Public data homogenization for AI model development in breast cancer

BACKGROUND

Developing trustworthy artificial intelligence (AI) models for clinical applications requires access to clinical and imaging data cohorts. Reusing of publicly available datasets has the potential to fill this gap. Specifically in the domain of breast cancer, a large archive of publicly accessible medical images along with the corresponding clinical data is available at The Cancer Imaging Archive (TCIA). However, existing datasets cannot be directly used as they are heterogeneous and cannot be effectively filtered for selecting specific image types required to develop AI models. This work focuses on the development of a homogenized dataset in the domain of breast cancer including clinical and imaging data.

METHODS

Five datasets were acquired from the TCIA and were harmonized. For the clinical data harmonization, a common data model was developed and a repeatable, documented "extract-transform-load" process was defined and executed for their homogenization. Further, Digital Imaging and COmmunications in Medicine (DICOM) information was extracted from magnetic resonance imaging (MRI) data and made accessible and searchable.

RESULTS

The resulting harmonized dataset includes information about 2,035 subjects with breast cancer. Further, a platform named RV-Cherry-Picker enables search over both the clinical and diagnostic imaging datasets, providing unified access, facilitating the downloading of all study imaging that correspond to specific series' characteristics (e.g., dynamic contrast-enhanced series), and reducing the burden of acquiring the appropriate set of images for the respective AI model scenario.

CONCLUSIONS

RV-Cherry-Picker provides access to the largest, publicly available, homogenized, imaging/clinical dataset for breast cancer to develop AI models on top.

RELEVANCE STATEMENT

We present a solution for creating merged public datasets supporting AI model development, using as an example the breast cancer domain and magnetic resonance imaging images.

KEY POINTS

• The proposed platform allows unified access to the largest, homogenized public imaging dataset for breast cancer. • A methodology for the semantically enriched homogenization of public clinical data is presented. • The platform is able to make a detailed selection of breast MRI data for the development of AI models.

Analysis of domain shift in whole prostate gland, zonal and lesions segmentation and detection, using multicentric retrospective data

Despite being one of the most prevalent forms of cancer, prostate cancer (PCa) shows a significantly high survival rate, provided there is timely detection and treatment. Computational methods can help make this detection process considerably faster and more robust. However, some modern machine-learning approaches require accurate segmentation of the prostate gland and the index lesion. Since performing manual segmentations is a very time-consuming task, and highly prone to inter-observer variability, there is a need to develop robust semi-automatic segmentation models. In this work, we leverage the large and highly diverse ProstateNet dataset, which includes 638 whole gland and 461 lesion segmentation masks, from 3 different scanner manufacturers provided by 14 institutions, in addition to other 3 independent public datasets, to train accurate and robust segmentation models for the whole prostate gland, zones and lesions. We show that models trained on large amounts of diverse data are better at generalizing to data from other institutions and obtained with other manufacturers, outperforming models trained on single-institution single-manufacturer datasets in all segmentation tasks. Furthermore, we show that lesion segmentation models trained on ProstateNet can be reliably used as lesion detection models.

Speech emotion recognition via graph-based representations

Speech emotion recognition (SER) has gained an increased interest during the last decades as part of enriched affective computing. As a consequence, a variety of engineering approaches have been developed addressing the challenge of the SER problem, exploiting different features, learning algorithms, and datasets. In this paper, we propose the application of the graph theory for classifying emotionally-colored speech signals. Graph theory provides tools for extracting statistical as well as structural information from any time series. We propose to use the mentioned information as a novel feature set. Furthermore, we suggest setting a unique feature-based identity for each emotion belonging to each speaker. The emotion classification is performed by a Random Forest classifier in a Leave-One-Speaker-Out Cross Validation (LOSO-CV) scheme. The proposed method is compared with two state-of-the-art approaches involving well known hand-crafted features as well as deep learning architectures operating on mel-spectrograms. Experimental results on three datasets, EMODB (German, acted) and AESDD (Greek, acted), and DEMoS (Italian, in-the-wild), reveal that our proposed method outperforms the comparative methods in these datasets. Specifically, we observe an average UAR increase of almost [Formula: see text], [Formula: see text] and [Formula: see text], respectively.

Detecting Minor Symptoms of Parkinson's Disease in the Wild Using Bi-LSTM with Attention Mechanism

Parkinson's disease (PD) is a neurodegenerative disorder characterized by motor and nonmotor impairment with various implications on patients' quality of life. Since currently available therapies are only symptomatic, identifying individuals with prodromal, preclinical, or early-stage PD is crucial, as they would be ideal candidates for future disease-modifying therapies. Our analysis aims to develop a robust model for accurate PD detection using accelerometer data collected from PD and non-PD individuals with mild or no tremor during phone conversations. An open-access dataset comprising accelerometer recordings from 22 PD patients and 11 healthy controls (HCs) was utilized. The data were preprocessed to extract relevant time-, frequency-, and energy-related features, and a bidirectional long short-term memory (Bi-LSTM) model with attention mechanism was employed for classification. The performance of the model was evaluated using fivefold cross-validation, and metrics of accuracy, precision, recall, specificity, and f1-score were computed. The proposed model demonstrated high accuracy (98%), precision (99%), recall (98%), specificity (96%), and f1-score (98%) in accurately distinguishing PD patients from HCs. Our findings indicate that the proposed model outperforms existing approaches and holds promise for detection of PD with subtle symptoms, like tremor, in the wild. Such symptoms can present in the early or even prodromal stage of the disease, and appropriate mobile-based applications may be a practical tool in real-life settings to alert individuals at risk to seek medical assistance or give patients feedback in monitoring their symptoms.

A segmentation-based method improving the performance of N4 bias field correction on T2weighted MR imaging data of the prostate

Magnetic Resonance (MR) images suffer from spatial inhomogeneity, known as bias field corruption. The N4ITK filter is a state-of-the-art method used for correcting the bias field to optimize MR-based quantification. In this study, a novel approach is presented to quantitatively evaluate the performance of N4 bias field correction for pelvic prostate imaging. An exploratory analysis, regarding the different values of convergence threshold, shrink factor, fitting level, number of iterations and use of mask, is performed to quantify the performance of N4 filter in pelvic MR images. The performance of a total of 240 different N4 configurations is examined using the Full Width at Half Maximum (FWHM) of the segmented periprostatic fat distribution as evaluation metric. Phantom T2weighted images were used to assess the performance of N4 for a uniform test tissue mimicking material, excluding factors such as patient related susceptibility and anatomy heterogeneity. Moreover, 89 and 204 T2weighted patient images from two public datasets acquired by scanners with a combined surface and endorectal coil at 1.5 T and a surface coil at 3 T, respectively, were utilized and corrected with a variable set of N4 parameters. Furthermore, two external public datasets were used to validate the performance of the N4 filter in T2weighted patient images acquired by various scanning conditions with different magnetic field strengths and coils. The results show that the set of N4 parameters, converging to optimal representations of fat in the image, were: convergence threshold 0.001, shrink factor 2, fitting level 6, number of iterations 100 and the use of default mask for prostate images acquired by a combined surface and endorectal coil at both 1.5 T and 3 T. The corresponding optimal N4 configuration for MR prostate images acquired by a surface coil at 1.5 T or 3 T was: convergence threshold 0.001, shrink factor 2, fitting level 5, number of iterations 25 and the use of default mask. Hence, periprostatic fat segmentation can be used to define the optimal settings for achieving T2weighted prostate images free from bias field corruption to provide robust input for further analysis.

MI-Common Data Model: Extending Observational Medical Outcomes Partnership-Common Data Model (OMOP-CDM) for Registering Medical Imaging Metadata and Subsequent Curation Processes

PURPOSE

The explosion of big data and artificial intelligence has rapidly increased the need for integrated, homogenized, and harmonized health data. Many common data models (CDMs) and standard vocabularies have appeared in an attempt to offer harmonized access to the available information, with Observational Medical Outcomes Partnership (OMOP)-CDM being one of the most prominent ones, allowing the standardization and harmonization of health care information. However, despite its flexibility, still capturing imaging metadata along with the corresponding clinical data continues to pose a challenge. This challenge arises from the absence of a comprehensive standard representation for image-related information and subsequent image curation processes and their interlinkage with the respective clinical information. Successful resolution of this challenge holds the potential to enable imaging and clinical data to become harmonized, quality-checked, annotated, and ready to be used in conjunction, in the development of artificial intelligence models and other data-dependent use cases.

METHODS

To address this challenge, we introduce medical imaging (MI)-CDM-an extension of the OMOP-CDM specifically designed for registering medical imaging data and curation-related processes. Our modeling choices were the result of iterative numerous discussions among clinical and AI experts to enable the integration of imaging and clinical data in the context of the ProCAncer-I project, for answering a set of clinical questions across the prostate cancer's continuum.

RESULTS

Our MI-CDM extension has been successfully implemented for the use case of prostate cancer for integrating imaging and curation metadata along with clinical information by using the OMOP-CDM and its oncology extension.

CONCLUSION

By using our proposed terminologies and standardized attributes, we demonstrate how diverse imaging modalities can be seamlessly integrated in the future.

Using the recurrence plots as indicators for the recognition of Parkinson's disease through phonemes assessment

Parkinson's disease (PD) is considered to be the second most common neurodegenerative disease which affects the patients' life throughout the years. As a consequence, its early diagnosis is of major importance for the improvement of life quality, implying that the severe symptoms can be delayed through appropriate clinical intervention and treatment. Among the most important premature symptoms of PD are the voice impairments of articulation, phonation and prosody. The objective of this study is to investigate whether the voice's dynamic behavior can be used as possible indicator for PD. Thus in this work, we employ the recurrence plots (RPs) which derive from the analysis of the three modulated vowels /a/, /e/ and /o/, which belong to the PC-GITA dataset, and are fed as input images to a 3-channel Convolutional Neural Network-based (CNN) architecture, which, finally, differentiates the 50 PD patients from 50 healthy subjects. The experimental results obtained provide evidence that the RP-based approach is a promising tool for the recognition of PD patients through the analysis of voice recordings, with a classification accuracy achieved equal to 87%.

A Full Transformer-based Framework for Automatic Pain Estimation using Videos

The automatic estimation of pain is essential in designing an optimal pain management system offering reliable assessment and reducing the suffering of patients. In this study, we present a novel full transformer-based framework consisting of a Transformer in Transformer (TNT) model and a Transformer leveraging cross-attention and self-attention blocks. Elaborating on videos from the BioVid database, we demonstrate state-of-the-art performances, showing the efficacy, efficiency, and generalization capability across all the primary pain estimation tasks.

LETHE: A Digital Intervention for Cognitive Decline

Dementia is the main cause of disability in elderly populations. It has been shown that the risk factors of dementia are a mixture of pathological, lifestyle and heritable factors, with some of those being provably modifiable. Early diagnosis of dementia and approaches to slow down its evolution are currently the most prominent management methodologies due to lack of a cure. For that reason, a plethora of home-based assistive technologies for dementia management do exist, with most of them focusing on the improvement of memory and thinking. The main objective of LETHE is prevention in the whole spectrum of cognitive decline in the elderly population at risk reaching from asymptomatic to subjective or mild cognitive impairment to prodromal Dementia. LETHE will provide a Big Data collection platform and analysis system, that will allow prevention, personalized risk detection and intervention on cognitive decline. Through the subsequent 2-year clinical trial, the LETHE system, as well as the respective knowledge gained will be evaluated and validated. The scope of the current paper is to introduce the LETHE study and its respective novel platform as a holistic approach to multidomain lifestyle intervention trial studies. The present work depicts the architectural perspective and extends beyond state-of-the-art guidelines and approaches to health management systems and cloud platform development.Clinical Relevance - Patient Management Systems as well as lifestyle management platforms have significant clinical relevance as they allow for remote and continuous monitoring of patients' health status. LETHE aims to improve patient outcomes by providing predictive models for cognitive decline and patient adherence to the multimodal lifestyle intervention, enabling prompt and appropriate medical decisions.

CARDIOCARE: An integrated platform for the management of elderly multimorbid patients with breast cancer therapy induced cardiac toxicity

Breast cancer (BC) remains the most diagnosed cancer in women, accounting for 12% of new annual cancer cases in Europe and worldwide. Advances in surgery, radiotherapy and systemic treatment have resulted in improved clinical outcomes and increased survival rates in recent years. However, BC therapy-related cardiotoxicity, may severely impact short- and long-term quality of life and survival. This study presents the CARDIOCARE platform and its main components, which by integrating patient-specific data from different categories, data from patient-oriented eHealth applications and wearable devices, and by employing advanced data mining and machine learning approaches, provides the healthcare professionals with a valuable tool for effectively managing BC patients and preventing or alleviating treatment induced cardiotoxicity.Clinical Relevance- Through the adoption of CARDIOCARE platform healthcare professionals are able to stratify patients for their risk for cardiotoxicity and timely apply adequate interventions to prevent its onset.

New Insights in the Era of Clinical Biomarkers as Potential Predictors of Systemic Therapy-Induced Cardiotoxicity in Women with Breast Cancer: A Systematic Review

Cardiotoxicity induced by breast cancer therapies is a potentially serious complication associated with the use of various breast cancer therapies. Prediction and better management of cardiotoxicity in patients receiving chemotherapy is of critical importance. However, the management of cancer therapy-related cardiac dysfunction (CTRCD) lacks clinical evidence and is based on limited clinical studies.

AIM

To provide an overview of existing and potentially novel biomarkers that possess a promising predictive value for the early and late onset of CTRCD in the clinical setting.

METHODS

A systematic review of published studies searching for promising biomarkers for the prediction of CTRCD in patients with breast cancer was undertaken according to PRISMA guidelines. A search strategy was performed using PubMed, Google Scholar, and Scopus for the period 2013-2023. All subjects were >18 years old, diagnosed with breast cancer, and received breast cancer therapies.

RESULTS

The most promising biomarkers that can be used for the development of an alternative risk cardiac stratification plan for the prediction and/or early detection of CTRCD in patients with breast cancer were identified.

CONCLUSIONS

We highlighted the new insights associated with the use of currently available biomarkers as a standard of care for the management of CTRCD and identified potentially novel clinical biomarkers that could be further investigated as promising predictors of CTRCD.

Multi-modal Deep Learning Diagnosis of Parkinson's Disease - A Systematic Review

Parkinson's Disease (PD) is among the most frequent neurological disorders. Approaches that employ artificial intelligence and notably deep learning, have been extensively embraced with promising outcomes. This study dispenses an exhaustive review between 2016 and January 2023 on deep learning techniques used in the prognosis and evolution of symptoms and characteristics of the disease based on gait, upper limb movement, speech and facial expression-related information as well as the fusion of more than one of the aforementioned modalities. The search resulted in the selection of 87 original research publications, of which we have summarized the relevant information regarding the utilized learning and development process, demographic information, primary outcomes, and sensory equipment related information. Various deep learning algorithms and frameworks have attained state-of-the-art performance in many PD-related tasks by outperforming conventional machine learning approaches, according to the research reviewed. In the meanwhile, we identify significant drawbacks in the existing research, including a lack of data availability and interpretability of models. The fast advancements in deep learning and the rise in accessible data provide the opportunity to address these difficulties in the near future and for the broad application of this technology in clinical settings.

Data infrastructures for AI in medical imaging: a report on the experiences of five EU projects

Artificial intelligence (AI) is transforming the field of medical imaging and has the potential to bring medicine from the era of 'sick-care' to the era of healthcare and prevention. The development of AI requires access to large, complete, and harmonized real-world datasets, representative of the population, and disease diversity. However, to date, efforts are fragmented, based on single-institution, size-limited, and annotation-limited datasets. Available public datasets (e.g., The Cancer Imaging Archive, TCIA, USA) are limited in scope, making model generalizability really difficult. In this direction, five European Union projects are currently working on the development of big data infrastructures that will enable European, ethically and General Data Protection Regulation-compliant, quality-controlled, cancer-related, medical imaging platforms, in which both large-scale data and AI algorithms will coexist. The vision is to create sustainable AI cloud-based platforms for the development, implementation, verification, and validation of trustable, usable, and reliable AI models for addressing specific unmet needs regarding cancer care provision. In this paper, we present an overview of the development efforts highlighting challenges and approaches selected providing valuable feedback to future attempts in the area.Key points• Artificial intelligence models for health imaging require access to large amounts of harmonized imaging data and metadata.• Main infrastructures adopted either collect centrally anonymized data or enable access to pseudonymized distributed data.• Developing a common data model for storing all relevant information is a challenge.• Trust of data providers in data sharing initiatives is essential.• An online European Union meta-tool-repository is a necessity minimizing effort duplication for the various projects in the area.

Evaluating Gait Impairment in Parkinson's Disease from Instrumented Insole and IMU Sensor Data

Parkinson's disease (PD) is characterized by a variety of motor and non-motor symptoms, some of them pertaining to gait and balance. The use of sensors for the monitoring of patients' mobility and the extraction of gait parameters, has emerged as an objective method for assessing the efficacy of their treatment and the progression of the disease. To that end, two popular solutions are pressure insoles and body-worn IMU-based devices, which have been used for precise, continuous, remote, and passive gait assessment. In this work, insole and IMU-based solutions were evaluated for assessing gait impairment, and were subsequently compared, producing evidence to support the use of instrumentation in everyday clinical practice. The evaluation was conducted using two datasets, generated during a clinical study, in which patients with PD wore, simultaneously, a pair of instrumented insoles and a set of wearable IMU-based devices. The data from the study were used to extract and compare gait features, independently, from the two aforementioned systems. Subsequently, subsets comprised of the extracted features, were used by machine learning algorithms for gait impairment assessment. The results indicated that insole gait kinematic features were highly correlated with those extracted from IMU-based devices. Moreover, both had the capacity to train accurate machine learning models for the detection of PD gait impairment.

Automatic assessment of pain based on deep learning methods: A systematic review

BACKGROUND AND OBJECTIVE

The automatic assessment of pain is vital in designing optimal pain management interventions focused on reducing suffering and preventing the functional decline of patients. In recent years, there has been a surge in the adoption of deep learning algorithms by researchers attempting to encode the multidimensional nature of pain into meaningful features. This systematic review aims to discuss the models, the methods, and the types of data employed in establishing the foundation of a deep learning-based automatic pain assessment system.

METHODS

The systematic review was conducted by identifying original studies searching digital libraries, namely Scopus, IEEE Xplore, and ACM Digital Library. Inclusion and exclusion criteria were applied to retrieve and select those of interest, published until December 2021.

RESULTS

A total of one hundred and ten publications were identified and categorized by the number of information channels used (unimodal versus multimodal approaches) and whether the temporal dimension was also used.

CONCLUSIONS

This review demonstrates the importance of multimodal approaches for automatic pain estimation, especially in clinical settings, and also reveals that significant improvements are observed when the temporal exploitation of modalities is included. It provides suggestions regarding better-performing deep architectures and learning methods. Also, it provides suggestions for adopting robust evaluation protocols and interpretation methods to provide objective and comprehensible results. Furthermore, the review presents the limitations of the available pain databases for optimally supporting deep learning model development, validation, and application as decision-support tools in real-life scenarios.

eSEE-d: Emotional State Estimation Based on Eye-Tracking Dataset

Affective state estimation is a research field that has gained increased attention from the research community in the last decade. Two of the main catalysts for this are the advancement in the data analysis using artificial intelligence and the availability of high-quality video. Unfortunately, benchmarks and public datasets are limited, thus making the development of new methodologies and the implementation of comparative studies essential. The current work presents the eSEE-d database, which is a resource to be used for emotional State Estimation based on Eye-tracking data. Eye movements of 48 participants were recorded as they watched 10 emotion-evoking videos, each of them followed by a neutral video. Participants rated four emotions (tenderness, anger, disgust, sadness) on a scale from 0 to 10, which was later translated in terms of emotional arousal and valence levels. Furthermore, each participant filled three self-assessment questionnaires. An extensive analysis of the participants’ answers to the questionnaires’ self-assessment scores as well as their ratings during the experiments is presented. Moreover, eye and gaze features were extracted from the low-level eye-recorded metrics, and their correlations with the participants’ ratings are investigated. Finally, we take on the challenge to classify arousal and valence levels based solely on eye and gaze features, leading to promising results. In particular, the Deep Multilayer Perceptron (DMLP) network we developed achieved an accuracy of 92% in distinguishing positive valence from non-positive and 81% in distinguishing low arousal from medium arousal. The dataset is made publicly available.

Region-adaptive magnetic resonance image enhancement for improving CNN-based segmentation of the prostate and prostatic zones

Automatic segmentation of the prostate of and the prostatic zones on MRI remains one of the most compelling research areas. While different image enhancement techniques are emerging as powerful tools for improving the performance of segmentation algorithms, their application still lacks consensus due to contrasting evidence regarding performance improvement and cross-model stability, further hampered by the inability to explain models' predictions. Particularly, for prostate segmentation, the effectiveness of image enhancement on different Convolutional Neural Networks (CNN) remains largely unexplored. The present work introduces a novel image enhancement method, named RACLAHE, to enhance the performance of CNN models for segmenting the prostate's gland and the prostatic zones. The improvement in performance and consistency across five CNN models (U-Net, U-Net++, U-Net3+, ResU-net and USE-NET) is compared against four popular image enhancement methods. Additionally, a methodology is proposed to explain, both quantitatively and qualitatively, the relation between saliency maps and ground truth probability maps. Overall, RACLAHE was the most consistent image enhancement algorithm in terms of performance improvement across CNN models with the mean increase in Dice Score ranging from 3 to 9% for the different prostatic regions, while achieving minimal inter-model variability. The integration of a feature driven methodology to explain the predictions after applying image enhancement methods, enables the development of a concrete, trustworthy automated pipeline for prostate segmentation on MR images.

Can Gait Features Help in Differentiating Parkinson's Disease Medication States and Severity Levels? A Machine Learning Approach

Parkinson's disease (PD) is one of the most prevalent neurological diseases, described by complex clinical phenotypes. The manifestations of PD include both motor and non-motor symptoms. We constituted an experimental protocol for the assessment of PD motor signs of lower extremities. Using a pair of sensor insoles, data were recorded from PD patients, Elderly and Adult groups. Assessment of PD patients has been performed by neurologists specialized in movement disorders using the Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS)-Part III: Motor Examination, on both ON and OFF medication states. Using as a reference point the quantified metrics of MDS-UPDRS-Part III, severity levels were explored by classifying normal, mild, moderate, and severe levels of PD. Elaborating the recorded gait data, 18 temporal and spatial characteristics have been extracted. Subsequently, feature selection techniques were applied to reveal the dominant features to be used for four classification tasks. Specifically, for identifying relations between the spatial and temporal gait features on: PD and non-PD groups; PD, Elderly and Adults groups; PD and ON/OFF medication states; MDS-UPDRS: Part III and PD severity levels. AdaBoost, Extra Trees, and Random Forest classifiers, were trained and tested. Results showed a recognition accuracy of 88%, 73% and 81% for, the PD and non-PD groups, PD-related medication states, and PD severity levels relevant to MDS-UPDRS: Part III ratings, respectively.

Enhancing cancer differentiation with synthetic MRI examinations via generative models: a systematic review

Contemporary deep learning-based decision systems are well-known for requiring high-volume datasets in order to produce generalized, reliable, and high-performing models. However, the collection of such datasets is challenging, requiring time-consuming processes involving also expert clinicians with limited time. In addition, data collection often raises ethical and legal issues and depends on costly and invasive procedures. Deep generative models such as generative adversarial networks and variational autoencoders can capture the underlying distribution of the examined data, allowing them to create new and unique instances of samples. This study aims to shed light on generative data augmentation techniques and corresponding best practices. Through in-depth investigation, we underline the limitations and potential methodology pitfalls from critical standpoint and aim to promote open science research by identifying publicly available open-source repositories and datasets.

A 3D-Printed Capacitive Smart Insole for Plantar Pressure Monitoring

Gait analysis refers to the systematic study of human locomotion and finds numerous applications in the fields of clinical monitoring, rehabilitation, sports science and robotics. Wearable sensors for real-time gait monitoring have emerged as an attractive alternative to the traditional clinical-based techniques, owing to their low cost and portability. In addition, 3D printing technology has recently drawn increased interest for the manufacturing of sensors, considering the advantages of diminished fabrication cost and time. In this study, we report the development of a 3D-printed capacitive smart insole for the measurement of plantar pressure. Initially, a novel 3D-printed capacitive pressure sensor was fabricated and its sensing performance was evaluated. The sensor exhibited a sensitivity of 1.19 MPa−1, a wide working pressure range (<872.4 kPa), excellent stability and durability (at least 2.280 cycles), great linearity (R2=0.993), fast response/recovery time (142−160 ms), low hysteresis (DH<10%) and the ability to support a broad spectrum of gait speeds (30−70 steps/min). Subsequently, 16 pressure sensors were integrated into a 3D-printed smart insole that was successfully applied for dynamic plantar pressure mapping and proven able to distinguish the various gait phases. We consider that the smart insole presented here is a simple, easy to manufacture and cost-effective solution with the potential for real-world applications.

Harmonization Strategies in Multicenter MRI-Based Radiomics

Radiomics analysis is a powerful tool aiming to provide diagnostic and prognostic patient information directly from images that are decoded into handcrafted features, comprising descriptors of shape, size and textural patterns. Although radiomics is gaining momentum since it holds great promise for accelerating digital diagnostics, it is susceptible to bias and variation due to numerous inter-patient factors (e.g., patient age and gender) as well as inter-scanner ones (different protocol acquisition depending on the scanner center). A variety of image and feature based harmonization methods has been developed to compensate for these effects; however, to the best of our knowledge, none of these techniques has been established as the most effective in the analysis pipeline so far. To this end, this review provides an overview of the challenges in optimizing radiomics analysis, and a concise summary of the most relevant harmonization techniques, aiming to provide a thorough guide to the radiomics harmonization process.

COLET: A dataset for COgnitive workLoad estimation based on eye-tracking

BACKGROUND AND OBJECTIVE

The cognitive workload is an important component in performance psychology, ergonomics, and human factors. Publicly available datasets are scarce, making it difficult to establish new approaches and comparative studies. In this work, COLET-COgnitive workLoad estimation based on Eye-Tracking dataset is presented.

METHODS

Forty-seven (47) individuals' eye movements were monitored as they solved puzzles involving visual search activities of varying complexity and duration. The participants' cognitive workload level was evaluated with the subjective test of NASA-TLX and this score is used as an annotation of the activity. Extensive data analysis was performed in order to derive eye and gaze features from low-level eye recorded metrics, and a range of machine learning models were evaluated and tested regarding the estimation of the cognitive workload level.

RESULTS

The activities induced four different levels of cognitive workload. Multi tasking and time pressure have induced a higher level of cognitive workload than the one induced by single tasking and absence of time pressure. Multi tasking had a significant effect on 17 eye features while time pressure had a significant effect on 7 eye features. Both binary and multi-class identification attempts were performed by testing a variety of well-known classifiers, resulting in encouraging results towards cognitive workload levels estimation, with up to 88% correct predictions between low and high cognitive workload.

CONCLUSIONS

Machine learning analysis demonstrated potential in discriminating cognitive workload levels using only eye-tracking characteristics. The proposed dataset includes a much higher sample size and a wider spectrum of eye and gaze metrics than other similar datasets, allowing for the examination of their relations with various cognitive states.

A User-Centric approach for Personalization based on Human Activity Recognition

The objective of this work focuses on multiple independent user profiles that capture behavioral, emotional, medical, and physical patterns in the working and living environment resulting in one general user profile. Depending on the user's current activity (e.g. walking, eating, etc.), medical history, and other influential factors, the developed framework acts as a supplemental assistant to the user by providing not only the ability to enable supportive functionalities (e.g. image filtering, magnification, etc.) but also informative recommendations (e.g. diet, alcohol, etc.). The personalization of such a profile lies within the user's past preferences using human activity recognition as a base, and it is achieved through a statistical model, the Bayesian belief network. Training and real-time methodological pipelines are introduced and validated. The employed deep learning techniques for identifying human activities are presented and validated in publicly available and in-house datasets. The overall accuracy of human activity recognition reaches up to 86.96 %.

Data Ingestion for AI in Prostate Cancer

Prostate cancer (PCa) is one of the most prevalent cancers in the male population. Current clinical practices lead to overdiagnosis and overtreatment necessitating more effective tools for improving diagnosis, thus the quality of life of patients. Recent advances in infrastructure, computing power and artificial intelligence enable the collection of tremendous amounts of clinical and imaging data that could assist towards this end. ProCAncer-I project aims to develop an AI platform integrating imaging data and models and hosting the largest collection of PCa (mp)MRI, anonymized image data worldwide. In this paper, we present an overview of the overall architecture focusing on the data ingestion part of the platform. We describe the workflow followed for uploading the data and the main repositories for storing imaging data, clinical data and their corresponding metadata.

Considerations for artificial intelligence clinical impact in oncologic imaging: an AI4HI position paper

To achieve clinical impact in daily oncological practice, emerging AI-based cancer imaging research needs to have clearly defined medical focus, AI methods, and outcomes to be estimated. AI-supported cancer imaging should predict major relevant clinical endpoints, aiming to extract associations and draw inferences in a fair, robust, and trustworthy way. AI-assisted solutions as medical devices, developed using multicenter heterogeneous datasets, should be targeted to have an impact on the clinical care pathway. When designing an AI-based research study in oncologic imaging, ensuring clinical impact in AI solutions requires careful consideration of key aspects, including target population selection, sample size definition, standards, and common data elements utilization, balanced dataset splitting, appropriate validation methodology, adequate ground truth, and careful selection of clinical endpoints. Endpoints may be pathology hallmarks, disease behavior, treatment response, or patient prognosis. Ensuring ethical, safety, and privacy considerations are also mandatory before clinical validation is performed. The Artificial Intelligence for Health Imaging (AI4HI) Clinical Working Group has discussed and present in this paper some indicative Machine Learning (ML) enabled decision-support solutions currently under research in the AI4HI projects, as well as the main considerations and requirements that AI solutions should have from a clinical perspective, which can be adopted into clinical practice. If effectively designed, implemented, and validated, cancer imaging AI-supported tools will have the potential to revolutionize the field of precision medicine in oncology.

Gait and balance patterns related to Free-Walking and TUG tests in Parkinson's Disease based on plantar pressure data

Continuous monitoring of patients with Parkinson's Disease (PD) is critical for their effective management, as early detection of improvement or degradation signs play an important role on pharmaceutical and/or interventional plans. Within this work, a group of seven PD patients and a group of ten controls performed a set of exercises related to the evaluation of PD gait. Plantar pressure signals were collected and used to derive a set of analytics. Statistical tests and feature selection approaches revealed that the spatial distribution of the Center of Pressure during a static balance exercise is the most discriminative analytic and may be used for every-day monitoring of the patients. Results have revealed that out of the 28 features extracted from the collected signals, 10 were statistically significant (p < 0.05) and can be used to machine learning algorithms and/or similar approaches.

Real Time Human Activity Recognition Using Acceleration and First-Person Camera data

The aim of this work is to present an automated method, working in real time, for human activity recognition based on acceleration and first-person camera data. A Long-Short-Term-Memory (LSTM) model has been built for recognizing locomotive activities (i.e. walking, sitting, standing, going upstairs, going downstairs) from acceleration data, while a ResNet model is employed for the recognition of stationary activities (i.e. eating, reading, writing, watching TV working on PC). The outcomes of the two models are fused in order for the final decision, regarding the performed activity, to be made. For the training, testing and evaluation of the proposed models, a publicly available dataset and an "in-house" dataset are utilized. The overall accuracy of the proposed algorithmic pipeline reaches 87.8%.

Review of eye tracking metrics involved in emotional and cognitive processes

Eye behaviour provides valuable information revealing one's higher cognitive functions and state of affect. Although eye tracking is gaining ground in the research community, it is not yet a popular approach for the detection of emotional and cognitive states. In this paper, we present a review of eye and pupil tracking related metrics (such as gaze, fixations, saccades, blinks, pupil size variation, etc.) utilized towards the detection of emotional and cognitive processes, focusing on visual attention, emotional arousal and cognitive workload. Besides, we investigate their involvement as well as the computational recognition methods employed for the reliable emotional and cognitive assessment. The publicly available datasets employed in relevant research efforts were collected and their specifications and other pertinent details are described. The multimodal approaches which combine eye-tracking features with other modalities (e.g. biosignals), along with artificial intelligence and machine learning techniques were also surveyed in terms of their recognition/classification accuracy. The limitations, current open research problems and prospective future research directions were discussed for the usage of eye-tracking as the primary sensor modality. This study aims to comprehensively present the most robust and significant eye/pupil metrics based on available literature towards the development of a robust emotional or cognitive computational model.

Status and Recommendations of Technological and Data-Driven Innovations in Cancer Care: Focus Group Study

BACKGROUND

The status of the data-driven management of cancer care as well as the challenges, opportunities, and recommendations aimed at accelerating the rate of progress in this field are topics of great interest. Two international workshops, one conducted in June 2019 in Cordoba, Spain, and one in October 2019 in Athens, Greece, were organized by four Horizon 2020 (H2020) European Union (EU)-funded projects: BOUNCE, CATCH ITN, DESIREE, and MyPal. The issues covered included patient engagement, knowledge and data-driven decision support systems, patient journey, rehabilitation, personalized diagnosis, trust, assessment of guidelines, and interoperability of information and communication technology (ICT) platforms. A series of recommendations was provided as the complex landscape of data-driven technical innovation in cancer care was portrayed.

OBJECTIVE

This study aims to provide information on the current state of the art of technology and data-driven innovations for the management of cancer care through the work of four EU H2020-funded projects.

METHODS

Two international workshops on ICT in the management of cancer care were held, and several topics were identified through discussion among the participants. A focus group was formulated after the second workshop, in which the status of technological and data-driven cancer management as well as the challenges, opportunities, and recommendations in this area were collected and analyzed.

RESULTS

Technical and data-driven innovations provide promising tools for the management of cancer care. However, several challenges must be successfully addressed, such as patient engagement, interoperability of ICT-based systems, knowledge management, and trust. This paper analyzes these challenges, which can be opportunities for further research and practical implementation and can provide practical recommendations for future work.

CONCLUSIONS

Technology and data-driven innovations are becoming an integral part of cancer care management. In this process, specific challenges need to be addressed, such as increasing trust and engaging the whole stakeholder ecosystem, to fully benefit from these innovations.

A Training Tool to support the management and diagnosis of Sjögren's syndrome

OBJECTIVES

The objective of this work is to present a Training Tool designed to support healthcare professionals involved in the diagnosis and management of Sjögren's syndrome.

METHODS

The Training Tool aims to fulfil the gap of targeted education by providing a structured protocol of training including state of the art guidelines and practices. For the development of the Training Tool, latest relevant technologies have been used to assure efficiency and usability. Core functionalities include training by a series of multimedia courses, testing during the learning process, and profiling for monitoring the progress. An iterative requirement analysis process was established involving a large number of clinical experts, with the objective to identify user's training needs.

RESULTS

Comprehensive usability evaluation was performed by applying, an Unmoderated Remote Usability Test resulting to 97.2% Success Rate; and the well-established System Usability Scale, reaching a score of 90.4 which classifies the Training Tool as "A" graded-excellent.

CONCLUSIONS

The Training Tool offers open-online training of healthcare professionals involved in the diagnosis and management of Sjögren's syndrome, using a well-designed training protocol in highly usable manner. To our knowledge, this is the first such tool for Sjögren's syndrome.

Patient empowerment for cancer patients through a novel ICT infrastructure

As a result of recent advances in cancer research and "precision medicine" approaches, i.e. the idea of treating each patient with the right drug at the right time, more and more cancer patients are being cured, or might have to cope with a life with cancer. For many people, cancer survival today means living with a complex and chronic condition. Surviving and living with or beyond cancer requires the long-term management of the disease, leading to a significant need for active rehabilitation of the patients. In this paper, we present a novel methodology employed in the iManageCancer project for cancer patient empowerment in which personal health systems, serious games, psychoemotional monitoring and other novel decision-support tools are combined into an integrated patient empowerment platform. We present in detail the ICT infrastructure developed and our evaluation with the involvement of cancer patients on two sites, a large-scale pilot for adults and a small-scale test for children. The evaluation showed mixed evidences on the improvement of patient empowerment, while ability to cope with cancer, including improvement in mood and resilience to cancer, increased for the participants of the adults' pilot.

Focal epileptic seizures anticipation based on patterns of heart rate variability parameters

BACKGROUND AND OBJECTIVE

Heart rate variability parameters are studied by the research community as potential valuable indices for seizure detection and anticipation. This paper investigates heart activity abnormalities during focal epileptic seizures in childhood.

METHODS

Seizures affect both the sympathetic and parasympathetic system which is expressed as abnormal patterns of heart rate variability (HRV) parameters. In the present study, a clinical dataset containing 42 focal seizures in long-term electrocardiographic (ECG) recordings from drug-resistant pediatric epileptic patients (with age 8.2 ± 4.3 years) was analyzed.

RESULTS

Results indicate that the time domain HRV parameters (heart rate, SDNN, standard deviation of heart rate, upper envelope) and spectral HRV parameters (LF/HF, normalized HF, normalized LF, total power) are significantly affected during ictal periods. The HRV features were ranked in terms of their relevance and efficacy to discriminate non-ictal/ictal periods and the top-ranked features were selected using the minimum Redundancy Maximum Relevance algorithm for further analysis. Then, a personalized anticipation algorithm based on multiple regression was introduced providing an "epileptic index" of imminent seizures. The performance of the system resulted in anticipation accuracy of 77.1% and an anticipation time of 21.8 s.

CONCLUSIONS

The results of this analysis could permit the anticipation of focal seizures only using electrocardiographic signals and the implementation of seizure anticipation strategies for a range of real-life clinical applications.

Deep learning opens new horizons in personalized medicine

Although the idea of the personalization of patient care dates back to the time of Hippocrates, recent advances in diagnostic medical imaging and molecular medicine are gradually transforming healthcare services, by offering information and diagnostic tools enabling individualized patient management. Facilitating personalized / precision medicine requires taking into account multiple heterogenous parameters, such as sociodemographics, gene variability, environmental and lifestyle factors. Therefore, one of the most critical challenges in personalized medicine is the need to transform large, multi-modal data into decision support tools, capable of bridging the translational gap to the clinical setting. Towards these challenges, deep learning (DL) provides a novel approach, which enables obtaining or developing high-accuracy, multi-modal predictive models, that allow the implementation of the personalized medicine vision in the near future. DL is a highly effective strategy in addressing these challenges, with DL-based models leading to unprecedented results, matching or even improving state-of-the-art prediction/detection rates based on both intuitive and non-intuitive disease descriptors. These results hold promise for significant socio-economic benefits from the application of DL personalized medicine.

Facial geometry and speech analysis for depression detection

Depression is one of the most prevalent mental disorders, burdening many people world-wide. A system with the potential of serving as a decision support system is proposed, based on novel features extracted from facial expression geometry and speech, by interpreting non-verbal manifestations of depression. The proposed system has been tested both in gender independent and gender based modes, and with different fusion methods. The algorithms were evaluated for several combinations of parameters and classification schemes, on the dataset provided by the Audio/Visual Emotion Challenge of 2013 and 2014. The proposed framework achieved a precision of 94.8% for detecting persons achieving high scores on a self-report scale of depressive symptomatology. Optimal system performance was obtained using a nearest neighbour classifier on the decision fusion of geometrical features in the gender independent mode, and audio based features in the gender based mode; single visual and audio decisions were combined with the OR binary operation.

Personal Health Information Recommender: implementing a tool for the empowerment of cancer patients

Nowadays, patients have a wealth of information available on the Internet. Despite the potential benefits of Internet health information seeking, several concerns have been raised about the quality of information and about the patient’s capability to evaluate medical information and to relate it to their own disease and treatment. As such, novel tools are required to effectively guide patients and provide high-quality medical information in an intelligent and personalised manner. With this aim, this paper presents the Personal Health Information Recommender (PHIR), a system to empower patients by enabling them to search in a high-quality document repository selected by experts, avoiding the information overload of the Internet. In addition, the information provided to the patients is personalised, based on individual preferences, medical conditions and other profiling information. Despite the generality of our approach, we apply the PHIR to a personal health record system constructed for cancer patients and we report on the design, the implementation and a preliminary validation of the platform. To the best of our knowledge, our platform is the only one combining natural language processing, ontologies and personal information to offer a unique user experience.

Digital patient: Personalized and translational data management through the MyHealthAvatar EU project

The advancements in healthcare practice have brought to the fore the need for flexible access to health-related information and created an ever-growing demand for the design and the development of data management infrastructures for translational and personalized medicine. In this paper, we present the data management solution implemented for the MyHealthAvatar EU research project, a project that attempts to create a digital representation of a patient's health status. The platform is capable of aggregating several knowledge sources relevant for the provision of individualized personal services. To this end, state of the art technologies are exploited, such as ontologies to model all available information, semantic integration to enable data and query translation and a variety of linking services to allow connecting to external sources. All original information is stored in a NoSQL database for reasons of efficiency and fault tolerance. Then it is semantically uplifted through a semantic warehouse which enables efficient access to it. All different technologies are combined to create a novel web-based platform allowing seamless user interaction through APIs that support personalized, granular and secure access to the relevant information.

Addressing drug-drug and drug-food interactions through personalized empowerment services for healthcare

Personalized healthcare systems support the provision of timely and appropriate information regarding healthcare options and treatment alternatives. Especially for patients that receive multi-drug treatments a key issue is the minimization of the risk of adverse effects due to drug-drug interactions (DDIs). DDIs may be the result of doctor prescribed drugs but also due to self-medication of conventional drugs, alternative medicines, food habits, alcohol or smoking. It is therefore crucial for personalized health systems, apart from assisting physicians for optimal prescription practices, to also provide appropriate information for individual users for drug-drug interactions or similar information regarding risks for modulation of the ensuing treatment. In this manuscript we describe a DDI service including drug-food, drug-herb and other lifestyle-related factors, developed in the context of a personalized patient empowerment platform. The solution enables guidance to patients for their medication on how to reduce the risk of unwanted drug interactions and side effects in a seamless and transparent way. We present and analyze the implemented services and provide examples on using an alerting service to identify potential DDIs in two different chronic diseases, congestive heart failure and osteoarthritis.

Video-based depression detection using local Curvelet binary patterns in pairwise orthogonal planes

Depression is an increasingly prevalent mood disorder. This is the reason why the field of computer-based depression assessment has been gaining the attention of the research community during the past couple of years. The present work proposes two algorithms for depression detection, one Frame-based and the second Video-based, both employing Curvelet transform and Local Binary Patterns. The main advantage of these methods is that they have significantly lower computational requirements, as the extracted features are of very low dimensionality. This is achieved by modifying the previously proposed algorithm which considers Three-Orthogonal-Planes, to only Pairwise-Orthogonal-Planes. Performance of the algorithms was tested on the benchmark dataset provided by the Audio/Visual Emotion Challenge 2014, with the person-specific system achieving 97.6% classification accuracy, and the person-independed one yielding promising preliminary results of 74.5% accuracy. The paper concludes with open issues, proposed solutions, and future plans.

Donor's support tool: Enabling informed secondary use of patient's biomaterial and personal data

PURPOSE

Biomedical research is being catalyzed by the vast amount of data rapidly collected through the application of information technologies (IT). Despite IT advances, the methods for involving patients and citizens in biomedical research remain static, paper-based and organized around national boundaries and anachronistic legal frameworks. The purpose of this paper is to study the current practices for obtaining consent for biobanking and the legal requirements for reusing the available biomaterial and data in EU and finally to present a novel tool to this direction enabling the secondary use of data and biomaterial.

METHOD

We review existing European legislation for secondary use of patient's biomaterial and data for research, identify types and scopes of consent, formal requirements for consent, and consider their implications for implementing electronic consent tools. To this direction, we proceed further to develop a modular tool, named Donor's Support Tool (DST), designed to connect researchers with participants, and to promote engagement, informed participation and individual decision making.

RESULTS

To identify the advantages of our solution we compare our tool with six other relevant approaches. The results show that our tool scores higher than the other tools in functionality, security and intelligence whereas it is the only one free and open-source. In addition, the potential of our solution is shown by a proof of concept deployment in an existing clinical setting, where it was really appreciated, as streamlining the relevant workflow.

MinePath: Mining for Phenotype Differential Sub-paths in Molecular Pathways

Pathway analysis methodologies couple traditional gene expression analysis with knowledge encoded in established molecular pathway networks, offering a promising approach towards the biological interpretation of phenotype differentiating genes. Early pathway analysis methodologies, named as gene set analysis (GSA), view pathways just as plain lists of genes without taking into account either the underlying pathway network topology or the involved gene regulatory relations. These approaches, even if they achieve computational efficiency and simplicity, consider pathways that involve the same genes as equivalent in terms of their gene enrichment characteristics. Most recent pathway analysis approaches take into account the underlying gene regulatory relations by examining their consistency with gene expression profiles and computing a score for each profile. Even with this approach, assessing and scoring single-relations limits the ability to reveal key gene regulation mechanisms hidden in longer pathway sub-paths. We introduce MinePath, a pathway analysis methodology that addresses and overcomes the aforementioned problems. MinePath facilitates the decomposition of pathways into their constituent sub-paths. Decomposition leads to the transformation of single-relations to complex regulation sub-paths. Regulation sub-paths are then matched with gene expression sample profiles in order to evaluate their functional status and to assess phenotype differential power. Assessment of differential power supports the identification of the most discriminant profiles. In addition, MinePath assess the significance of the pathways as a whole, ranking them by their p-values. Comparison results with state-of-the-art pathway analysis systems are indicative for the soundness and reliability of the MinePath approach. In contrast with many pathway analysis tools, MinePath is a web-based system (www.minepath.org) offering dynamic and rich pathway visualization functionality, with the unique characteristic to color regulatory relations between genes and reveal their phenotype inclination. This unique characteristic makes MinePath a valuable tool for in silico molecular biology experimentation as it serves the biomedical researchers' exploratory needs to reveal and interpret the regulatory mechanisms that underlie and putatively govern the expression of target phenotypes.

Detection of stress/anxiety state from EEG features during video watching

This paper studies the effect of stress/anxiety states on EEG signals during video sessions. The levels of arousal and valence that are induced to each subject while watching each video are self rated. These levels are mapped in stress and relaxed states and subjects that fufill criteria of adequate anxiety/stress scale were chosen leading to a subset of 18 subjects. Then, temporal, spectral and non linear EEG features are evaluated for being able to represent accurately states under investigation. Feature selection schemes choose the most significant of them in order to provide increased discrimination ability between relaxed and anxiety/stress states.

Technology-Based Innovations to Foster Personalized Healthy Lifestyles and Well-Being: A Targeted Review

BACKGROUND

New community-based arrangements and novel technologies can empower individuals to be active participants in their health maintenance, enabling people to control and self-regulate their health and wellness and make better health- and lifestyle-related decisions. Mobile sensing technology and health systems responsive to individual profiles combined with cloud computing can expand innovation for new types of interoperable services that are consumer-oriented and community-based. This could fuel a paradigm shift in the way health care can be, or should be, provided and received, while lessening the burden on exhausted health and social care systems.

OBJECTIVE

Our goal is to identify and discuss the main scientific and engineering challenges that need to be successfully addressed in delivering state-of-the-art, ubiquitous eHealth and mHealth services, including citizen-centered wellness management services, and reposition their role and potential within a broader context of diverse sociotechnical drivers, agents, and stakeholders.

METHODS

We review the state-of-the-art relevant to the development and implementation of eHealth and mHealth services in critical domains. We identify and discuss scientific, engineering, and implementation-related challenges that need to be overcome to move research, development, and the market forward.

RESULTS

Several important advances have been identified in the fields of systems for personalized health monitoring, such as smartphone platforms and intelligent ubiquitous services. Sensors embedded in smartphones and clothes are making the unobtrusive recognition of physical activity, behavior, and lifestyle possible, and thus the deployment of platforms for health assistance and citizen empowerment. Similarly, significant advances are observed in the domain of infrastructure supporting services. Still, many technical problems remain to be solved, combined with no less challenging issues related to security, privacy, trust, and organizational dynamics.

CONCLUSIONS

Delivering innovative ubiquitous eHealth and mHealth services, including citizen-centered wellness and lifestyle management services, goes well beyond the development of technical solutions. For the large-scale information and communication technology-supported adoption of healthier lifestyles to take place, crucial innovations are needed in the process of making and deploying usable empowering end-user services that are trusted and user-acceptable. Such innovations require multidomain, multilevel, transdisciplinary work, grounded in theory but driven by citizens' and health care professionals' needs, expectations, and capabilities and matched by business ability to bring innovation to the market.