arXiv subjects

Anastasios Delopoulos

Publications and source records attributed to Anastasios Delopoulos.

At least 19 recordsLinked to original sources

arXiv2026

Deep Learning for Biopsy-Free Subtyping of Basal Cell Carcinoma from Dermatoscopic Images

Basal Cell Carcinoma (BCC) is the most common type of skin cancer, accounting for nearly 80% of skin cancer di- agnoses. Its optimal clinical management is guided by the distinct histopathologic subtype, with aggressive variants requiring more drastic measures. In current clinical practice, subtyping relies on skin biopsies, a procedure both costly and invasive. In this paper, we conduct a preliminary investigation into using deep learning for BCC subtyping, solely from a single dermatoscopic image of the lesion. Given the limited data at our disposal, we employ pre-trained vision transformers (ViTs), a state-of-the-art family of models highly effective for challenging downstream tasks with limited labeled data. Through repeated stratified k-fold cross-validation, we demonstrate that ViTs can achieve superior performance (AUC 0.784 on a dataset of 1271 dermatoscopic images of various BCC subtypes) over standard CNN-based baselines as well as previously-reported human reader perfor- mance, on the task of differentiating aggressive BCCs from other subtype families. These initial findings highlight the potential of combining deep learning and dermatoscopy to provide a biopsy- free alternative for BCC subtyping, thus aiding in improving treatment planning and patient outcomes.

cs.CV↗

arXiv2025

Weakly Supervised Food Image Segmentation using Vision Transformers and Segment Anything Model

In this paper, we propose a weakly supervised semantic segmentation approach for food images which takes advantage of the zero-shot capabilities and promptability of the Segment Anything Model (SAM) along with the attention mechanisms of Vision Transformers (ViTs). Specifically, we use class activation maps (CAMs) from ViTs to generate prompts for SAM, resulting in masks suitable for food image segmentation. The ViT model, a Swin Transformer, is trained exclusively using image-level annotations, eliminating the need for pixel-level annotations during training. Additionally, to enhance the quality of the SAM-generated masks, we examine the use of image preprocessing techniques in combination with single-mask and multi-mask SAM generation strategies. The methodology is evaluated on the FoodSeg103 dataset, generating an average of 2.4 masks per image (excluding background), and achieving an mIoU of 0.54 for the multi-mask scenario. We envision the proposed approach as a tool to accelerate food image annotation tasks or as an integrated component in food and nutrition tracking applications.

cs.CV↗

arXiv2025

Estimation of Food Intake Quantity Using Inertial Signals from Smartwatches

Accurate monitoring of eating behavior is crucial for managing obesity and eating disorders such as bulimia nervosa. At the same time, existing methods rely on multiple and/or specialized sensors, greatly harming adherence and ultimately, the quality and continuity of data. This paper introduces a novel approach for estimating the weight of a bite, from a commercial smartwatch. Our publicly-available dataset contains smartwatch inertial data from ten participants, with manually annotated start and end times of each bite along with their corresponding weights from a smart scale, under semi-controlled conditions. The proposed method combines extracted behavioral features such as the time required to load the utensil with food, with statistical features of inertial signals, that serve as input to a Support Vector Regression model to estimate bite weights. Under a leave-one-subject-out cross-validation scheme, our approach achieves a mean absolute error (MAE) of 3.99 grams per bite. To contextualize this performance, we introduce the improvement metric, that measures the relative MAE difference compared to a baseline model. Our method demonstrates a 17.41% improvement, while the adapted state-of-the art method shows a -28.89% performance against that same baseline. The results presented in this work establish the feasibility of extracting meaningful bite weight estimates from commercial smartwatch inertial sensors alone, laying the groundwork for future accessible, non-invasive dietary monitoring systems.

eess.SP↗

arXiv2025

A system for objectively measuring behavior and the environment to support large-scale studies on childhood obesity

Advances in IoT technologies combined with new algorithms have enabled the collection and processing of high-rate multi-source data streams that quantify human behavior in a fine-grained level and can lead to deeper insights on individual behaviors as well as on the interplay between behaviors and the environment. In this paper, we present an integrated system that collects and extracts multiple behavioral and environmental indicators, aiming at improving public health policies for tackling obesity. Data collection takes place using passive methods based on smartphone and smartwatch applications that require minimal interaction with the user. Our goal is to present a detailed account of the design principles, the implementation processes, and the evaluation of integrated algorithms, especially given the challenges we faced, in particular (a) integrating multiple technologies, algorithms, and components under a single, unified system, and (b) large scale (big data) requirements. We also present evaluation results of the algorithms on datasets (public for most cases) such as an absolute error of 8-9 steps when counting steps, 0.86 F1-score for detecting visited locations, and an error of less than 12 mins for gross sleep time. Finally, we also briefly present studies that have been materialized using our system, thus demonstrating its potential value to public authorities and individual researchers.

cs.CY↗

arXiv2024

Prediabetes detection in unconstrained conditions using wearable sensors

Prediabetes is a common health condition that often goes undetected until it progresses to type 2 diabetes. Early identification of prediabetes is essential for timely intervention and prevention of complications. This research explores the feasibility of using wearable continuous glucose monitoring along with smartwatches with embedded inertial sensors to collect glucose measurements and acceleration signals respectively, for the early detection of prediabetes. We propose a methodology based on signal processing and machine learning techniques. Two feature sets are extracted from the collected signals, based both on a dynamic modeling of the human glucose-homeostasis system and on the Glucose curve, inspired by three major glucose related blood tests. Features are aggregated per individual using bootstrap. Support Vector Machines are used to classify normoglycemic vs. prediabetic individuals. We collected data from 22 participants for evaluation. The results are highly encouraging, demonstrating high sensitivity and precision. This work is a proof of concept, highlighting the potential of wearable devices in prediabetes assessment. Future directions involve expanding the study to a larger, more diverse population and exploring the integration of CGM and smartwatch functionalities into a unified device. Automated eating detecting algorithms can also be used.

eess.SP↗

arXiv2024

Transportation mode recognition based on low-rate acceleration and location signals with an attention-based multiple-instance learning network

Transportation mode recognition (TMR) is a critical component of human activity recognition (HAR) that focuses on understanding and identifying how people move within transportation systems. It is commonly based on leveraging inertial, location, or both types of signals, captured by modern smartphone devices. Each type has benefits (such as increased effectiveness) and drawbacks (such as increased battery consumption) depending on the transportation mode (TM). Combining the two types is challenging as they exhibit significant differences such as very different sampling rates. This paper focuses on the TMR task and proposes an approach for combining the two types of signals in an effective and robust classifier. Our network includes two sub-networks for processing acceleration and location signals separately, using different window sizes for each signal. The two sub-networks are designed to also embed the two types of signals into the same space so that we can then apply an attention-based multiple-instance learning classifier to recognize TM. We use very low sampling rates for both signal types to reduce battery consumption. We evaluate the proposed methodology on a publicly available dataset and compare against other well known algorithms.

eess.SP↗

arXiv2023

Leveraging Unlabelled Data in Multiple-Instance Learning Problems for Improved Detection of Parkinsonian Tremor in Free-Living Conditions

Data-driven approaches for remote detection of Parkinson's Disease and its motor symptoms have proliferated in recent years, owing to the potential clinical benefits of early diagnosis. The holy grail of such approaches is the free-living scenario, in which data are collected continuously and unobtrusively during every day life. However, obtaining fine-grained ground-truth and remaining unobtrusive is a contradiction and therefore, the problem is usually addressed via multiple-instance learning. Yet for large scale studies, obtaining even the necessary coarse ground-truth is not trivial, as a complete neurological evaluation is required. In contrast, large scale collection of data without any ground-truth is much easier. Nevertheless, utilizing unlabelled data in a multiple-instance setting is not straightforward, as the topic has received very little research attention. Here we try to fill this gap by introducing a new method for combining semi-supervised with multiple-instance learning. Our approach builds on the Virtual Adversarial Training principle, a state-of-the-art approach for regular semi-supervised learning, which we adapt and modify appropriately for the multiple-instance setting. We first establish the validity of the proposed approach through proof-of-concept experiments on synthetic problems generated from two well-known benchmark datasets. We then move on to the actual task of detecting PD tremor from hand acceleration signals collected in-the-wild, but in the presence of additional completely unlabelled data. We show that by leveraging the unlabelled data of 454 subjects we can achieve large performance gains (up to 9% increase in F1-score) in per-subject tremor detection for a cohort of 45 subjects with known tremor ground-truth.

cs.LG↗

arXiv2022

Listen2YourHeart: A Self-Supervised Approach for Detecting Murmur in Heart-Beat Sounds

Heart murmurs are abnormal sounds present in heartbeats, caused by turbulent blood flow through the heart. The PhysioNet 2022 challenge targets automatic detection of murmur from audio recordings of the heart and automatic detection of normal vs. abnormal clinical outcome. The recordings are captured from multiple locations around the heart. Our participation investigates the effectiveness of selfsupervised learning for murmur detection. We train the layers of a backbone CNN in a self-supervised way with data from both this year's and the 2016 challenge. We use two different augmentations on each training sample, and normalized temperature-scaled cross-entropy loss. We experiment with different augmentations to learn effective phonocardiogram representations. To build the final detectors we train two classification heads, one for each challenge task. We present evaluation results for all combinations of the available augmentations, and for our multipleaugmentation approach. Our team's, Listen2YourHeart, SSL murmur detection classifier received a weighted accuracy score of 0.737 (ranked 13th out of 40 teams) and an outcome identification challenge cost score of 11946 (ranked 7th out of 39 teams) on the hidden test set.

cs.LG↗

arXiv2022

Chewing Detection from Commercial Smart-glasses

Automatic dietary monitoring has progressed significantly during the last years, offering a variety of solutions, both in terms of sensors and algorithms as well as in terms of what aspect or parameters of eating behavior are measured and monitored. Automatic detection of eating based on chewing sounds has been studied extensively, however, it requires a microphone to be mounted on the subject's head for capturing the relevant sounds. In this work, we evaluate the feasibility of using an off-the-shelf commercial device, the Razer Anzu smart-glasses, for automatic chewing detection. The smart-glasses are equipped with stereo speakers and microphones that communicate with smart-phones via Bluetooth. The microphone placement is not optimal for capturing chewing sounds, however, we find that it does not significantly affect the detection effectiveness. We apply an algorithm from literature with some adjustments on a challenging dataset that we have collected in house. Leave-one-subject-out experiments yield promising results, with an F1-score of 0.96 for the best case of duration-based evaluation of eating time.

eess.AS↗

arXiv2021

A Bottom-up method Towards the Automatic and Objective Monitoring of Smoking Behavior In-the-wild using Wrist-mounted Inertial Sensors

The consumption of tobacco has reached global epidemic proportions and is characterized as the leading cause of death and illness. Among the different ways of consuming tobacco (e.g., smokeless, cigars), smoking cigarettes is the most widespread. In this paper, we present a two-step, bottom-up algorithm towards the automatic and objective monitoring of cigarette-based, smoking behavior during the day, using the 3D acceleration and orientation velocity measurements from a commercial smartwatch. In the first step, our algorithm performs the detection of individual smoking gestures (i.e., puffs) using an artificial neural network with both convolutional and recurrent layers. In the second step, we make use of the detected puff density to achieve the temporal localization of smoking sessions that occur throughout the day. In the experimental section we provide extended evaluation regarding each step of the proposed algorithm, using our publicly available, realistic Smoking Event Detection (SED) and Free-living Smoking Event Detection (SED-FL) datasets recorded under semi-controlled and free-living conditions, respectively. In particular, leave-one-subject-out (LOSO) experiments reveal an F1-score of 0.863 for the detection of puffs and an F1-score/Jaccard index equal to 0.878/0.604 towards the temporal localization of smoking sessions during the day. Finally, to gain further insight, we also compare the puff detection part of our algorithm with a similar approach found in the recent literature.

eess.SP↗

arXiv2021

Self-Supervised Feature Learning of 1D Convolutional Neural Networks with Contrastive Loss for Eating Detection Using an In-Ear Microphone

The importance of automated and objective monitoring of dietary behavior is becoming increasingly accepted. The advancements in sensor technology along with recent achievements in machine-learning--based signal-processing algorithms have enabled the development of dietary monitoring solutions that yield highly accurate results. A common bottleneck for developing and training machine learning algorithms is obtaining labeled data for training supervised algorithms, and in particular ground truth annotations. Manual ground truth annotation is laborious, cumbersome, can sometimes introduce errors, and is sometimes impossible in free-living data collection. As a result, there is a need to decrease the labeled data required for training. Additionally, unlabeled data, gathered in-the-wild from existing wearables (such as Bluetooth earbuds) can be used to train and fine-tune eating-detection models. In this work, we focus on training a feature extractor for audio signals captured by an in-ear microphone for the task of eating detection in a self-supervised way. We base our approach on the SimCLR method for image classification, proposed by Chen et al. from the domain of computer vision. Results are promising as our self-supervised method achieves similar results to supervised training alternatives, and its overall effectiveness is comparable to current state-of-the-art methods. Code is available at https://github.com/mug-auth/ssl-chewing .

eess.AS↗

arXiv2021

Bite-Weight Estimation Using Commercial Ear Buds

While automatic tracking and measuring of our physical activity is a well established domain, not only in research but also in commercial products and every-day life-style, automatic measurement of eating behavior is significantly more limited. Despite the abundance of methods and algorithms that are available in bibliography, commercial solutions are mostly limited to digital logging applications for smart-phones. One factor that limits the adoption of such solutions is that they usually require specialized hardware or sensors. Based on this, we evaluate the potential for estimating the weight of consumed food (per bite) based only on the audio signal that is captured by commercial ear buds (Samsung Galaxy Buds). Specifically, we examine a combination of features (both audio and non-audio features) and trainable estimators (linear regression, support vector regression, and neural-network based estimators) and evaluate on an in-house dataset of 8 participants and 4 food types. Results indicate good potential for this approach: our best results yield mean absolute error of less than 1 g for 3 out of 4 food types when training food-specific models, and 2.1 g when training on all food types together, both of which improve over an existing literature approach.

eess.AS↗

arXiv2021

Recognition of food-texture attributes using an in-ear microphone

Food texture is a complex property; various sensory attributes such as perceived crispiness and wetness have been identified as ways to quantify it. Objective and automatic recognition of these attributes has applications in multiple fields, including health sciences and food engineering. In this work we use an in-ear microphone, commonly used for chewing detection, and propose algorithms for recognizing three food-texture attributes, specifically crispiness, wetness (moisture), and chewiness. We use binary SVMs, one for each attribute, and propose two algorithms: one that recognizes each texture attribute at the chew level and one at the chewing-bout level. We evaluate the proposed algorithms using leave-one-subject-out cross-validation on a dataset with 9 subjects. We also evaluate them using leave-one-food-type-out cross-validation, in order to examine the generalization of our approach to new, unknown food types. Our approach performs very well in recognizing crispiness (0.95 weighted accuracy on new subjects and 0.93 on new food types) and demonstrates promising results for objective and automatic recognition of wetness and chewiness.

eess.SP↗

arXiv2021

An Interpretable Multiple-Instance Approach for the Detection of referable Diabetic Retinopathy from Fundus Images

Diabetic Retinopathy (DR) is a leading cause of vision loss globally. Yet despite its prevalence, the majority of affected people lack access to the specialized ophthalmologists and equipment required for assessing their condition. This can lead to delays in the start of treatment, thereby lowering their chances for a successful outcome. Machine learning systems that automatically detect the disease in eye fundus images have been proposed as a means of facilitating access to DR severity estimates for patients in remote regions or even for complementing the human expert's diagnosis. In this paper, we propose a machine learning system for the detection of referable DR in fundus images that is based on the paradigm of multiple-instance learning. By extracting local information from image patches and combining it efficiently through an attention mechanism, our system is able to achieve high classification accuracy. Moreover, it can highlight potential image regions where DR manifests through its characteristic lesions. We evaluate our approach on publicly available retinal image datasets, in which it exhibits near state-of-the-art performance, while also producing interpretable visualizations of its predictions.

cs.CV↗

arXiv2020

A Data Driven End-to-end Approach for In-the-wild Monitoring of Eating Behavior Using Smartwatches

The increased worldwide prevalence of obesity has sparked the interest of the scientific community towards tools that objectively and automatically monitor eating behavior. Despite the study of obesity being in the spotlight, such tools can also be used to study eating disorders (e.g. anorexia nervosa) or provide a personalized monitoring platform for patients or athletes. This paper presents a complete framework towards the automated i) modeling of in-meal eating behavior and ii) temporal localization of meals, from raw inertial data collected in-the-wild using commercially available smartwatches. Initially, we present an end-to-end Neural Network which detects food intake events (i.e. bites). The proposed network uses both convolutional and recurrent layers that are trained simultaneously. Subsequently, we show how the distribution of the detected bites throughout the day can be used to estimate the start and end points of meals, using signal processing algorithms. We perform extensive evaluation on each framework part individually. Leave-one-subject-out (LOSO) evaluation shows that our bite detection approach outperforms four state-of-the-art algorithms towards the detection of bites during the course of a meal (0.923 F1 score). Furthermore, LOSO and held-out set experiments regarding the estimation of meal start/end points reveal that the proposed approach outperforms a relevant approach found in the literature (Jaccard Index of 0.820 and 0.821 for the LOSO and heldout experiments, respectively). Experiments are performed using our publicly available FIC and the newly introduced FreeFIC datasets.

eess.SP↗

arXiv2020

Collecting big behavioral data for measuring behavior against obesity

Obesity is currently affecting very large portions of the global population. Effective prevention and treatment starts at the early age and requires objective knowledge of population-level behavior on the region/neighborhood scale. To this end, we present a system for extracting and collecting behavioral information on the individual-level objectively and automatically. The behavioral information is related to physical activity, types of visited places, and transportation mode used between them. The system employs indicator-extraction algorithms from the literature which we evaluate on publicly available datasets. The system has been developed and integrated in the context of the EU-funded BigO project that aims at preventing obesity in young populations.

cs.CY↗

arXiv2020

Inferring the Spatial Distribution of Physical Activity in Children Population from Characteristics of the Environment

Obesity affects a rising percentage of the children and adolescent population, contributing to decreased quality of life and increased risk for comorbidities. Although the major causes of obesity are known, the obesogenic behaviors manifest as a result of complex interactions of the individual with the living environment. For this reason, addressing childhood obesity remains a challenging problem for public health authorities. The BigO project (https://bigoprogram.eu) relies on large-scale behavioral and environmental data collection to create tools that support policy making and intervention design. In this work, we propose a novel analysis approach for modeling the expected population behavior as a function of the local environment. We experimentally evaluate this approach in predicting the expected physical activity level in small geographic regions using urban environment characteristics. Experiments on data collected from 156 children and adolescents verify the potential of the proposed approach. Specifically, we train models that predict the physical activity level in a region, achieving 81% leave-one-out accuracy. In addition, we exploit the model predictions to automatically visualize heatmaps of the expected population behavior in areas of interest, from which we draw useful insights. Overall, the predictive models and the automatic heatmaps are promising tools in gaining direct perception for the spatial distribution of the population's behavior, with potential uses by public health authorities.

cs.CY↗

arXiv2020

BigO: A public health decision support system for measuring obesogenic behaviors of children in relation to their local environment

Obesity is a complex disease and its prevalence depends on multiple factors related to the local socioeconomic, cultural and urban context of individuals. Many obesity prevention strategies and policies, however, are horizontal measures that do not depend on context-specific evidence. In this paper we present an overview of BigO (http://bigoprogram.eu), a system designed to collect objective behavioral data from children and adolescent populations as well as their environment in order to support public health authorities in formulating effective, context-specific policies and interventions addressing childhood obesity. We present an overview of the data acquisition, indicator extraction, data exploration and analysis components of the BigO system, as well as an account of its preliminary pilot application in 33 schools and 2 clinics in four European countries, involving over 4,200 participants.

cs.CY↗