861 research outputs found
Development of Diabetic Foot Ulcer Datasets : An Overview
No full textThis paper provides conceptual foundation and procedures used in the development of diabetic foot ulcer datasets over the past decade, with a timeline to demonstrate progress. We conduct a survey on data capturing methods for foot photographs, an overview of research in developing private and public datasets, the related computer vision tasks (detection, segmentation and classification), the diabetic foot ulcer challenges and the future direction of the development of the datasets. We report the distribution of dataset users by country and year. Our aim is to share the technical challenges that we encountered together with good practices in dataset development, and provide motivation for other researchers to participate in data sharing in this domain
Diabetic Foot Ulcer Grand Challenge 2022 Summary
No full textThe Diabetic Foot Ulcer Challenge 2022 focused on the task of diabetic foot ulcer segmentation, based on the work completed in previous DFU challenges. The challenge provided 4000 images of full-view foot ulcer images together with corresponding delineation of ulcer regions. This paper provides an overview of the challenge, a summary of the methods proposed by the challenge participants, the results obtained from each technique, and a comparison of the challenge results. The best-performing network was a modified HarDNet-MSEG, with a Dice score of 0.7287
Quantifying the Effect of Image Similarity on Diabetic Foot Ulcer Classification
No full textThis research conducts an investigation on the effect of visually similar images within a publicly available diabetic foot ulcer dataset when training deep learning classification networks. The presence of binary-identical duplicate images in datasets used to train deep learning algorithms is a well known issue that can introduce unwanted bias which can degrade network performance. However, the effect of visually similar non-identical images is an under-researched topic, and has so far not been investigated in any diabetic foot ulcer studies. We use an open-source fuzzy algorithm to identify groups of increasingly similar images in the Diabetic Foot Ulcers Challenge 2021 (DFUC2021) training dataset. Based on each similarity threshold, we create new training sets that we use to train a range of deep learning multi-class classifiers. We then evaluate the performance of the best performing model on the DFUC2021 test set. Our findings show that the model trained on the training set with the 80% similarity threshold images removed achieved the best performance using the InceptionResNetV2 network. This model showed improvements in F1-score, precision, and recall of 0.023, 0.029, and 0.013, respectively. These results indicate that highly similar images can contribute towards the presence of performance degrading bias within the Diabetic Foot Ulcers Challenge 2021 dataset, and that the removal of images that are 80% similar from the training set can help to boost classification performance
HCMV infection increases YAP at the transcriptional level to regulate STING gene expression.
No full textqPCR analysis of (A) YAP and (B) STING gene expression was performed using HFF cells infected with HCMV at an MOI of 0.5 and harvested at the indicated hpi. (C) Western blot analysis of YAP and STING proteins using HFF cells infected with HCMV at an MOI of 0.5. (D, E) Quantification of YAP and STING band intensities, respectively, in (C). (F) YAP shRNA-expressing HFF cells infected with HCMV at an MOI of 0.5 were collected for qPCR analysis of STING. n = 3 biological replicates for each experiment. Error bars represent SEM. One-way ANOVA with Turkey’s multiple comparisons test was used to determine statistical significance. *P P < 0.001.</p
AAU-Net: An Adaptive Attention U-Net for Breast Lesions Segmentation in Ultrasound Images
No full textVarious deep learning methods have been proposed to segment breast lesions from ultrasound images. However, similar intensity distributions, variable tumor morphologies and blurred boundaries present challenges for breast lesions segmentation, especially for malignant tumors with irregular shapes. Considering the complexity of ultrasound images, we develop an adaptive attention U-net (AAU-net) to segment breast lesions automatically and stably from ultrasound images. Specifically, we introduce a hybrid adaptive attention module (HAAM), which mainly consists of a channel self-attention block and a spatial self-attention block, to replace the traditional convolution operation. Compared with the conventional convolution operation, the design of the hybrid adaptive attention module can help us capture more features under different receptive fields. Different from existing attention mechanisms, the HAAM module can guide the network to adaptively select more robust representation in channel and space dimensions to cope with more complex breast lesions segmentation. Extensive experiments with several state-of-the-art deep learning segmentation methods on three public breast ultrasound datasets show that our method has better performance on breast lesions segmentation. Furthermore, robustness analysis and external experiments demonstrate that our proposed AAU-net has better generalization performance in the breast lesion segmentation. Moreover, the HAAM module can be flexibly applied to existing network frameworks. The source code is available on https://github.com/CGPxy/AAU-net
HCMV replication is inhibited by YAP expression.
No full text(A) Schematic representation of the retroviral vector used in this study. A retroviral vector which bicistronically expresses YAP and GFP using an internal ribosome entry site (IRES) was used to transduce HFF cells. As a negative control, retroviral vectors containing only the GFP gene were used. Therefore, GFP was used as a marker for transgene expression throughout the study. LTR, long terminal repeat; MCS, multicloning site. (B) HCMV progeny virus titration assay. 24 h prior to HCMV infection, HFF cells were transduced with a retroviral vector bicistronically expressing YAP and GFP. The cells were then infected with HCMV at an MOI of 0.1 or 0.5, and progeny viruses were harvested at 72, 96, and 120 hpi. Before infection for viral titration, all the MOI 0.5 samples were diluted to 1:10. Titration of progeny viruses collected from control- or YAP-transduced HFF cells infected with HCMV at an MOI of (C) 0.1 and (E) 0.5 at the indicated time points by anti-IE1 immunostaining (red). Cells were counterstained with DAPI to visualize nuclei (blue). (G) Western blot analysis for YAP proteins in HFF cells transduced with a dominant negative form of LATS1/2 (dnLATS1/2) together with or without shRNA specific to YAP (shYAP). (I) HFF cells were transduced with dnLATS1/2 and/or shYAP and then infected with HCMV at an MOI of 0.5. Progeny viruses were titered by IE1 immunostaining after HFF cell infection (red). (D, F, H, J) Quantification of (C, E, G, I), respectively. For (D, F, J), numbers of IE1+ cells in each control were set to 1. Scale bars, 100 μm. n = 3 biological replicates for each experiment. Error bars represent SEM. Student’s t-test (for D, F), one-way ANOVA with Turkey’s multiple comparison test (for H, J) was used to determine statistical significance. *P P P < 0.001.</p
HCMV immediate-early gene expression was reduced by YAP expression.
No full text(A) qPCR analysis for representative immediate-early (IE1), early (UL44 and UL83) and late (UL99 and UL108) viral gene expression using YAP-transduced HFF cells infected with HCMV at an MOI of 0.5 and harvested at the indicated hpi. Each mRNA level was normalized to β-actin mRNA. (B) Western blot for HCMV IE1, pp52 and pp28 proteins using YAP-expressing HFF cells infected with HCMV at MOI of 0.5 and harvested at the indicated hpi. (C) Quantification of (B). Error bars represent SEM. n = 3 biological replicates for each experiment. Two-way ANOVA with Sidak’s multiple comparisons test was used to determine statistical significance. *P P P < 0.001.</p
Computational modelling unveils how epiblast remodelling and positioning rely on trophectoderm morphogenesis during mouse implantation
No full textUnderstanding the processes by which the mammalian embryo implants in the maternal uterus is a long-standing challenge in embryology. New insights into this morphogenetic event could be of great importance in helping, for example, to reduce human infertility. During implantation the blastocyst, composed of epiblast, trophectoderm and primitive endoderm, undergoes significant remodelling from an oval ball to an egg cylinder. A main feature of this transformation is symmetry breaking and reshaping of the epiblast into a "cup". Based on previous studies, we hypothesise that this event is the result of mechanical constraints originating from the trophectoderm, which is also significantly transformed during this process. In order to investigate this hypothesis we propose MG# (MechanoGenetic Sharp), an original computational model of biomechanics able to reproduce key cell shape changes and tissue level behaviours in silico. With this model, we simulate epiblast and trophectoderm morphogenesis during implantation. First, our results uphold experimental findings that repulsion at the apical surface of the epiblast is essential to drive lumenogenesis. Then, we provide new theoretical evidence that trophectoderm morphogenesis indeed can dictate the cup shape of the epiblast and fosters its movement towards the uterine tissue. Our results offer novel mechanical insights into mouse peri-implantation and highlight the usefulness of agent-based modelling methods in the study of embryogenesis
MAPK-Mediated YAP Activation Controls Mechanical-Tension-Induced Pulmonary Alveolar Regeneration
No full textSummaryThe pulmonary alveolar epithelium undergoes extensive regeneration in response to lung injuries, including lung resection. In recent years, our understanding of cell lineage relationships in the pulmonary alveolar epithelium has improved significantly. However, the molecular and cellular mechanisms that regulate pneumonectomy (PNX)-induced alveolar regeneration remain largely unknown. In this study, we demonstrate that mechanical-tension-induced YAP activation in alveolar stem cells plays a major role in promoting post-PNX alveolar regeneration. Our results indicate that JNK and p38 MAPK signaling is critical for mediating actin-cytoskeleton-remodeling-induced nuclear YAP expression in alveolar stem cells. Moreover, we show that Cdc42-controlled actin remodeling is required for the activation of JNK, p38, and YAP in post-PNX lungs. Our findings together establish that the Cdc42/F-actin/MAPK/YAP signaling cascade is essential for promoting alveolar regeneration in response to mechanical tension in the lung
YAP inhibition of HCMV progeny virus production is transcriptional activity-dependent.
No full text(A) Schematic representation of wild-type and mutant YAP genes used in this study. (B) HFF cells were transduced with a retroviral vector expressing YAP genes and harvested for an XTT assay 4 and 24 h after the cell confluence reached 100%. Titration of progeny viruses harvested at 120 hpi from (C) YAP ΔPDZ or YAP S94A-transduced cells, and (E) YAP WW domain mutant-transduced cells infected with HCMV at an MOI of 0.5. (F) qPCR analysis of CTGF gene expression using dnLATS1/2 and TEAD shRNA (shTEAD)-transduced HFF cells at 2 days post-transduction. (G) HFF cells were transduced with dnLATS1/2 together with or without shTEAD-expressing retroviral vectors, and then infected with HCMV at an MOI of 0.5. Progeny viruses were titered by IE1 immunostaining after HFF cell infection (red). (I) Effects of TAZ expression on HCMV progeny virus production. TAZ-transduced HFF cells were infected with HCMV, and progeny viruses were harvested at 72, 96, and 120 hpi. Titration of progeny viruses was performed by anti-IE1 immunostaining (red). Cells were counterstained with DAPI to visualize nuclei (blue). (D, H, J) Quantification of (C, G, I), respectively. Scale bars, 100 μm. n = 3 biological replicates for each experiment except for (B, n = 5 biological replicates). Error bars represent SEM. One-way ANOVA with Turkey’s multiple comparison (for D, F, H), and Student’s t-test (for J) were used to determine statistical significance. *P P P < 0.001.</p
- …
