Motion Capture Sensor-Based Emotion Recognition Using a Bi-Modular Sequential Neural Network

Motion capture sensor-based gait emotion recognition is an emerging sub-domain of human emotion recognition. Its applications span a variety of fields including smart home design, border security, robotics, virtual reality, and gaming. In recent years, several deep learning-based approaches have been successful in solving the Gait Emotion Recognition (GER) problem. However, a vast majority of such methods rely on Deep Neural Networks (DNNs) with a significant number of model parameters, which lead to model overfitting as well as increased inference time. This paper contributes to the domain of knowledge by proposing a new lightweight bi-modular architecture with handcrafted features that is trained using a RMSprop optimizer and stratified data shuffling. The method is highly effective in correctly inferring human emotions from gait, achieving a micro-mean average precision of 0.97 on the Edinburgh Locomotive Mocap Dataset. It outperforms all recent deep-learning methods, while having the lowest inference time of 16.3 milliseconds per gait sample. This research study is beneficial to applications spanning various fields, such as emotionally aware assistive robotics, adaptive therapy and rehabilitation, and surveillance.

CT-on-Rails versus in-Room CBCT for Online Daily Adaptive Proton Therapy of Head-and-Neck Cancers

Purpose: To compare the efficacy of CT-on-rails versus in-room CBCT for daily adaptive proton therapy. Methods: We analyzed a cohort of ten head-and-neck patients with daily CBCT and corresponding virtual CT images. The necessity of moving the patient after a CT scan is the most significant difference in the adaptation workflow, leading to an increased treatment execution uncertainty σ. It is a combination of the isocenter-matching σi and random patient movements induced by the couch motion σm. The former is assumed to never exceed 1 mm. For the latter, we studied three different scenarios with σm = 1, 2, and 3 mm. Accordingly, to mimic the adaptation workflow with CT-on-rails, we introduced random offsets after Monte-Carlo-based adaptation but before delivery of the adapted plan. Results: There were no significant differences in accumulated dose-volume histograms and dose distributions for σm = 1 and 2 mm. Offsets with σm = 3 mm resulted in underdosage to CTV and hot spots of considerable volume. Conclusion: Since σm typically does not exceed 2 mm for in-room CT, there is no clinically significant dosimetric difference between the two modalities for online adaptive therapy of head-and-neck patients. Therefore, in-room CT-on-rails can be considered a good alternative to CBCT for adaptive proton therapy.

Population Dynamics of Hybrid State during Adaptive Therapy in Cancer

Drug resistance emerges due to drug-induced phenotypic switching of drug-sensitive to drug-resistant subpopulations in cancer during therapy. Existing models indicate the competitive advantage of sensitive over resistant population to regulate tumor and reducing the treatment cost with increased time to progression of tumor ultimately benefiting the patient in a clinical setting. Here, we present a Lotka Volterra (LV) based population dynamics (PD) model of the drug-sensitive, drug-resistant, and transient drug-hybrid state along with phenotypic switching during adaptive therapy based on a simple cancer biomarker (CB) to decide the adaptive therapy dosage to regulate cancer. We identified that the strength of intra-competition along with phenotypic switching parameters is crucial to mediate the effectiveness of adaptive therapy and also investigated the significance of the initial fraction of subpopulations on AT. We hypothesize and predict the dynamics of drug-induced transient hybrid state playing a key role in the cancer cells undergoing metastasis.

Optimizing Adaptive Therapy Based on the Reachability to Tumor Resistant Subpopulation

Adaptive therapy exploits the self-organization of tumor cells to delay the outgrowth of resistant subpopulations successfully. When the tumor has aggressive resistant subpopulations, the outcome of adaptive therapy was not superior to maximum tolerated dose therapy (MTD). To explore methods to improve the adaptive therapy's performance of this case, the tumor system was constructed by osimertinib-sensitive and resistant cell lines and illustrated by the Lotka-Volterra model in this study. Restore index proposed to assess the system reachability can predict the duration of each treatment cycle. Then the threshold of the restore index was estimated to evaluate the timing of interrupting the treatment cycle and switching to high-frequency administration. The introduced reachability-based adaptive therapy and classic adaptive therapy were compared through simulation and animal experiments. The results suggested that reachability-based adaptive therapy showed advantages when the tumor has an aggressive resistant subpopulation. This study provides a feasible method for evaluating whether to continue the adaptive therapy treatment cycle or switch to high-frequency administration. This method improves the gain of adaptive therapy by taking into account the benefits of tumor intra-competition and the tumor control of killing sensitive subpopulation.

Darwinian Approaches for Cancer Treatment: Benefits of Mathematical Modeling

One of the major problems of traditional anti-cancer treatments is that they lead to the emergence of treatment-resistant cells, which results in treatment failure. To avoid or delay this phenomenon, it is relevant to take into account the eco-evolutionary dynamics of tumors. Designing evolution-based treatment strategies may help overcoming the problem of drug resistance. In particular, a promising candidate is adaptive therapy, a containment strategy which adjusts treatment cycles to the evolution of the tumors in order to keep the population of treatment-resistant cells under control. Mathematical modeling is a crucial tool to understand the dynamics of cancer in response to treatments, and to make predictions about the outcomes of these treatments. In this review, we highlight the benefits of in silico modeling to design adaptive therapy strategies, and to assess whether they could effectively improve treatment outcomes. Specifically, we review how two main types of models (i.e., mathematical models based on Lotka–Volterra equations and agent-based models) have been used to model tumor dynamics in response to adaptive therapy. We give examples of the advances they permitted in the field of adaptive therapy and discuss about how these models can be integrated in experimental approaches and clinical trial design.

Evolutionary Dynamics of Treatment-Induced Resistance in Cancer Informs Understanding of Rapid Evolution in Natural Systems

Rapid evolution is ubiquitous in nature. We briefly review some of this quite broadly, particularly in the context of response to anthropogenic disturbances. Nowhere is this more evident, replicated and accessible to study than in cancer. Curiously cancer has been late - relative to fisheries, antibiotic resistance, pest management and evolution in human dominated landscapes - in recognizing the need for evolutionarily informed management strategies. The speed of evolution matters. Here, we employ game-theoretic modeling to compare time to progression with continuous maximum tolerable dose to that of adaptive therapy where treatment is discontinued when the population of cancer cells gets below half of its initial size and re-administered when the cancer cells recover, forming cycles with and without treatment. We show that the success of adaptive therapy relative to continuous maximum tolerable dose therapy is much higher if the population of cancer cells is defined by two cell types (sensitive vs. resistant in a polymorphic population). Additionally, the relative increase in time to progression increases with the speed of evolution. These results hold with and without a cost of resistance in cancer cells. On the other hand, treatment-induced resistance can be modeled as a quantitative trait in a monomorphic population of cancer cells. In that case, when evolution is rapid, there is no advantage to adaptive therapy. Initial responses to therapy are blunted by the cancer cells evolving too quickly. Our study emphasizes how cancer provides a unique system for studying rapid evolutionary changes within tumor ecosystems in response to human interventions; and allows us to contrast and compare this system to other human managed or dominated systems in nature.