Automatic de-identification of French electronic health records: a cost-effective approach exploiting distant supervision and deep learning models.

BACKGROUND: Electronic health records (EHRs) contain valuable information for clinical research; however, the sensitive nature of healthcare data presents security and confidentiality challenges. De-identification is therefore essential to protect personal data in EHRs and comply with government regulations. Named entity recognition (NER) methods have been proposed to remove personal identifiers, with deep learning-based models achieving better performance. However, manual annotation of training data is time-consuming and expensive. The aim of this study was to develop an automatic de-identification pipeline for all kinds of clinical documents based on a distant supervised method to significantly reduce the cost of manual annotations and to facilitate the transfer of the de-identification pipeline to other clinical centers. METHODS: We proposed an automated annotation process for French clinical de-identification, exploiting data from the eHOP clinical data warehouse (CDW) of the CHU de Rennes and national knowledge bases, as well as other features. In addition, this paper proposes an assisted data annotation solution using the Prodigy annotation tool. This approach aims to reduce the cost required to create a reference corpus for the evaluation of state-of-the-art NER models. Finally, we evaluated and compared the effectiveness of different NER methods. RESULTS: A French de-identification dataset was developed in this work, based on EHRs provided by the eHOP CDW at Rennes University Hospital, France. The dataset was rich in terms of personal information, and the distribution of entities was quite similar in the training and test datasets. We evaluated a Bi-LSTM + CRF sequence labeling architecture, combined with Flair + FastText word embeddings, on a test set of manually annotated clinical reports. The model outperformed the other tested models with a significant F1 score of 96,96%, demonstrating the effectiveness of our automatic approach for deidentifying sensitive information. CONCLUSIONS: This study provides an automatic de-identification pipeline for clinical notes, which can facilitate the reuse of EHRs for secondary purposes such as clinical research. Our study highlights the importance of using advanced NLP techniques for effective de-identification, as well as the need for innovative solutions such as distant supervision to overcome the challenge of limited annotated data in the medical domain.

Double color image encryption using iterative phase retrieval algorithm in quaternion gyrator domain.

This paper describes a novel algorithm to encrypt double color images into a single undistinguishable image in quaternion gyrator domain. By using an iterative phase retrieval algorithm, the phase masks used for encryption are obtained. Subsequently, the encrypted image is generated via cascaded quaternion gyrator transforms with different rotation angles. The parameters in quaternion gyrator transforms and phases serve as encryption keys. By knowing these keys, the original color images can be fully restituted. Numerical simulations have demonstrated the validity of the proposed encryption system as well as its robustness against loss of data and additive Gaussian noise.

RED-Net: Residual and Enhanced Discriminative Network for Image Steganalysis in the Internet of Medical Things and Telemedicine.

Internet of Medical Things (IoMT) and telemedicine technologies utilize computers, communications, and medical devices to facilitate off-site exchanges between specialists and patients, specialists, and medical staff. If the information communicated in IoMT is illegally steganography, tampered or leaked during transmission and storage, it will directly impact patient privacy or the consultation results with possible serious medical incidents. Steganalysis is of great significance for the identification of medical images transmitted illegally in IoMT and telemedicine. In this article, we propose a Residual and Enhanced Discriminative Network (RED-Net) for image steganalysis in the internet of medical things and telemedicine. RED-Net consists of a steganographic information enhancement module, a deep residual network, and steganographic information discriminative mechanism. Specifically, a steganographic information enhancement module is adopted by the RED-Net to boost the illegal steganographic signal in texturally complex high-dimensional medical image features. A deep residual network is utilized for steganographic feature extraction and compression. A steganographic information discriminative mechanism is employed by the deep residual network to enable it to recalibrate the steganographic features and drop high-frequency features that are mistaken for steganographic information. Experiments conducted on public and private datasets with data hiding payloads ranging from 0.1bpp/bpnzac-0.5bpp/bpnzac in the spatial and JPEG domain led to RED-Net's steganalysis error PE in the range of 0.0732-0.0010 and 0.231-0.026, respectively. In general, qualitative and quantitative results on public and private datasets demonstrate that the RED-Net outperforms 8 state-of-art steganography detectors.

Pathological Asymmetry-Guided Progressive Learning for Acute Ischemic Stroke Infarct Segmentation.

Quantitative infarct estimation is crucial for diagnosis, treatment and prognosis in acute ischemic stroke (AIS) patients. As the early changes of ischemic tissue are subtle and easily confounded by normal brain tissue, it remains a very challenging task. However, existing methods often ignore or confuse the contribution of different types of anatomical asymmetry caused by intrinsic and pathological changes to segmentation. Further, inefficient domain knowledge utilization leads to mis-segmentation for AIS infarcts. Inspired by this idea, we propose a pathological asymmetry-guided progressive learning (PAPL) method for AIS infarct segmentation. PAPL mimics the step-by-step learning patterns observed in humans, including three progressive stages: knowledge preparation stage, formal learning stage, and examination improvement stage. First, knowledge preparation stage accumulates the preparatory domain knowledge of the infarct segmentation task, helping to learn domain-specific knowledge representations to enhance the discriminative ability for pathological asymmetries by constructed contrastive learning task. Then, formal learning stage efficiently performs end-to-end training guided by learned knowledge representations, in which the designed feature compensation module (FCM) can leverage the anatomy similarity between adjacent slices from the volumetric medical image to help aggregate rich anatomical context information. Finally, examination improvement stage encourages improving the infarct prediction from the previous stage, where the proposed perception refinement strategy (RPRS) further exploits the bilateral difference comparison to correct the mis-segmentation infarct regions by adaptively regional shrink and expansion. Extensive experiments on public and in-house NCCT datasets demonstrated the superiority of the proposed PAPL, which is promising to help better stroke evaluation and treatment.

A multiple catheter tips tracking method in X-ray fluoroscopy images by a new lightweight segmentation network and Bayesian filtering.

During percutaneous coronary intervention, the guiding catheter plays an important role. Tracking the catheter tip placed at the coronary ostium in the X-ray fluoroscopy sequence can obtain image displacement information caused by the heart beating, which can help dynamic coronary roadmap overlap on X-ray fluoroscopy images. Due to a low exposure dose, the X-ray fluoroscopy is noisy and low contrast, which causes some difficulties in tracking. In this paper, we developed a new catheter tip tracking framework. First, a lightweight efficient catheter tip segmentation network is proposed and boosted by a self-distillation training mechanism. Then, the Bayesian filtering post-processing method is used to consider the sequence information to refine the single image segmentation results. By separating the segmentation results into several groups based on connectivity, our framework can track multiple catheter tips. The proposed tracking framework is validated on a clinical X-ray sequence dataset.

Unsharp Structure Guided Filtering for Self-Supervised Low-Dose CT Imaging.

Low-dose computed tomography (LDCT) imaging faces great challenges. Although supervised learning has revealed great potential, it requires sufficient and high-quality references for network training. Therefore, existing deep learning methods have been sparingly applied in clinical practice. To this end, this paper presents a novel Unsharp Structure Guided Filtering (USGF) method, which can reconstruct high-quality CT images directly from low-dose projections without clean references. Specifically, we first employ low-pass filters to estimate the structure priors from the input LDCT images. Then, inspired by classical structure transfer techniques, deep convolutional networks are adopted to implement our imaging method which combines guided filtering and structure transfer. Finally, the structure priors serve as the guidance images to alleviate over-smoothing, as they can transfer specific structural characteristics to the generated images. Furthermore, we incorporate traditional FBP algorithms into self-supervised training to enable the transformation of projection domain data to the image domain. Extensive comparisons and analyses on three datasets demonstrate that the proposed USGF has achieved superior performance in terms of noise suppression and edge preservation, and could have a significant impact on LDCT imaging in the future.

Ontology based log content extraction engine for a posteriori security control.

In a posteriori access control, users are accountable for actions they performed and must provide evidence, when required by some legal authorities for instance, to prove that these actions were legitimate. Generally, log files contain the needed data to achieve this goal. This logged data can be recorded in several formats; we consider here IHE-ATNA (Integrating the healthcare enterprise-Audit Trail and Node Authentication) as log format. The difficulty lies in extracting useful information regardless of the log format. A posteriori access control frameworks often include a log filtering engine that provides this extraction function. In this paper we define and enforce this function by building an IHE-ATNA based ontology model, which we query using SPARQL, and show how the a posteriori security controls are made effective and easier based on this function.

Watermarking as a traceability standard.

The exponential increase in the number of electronic document exchanges in healthcare has considerably increased the risk of document drop-out or address errors. It may therefore be important to know to whom the information belongs and who produced it. This becomes a major concern when the document has been involved in processes leading to the choice of therapy and eventually in cases where patients seek damages for medical malpractice. Watermarking, which is the embedding of security elements, such as a digital signature, within a document, can help to ensure that a digital document is reliable. However, at the same time, questions arise about the validity of watermarking-based evidence. In this paper, beyond the technical aspects, we discuss the worldwide legal acceptability of watermarking and the need for its recognition as a standard according to technical characteristics that the CEN and ISO need to agree on.

Automatic Video Analysis Framework for Exposure Region Recognition in X-Ray Imaging Automation.

The deep learning-based automatic recognition of the scanning or exposing region in medical imaging automation is a promising new technique, which can decrease the heavy workload of the radiographers, optimize imaging workflow and improve image quality. However, there is little related research and practice in X-ray imaging. In this paper, we focus on two key problems in X-ray imaging automation: automatic recognition of the exposure moment and the exposure region. Consequently, we propose an automatic video analysis framework based on the hybrid model, approaching real-time performance. The framework consists of three interdependent components: Body Structure Detection, Motion State Tracing, and Body Modeling. Body Structure Detection disassembles the patient to obtain the corresponding body keypoints and body Bboxes. Combining and analyzing the two different types of body structure representations is to obtain rich spatial location information about the patient body structure. Motion State Tracing focuses on the motion state analysis of the exposure region to recognize the appropriate exposure moment. The exposure region is calculated by Body Modeling when the exposure moment appears. A large-scale dataset for X-ray examination scene is built to validate the performance of the proposed method. Extensive experiments demonstrate the superiority of the proposed method in automatically recognizing the exposure moment and exposure region. This paradigm provides the first method that can enable automatically and accurately recognize the exposure region in X-ray imaging without the help of the radiographer.

Medical record: systematic centralization versus secure on demand aggregation.

BACKGROUND: As patients often see the data of their medical histories scattered among various medical records hosted in several health-care establishments, the purpose of our multidisciplinary study was to define a pragmatic and secure on-demand based system able to gather this information, with no risk of breaching confidentiality, and to relay it to a medical professional who asked for the information via a specific search engine. METHODS: Scattered data are often heterogeneous, which makes the task of gathering information very hard. Two methods can be compared: trying to solve the problem by standardizing and centralizing all the information about every patient in a single Medical Record system or trying to use the data "as is" and find a way to obtain the most complete and the most accurate information. Given the failure of the first approach, due to the lack of standardization or privacy and security problems, for example, we propose an alternative that relies on the current state of affairs: an on-demand system, using a specific search engine that is able to retrieve information from the different medical records of a single patient. RESULTS: We describe the function of Medical Record Search Engines (MRSE), which are able to retrieve all the available information regarding a patient who has been hospitalized in different hospitals and to provide this information to health professionals upon request. MRSEs use pseudonymized patient identities and thus never have access to the patient's identity. However, though the system would be easy to implement as it by-passes many of the difficulties associated with a centralized architecture, the health professional would have to validate the information, i.e. read all of the information and create his own synthesis and possibly reject extra data, which could be a drawback. We thus propose various feasible improvements, based on the implementation of several tools in our on-demand based system. CONCLUSIONS: A system that gathers all of the currently available information regarding a patient on the request of health-care professionals could be of great interest. This low-cost pragmatic alternative to centralized medical records could be developed quickly and easily. It could also be designed to include extra features and should thus be considered by health authorities.

Watermarking - a new way to bring evidence in case of telemedicine litigation.

When dealing with medical data sharing, in particular within telemedicine applications, there is a need to ensure information security. Being able to verify that the information belongs to the right patient and is from the right source or that it has been rerouted or modified is a major concern. Watermarking, which is the embedding of security elements, such as a digital signature, within a document, can help to ensure that a digital document is reliable. However, at the same time, questions arise about the validity of watermarking-based proof. In this paper, beyond the technical aspects, we discuss the legal acceptability of watermarking in the context of telemedicine applications.

Empowerment of patients over their personal health record implies sharing responsibility with the physician.

Through this article, we point out the unavoidable empowerment of patients with regard to their personal health record and propose the mixed management of patients' medical records. This mixed management implies sharing responsibilities between the patient and the Medical Practitioner (MP) by making patients responsible for the validation of their administrative information, and MPs responsible for the validation of their patients' medical information. We propose a solution to gather and update patients' administrative and medical data in order to reconstitute patients' medical histories accurately. This method is based on two processes. The aim of the first process is to provide patients administrative data, in order to know where and when they received care (name of the health structure or health practitioner, type of care: outpatient or inpatient). The aim of the second process is to provide patients' medical information and to validate it under the responsibility of the MP with the help of patients if needed. During these two processes, the patients' privacy will be ensured through cryptographic hash functions like the Secure Hash Algorithm, which allows the pseudonymization of patients' identities. The Medical Record Search Engine we propose will be able to retrieve and to provide upon a request formulated by the MP all the available information concerning a patient who has received care in different health structures without divulging the patient's true identity. Associated with strong traceability of all access, modifications or deletions, our method can lead to improved efficiency of personal medical record management while reinforcing the empowerment of patients over their medical records.

Towards improved breast mass detection using dual-view mammogram matching.

Breast cancer screening benefits from the visual analysis of multiple views of routine mammograms. As for clinical practice, computer-aided diagnosis (CAD) systems could be enhanced by integrating multi-view information. In this work, we propose a new multi-tasking framework that combines craniocaudal (CC) and mediolateral-oblique (MLO) mammograms for automatic breast mass detection. Rather than addressing mass recognition only, we exploit multi-tasking properties of deep networks to jointly learn mass matching and classification, towards better detection performance. Specifically, we propose a unified Siamese network that combines patch-level mass/non-mass classification and dual-view mass matching to take full advantage of multi-view information. This model is exploited in a full image detection pipeline based on You-Only-Look-Once (YOLO) region proposals. We carry out exhaustive experiments to highlight the contribution of dual-view matching for both patch-level classification and examination-level detection scenarios. Results demonstrate that mass matching highly improves the full-pipeline detection performance by outperforming conventional single-task schemes with 94.78% as Area Under the Curve (AUC) score and a classification accuracy of 0.8791. Interestingly, mass classification also improves the performance of mass matching, which proves the complementarity of both tasks. Our method further guides clinicians by providing accurate dual-view mass correspondences, which suggests that it could act as a relevant second opinion for mammogram interpretation and breast cancer diagnosis.

CLEAR: Comprehensive Learning Enabled Adversarial Reconstruction for Subtle Structure Enhanced Low-Dose CT Imaging.

X-ray computed tomography (CT) is of great clinical significance in medical practice because it can provide anatomical information about the human body without invasion, while its radiation risk has continued to attract public concerns. Reducing the radiation dose may induce noise and artifacts to the reconstructed images, which will interfere with the judgments of radiologists. Previous studies have confirmed that deep learning (DL) is promising for improving low-dose CT imaging. However, almost all the DL-based methods suffer from subtle structure degeneration and blurring effect after aggressive denoising, which has become the general challenging issue. This paper develops the Comprehensive Learning Enabled Adversarial Reconstruction (CLEAR) method to tackle the above problems. CLEAR achieves subtle structure enhanced low-dose CT imaging through a progressive improvement strategy. First, the generator established on the comprehensive domain can extract more features than the one built on degraded CT images and directly map raw projections to high-quality CT images, which is significantly different from the routine GAN practice. Second, a multi-level loss is assigned to the generator to push all the network components to be updated towards high-quality reconstruction, preserving the consistency between generated images and gold-standard images. Finally, following the WGAN-GP modality, CLEAR can migrate the real statistical properties to the generated images to alleviate over-smoothing. Qualitative and quantitative analyses have demonstrated the competitive performance of CLEAR in terms of noise suppression, structural fidelity and visual perception improvement.

The mixed management of patients' medical records: responsibility sharing between the patient and the physician.

Through this article, we propose a mixed management of patients' medical records, so as to share responsibilities between the patient and the Medical Practitioner by making Patients responsible for the validation of their administrative information, and MPs responsible for the validation of their Patients' medical information. Our proposal can be considered a solution to the main problem faced by patients, health practitioners and the authorities, namely the gathering and updating of administrative and medical data belonging to the patient in order to accurately reconstitute a patient's medical history. This method is based on two processes. The aim of the first process is to provide a patient's administrative data, in order to know where and when the patient received care (name of the health structure or health practitioner, type of care: out patient or inpatient). The aim of the second process is to provide a patient's medical information and to validate it under the accountability of the Medical Practitioner with the help of the patient if needed. During these two processes, the patient's privacy will be ensured through cryptographic hash functions like the Secure Hash Algorithm, which allows pseudonymisation of a patient's identity. The proposed Medical Record Search Engines will be able to retrieve and to provide upon a request formulated by the Medical Practitioner all the available information concerning a patient who has received care in different health structures without divulging the patient's identity. Our method can lead to improved efficiency of personal medical record management under the mixed responsibilities of the patient and the MP.

Secure Collapsing Method Based on Fully Homomorphic Encryption.

In this paper, we propose a new approach for performing privacy-preserving genome-wide association study (GWAS) in cloud environments. This method allows a Genomic Research Unit (GRU) who possesses genetic variants of diseased individuals (cases) to compare his/her data against genetic variants of healthy individuals (controls) from a Genomic Research Center (GRC). The originality of this work stands on a secure version of the collapsing method based on the logistic regression model considering that all data of GRU are stored into the cloud. To do so, we take advantage of fully homomorphic encryption and of secure multiparty computation. Experiment results carried out on real genetic data using the BGV cryptosystem indicate that the proposed scheme provides the same results as the ones achieved on clear data.

Coarse-to-fine classification for diabetic retinopathy grading using convolutional neural network.

Diabetic retinopathy (DR) is the most common eye complication of diabetes and one of the leading causes of blindness and vision impairment. Automated and accurate DR grading is of great significance for the timely and effective treatment of fundus diseases. Current clinical methods remain subject to potential time-consumption and high-risk. In this paper, a hierarchically Coarse-to-fine network (CF-DRNet) is proposed as an automatic clinical tool to classify five stages of DR severity grades using convolutional neural networks (CNNs). The CF-DRNet conforms to the hierarchical characteristic of DR grading and effectively improves the classification performance of five-class DR grading, which consists of the following: (1) The Coarse Network performs two-class classification including No DR and DR, where the attention gate module highlights the salient lesion features and suppresses irrelevant background information. (2) The Fine Network is proposed to classify four stages of DR severity grades of the grade DR from the Coarse Network including mild, moderate, severe non-proliferative DR (NPDR) and proliferative DR (PDR). Experimental results show that proposed CF-DRNet outperforms some state-of-art methods in the publicly available IDRiD and Kaggle fundus image datasets. These results indicate our method enables an efficient and reliable DR grading diagnosis in clinic.

Centralised versus decentralised management of patients' medical records.

For more than 20 years, many countries have been trying to set up a standardised medical record at the regional or at the national level. Most of them have not reached this goal, essentially due to two main difficulties related to patient identification and medical records standardisation. Moreover, the issues raised by the centralisation of all gathered medical data have to be tackled particularly in terms of security and privacy. We discuss here the interest of a non-centralised management of medical records which would require a specific procedure that gives to the patient access to his/her distributed medical data, wherever he/she is located.

Secure Processing of Stream Cipher Encrypted Data Issued from IOT: Application to a Connected Knee Prosthesis.

In this paper, we propose a secure protocol that allows processing encrypted data emitted by a medical IOT device. Its originality stands on a new fast algorithm which makes possible the conversion of Combined Linear Congruential Generator (CLCG) encrypted data into data homomorphically encrypted with the Damgard-Jurik (D-J) cryptosystem. By doing so, an honest-but-curious third party, like a smartphone, can process data issued from the IOT devices (e.g. raising a health alert) without endangering data privacy while CLCG can be integrated in an IOT of low computation capabilities. Moreover, in order to reduce communication and computation complexities compared to existing solutions and to achieve a real time solution, we further propose a secure packed version of CLCG in the D-J domain. With it a medical IOT can encrypt several pieces of data at once while allowing a third party to independently convert and process them in their D-J homomorphic encrypted form. We theoretically and experimentally demonstrate the performance of our solution in the case of a connected knee prosthesis, the data of which are processed for patient monitoring.

Image denoising via a non-local patch graph total variation.

Total variation (TV) based models are very popular in image denoising but suffer from some drawbacks. For example, local TV methods often cannot preserve edges and textures well when they face excessive smoothing. Non-local TV methods constitute an alternative, but their computational cost is huge. To overcome these issues, we propose an image denoising method named non-local patch graph total variation (NPGTV). Its main originality stands for the graph total variation method, which combines the total variation with graph signal processing. Schematically, we first construct a K-nearest graph from the original image using a non-local patch-based method. Then the model is solved with the Douglas-Rachford Splitting algorithm. By doing so, the image details can be well preserved while being denoised. Experiments conducted on several standard natural images illustrate the effectiveness of our method when compared to some other state-of-the-art denoising methods like classical total variation, non-local means filter (NLM), non-local graph based transform (NLGBT), adaptive graph-based total variation (AGTV).