration interfaces, a mitosis detection algorithm was successfully installed into the platform, and it was trained with 2400 annotations collected from breast carcinoma images. CONCLUSION: Interoperability is a key factor when discussing digital pathology solutions, as it facilitates their integration into existing institutions' information systems. Moreover, it improves data sharing and integration of third-party services such as image analysis services, which have become relevant in today's digital pathology workflow. The proposed solution fully embraces the DICOM standard for digital pathology, presenting an interoperable cloud-based solution that provides great feature customization thanks to its extensible architecture.

Insights into S. aureus-Induced Bone Deformation in a Mouse Model of Chronic Osteomyelitis Using Fluorescence and Raman Imaging.

Osteomyelitis is an infection of the bone that is often difficult to treat and causes a significant healthcare burden. Staphylococcus aureus is the most common pathogen causing osteomyelitis. Osteomyelitis mouse models have been established to gain further insights into the pathogenesis and host response. Here, we use an established S. aureus hematogenous osteomyelitis mouse model to investigate morphological tissue changes and bacterial localization in chronic osteomyelitis with a focus on the pelvis. X-ray imaging was performed to follow the disease progression. Six weeks post infection, when osteomyelitis had manifested itself with a macroscopically visible bone deformation in the pelvis, we used two orthogonal methods, namely fluorescence imaging and label-free Raman spectroscopy, to characterise tissue changes on a microscopic scale and to localise bacteria in different tissue regions. Hematoxylin and eosin as well as Gram staining were performed as a reference method. We could detect all signs of a chronically florid tissue infection with osseous and soft tissue changes as well as with different inflammatory infiltrate patterns. Large lesions dominated in the investigated tissue samples. Bacteria were found to form abscesses and were distributed in high numbers in the lesion, where they could occasionally also be detected intracellularly. In addition, bacteria were found in lower numbers in surrounding muscle tissue and even in lower numbers in trabecular bone tissue. The Raman spectroscopic imaging revealed a metabolic state of the bacteria with reduced activity in agreement with small cell variants found in other studies. In conclusion, we present novel optical methods to characterise bone infections, including inflammatory host tissue reactions and bacterial adaptation.

IMAGE-IN: Interactive web-based multidimensional 3D visualizer for multi-modal microscopy images.

Advances in microscopy hardware and storage capabilities lead to increasingly larger multidimensional datasets. The multiple dimensions are commonly associated with space, time, and color channels. Since "seeing is believing", it is important to have easy access to user-friendly visualization software. Here we present IMAGE-IN, an interactive web-based multidimensional (N-D) viewer designed specifically for confocal laser scanning microscopy (CLSM) and focused ion beam scanning electron microscopy (FIB-SEM) data, with the goal of assisting biologists in their visualization and analysis tasks and promoting digital workflows. This new visualization platform includes intuitive multidimensional opacity fine-tuning, shading on/off, multiple blending modes for volume viewers, and the ability to handle multichannel volumetric data in volume and surface views. The software accepts a sequence of image files or stacked 3D images as input and offers a variety of viewing options ranging from 3D volume/surface rendering to multiplanar reconstruction approaches. We evaluate the performance by comparing the loading and rendering timings of a heterogeneous dataset of multichannel CLSM and FIB-SEM images on two devices with installed graphic cards, as well as comparing rendered image quality between ClearVolume (the ImageJ open-source desktop viewer), Napari (the Python desktop viewer), Imaris (the closed-source desktop viewer), and our proposed IMAGE-IN web viewer.

DICOMization of Proprietary Files Obtained from Confocal, Whole-Slide, and FIB-SEM Microscope Scanners.

The evolution of biomedical imaging technology is allowing the digitization of hundreds of glass slides at once. There are multiple microscope scanners available in the market including low-cost solutions that can serve small centers. Moreover, new technology is being researched to acquire images and new modalities are appearing in the market such as electron microscopy. This reality offers new diagnostics tools to clinical practice but emphasizes also the lack of multivendor system's interoperability. Without the adoption of standard data formats and communications methods, it will be impossible to build this industry through the installation of vendor-neutral archives and the establishment of telepathology services in the cloud. The DICOM protocol is a feasible solution to the aforementioned problem because it already provides an interface for visible light and whole slide microscope imaging modalities. While some scanners currently have DICOM interfaces, the vast majority of manufacturers continue to use proprietary solutions. This article proposes an automated DICOMization pipeline that can efficiently transform distinct proprietary microscope images from CLSM, FIB-SEM, and WSI scanners into standard DICOM with their biological information maintained within their metadata. The system feasibility and performance were evaluated with fifteen distinct proprietary modalities, including stacked WSI samples. The results demonstrated that the proposed methodology is accurate and can be used in production. The normalized objects were stored through the standard communications in the Dicoogle open-source archive.

EMIF Catalogue: A collaborative platform for sharing and reusing biomedical data.

OBJECTIVE: The collaboration and knowledge exchange between researchers are often hindered by the nonexistence of accurate information about which databases may support research studies. Even though a considerable amount of patient health information does exist, it is usually distributed and hidden in many institutions. The goal of this project is to provide, for any research community, a holistic view of biomedical datasets of interests, from which researchers can explore several distinct levels of granularity. METHODS: We developed a community-centered approach to facilitate data sharing while ensuring privacy. A dynamic schema allows exposing any metadata model about existing repositories. The framework was developed following a modular plugin-based architecture that facilitates the integration of internal and external tools. RESULTS: The EMIF Catalogue, a web platform for sharing and reusing biomedical data. Through this system, data custodians can publish and share different levels of information, while the researchers can search for databases that fulfill research requirements. CONCLUSIONS: The EMIF Catalogue currently fosters several distinct research communities, with different levels of data governance, combining, for instance, data available in pan-European EHR and Alzheimer cohorts. This portal is publicly available at https://emif-catalogue.eu.

MONTRA: An agile architecture for data publishing and discovery.

BACKGROUND AND OBJECTIVE: Data catalogues are a common form of capturing and presenting information about a specific kind of entity (e.g. products, services, professionals, datasets, etc.). However, the construction of a web-based catalogue for a particular scenario normally implies the development of a specific and dedicated solution. In this paper, we present MONTRA, a rapid-application development framework designed to facilitate the integration and discovery of heterogeneous objects, which may be characterized by distinct data structures. METHODS: MONTRA was developed following a plugin-based architecture to allow dynamic composition of services over represented datasets. The core of MONTRA's functionalities resides in a flexible data skeleton used to characterize data entities, and from which a fully-fledged web data catalogue is automatically generated, ensuring access control and data privacy. RESULTS: MONTRA is being successfully used by several European projects to collect and manage biomedical databases. In this paper, we describe three of these applications scenarios. CONCLUSIONS: This work was motivated by the plethora of geographically scattered biomedical repositories, and by the role they can play altogether for the understanding of diseases and of the real-world effectiveness of treatments. Using metadata to expose datasets' characteristics, MONTRA greatly simplifies the task of building data catalogues. The source code is publicly available at https://github.com/bioinformatics-ua/montra.

A Dynamic Approach to Support Interoperability for Medical Reports Using DICOM SR.

The standardization of data structures for clinical observations in medical imaging environments is a relatively recent effort. DICOM standard defines a set of supplements for different medical reports denominated as Structured Reports (SR). In 2013, Integrating the Healthcare Enterprise (IHE) also followed this trend by publishing the profile Management of Radiology Report Templates (MRRT). However, the generalized adoption of these normalized reports has been delayed due to several factors. In fact, numerous medical institutions still use proprietary formats that do not promote sharing and remote access. New strategies to incentivise the adoption of normalized report templates are needed to make them interoperable between distinct applications. This article proposes a new method to automatically generate DICOM SR from distinct data sources. It encompasses a flexible mapping schema that can be used with distinct medical imaging modalities. Our ultimate goal is to encourage the usage of DICOM SR by providing an effortless method to convert proprietary formats into standard ones. Moreover, the developed methods can be also used for supporting IHE MRRT profiles, making the reports accessible across different information systems and institutions.

A Routing Mechanism for Cloud Outsourcing of Medical Imaging Repositories.

Web-based technologies have been increasingly used in picture archive and communication systems (PACS), in services related to storage, distribution, and visualization of medical images. Nowadays, many healthcare institutions are outsourcing their repositories to the cloud. However, managing communications between multiple geo-distributed locations is still challenging due to the complexity of dealing with huge volumes of data and bandwidth requirements. Moreover, standard methodologies still do not take full advantage of outsourced archives, namely because their integration with other in-house solutions is troublesome. In order to improve the performance of distributed medical imaging networks, a smart routing mechanism was developed. This includes an innovative cache system based on splitting and dynamic management of digital imaging and communications in medicine objects. The proposed solution was successfully deployed in a regional PACS archive. The results obtained proved that it is better than conventional approaches, as it reduces remote access latency and also the required cache storage space.

Architecture to Summarize Patient-Level Data Across Borders and Countries.

Translational medicine is becoming fundamental in promoting information flow between basic research and clinical practice, and in improving patients' health. The need for efficient systems to process and share information from multiple sources--including distinct areas of medicine--is a pressing need in biomedical research. Nevertheless, healthcare information systems are fragmented over different databases, medical institutions, and geographical locations. There are already several approaches to tackle this problem based on centralized or distributed solutions. Nonetheless, mainly due to privacy reasons, these models only work for specific silos. In this paper, we present a new ecosystem for connecting database owners and researchers. Our approach consists of gathering, via a common fingerprint, an extensive characterization of dispersed databases. This fingerprint typically contains high-level aggregated information addressing questions at a population level and allowing, for instance, quick identification of databases with data that may help to answer a specific research question. This work is being conducted in the context of EMIF (European Medical Information Framework), an IMI (The Innovative Medicines Initiative) joint undertaking funded project, wherein the Catalogue is being used to collect data from cohorts and Electronic Health Record systems of several European countries.

Multi-provider architecture for cloud outsourcing of medical imaging repositories.

Over the last few years, the extended usage of medical imaging procedures has raised the medical community attention towards the optimization of their workflows. More recently, the federation of multiple institutions into a seamless distribution network has brought hope of increased quality healthcare services along with more efficient resource management. As a result, medical institutions are constantly looking for the best infrastructure to deploy their imaging archives. In this scenario, public cloud infrastructures arise as major candidates, as they offer elastic storage space, optimal data availability without great requirements of maintenance costs or IT personnel, in a pay-as-you-go model. However, standard methodologies still do not take full advantage of outsourced archives, namely because their integration with other in-house solutions is troublesome. This document proposes a multi-provider architecture for integration of outsourced archives with in-house PACS resources, taking advantage of foreign providers to store medical imaging studies, without disregarding security. It enables the retrieval of images from multiple archives simultaneously, improving performance, data availability and avoiding the vendor-locking problem. Moreover it enables load balancing and cache techniques.

Screening radiation exposure for quality assurance.

Quality assurance for planned radiation exposure situations (e.g. Digital Radiography, Computed Tomography or Radio Fluoroscopic studies) requires the application of examination-specific scans protocols. These are tailored to patient age or size, body region and clinical indication for ensuring that the dose applied to each patient is as low as reasonably achievable for the clinical purpose of the image acquisition (ALARA principle). The European legal framework--2013/59/EURATOM--points that health authorities will be more pervasive on inspecting the dosimetry applied to patients. This paper discusses these legal alterations and presents an interoperable distributed system for dose monitoring, which is compliant with legal procedures and the IHE Radiation Exposure Monitoring profile (REM). The system combines the most representative stakeholders affected and directly interested in the patient radiological protection: patients, radiologists, practitioners, health authorities, and ethics committee. The system is capable of gathering, in real-time, dose information applied to the patient and storing it in a regional or national wide dose registry. The paper addresses which information should such systems hold and which should be accessed, from each stakeholder perspective. Furthermore, the system may detect irregular dose patterns, which could indicate dose abuses, and signal those findings to the appropriate stakeholders.