Optical-resolution photoacoustic microscopy (OR-PAM) has been shown to be an excellent tool for high-resolution imaging of microvasculature, and quantitative analysis of the microvasculature can provide valuable information for the early diagnosis and treatment of various vascular-related diseases. In order to address the characteristics of weak signals, discontinuity and small diameters in photoacoustic microvascular images, we propose a method adaptive to the microvascular segmentation in photoacoustic images, including Hessian matrix enhancement and the morphological connection operators. The accuracy of our vascular segmentation method is quantitatively evaluated by the multiple criteria. To obtain more precise and continuous microvascular skeletons, an improved skeleton extraction framework based on the multistencil fast marching (MSFM) method is developed. We carried out in vivo OR-PAM microvascular imaging in mouse ears and subcutaneous hepatoma tumor model to verify the correctness and superiority of our proposed method. Compared with the previous methods, our proposed method can extract the microvascular network more completely, continuously and accurately, and provide an effective solution for the quantitative analysis of photoacoustic microvascular images with many small branches.
Optical coherence tomography (OCT) is an imaging modality that acquires high‐resolution cross‐sectional images of living tissues and it has become the standard in ophthalmological diagnoses. However, most quantitative morphological measurements are based on the raw OCT images which are distorted by several mechanisms such as the refraction of probe light in the sample and the scan geometries and thus the analysis of the raw OCT images inevitably induced calculation errors. In this paper, based on Fermat's principle and the concept of inverse light tracing, image distortions due to refraction occurred at tissue boundaries in the whole‐eye OCT imaging of mouse by telecentric scanning were corrected. Specially, the mathematical correction models were deducted for each interface, and the high‐precision whole‐eye image was recovered segment by segment. We conducted phantom and in vivo experiments on mouse and human eyes to verify the distortion correction algorithm, and several parameters of the radius of curvature, thickness of tissues and error, were calculated to quantitatively evaluate the images. Experimental results demonstrated that the method can provide accurate and reliable measurements of whole‐eye parameters and thus be a valuable tool for the research and clinical diagnosis.
Optical coherence tomography (OCT) angiography has drawn much attention in the medical imaging field. Binarization plays an important role in quantitative analysis of eye with optical coherence tomography. To address the problem of few training samples and contrast-limited scene, we proposed a new binarization framework with specific-patch SVM (SPSVM) for low-intensity OCT image, which is open and classification-based framework. This new framework contains two phases: training model and binarization threshold. In the training phase, firstly, the patches of target and background from few training samples are extracted as the ROI and the back-ground, respectively. Then, PCA is conducted on all patches to reduce the dimension and learn the eigenvector subspace. Finally, the classification model is trained from the features of patches to get the target value of different patches. In the testing phase, the learned eigenvector subspace is conducted on the pixels of each patch. The binarization threshold of patch is obtained with the learned SVM model. We acquire a new OCT mice eye (OCT-ME) database, which is publicly available at https://mip2019.github.io/spsvm. Extensive experiments were performed to demonstrate the effectiveness of the proposed SPSVM framework.
Remote surveillance is an effective method in restraining the spread of infectious diseases via monitoring crowds in affected areas. However, the monitoring targets in existing works are crowds, leading to high system cost, and most of them focus on finding close contacts, less considering the privacy protection and suspected treatment issues. To conquer above problems, this paper develops a new remote surveillance system for infectious diseases, which contains the following major contributions: (1) the monitoring targets are the ordinary contacts not all crowds, effectively decreasing the system cost; (2) establish the joint-control mechanism among contacts, health center, and the hospital to facilitate the prediagnosis and in-time treatment for suspected patients; (3) to avoid the privacy leakage of contacts, a double encryption strategy is designed to protect the location information, and a separating database-storage mechanism is used to improve the contact’s data security on the whole. Theoretical security analysis showed that the proposed system and privacy protection methods can effectively fight transmission attacks and avoid privacy leakage during data usage. Based on the created COVID-19 dataset, the simulation experiments were carried out to evaluate the effectiveness and feasibility of the proposed system, on the metrics of the accuracy of prediagnosis, encryption, and decryption time for health and location data. In summary, this work provides a promising way of low-cost remote surveillance system without privacy leakage to control the spreading of infectious disease.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.