CBCT-guided adaptive radiotherapy using self-supervised sequential domain adaptation with uncertainty estimation.

Adaptive radiotherapy (ART) is an advanced technology in modern cancer treatment that incorporates progressive changes in patient anatomy into active plan/dose adaption during the fractionated treatment. However, the clinical application relies on the accurate segmentation of cancer tumors on low-quality on-board images, which has posed challenges for both manual delineation and deep learning-based models. In this paper, we propose a novel sequence transduction deep neural network with an attention mechanism to learn the shrinkage of the cancer tumor based on patients' weekly cone-beam computed tomography (CBCT). We design a self-supervised domain adaption (SDA) method to learn and adapt the rich textural and spatial features from pre-treatment high-quality computed tomography (CT) to CBCT modality in order to address the poor image quality and lack of labels. We also provide uncertainty estimation for sequential segmentation, which aids not only in the risk management of treatment planning but also in the calibration and reliability of the model. Our experimental results based on a clinical non-small cell lung cancer (NSCLC) dataset with sixteen patients and ninety-six longitudinal CBCTs show that our model correctly learns weekly deformation of the tumor over time with an average dice score of 0.92 on the immediate next step, and is able to predict multiple steps (up to 5 weeks) for future patient treatments with an average dice score reduction of 0.05. By incorporating the tumor shrinkage predictions into a weekly re-planning strategy, our proposed method demonstrates a significant decrease in the risk of radiation-induced pneumonitis up to 35% while maintaining the high tumor control probability.

Can Hierarchical Transformers Learn Facial Geometry?

Human faces are a core part of our identity and expression, and thus, understanding facial geometry is key to capturing this information. Automated systems that seek to make use of this information must have a way of modeling facial features in a way that makes them accessible. Hierarchical, multi-level architectures have the capability of capturing the different resolutions of representation involved. In this work, we propose using a hierarchical transformer architecture as a means of capturing a robust representation of facial geometry. We further demonstrate the versatility of our approach by using this transformer as a backbone to support three facial representation problems: face anti-spoofing, facial expression representation, and deepfake detection. The combination of effective fine-grained details alongside global attention representations makes this architecture an excellent candidate for these facial representation problems. We conduct numerous experiments first showcasing the ability of our approach to address common issues in facial modeling (pose, occlusions, and background variation) and capture facial symmetry, then demonstrating its effectiveness on three supplemental tasks.

Multimodal explainable AI predicts upcoming speech behavior in adults who stutter.

A key goal of cognitive neuroscience is to better understand how dynamic brain activity relates to behavior. Such dynamics, in terms of spatial and temporal patterns of brain activity, are directly measured with neurophysiological methods such as EEG, but can also be indirectly expressed by the body. Autonomic nervous system activity is the best-known example, but, muscles in the eyes and face can also index brain activity. Mostly parallel lines of artificial intelligence research show that EEG and facial muscles both encode information about emotion, pain, attention, and social interactions, among other topics. In this study, we examined adults who stutter (AWS) to understand the relations between dynamic brain and facial muscle activity and predictions about future behavior (fluent or stuttered speech). AWS can provide insight into brain-behavior dynamics because they naturally fluctuate between episodes of fluent and stuttered speech behavior. We focused on the period when speech preparation occurs, and used EEG and facial muscle activity measured from video to predict whether the upcoming speech would be fluent or stuttered. An explainable self-supervised multimodal architecture learned the temporal dynamics of both EEG and facial muscle movements during speech preparation in AWS, and predicted fluent or stuttered speech at 80.8% accuracy (chance=50%). Specific EEG and facial muscle signals distinguished fluent and stuttered trials, and systematically varied from early to late speech preparation time periods. The self-supervised architecture successfully identified multimodal activity that predicted upcoming behavior on a trial-by-trial basis. This approach could be applied to understanding the neural mechanisms driving variable behavior and symptoms in a wide range of neurological and psychiatric disorders. The combination of direct measures of neural activity and simple video data may be applied to developing technologies that estimate brain state from subtle bodily signals.

Deepfake forensics analysis: An explainable hierarchical ensemble of weakly supervised models.

Deepfakes have become exponentially more common and sophisticated in recent years, so much so that forensic specialists, policy makers, and the public alike are anxious about their role in spreading disinformation. Recently, the detection and creation of such forgery became a popular research topic, leading to significant growth in publications related to the creation of deepfakes, detection methods, and datasets containing the latest deepfake creation methods. The most successful approaches in identifying and preventing deepfakes are deep learning methods that rely on convolutional neural networks as the backbone for a binary classification task. A convolutional neural network extracts the underlying patterns from the input frames. It feeds these to a binary classification fully connected network, which classifies these patterns as trustworthy or untrustworthy. We claim that this method is not ideal in a scenario in which the generation algorithms constantly evolve since the detection algorithm is not robust enough to detect comparably minor artifacts introduced by the generation algorithms. This work proposes a hierarchical explainable forensics algorithm that incorporates humans in the detection loop. We curate the data through a deep learning detection algorithm and share an explainable decision to humans alongside a set of forensic analyses on the decision region. On the detection side, we propose an attention-based explainable deepfake detection algorithm. We address this generalization issue by implementing an ensemble of standard and attention-based data-augmented detection networks. We use the attention blocks to evaluate the face regions where the model focuses its decision. We simultaneously drop and enlarge the region to push the model to base its decision on more regions of the face, while maintaining a specific focal point for its decision. In this case, we use an ensemble of models to improve the generalization. We also evaluate the models' decision using Grad-CAM explanation to focus on the attention maps. The region uncovered by the explanation layer is cropped and undergoes a series of frequency and statistical analyses that help humans decide if the frame is real or fake. We evaluate our model in one of the most challenging datasets, the DFDC, and achieve an accuracy of 92.4%. We successfully maintain this accuracy in datasets not used in the training process.

Interpretable Self-Supervised Facial Micro-Expression Learning to Predict Cognitive State and Neurological Disorders.

Human behavior is the confluence of output from voluntary and involuntary motor systems. The neural activities that mediate behavior, from individual cells to distributed networks, are in a state of constant flux. Artificial intelligence (AI) research over the past decade shows that behavior, in the form of facial muscle activity, can reveal information about fleeting voluntary and involuntary motor system activity related to emotion, pain, and deception. However, the AI algorithms often lack an explanation for their decisions, and learning meaningful representations requires large datasets labeled by a subject-matter expert. Motivated by the success of using facial muscle movements to classify brain states and the importance of learning from small amounts of data, we propose an explainable self-supervised representation-learning paradigm that learns meaningful temporal facial muscle movement patterns from limited samples. We validate our methodology by carrying out comprehensive empirical study to predict future speech behavior in a real-world dataset of adults who stutter (AWS). Our explainability study found facial muscle movements around the eyes (p <0.×001) and lips (p <0.001) differ significantly before producing fluent vs. disfluent speech. Evaluations using the AWS dataset demonstrates that the proposed self-supervised approach achieves a minimum of 2.51% accuracy improvement over fully-supervised approaches.

Summarizing Complex Graphical Models of Multiple Chronic Conditions Using the Second Eigenvalue of Graph Laplacian: Algorithm Development and Validation.

BACKGROUND: It is important but challenging to understand the interactions of multiple chronic conditions (MCC) and how they develop over time in patients and populations. Clinical data on MCC can now be represented using graphical models to study their interaction and identify the path toward the development of MCC. However, the current graphical models representing MCC are often complex and difficult to analyze. Therefore, it is necessary to develop improved methods for generating these models. OBJECTIVE: This study aimed to summarize the complex graphical models of MCC interactions to improve comprehension and aid analysis. METHODS: We examined the emergence of 5 chronic medical conditions (ie, traumatic brain injury [TBI], posttraumatic stress disorder [PTSD], depression [Depr], substance abuse [SuAb], and back pain [BaPa]) over 5 years among 257,633 veteran patients. We developed 3 algorithms that utilize the second eigenvalue of the graph Laplacian to summarize the complex graphical models of MCC by removing less significant edges. The first algorithm learns a sparse probabilistic graphical model of MCC interactions directly from the data. The second algorithm summarizes an existing probabilistic graphical model of MCC interactions when a supporting data set is available. The third algorithm, which is a variation of the second algorithm, summarizes the existing graphical model of MCC interactions with no supporting data. Finally, we examined the coappearance of the 100 most common terms in the literature of MCC to validate the performance of the proposed model. RESULTS: The proposed summarization algorithms demonstrate considerable performance in extracting major connections among MCC without reducing the predictive accuracy of the resulting graphical models. For the model learned directly from the data, the area under the curve (AUC) performance for predicting TBI, PTSD, BaPa, SuAb, and Depr, respectively, during the next 4 years is as follows-year 2: 79.91%, 84.04%, 78.83%, 82.50%, and 81.47%; year 3: 76.23%, 80.61%, 73.51%, 79.84%, and 77.13%; year 4: 72.38%, 78.22%, 72.96%, 77.92%, and 72.65%; and year 5: 69.51%, 76.15%, 73.04%, 76.72%, and 69.99%, respectively. This demonstrates an overall 12.07% increase in the cumulative sum of AUC in comparison with the classic multilevel temporal Bayesian network. CONCLUSIONS: Using graph summarization can improve the interpretability and the predictive power of the complex graphical models of MCC.