28 December 2020 in Advanced Electronic Materials
In this study, a novel, fully polymeric setup for piezoresistive sensing is prepared and tested. Monolayers of polystyrene (PS) nanospheres are assembled on flexible polyethylene naphthalate substrates. Subsequently, thin layers (≈50–100 nm) of poly(3,4‐ethylenedioxythiophene) (PEDOT) are deposited conformally around the spheres by oxidative chemical vapor deposition (oCVD). Voltage−current characteristics and direct resistance measurements are performed to test the electrical properties of the samples in their unstrained state and their piezoresistive response during bending. Substrate deposition temperature (Tsub) and film thickness (tPEDOT) are used as parameters to alter properties of the PEDOT thin films; increased Tsub and tPEDOT lead to samples exhibiting lower intrinsic resistance. The electrical conductivity of the samples is estimated to range as high as tens of S cm−1. Dopant exchange of the oCVD‐PEDOT layer (intrinsically, chlorine‐doped) is performed by putting the samples in 0.5 m sulfuric acid, which decreases their resistance by ≈1/3. Regarding the piezoresistive properties of the devices, acid treatment, higher Tsub and tPEDOT (thus, lower intrinsic resistance) yield samples with increased response. As a result, gauge factors as high as 11.4 are achieved. Due to their flexibility and low‐cost, the proposed structures can be readily employed as skin‐inspired or wearable electronic devices.
28 March 2026 in Artificial Intelligence in Medicine
State-of-the-art radiotherapy machines with integrated magnetic resonance (MR) imaging, known as MR-Linacs, provide the capability to track tumors in real time. This capability aids delivery of precise irradiation in the presence of patient motion, such as breathing, by adjusting the radiation beam. However, current solutions rely solely on geometric tracking without closing the loop by considering the actual endpoint-the delivered radiation (here called dose). Real-time dose-based adaptation within a single session remains highly challenging due to the immense dimensionality of the problem. To overcome this, we have developed a radiotherapy simulator and propose a novel reinforcement learning (RL)-based approach for real-time adaptive radiotherapy using 2D fluence, as a surrogate to 3D dose. To our knowledge, this is the first application of RL in real-time adaptive radiotherapy. Our in-silico experiments showed the feasibility of using RL to close the feedback loop, dynamically adapting to patient motion and minimizing discrepancies between delivered and intended dose in clinical cases. Our approach introduces a new treatment delivery paradigm, enabling delivery based on a reference fluence and motion without predefined machine settings.