We start from a realistic half space then use to develop a mathematical asymptotic model for thermal imaging, which we analysis well suited for the design of reconstruction algorithms. We seek to reconstruct thermal a...We start from a realistic half space then use to develop a mathematical asymptotic model for thermal imaging, which we analysis well suited for the design of reconstruction algorithms. We seek to reconstruct thermal anomalies only through their rough features. With this way our proposed algorithms are stable against measurement noise and geometry perturbations. Based on rigorous asymptotic estimates, we first obtain an approximation for the temperature profile which we then use to design noniterative detection algorithms. We show on numerical simulations evidence that they are accurate and robust. Moreover, we provide a mathematical model for ultrasonic temperature imaging, which is an important technique in cancerous tissue ablation therapy.展开更多
基金supported by the ANR project EchoScan(AN-06-Blan-0089)the NSF grant DMS 0707421.
文摘We start from a realistic half space then use to develop a mathematical asymptotic model for thermal imaging, which we analysis well suited for the design of reconstruction algorithms. We seek to reconstruct thermal anomalies only through their rough features. With this way our proposed algorithms are stable against measurement noise and geometry perturbations. Based on rigorous asymptotic estimates, we first obtain an approximation for the temperature profile which we then use to design noniterative detection algorithms. We show on numerical simulations evidence that they are accurate and robust. Moreover, we provide a mathematical model for ultrasonic temperature imaging, which is an important technique in cancerous tissue ablation therapy.
