Search

Cerebrovascular diseases (CVDs) remain a leading cause of global disability and mortality. Digital Subtraction Angiography (DSA) sequences, recognized as the golden standard for diagnosing CVDs, can clearly visualize the dynamic flow and reveal pathological conditions within the cerebrovasculature. Therefore, precise segmentation of cerebral arteries (CAs) and classification between their main trunks and branches are crucial for physicians to accurately quantify diseases. However, achieving accurate CA segmentation in DSA sequences remains a challenging task due to small vessels with low contrast, and ambiguity between vessels and residual skull structures. Moreover, the lack of publicly available datasets limits exploration in the field. In this paper, we introduce a DSA Sequence-based Cerebral Artery segmentation dataset (DSCA), the first publicly accessible dataset designed specifically for pixel-level semantic segmentation of CAs. Additionally, we propose DSANet, a spatio-temporal network for CA segmentation in DSA sequences. Unlike existing DSA segmentation methods that focus only on a single frame, the proposed DSANet introduces a separate temporal encoding branch to capture dynamic vessel details across multiple frames. To enhance small vessel segmentation and improve vessel connectivity, we design a novel TemporalFormer module to capture global context and correlations among sequential frames. Furthermore, we develop a Spatio-Temporal Fusion (STF) module to effectively integrate spatial and temporal features from the encoder. Extensive experiments demonstrate that DSANet outperforms other state-of-the-art methods in CA segmentation, achieving a Dice of 0.9033.

Trans-endothelial electrical resistance (TEER) is one of the most widely used indicators to quantify the barrier integrity of endothelial layers. Over the last decade, the integration of TEER sensors into organ-on-a-chip (OOC) platforms has gained increasing interest for its efficient and effective measurement of TEER in OOCs. To date, microfabricated electrodes or direct insertion of wires has been used to integrate TEER sensors into OOCs, with each method having advantages and disadvantages. In this study, we developed a TEER-SPE chip consisting of carbon-based screen-printed electrodes (SPEs) embedded in a poly(methyl methacrylate) (PMMA)-based multi-layered microfluidic device with a porous poly(ethylene terephthalate) membrane in-between. As proof of concept, we demonstrated the successful cultures of hCMEC/D3 cells and the formation of confluent monolayers in the TEER-SPE chip and obtained TEER measurements for 4 days. Additionally, the TEER-SPE chip could detect changes in the barrier integrity due to shear stress or an inflammatory cytokine (i.e., tumor necrosis factor-& alpha;). The novel approach enables a low-cost and facile fabrication of carbon-based SPEs on PMMA substrates and the subsequent assembly of PMMA layers for rapid prototyping. Being cost-effective and cleanroom-free, our method lowers the existing logistical and technical barriers presenting itself as another step forward to the broader adoption of OOCs with TEER measurement capability., QC 20231009

Chen Z, Mou L, Pan Y, Feng C, Zhang J, Li J. Onco Targets Ther. 2019;12:8125–8138. The Editor and Publisher of OncoTargets and Therapy wish to retract the published article. Concerns were raised following the authors request to make corrections to images in Supplemental Figures 3, 4 and 5. Our investigation found that images within these figures appeared to have duplicated and further image duplication was found within Figures 3 and 4 from the main body of the article. Specifically, Figure 3B, U-251MG, None, appears to have been duplicated with the same image in Figure 3C, U-87MG, sh-CXCL8#1, which has been rotated. Figure 4A, U-251MG, LV-Vector, N-cadherin, appears to have been duplicated with regions from the image used in Figure 4A, U-251MG, LV-Vector, Vimentin. Figure 4A, U-87MG, CXCL8-shRNA, DAPI/CXCL8, appears to have been duplicated with regions from the image used in Figure 4A, U-251MG, LV-Vector, Vimentin. Figure S3C, U-87MG, None, appears to have been duplicated with the same image in Figure S3D, U-251MG, Vector. Figure S3C, U-87MG, CXCL8(KD), appears to have been duplicated with the same image in Figure S4D, U-251MG, Vector. Figure S4E, U-87MG, None, appears to have been duplicated with the same image in Figure S4E, U-87MG, Vector. The authors cooperated with the investigation and provided data associated with the study. However, despite the authors’ assistance, it was still not clear how the images came to be duplicated, and, as we cannot verify the validity of the published work, we are therefore retracting the article and the authors were notified of this. We have been informed in our decision-making by our policy on publishing ethics and integrity and the COPE guidelines on retractions. The retracted article will remain online to maintain the scholarly record, but it will be digitally watermarked on each page as “Retracted”.

Automated detection of curvilinear structures, e.g., blood vessels or nerve fibres, from medical and biomedical images is a crucial early step in automatic image interpretation associated to the management of many diseases. Precise measurement of the morphological changes of these curvilinear organ structures informs clinicians for understanding the mechanism, diagnosis, and treatment of e.g. cardiovascular, kidney, eye, lung, and neurological conditions. In this work, we propose a generic and unified convolution neural network for the segmentation of curvilinear structures and illustrate in several 2D/3D medical imaging modalities. We introduce a new curvilinear structure segmentation network (CS 2-Net), which includes a self-attention mechanism in the encoder and decoder to learn rich hierarchical representations of curvilinear structures. Two types of attention modules - spatial attention and channel attention - are utilized to enhance the inter-class discrimination and intra-class responsiveness, to further integrate local features with their global dependencies and normalization, adaptively. Furthermore, to facilitate the segmentation of curvilinear structures in medical images, we employ a 1×3 and a 3×1 convolutional kernel to capture boundary features. Besides, we extend the 2D attention mechanism to 3D to enhance the network's ability to aggregate depth information across different layers/slices. The proposed curvilinear structure segmentation network is thoroughly validated using both 2D and 3D images across six different imaging modalities. Experimental results across nine datasets show the proposed method generally outperforms other state-of-the-art algorithms in various metrics.

Automated detection of curvilinear structures, e.g., blood vessels or nerve fibres, from medical and biomedical images is a crucial early step in automatic image interpretation associated to the management of many diseases. Precise measurement of the morphological changes of these curvilinear organ structures informs clinicians for understanding the mechanism, diagnosis, and treatment of e.g. cardiovascular, kidney, eye, lung, and neurological conditions. In this work, we propose a generic and unified convolution neural network for the segmentation of curvilinear structures and illustrate in several 2D/3D medical imaging modalities. We introduce a new curvilinear structure segmentation network (CS 2-Net), which includes a self-attention mechanism in the encoder and decoder to learn rich hierarchical representations of curvilinear structures. Two types of attention modules - spatial attention and channel attention - are utilized to enhance the inter-class discrimination and intra-class responsiveness, to further integrate local features with their global dependencies and normalization, adaptively. Furthermore, to facilitate the segmentation of curvilinear structures in medical images, we employ a 1×3 and a 3×1 convolutional kernel to capture boundary features. Besides, we extend the 2D attention mechanism to 3D to enhance the network's ability to aggregate depth information across different layers/slices. The proposed curvilinear structure segmentation network is thoroughly validated using both 2D and 3D images across six different imaging modalities. Experimental results across nine datasets show the proposed method generally outperforms other state-of-the-art algorithms in various metrics.

Automated detection of curvilinear structures, e.g., blood vessels or nerve fibres, from medical and biomedical images is a crucial early step in automatic image interpretation associated to the management of many diseases. Precise measurement of the morphological changes of these curvilinear organ structures informs clinicians for understanding the mechanism, diagnosis, and treatment of e.g. cardiovascular, kidney, eye, lung, and neurological conditions. In this work, we propose a generic and unified convolution neural network for the segmentation of curvilinear structures and illustrate in several 2D/3D medical imaging modalities. We introduce a new curvilinear structure segmentation network (CS2-Net), which includes a self-attention mechanism in the encoder and decoder to learn rich hierarchical representations of curvilinear structures. Two types of attention modules - spatial attention and channel attention - are utilized to enhance the inter-class discrimination and intra-class responsiveness, to further integrate local features with their global dependencies and normalization, adaptively. Furthermore, to facilitate the segmentation of curvilinear structures in medical images, we employ a 1x3 and a 3x1 convolutional kernel to capture boundary features. ...

The detection of retinal vessel is of great importance in the diagnosis and treatment of many ocular diseases. Many methods have been proposed for vessel detection. However, most of the algorithms neglect the connectivity of the vessels, which plays an important role in the diagnosis. In this paper, we propose a novel method for retinal vessel detection. The proposed method includes a dense dilated network to get an initial detection of the vessels and a probability regularized walk algorithm to address the fracture issue in the initial detection. The dense dilated network integrates newly proposed dense dilated feature extraction blocks into an encoder-decoder structure to extract and accumulate features at different scales. A multiscale Dice loss function is adopted to train the network. To improve the connectivity of the segmented vessels, we also introduce a probability regularized walk algorithm to connect the broken vessels. The proposed method has been applied on three public data sets: DRIVE, STARE and CHASE_DB1. The results show that the proposed method outperforms the state-of-the-art methods in accuracy, sensitivity, specificity and also are under receiver operating characteristic curve.

The optic disc segmentation is an important step for retinal image-based disease diagnosis such as glaucoma. The inner limiting membrane (ILM) is the first boundary in the OCT, which can help to extract the retinal pigment epithelium (RPE) through gradient edge information to locate the boundary of the optic disc. Thus, the ILM layer segmentation is of great importance for optic disc localization. In this paper, we build a new optic disc centered dataset from 20 volunteers and manually annotated the ILM boundary in each OCT scan as ground-truth. We also propose a channel attention based context encoder network modified from the CE-Net to segment the optic disc. It mainly contains three phases: the encoder module, the channel attention based context encoder module, and the decoder module. Finally, we demonstrate that our proposed method achieves state-of-the-art disc segmentation performance on our dataset mentioned above., Comment: This paper has been accepted by the miccai workshop (OMIA-6)

This paper has been retracted. Chen Z, Mou L, Pan Y, Feng C, Zhang J, Li J. Onco Targets Ther. 2019;12:8125–8138. The Editor and Publisher of OncoTargets and Therapy wish to retract the published article. Concerns were raised following the authors request to make corrections to images in Supplemental Figures 3, 4 and 5. Our investigation found that images within these figures appeared to have duplicated and further image duplication was found within Figures 3 and 4 from the main body of the article. Specifically, Figure 3B, U-251MG, None, appears to have been duplicated with the same image in Figure 3C, U-87MG, sh-CXCL8#1, which has been rotated. Figure 4A, U-251MG, LV-Vector, N-cadherin, appears to have been duplicated with regions from the image used in Figure 4A, U-251MG, LV-Vector, Vimentin. Figure 4A, U-87MG, CXCL8-shRNA, DAPI/CXCL8, appears to have been duplicated with regions from the image used in Figure 4A, U-251MG, LV-Vector, Vimentin. Figure S3C, U-87MG, None, appears to have been duplicated with the same image in Figure S3D, U-251MG, Vector. Figure S3C, U-87MG, CXCL8(KD), appears to have been duplicated with the same image in Figure S4D, U-251MG, Vector. Figure S4E, U-87MG, None, appears to have been duplicated with the same image in Figure S4E, U-87MG, Vector. The authors cooperated with the investigation and provided data associated with the study. However, despite the authors’ assistance, it was still not clear how the images came to be duplicated, and, as we cannot verify the validity of the published work, we are therefore retracting the article and the authors were notified of this. We have been informed in our decision-making by our policy on publishing ethics and integrity and the COPE guidelines on retractions. The retracted article will remain online to maintain the scholarly record, but it will be digitally watermarked on each page as “Retracted”.

Monitor inlining is a program rewriting technique to enforce security policy to an untrusted program. The program is modified so that the code for monitoring and policy enforcement is inserted into appropriate points. The embedded code will monitor the action of the program and alter its behavior in case of policy violation (security), otherwise interfere with it as little as possible (conservativity and transparency). For sequential and multi threaded Java-like programs, inlining algorithms have been proposed, but for languages with different concurrency model, the problem remains to be solved. This master thesis is done in the context of the HATS (Highly Adaptable and Trustworthy Software) project. A framework for ConSpec policy enforcement for the Abstract Behavioral Specification (ABS) language is devised. ABS language is the central contribution of the HATS project, its concurrency model is based on Concurrent Object Groups, Asynchronous Method Calls and Futures. In the framework, an adapted version of ConSpec is used and implemented. The inliner is implemented in Java and is applied to the HATS case study trading system, and its correctness properties are discussed.

Monitor inlining is a program rewriting technique to enforce security policy to an untrusted program. The program is modified so that the code for monitoring and policy enforcement is inserted into appropriate points. The embedded code will monitor the action of the program and alter its behavior in case of policy violation (security), otherwise interfere with it as little as possible (conservativity and transparency). For sequential and multi threaded Java-like programs, inlining algorithms have been proposed, but for languages with different concurrency model, the problem remains to be solved. This master thesis is done in the context of the HATS (Highly Adaptable and Trustworthy Software) project. A framework for ConSpec policy enforcement for the Abstract Behavioral Specification (ABS) language is devised. ABS language is the central contribution of the HATS project, its concurrency model is based on Concurrent Object Groups, Asynchronous Method Calls and Futures. In the framework, an adapted version of ConSpec is used and implemented. The inliner is implemented in Java and is applied to the HATS case study trading system, and its correctness properties are discussed.