NeuroCellCentreDB: Exploring a Novel Dataset for Neuron-like Cell Centre Detection with Deep Neural Networks.

The manipulation and stimulation of cell growth is invaluable for neuroscience research such as brain-machine interfaces or applications of neural tissue engineering. For the implementation of such research avenues, in particular the analysis of cells' migration behaviour, and accordingly, the determination of cell positions on microscope images is essential, causing a current need for labour-intensive, manual annotation efforts of the cell positions. In an attempt towards automation of the required annotation efforts, we i) introduce NeuroCellCentreDB, a novel dataset of neuron-like cells on microscope images with annotated cell centres, ii) evaluate a common (bounding box-based) object detector, faster region-based convolutional neural network (FRCNN), for the task at hand, and iii) design and test a fully convolutional neural network, with the specific goal of cell centre detection. We achieve an F1 score of up to 0.766 on the test data with a tolerance radius of 16 pixels. Our code and dataset are publicly available.

HEAR4Health: a blueprint for making computer audition a staple of modern healthcare.

Recent years have seen a rapid increase in digital medicine research in an attempt to transform traditional healthcare systems to their modern, intelligent, and versatile equivalents that are adequately equipped to tackle contemporary challenges. This has led to a wave of applications that utilise AI technologies; first and foremost in the fields of medical imaging, but also in the use of wearables and other intelligent sensors. In comparison, computer audition can be seen to be lagging behind, at least in terms of commercial interest. Yet, audition has long been a staple assistant for medical practitioners, with the stethoscope being the quintessential sign of doctors around the world. Transforming this traditional technology with the use of AI entails a set of unique challenges. We categorise the advances needed in four key pillars: Hear, corresponding to the cornerstone technologies needed to analyse auditory signals in real-life conditions; Earlier, for the advances needed in computational and data efficiency; Attentively, for accounting to individual differences and handling the longitudinal nature of medical data; and, finally, Responsibly, for ensuring compliance to the ethical standards accorded to the field of medicine. Thus, we provide an overview and perspective of HEAR4Health: the sketch of a modern, ubiquitous sensing system that can bring computer audition on par with other AI technologies in the strive for improved healthcare systems.

Airborne pollen grain detection from partially labelled data utilising semi-supervised learning.

Airborne pollen monitoring has been conducted for more than a century now, as knowledge of the quantity and periodicity of airborne pollen has diverse use cases, like reconstructing historic climates and tracking current climate change, forensic applications, and up to warning those affected by pollen-induced respiratory allergies. Hence, related work on automation of pollen classification already exists. In contrast, detection of pollen is still conducted manually, and it is the gold standard for accuracy. So, here we used a new-generation, automated, near-real-time pollen monitoring sampler, the BAA500, and we used data consisting of both raw and synthesised microscope images. Apart from the automatically generated, commercially-labelled data of all pollen taxa, we additionally used manual corrections to the pollen taxa, as well as a manually created test set of bounding boxes and pollen taxa, so as to more accurately evaluate the real-life performance. For the pollen detection, we employed two-stage deep neural network object detectors. We explored a semi-supervised training scheme to remedy the partial labelling. Using a teacher-student approach, the model can add pseudo-labels to complete the labelling during training. To evaluate the performance of our deep learning algorithms and to compare them to the commercial algorithm of the BAA500, we created a manual test set, in which an expert aerobiologist corrected automatically annotated labels. For the novel manual test set, both the supervised and semi-supervised approaches clearly outperform the commercial algorithm with an F1 score of up to 76.9 % compared to 61.3 %. On an automatically created and partially labelled test dataset, we obtain a maximum mAP of 92.7 %. Additional experiments on raw microscope images show comparable performance for the best models, which potentially justifies reducing the complexity of the image generation process. Our results bring automatic pollen monitoring a step forward, as they close the gap in pollen detection performance between manual and automated procedure.

Personalised depression forecasting using mobile sensor data and ecological momentary assessment.

Introduction: Digital health interventions are an effective way to treat depression, but it is still largely unclear how patients' individual symptoms evolve dynamically during such treatments. Data-driven forecasts of depressive symptoms would allow to greatly improve the personalisation of treatments. In current forecasting approaches, models are often trained on an entire population, resulting in a general model that works overall, but does not translate well to each individual in clinically heterogeneous, real-world populations. Model fairness across patient subgroups is also frequently overlooked. Personalised models tailored to the individual patient may therefore be promising. Methods: We investigate different personalisation strategies using transfer learning, subgroup models, as well as subject-dependent standardisation on a newly-collected, longitudinal dataset of depression patients undergoing treatment with a digital intervention ( N = 65 patients recruited). Both passive mobile sensor data as well as ecological momentary assessments were available for modelling. We evaluated the models' ability to predict symptoms of depression (Patient Health Questionnaire-2; PHQ-2) at the end of each day, and to forecast symptoms of the next day. Results: In our experiments, we achieve a best mean-absolute-error (MAE) of 0.801 (25% improvement) for predicting PHQ-2 values at the end of the day with subject-dependent standardisation compared to a non-personalised baseline ( MAE = 1.062 ). For one day ahead-forecasting, we can improve the baseline of 1.539 by 12 % to a MAE of 1.349 using a transfer learning approach with shared common layers. In addition, personalisation leads to fairer models at group-level. Discussion: Our results suggest that personalisation using subject-dependent standardisation and transfer learning can improve predictions and forecasts, respectively, of depressive symptoms in participants of a digital depression intervention. We discuss technical and clinical limitations of this approach, avenues for future investigations, and how personalised machine learning architectures may be implemented to improve existing digital interventions for depression.

Journaling Data for Daily PHQ-2 Depression Prediction and Forecasting.

Digital health applications are becoming increasingly important for assessing and monitoring the wellbeing of people suffering from mental health conditions like depression. A common target of said applications is to predict the results of self-assessed Patient-Health-Questionnaires (PHQ), indicating current symptom severity of depressive individuals. Many of the currently available approaches to predict PHQ scores use passive data, e.g., from smartphones. However, there are several other scores and data besides PHQ, e.g., the Behavioral Activation for Depression Scale-Short Form (BADSSF), the Center for Epidemiologic Studies Depression Scale (CESD), or the Personality Dynamics Diary (PDD), all of which can be effortlessly collected on a daily basis. In this work, we explore the potential of using actively-collected data to predict and forecast daily PHQ-2 scores on a newly-collected longitudinal dataset. We obtain a best MAE of 1.417 for daily prediction of PHQ-2 scores, which specifically in the used dataset have a range of 0 to 12, using leave-one-subject-out cross-validation, as well as a best MAE of 1.914 for forecasting PHQ-2 scores using data from up to the last 7 days. This illustrates the additive value that can be obtained by incorporating actively-collected data in a depression monitoring application.

Depression Diagnosis and Forecast based on Mobile Phone Sensor Data.

Previous studies have shown the correlation be-tween sensor data collected from mobile phones and human depression states. Compared to the traditional self-assessment questionnaires, the passive data collected from mobile phones is easier to access and less time-consuming. In particular, passive mobile phone data can be collected on a flexible time interval, thus detecting moment-by-moment psychological changes and helping achieve earlier interventions. Moreover, while previous studies mainly focused on depression diagnosis using mobile phone data, depression forecasting has not received sufficient attention. In this work, we extract four types of passive features from mobile phone data, including phone call, phone usage, user activity, and GPS features. We implement a long short-term memory (LSTM) network in a subject-independent 10-fold cross-validation setup to model both a diagnostic and a forecasting tasks. Experimental results show that the forecasting task achieves comparable results with the diagnostic task, which indicates the possibility of forecasting depression from mobile phone sensor data. Our model achieves an accuracy of 77.0 % for major depression forecasting (binary), an accuracy of 53.7 % for depression severity forecasting (5 classes), and a best RMSE score of 4.094 (PHQ-9, range from 0 to 27).

Is Speech the New Blood? Recent Progress in AI-Based Disease Detection From Audio in a Nutshell.

In recent years, advancements in the field of artificial intelligence (AI) have impacted several areas of research and application. Besides more prominent examples like self-driving cars or media consumption algorithms, AI-based systems have further started to gain more and more popularity in the health care sector, however whilst being restrained by high requirements for accuracy, robustness, and explainability. Health-oriented AI research as a sub-field of digital health investigates a plethora of human-centered modalities. In this article, we address recent advances in the so far understudied but highly promising audio domain with a particular focus on speech data and present corresponding state-of-the-art technologies. Moreover, we give an excerpt of recent studies on the automatic audio-based detection of diseases ranging from acute and chronic respiratory diseases via psychiatric disorders to developmental disorders and neurodegenerative disorders. Our selection of presented literature shows that the recent success of deep learning methods in other fields of AI also more and more translates to the field of digital health, albeit expert-designed feature extractors and classical ML methodologies are still prominently used. Limiting factors, especially for speech-based disease detection systems, are related to the amount and diversity of available data, e. g., the number of patients and healthy controls as well as the underlying distribution of age, languages, and cultures. Finally, we contextualize and outline application scenarios of speech-based disease detection systems as supportive tools for health-care professionals under ethical consideration of privacy protection and faulty prediction.

Towards automatic airborne pollen monitoring: From commercial devices to operational by mitigating class-imbalance in a deep learning approach.

Allergic diseases have been the epidemic of the century among chronic diseases. Particularly for pollen allergies, and in the context of climate change, as airborne pollen seasons have been shifting earlier and abundances have been becoming higher, pollen monitoring plays an important role in generating high-risk allergy alerts. However, this task requires labour-intensive and time-consuming manual classification via optical microscopy. Even new-generation, automatic, monitoring devices require manual pollen labelling to increase accuracy and to advance to genuinely operational devices. Deep Learning-based models have the potential to increase the accuracy of automated pollen monitoring systems. In the current research, transfer learning-based convolutional neural networks were employed to classify pollen grains from microscopic images. Given a high imbalance in the dataset, we incorporated class weighted loss, focal loss and weight vector normalisation for class balancing as well as data augmentation and weight penalties for regularisation. Airborne pollen has been routinely recorded by a Bio-Aerosol Analyzer (BAA500, Hund GmbH) located in Augsburg, Germany. Here we utilised a database referring to manually classified airborne pollen images of the whole pollen diversity throughout an annual pollen season. By using the cropped pollen images collected by this device, we achieved an unweighted average F1 score of 93.8% across 15 classes and an unweighted average F1 score of 75.9% across 31 classes. The majority of taxa (9 of 15), being also the most abundant and allergenic, showed a recall of at least 95%, reaching up to a remarkable 100% in pollen from Taxus and Urticaceae. The recent introduction of novel pollen monitoring devices worldwide has pointed to the necessity for real-time, automatic measurements of airborne pollen and fungal spores. Thus, we may improve everyday clinical practice and achieve the most efficient prophylaxis of allergic patients.

Synchronization in Interpersonal Speech.

During both positive and negative dyadic exchanges, individuals will often unconsciously imitate their partner. A substantial amount of research has been made on this phenomenon, and such studies have shown that synchronization between communication partners can improve interpersonal relationships. Automatic computational approaches for recognizing synchrony are still in their infancy. In this study, we extend on previous work in which we applied a novel method utilizing hand-crafted low-level acoustic descriptors and autoencoders (AEs) to analyse synchrony in the speech domain. For this purpose, a database consisting of 394 in-the-wild speakers from six different cultures, is used. For each speaker in the dyadic exchange, two AEs are implemented. Post the training phase, the acoustic features for one of the speakers is tested using the AE trained on their dyadic partner. In this same way, we also explore the benefits that deep representations from audio may have, implementing the state-of-the-art Deep Spectrum toolkit. For all speakers at varied time-points during their interaction, the calculation of reconstruction error from the AE trained on their respective dyadic partner is made. The results obtained from this acoustic analysis are then compared with the linguistic experiments based on word counts and word embeddings generated by our word2vec approach. The results demonstrate that there is a degree of synchrony during all interactions. We also find that, this degree varies across the 6 cultures found in the investigated database. These findings are further substantiated through the use of 4,096 dimensional Deep Spectrum features.