Optical polarimetry has previously imaged the spatial extent of a typical radiofrequency ablated (RFA) lesion in myocardial tissue, exhibiting significantly lower total depolarization at the necrotic core compared to healthy tissue, and intermediate values at the RFA rim region. Here, total depolarization in ablated myocardium was used to segment the total depolarization image into three (core, rim and healthy) zones. A local fuzzy thresholding algorithm was used for this multi-region segmentation, and then compared with a ground truth segmentation obtained from manual demarcation of RFA core and rim regions on the histopathology image. Quantitative comparison of the algorithm segmentation results was performed with evaluation metrics such as dice similarity coefficient (DSC = 0.78 ± 0.02 and 0.80 ± 0.02), sensitivity (S_n = 0.83 ± 0.10 and 0.91 ± 0.08), specificity (S_p = 0.76 ± 0.17 and 0.72 ± 0.17) and accuracy (Acc = 0.81 ± 0.09 and 0.71 ± 0.10) for RFA core and rim regions, respectively. This automatic segmentation of parametric depolarization images suggests a novel application of optical polarimetry, namely its use in objective RFA image quantification.

Natural scene classification, which has potential applications in precision agriculture, environmental monitoring, and disaster management, poses significant challenges due to variations in the spatial resolution, spectral resolution, texture, and size of remotely sensed images of natural scenes on Earth. For such challenging problems, deep-learning-based algorithms have demonstrated amazing performances in recent years. Among these methodologies, transfer learning is a useful technique which employs the learned features already extracted from the pre-trained models from large-scale datasets for the problem at hand, resulting in quicker and more accurate models. In this study, we deployed cross-domain transfer learning for the land-cover classification of remotely sensed images of natural scenes. We conducted extensive experiments to measure the performance of the proposed method and explored the factors that affect the performance of the models. Our findings suggest that fine-tuning the ResNet-50 model outperforms various other models in terms of the classification accuracy. The experimental results showed that the deployed cross-domain transfer-learning system achieved outstanding (99.5% and 99.1%) accurate performances compared to previous benchmarks on the NaSC-TG2 dataset with the final tuning of the whole structure and only the last three layers, respectively.