Ischemic stroke lesion segmentation in Computed Tomography Perfusion (CTP) images is crucial for the quantitative diagnosis of stroke. However, it remains a challenging problem due to the poor image quality of CTP and the complex appearance of the lesions. In this study, we develop a U-shape transformer network with an adaptive scale for ischemic stroke lesion segmentation in CTP images. The state-of-the-art nnU-Net structure is used as the backbone, and a transformer block with self-adapting scale is introduced. The proposed network adopts the advantage of transformer in capturing global information and retains the advantage of convolutional neural network (CNN) in extracting local correlation features. In order to obtain better adaptation of transformer block to ischemic stroke segmentation task, we propose a self-adapting scale selection strategy that offer better patch size and window size to assist the transformer block capture more global information and avoid semantic information being corrupted. Five-fold cross-validation was used in training of the networks, and nnUNet was used as a baseline model in the performance evaluation. The results showed that after involving the proposed method, the mean DICE of the segmentation improved from 0.72 to 0.78 in the ISLES public dataset. For the independent test set, the proposed method achieved a mean DICE of 0.48, a mean precision of 0.60, and a mean recall of 0.46, compared to 0.46, 0.57 and 0.43 by the baseline model. The proposed framework has the potential for improving diagnosis and treatment of ischemic stroke in CTP.
Droplet-based microfluidics has been demonstrated to offer the advantage of high precision control, high throughput, and material savings. Traditional fabrication methods of droplet generation involve soft lithography, molding, etching, and embossing process, relying on expensive equipment, tedious operations, and even requiring a cleanroom fabrication environment. Recently, 3D printing with the characteristics of low cost, easy reprinting, and well-achieved microstructure in three dimensions has been suggested as a promising technology to improve the fabrication of microfluidics. In this study, we combined 3D printing technology and microfluidics to design a microfluidic device that enables the continuous generation of droplets, which can be utilized to encapsulate single particles and cells. The digital model of the microfluidic device was designed and edited by software, and then uploaded to a stereolithography 3D printer with a resolution of 10 μm for printing. To verify the feasibility of the device to generate droplets, the mineral oil and water were used as the continuous phase and the dispersed phase, respectively. The diameters of droplets ranging from about 70 μm to 240 μm and the product rate about 1500/min can be achieved. The result of encapsulation probability of microspheres is around 55% with that of the single-microspheres about 30%, which verifies the ability of droplet device for encapsulating single particles. The droplet microfluidics is applied for cell imaging to monitor the cell viability for a long time. The result presents the viability changes from the living state to death of MDA-MB-231 breast cancer cells.
In this manuscript, we aim to develop the dynamic light scattering imaging (DLSI) method to investigate the difference between triple negative breast cancer (TNBC) and human epidermal growth factor receptor-2 (HER-2) positive breast cancer. The experimental device with the capability to obtain time-series light scattering images was well designed and built. The breast cancer cell lines of MDA-MB-231 and HER-2 enriched SKBR3 were prepared and used for experiments. The autocorrelation functions of the light intensity fluctuation were calculated to characterize both types of breast cancer cells. The dynamic light scattering images were further analyzed to establish a DLSI-based approach for automatic classification of the two types of cells. The results show that the proposed DLSI-based model achieved better classification performance compared to the conventional static light scattering-based model.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.