Dietary assessment is a key contributor to monitoring health status. Existing self-report methods are tedious and time-consuming with substantial biases and errors. Image-based food portion estimation aims to estimate food energy values directly from food images, showing great potential for automated dietary assessment solutions. Existing image-based methods either use a single-view image or incorporate multi-view images and depth information to estimate the food energy, which either has limited performance or creates user burdens. In this paper, we propose an end-to-end deep learning framework for food energy estimation from a monocular image through 3D shape reconstruction. We leverage a generative model to reconstruct the voxel representation of the food object from the input image to recover the missing 3D information. Our method is evaluated on a publicly available food image dataset Nutrition5k, resulting a Mean Absolute Error (MAE) of 40.05 kCal and Mean Absolute Percentage Error (MAPE) of 11.47% for food energy estimation. Our method uses RGB image as the only input at the inference stage and achieves competitive results compared to the existing method requiring both RGB and depth information.
相關內容
Background: With the ever-increasing amount of medical imaging data, the demand for algorithms to assist clinicians has amplified. Unsupervised anomaly detection (UAD) models promise to aid in the crucial first step of disease detection. While previous studies have thoroughly explored fairness in supervised models in healthcare, for UAD, this has so far been unexplored. Methods: In this study, we evaluated how dataset composition regarding subgroups manifests in disparate performance of UAD models along multiple protected variables on three large-scale publicly available chest X-ray datasets. Our experiments were validated using two state-of-the-art UAD models for medical images. Finally, we introduced a novel subgroup-AUROC (sAUROC) metric, which aids in quantifying fairness in machine learning. Findings: Our experiments revealed empirical "fairness laws" (similar to "scaling laws" for Transformers) for training-dataset composition: Linear relationships between anomaly detection performance within a subpopulation and its representation in the training data. Our study further revealed performance disparities, even in the case of balanced training data, and compound effects that exacerbate the drop in performance for subjects associated with multiple adversely affected groups. Interpretation: Our study quantified the disparate performance of UAD models against certain demographic subgroups. Importantly, we showed that this unfairness cannot be mitigated by balanced representation alone. Instead, the representation of some subgroups seems harder to learn by UAD models than that of others. The empirical fairness laws discovered in our study make disparate performance in UAD models easier to estimate and aid in determining the most desirable dataset composition.
Cognitive biases exert a significant influence on human thinking and decision-making. In order to identify how they influence the occurrence of architectural technical debt, a series of semi-structured interviews with software architects was performed. The results show which classes of architectural technical debt originate from cognitive biases, and reveal the antecedents of technical debt items (classes) through biases. This way, we analysed how and when cognitive biases lead to the creation of technical debt. We also identified a set of debiasing techniques that can be used in order to prevent the negative influence of cognitive biases. The observations of the role of organisational culture in the avoidance of inadvertent technical debt throw a new light on that issue.
Effective patient monitoring is vital for timely interventions and improved healthcare outcomes. Traditional monitoring systems often struggle to handle complex, dynamic environments with fluctuating vital signs, leading to delays in identifying critical conditions. To address this challenge, we propose a novel AI-driven patient monitoring framework using multi-agent deep reinforcement learning (DRL). Our approach deploys multiple learning agents, each dedicated to monitoring a specific physiological feature, such as heart rate, respiration, and temperature. These agents interact with a generic healthcare monitoring environment, learn the patients' behavior patterns, and make informed decisions to alert the corresponding Medical Emergency Teams (METs) based on the level of emergency estimated. In this study, we evaluate the performance of the proposed multi-agent DRL framework using real-world physiological and motion data from two datasets: PPG-DaLiA and WESAD. We compare the results with several baseline models, including Q-Learning, PPO, Actor-Critic, Double DQN, and DDPG, as well as monitoring frameworks like WISEML and CA-MAQL. Our experiments demonstrate that the proposed DRL approach outperforms all other baseline models, achieving more accurate monitoring of patient's vital signs. Furthermore, we conduct hyperparameter optimization to fine-tune the learning process of each agent. By optimizing hyperparameters, we enhance the learning rate and discount factor, thereby improving the agents' overall performance in monitoring patient health status. Our AI-driven patient monitoring system offers several advantages over traditional methods, including the ability to handle complex and uncertain environments, adapt to varying patient conditions, and make real-time decisions without external supervision.
Dietary assessment is essential to maintaining a healthy lifestyle. Automatic image-based dietary assessment is a growing field of research due to the increasing prevalence of image capturing devices (e.g. mobile phones). In this work, we estimate food energy from a single monocular image, a difficult task due to the limited hard-to-extract amount of energy information present in an image. To do so, we employ an improved encoder-decoder framework for energy estimation; the encoder transforms the image into a representation embedded with food energy information in an easier-to-extract format, which the decoder then extracts the energy information from. To implement our method, we compile a high-quality food image dataset verified by registered dietitians containing eating scene images, food-item segmentation masks, and ground truth calorie values. Our method improves upon previous caloric estimation methods by over 10\% and 30 kCal in terms of MAPE and MAE respectively.
Many diseases and traits involve a complex interplay between genes and environment, generating significant interest in studying gene-environment interaction through observational data. However, for lifestyle and environmental risk factors, they are often susceptible to unmeasured confounding factors and as a result, may bias the assessment of the joint effect of gene and environment. Recently, Mendelian randomization (MR) has evolved into a versatile method for assessing causal relationships based on observational data to account for unmeasured confounders. This approach utilizes genetic variants as instrumental variables (IVs) and aims to offer a reliable statistical test and estimation of causal effects. MR has gained substantial popularity in recent years largely due to the success of large-scale genome-wide association studies in identifying genetic variants associated with lifestyle and environmental factors. Many methods have been developed for MR; however, little work has been done for evaluating gene-environment interaction. In this paper, we focus on two primary IV approaches: the 2-stage predictor substitution (2SPS) and the 2-stage residual inclusion (2SRI), and extend them to accommodate gene-environment interaction under both the linear and logistic regression models for the continuous and binary outcomes, respectively. Extensive simulation and analytical derivations show that finding solutions in the linear regression model setting is relatively straightforward; however, the logistic regression model is significantly more complex and demands additional effort.
Multimodal medical data fusion has emerged as a transformative approach in smart healthcare, enabling a comprehensive understanding of patient health and personalized treatment plans. In this paper, a journey from data to information to knowledge to wisdom (DIKW) is explored through multimodal fusion for smart healthcare. We present a comprehensive review of multimodal medical data fusion focused on the integration of various data modalities. The review explores different approaches such as feature selection, rule-based systems, machine learning, deep learning, and natural language processing, for fusing and analyzing multimodal data. This paper also highlights the challenges associated with multimodal fusion in healthcare. By synthesizing the reviewed frameworks and theories, it proposes a generic framework for multimodal medical data fusion that aligns with the DIKW model. Moreover, it discusses future directions related to the four pillars of healthcare: Predictive, Preventive, Personalized, and Participatory approaches. The components of the comprehensive survey presented in this paper form the foundation for more successful implementation of multimodal fusion in smart healthcare. Our findings can guide researchers and practitioners in leveraging the power of multimodal fusion with the state-of-the-art approaches to revolutionize healthcare and improve patient outcomes.
Artificial intelligence (AI) methods hold immense potential to revolutionize numerous medical care by enhancing the experience of medical experts and patients. AI-based computer-assisted diagnosis and treatment tools can democratize healthcare by matching the clinical level or surpassing clinical experts. As a result, advanced healthcare services can be affordable to all populations, irrespective of demographics, race, or socioeconomic background. The democratization of such AI tools can reduce the cost of care, optimize resource allocation, and improve the quality of care. In contrast to humans, AI can uncover complex relations in the data from a large set of inputs and even lead to new evidence-based knowledge in medicine. However, integrating AI into healthcare raises several ethical and philosophical concerns, such as bias, transparency, autonomy, responsibility, and accountability. Here, we emphasize recent advances in AI-assisted medical image analysis, existing standards, and the significance of comprehending ethical issues and best practices for clinical settings. We cover the technical and ethical challenges and implications of deploying AI in hospitals and public organizations. We also discuss key measures and techniques to address ethical challenges, data scarcity, racial bias, lack of transparency, and algorithmic bias and provide recommendations and future directions.
Decision-making algorithms are being used in important decisions, such as who should be enrolled in health care programs and be hired. Even though these systems are currently deployed in high-stakes scenarios, many of them cannot explain their decisions. This limitation has prompted the Explainable Artificial Intelligence (XAI) initiative, which aims to make algorithms explainable to comply with legal requirements, promote trust, and maintain accountability. This paper questions whether and to what extent explainability can help solve the responsibility issues posed by autonomous AI systems. We suggest that XAI systems that provide post-hoc explanations could be seen as blameworthy agents, obscuring the responsibility of developers in the decision-making process. Furthermore, we argue that XAI could result in incorrect attributions of responsibility to vulnerable stakeholders, such as those who are subjected to algorithmic decisions (i.e., patients), due to a misguided perception that they have control over explainable algorithms. This conflict between explainability and accountability can be exacerbated if designers choose to use algorithms and patients as moral and legal scapegoats. We conclude with a set of recommendations for how to approach this tension in the socio-technical process of algorithmic decision-making and a defense of hard regulation to prevent designers from escaping responsibility.
Human doctors with well-structured medical knowledge can diagnose a disease merely via a few conversations with patients about symptoms. In contrast, existing knowledge-grounded dialogue systems often require a large number of dialogue instances to learn as they fail to capture the correlations between different diseases and neglect the diagnostic experience shared among them. To address this issue, we propose a more natural and practical paradigm, i.e., low-resource medical dialogue generation, which can transfer the diagnostic experience from source diseases to target ones with a handful of data for adaptation. It is capitalized on a commonsense knowledge graph to characterize the prior disease-symptom relations. Besides, we develop a Graph-Evolving Meta-Learning (GEML) framework that learns to evolve the commonsense graph for reasoning disease-symptom correlations in a new disease, which effectively alleviates the needs of a large number of dialogues. More importantly, by dynamically evolving disease-symptom graphs, GEML also well addresses the real-world challenges that the disease-symptom correlations of each disease may vary or evolve along with more diagnostic cases. Extensive experiment results on the CMDD dataset and our newly-collected Chunyu dataset testify the superiority of our approach over state-of-the-art approaches. Besides, our GEML can generate an enriched dialogue-sensitive knowledge graph in an online manner, which could benefit other tasks grounded on knowledge graph.
Textual entailment is a fundamental task in natural language processing. Most approaches for solving the problem use only the textual content present in training data. A few approaches have shown that information from external knowledge sources like knowledge graphs (KGs) can add value, in addition to the textual content, by providing background knowledge that may be critical for a task. However, the proposed models do not fully exploit the information in the usually large and noisy KGs, and it is not clear how it can be effectively encoded to be useful for entailment. We present an approach that complements text-based entailment models with information from KGs by (1) using Personalized PageR- ank to generate contextual subgraphs with reduced noise and (2) encoding these subgraphs using graph convolutional networks to capture KG structure. Our technique extends the capability of text models exploiting structural and semantic information found in KGs. We evaluate our approach on multiple textual entailment datasets and show that the use of external knowledge helps improve prediction accuracy. This is particularly evident in the challenging BreakingNLI dataset, where we see an absolute improvement of 5-20% over multiple text-based entailment models.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191