Medical Imaging and Privacy in the Era of Artificial Intelligence: Myth, Fallacy, and the Future

Privacy preserving image registration

Image registration is a key task in medical imaging applications, allowing to represent medical images in a common spatial reference frame. Current approaches to image registration are generally based on the assumption that the content of the images is usually accessible in clear form, from which the spatial transformation is subsequently estimated. This common assumption may not be met in practical applications, since the sensitive nature of medical images may ultimately require their analysis under privacy constraints, preventing to openly share the image content. In this work, we formulate the problem of image registration under a privacy preserving regime, where images are assumed to be confidential and cannot be disclosed in clear. We derive our privacy preserving image registration framework by extending classical registration paradigms to account for advanced cryptographic tools, such as secure multi-party computation and homomorphic encryption, that enable the execution of operations without leaking the underlying data. To overcome the problem of performance and scalability of cryptographic tools in high dimensions, we propose several techniques to optimize the image registration operations by using gradient approximations, and by revisiting the use of homomorphic encryption trough packing, to allow the efficient encryption and multiplication of large matrices. We focus on registration methods of increasing complexity, including rigid, affine, and non-linear registration based on cubic splines or diffeomorphisms parameterized by time-varying velocity fields. In all these settings, we demonstrate how the registration problem can be naturally adapted for accounting to privacy-preserving operations, and illustrate the effectiveness of PPIR on a variety of registration tasks.

Unlocking the potential of big data and AI in medicine: insights from biobanking

Big data and artificial intelligence are key elements in the medical field as they are expected to improve accuracy and efficiency in diagnosis and treatment, particularly in identifying biomedically relevant patterns, facilitating progress towards individually tailored preventative and therapeutic interventions. These applications belong to current research practice that is data-intensive. While the combination of imaging, pathological, genomic, and clinical data is needed to train algorithms to realize the full potential of these technologies, biobanks often serve as crucial infrastructures for data-sharing and data flows. In this paper, we argue that the 'data turn' in the life sciences has increasingly re-structured major infrastructures, which often were created for biological samples and associated data, as predominantly data infrastructures. These have evolved and diversified over time in terms of tackling relevant issues such as harmonization and standardization, but also consent practices and risk assessment. In line with the datafication, an increased use of AI-based technologies marks the current developments at the forefront of the big data research in life science and medicine that engender new issues and concerns along with opportunities. At a time when secure health data environments, such as European Health Data Space, are in the making, we argue that such meta-infrastructures can benefit both from the experience and evolution of biobanking, but also the current state of affairs in AI in medicine, regarding good governance, the social aspects and practices, as well as critical thinking about data practices, which can contribute to trustworthiness of such meta-infrastructures.

Real world validation of an AI-based CT hemorrhage detection tool

Introduction

Intracranial hemorrhage (ICH) is a potentially life-threatening medical event that requires expedited diagnosis with computed tomography (CT). Automated medical imaging triaging tools can rapidly bring scans containing critical abnormalities, such as ICH, to the attention of radiologists and clinicians. Here, we retrospectively investigated the real-world performance of VeriScout™, an artificial intelligence-based CT hemorrhage detection and triage tool.

Methods

Ground truth for the presence or absence of ICH was iteratively determined by expert consensus in an unselected dataset of 527 consecutively acquired non-contrast head CT scans, which were sub-grouped according to the presence of artefact, post-operative features and referral source. The performance of VeriScout™ was compared with the ground truths for all groups.

Results

VeriScout™ detected hemorrhage with a sensitivity of 0.92 (CI 0.84-0.96) and a specificity of 0.96 (CI 0.94-0.98) in the global dataset, exceeding the sensitivity of general radiologists (0.88) with only a minor relative decrement in specificity (0.98). Crucially, the AI tool detected 13/14 cases of subarachnoid hemorrhage, a potentially fatal condition that is often missed in emergency department settings. There was no decrement in the performance of VeriScout™ in scans containing artefact or postoperative change. Using an integrated informatics platform, VeriScout™ was deployed into the existing radiology workflow. Detected hemorrhage cases were flagged in the hospital radiology information system (RIS) and relevant, annotated, preview images made available in the picture archiving and communications system (PACS) within 10 min.

Conclusion

AI-based radiology worklist prioritization for critical abnormalities, such as ICH, may enhance patient care without adding to radiologist or clinician burden.

Predicting demographics from meibography using deep learning

This study introduces a deep learning approach to predicting demographic features from meibography images. A total of 689 meibography images with corresponding subject demographic data were used to develop a deep learning model for predicting gland morphology and demographics from images. The model achieved on average 77%, 76%, and 86% accuracies for predicting Meibomian gland morphological features, subject age, and ethnicity, respectively. The model was further analyzed to identify the most highly weighted gland morphological features used by the algorithm to predict demographic characteristics. The two most important gland morphological features for predicting age were the percent area of gland atrophy and the percentage of ghost glands. The two most important morphological features for predicting ethnicity were gland density and the percentage of ghost glands. The approach offers an alternative to traditional associative modeling to identify relationships between Meibomian gland morphological features and subject demographic characteristics. This deep learning methodology can currently predict demographic features from de-identified meibography images with better than 75% accuracy, a number which is highly likely to improve in future models using larger training datasets, which has significant implications for patient privacy in biomedical imaging.

A digital mask to safeguard patient privacy

The storage of facial images in medical records poses privacy risks due to the sensitive nature of the personal biometric information that can be extracted from such images. To minimize these risks, we developed a new technology, called the digital mask (DM), which is based on three-dimensional reconstruction and deep-learning algorithms to irreversibly erase identifiable features, while retaining disease-relevant features needed for diagnosis. In a prospective clinical study to evaluate the technology for diagnosis of ocular conditions, we found very high diagnostic consistency between the use of original and reconstructed facial videos (κ ≥ 0.845 for strabismus, ptosis and nystagmus, and κ = 0.801 for thyroid-associated orbitopathy) and comparable diagnostic accuracy (P ≥ 0.131 for all ocular conditions tested) was observed. Identity removal validation using multiple-choice questions showed that compared to image cropping, the DM could much more effectively remove identity attributes from facial images. We further confirmed the ability of the DM to evade recognition systems using artificial intelligence-powered re-identification algorithms. Moreover, use of the DM increased the willingness of patients with ocular conditions to provide their facial images as health information during medical treatment. These results indicate the potential of the DM algorithm to protect the privacy of patients' facial images in an era of rapid adoption of digital health technologies.

A Two-Stage De-Identification Process for Privacy-Preserving Medical Image Analysis

Identification and re-identification are two major security and privacy threats to medical imaging data. De-identification in DICOM medical data is essential to preserve the privacy of patients' Personally Identifiable Information (PII) and requires a systematic approach. However, there is a lack of sufficient detail regarding the de-identification process of DICOM attributes, for example, what needs to be considered before removing a DICOM attribute. In this paper, we first highlight and review the key challenges in the medical image data de-identification process. In this paper, we develop a two-stage de-identification process for CT scan images available in DICOM file format. In the first stage of the de-identification process, the patient's PII-including name, date of birth, etc., are removed at the hospital facility using the export process available in their Picture Archiving and Communication System (PACS). The second stage employs the proposed DICOM de-identification tool for an exhaustive attribute-level investigation to further de-identify and ensure that all PII has been removed. Finally, we provide a roadmap for future considerations to build a semi-automated or automated tool for the DICOM datasets de-identification.

Deep Learning in Large and Multi-Site Structural Brain MR Imaging Datasets

Large, multi-site, heterogeneous brain imaging datasets are increasingly required for the training, validation, and testing of advanced deep learning (DL)-based automated tools, including structural magnetic resonance (MR) image-based diagnostic and treatment monitoring approaches. When assembling a number of smaller datasets to form a larger dataset, understanding the underlying variability between different acquisition and processing protocols across the aggregated dataset (termed “batch effects”) is critical. The presence of variation in the training dataset is important as it more closely reflects the true underlying data distribution and, thus, may enhance the overall generalizability of the tool. However, the impact of batch effects must be carefully evaluated in order to avoid undesirable effects that, for example, may reduce performance measures. Batch effects can result from many sources, including differences in acquisition equipment, imaging technique and parameters, as well as applied processing methodologies. Their impact, both beneficial and adversarial, must be considered when developing tools to ensure that their outputs are related to the proposed clinical or research question (i.e., actual disease-related or pathological changes) and are not simply due to the peculiarities of underlying batch effects in the aggregated dataset. We reviewed applications of DL in structural brain MR imaging that aggregated images from neuroimaging datasets, typically acquired at multiple sites. We examined datasets containing both healthy control participants and patients that were acquired using varying acquisition protocols. First, we discussed issues around Data Access and enumerated the key characteristics of some commonly used publicly available brain datasets. Then we reviewed methods for correcting batch effects by exploring the two main classes of approaches: Data Harmonization that uses data standardization, quality control protocols or other similar algorithms and procedures to explicitly understand and minimize unwanted batch effects; and Domain Adaptation that develops DL tools that implicitly handle the batch effects by using approaches to achieve reliable and robust results. In this narrative review, we highlighted the advantages and disadvantages of both classes of DL approaches, and described key challenges to be addressed in future studies.

The Ethics of Artificial Intelligence in Pathology and Laboratory Medicine: Principles and Practice

Growing numbers of artificial intelligence applications are being developed and applied to pathology and laboratory medicine. These technologies introduce risks and benefits that must be assessed and managed through the lens of ethics. This article describes how long-standing principles of medical and scientific ethics can be applied to artificial intelligence using examples from pathology and laboratory medicine.