Loss Of Contour Research Articles

HSMix: Hard and soft mixing data augmentation for medical image segmentation

Due to the high cost of annotation or the rarity of some diseases, medical image segmentation is often limited by data scarcity and the resulting overfitting problem. Self-supervised learning and semi-supervised learning can mitigate the data scarcity challenge to some extent. However, both of these paradigms are complex and require either hand-crafted pretexts or well-defined pseudo-labels. In contrast, data augmentation represents a relatively simple and straightforward approach to addressing data scarcity issues. It has led to significant improvements in image recognition tasks. However, the effectiveness of local image editing augmentation techniques in the context of segmentation has been less explored. Additionally, traditional data augmentation methods for local image editing augmentation methods generally utilize square regions, which cause a loss of contour information.We propose HSMix, a novel approach to local image editing data augmentation involving hard and soft mixing for medical semantic segmentation. In our approach, a hard-augmented image is created by combining homogeneous regions (superpixels) from two source images. A soft mixing method further adjusts the brightness of these composed regions with brightness mixing based on locally aggregated pixel-wise saliency coefficients. The ground-truth segmentation masks of the two source images undergo the same mixing operations to generate the associated masks for the augmented images.Our method fully exploits both the prior contour and saliency information, thus preserving local semantic information in the augmented images while enriching the augmentation space with more diversity. Our method is a plug-and-play solution that is model agnostic and applicable to a range of medical imaging modalities. Extensive experimental evidence has demonstrated its effectiveness in a variety of medical segmentation tasks. The source code is available in https://github.com/DanielaPlusPlus/HSMix.

GCN-Enhanced Spatial-Spectral Dual-Encoder Network for Simultaneous Segmentation of Retinal Layers and Fluid in OCT Images

Changes in retinal thickness and the morphology of fluid provide valuable diagnostic information for Macular Edema (ME). Optical Coherence Tomography (OCT) is a pivotal diagnostic tool for ME, and the accurate segmentation of OCT retinal images aids ophthalmologists in monitoring disease progression. However, the unpredictable nature of ME’s occurrence poses significant challenges for existing methods in achieving precise segmentation of both retinal layers and fluids simultaneously. In this study, a novel U-shaped encoder-decoder architecture named GD-Net, is introduced for simultaneously segmenting retinal layers of diverse thicknesses and fluids. Specifically, a novel Fast Fourier Encoder is integrated within the encoder branch to capture spectral domain features overlooked by the spatial encoder. Additionally, Multi-scale Graph Convolution module is inserted between the encoder and decoder branches to leverage retinal layer topology for spatial reasoning. GD-Net is further optimized using a joint loss function, which includes a weighted version of region segmentation loss and contour loss, effectively mitigating the issues of blurred fluid edges and internal holes. The method was validated on three publicly available datasets: DUKE DME, Peripapillary OCT, and RETOUCH, achieving overall mean Dice score of 0.839, 0.826, and 0.872, respectively, outperforming the other state-of-the-art techniques. GD-Net demonstrated consistent high-precision segmentation on B-scans from different devices, proving its robustness and surpassing other methods in terms of visual quality, thus offering substantial support for clinical ophthalmologists in diagnosing ME. The code and weights are publicly available at: https://github.com/DBook111/GD-Net.

Study on lung CT image segmentation algorithm based on threshold-gradient combination and improved convex hull method

Lung images often have the characteristics of strong noise, uneven grayscale distribution, and complex pathological structures, which makes lung image segmentation a challenging task. To solve this problems, this paper proposes an initial lung mask extraction algorithm that combines threshold and gradient. The gradient used in the algorithm is obtained by the time series feature extraction method based on differential memory (TFDM), which is obtained by the grayscale threshold and image grayscale features. At the same time, we also proposed a lung contour repair algorithm based on the improved convex hull method to solve the contour loss caused by solid nodules and other lesions. Experimental results show that on the COVID-19 CT segmentation dataset, the advanced lung segmentation algorithm proposed in this article achieves better segmentation results and greatly improves the consistency and accuracy of lung segmentation. Our method can obtain more lung information, resulting in ideal segmentation effects with improved accuracy and robustness.

Customizable, biocompatible implants for dorsal nasal augmentation: An in vivo pilot study of eight polylactic acid scaffold designs.

Augmentation of the nasal dorsum often requires implantation of structural material. Existing methods include autologous, cadaveric or alloplastic materials and injectable hydrogels. Each of these options is associated with considerable limitations. There is an ongoing need for precise and versatile implants that produce long-lasting craniofacial augmentation. Four separate polylactic acid (PLA) dorsal nasal implant designs were 3D-printed. Two implants had internal PLA rebar of differing porosities and two were designed as "shells" of differing porosities. Shell designs were implanted without infill or with either minced or zested processed decellularized ovine cartilage infill to serve as a "biologic rebar", yielding eight total treatment groups. Scaffolds were implanted heterotopically on rat dorsa (N = 4 implants per rat) for explant after 3, 6, and 12 months followed by volumetric, histopathologic, and biomechanical analysis. Low porosity implants with either minced cartilage or PLA rebar infill had superior volume retention across all timepoints. Overall, histopathologic and immunohistochemical analysis showed a resolving inflammatory response with an M1/M2 ratio consistently favoring tissue regeneration over the study course. However, xenograft cartilage showed areas of degradation and pro-inflammatory infiltrate contributing to volume and contour loss over time. Biomechanical analysis revealed all constructs had equilibrium and instantaneous moduli higher than human septal cartilage controls. Biocompatible, degradable polymer implants can induce healthy neotissue ingrowth resulting in guided soft tissue augmentation and offer a simple, customizable and clinically-translatable alternative to existing craniofacial soft tissue augmentation materials. PLA-only implants may be superior to combination PLA and xenograft implants due to contour irregularities associated with cartilage degradation.

Uncertainty estimation using a 3D probabilistic U-Net for segmentation with small radiotherapy clinical trial datasets

Background and objectivesBio-medical image segmentation models typically attempt to predict one segmentation that resembles a ground-truth structure as closely as possible. However, as medical images are not perfect representations of anatomy, obtaining this ground truth is not possible. A surrogate commonly used is to have multiple expert observers define the same structure for a dataset. When multiple observers define the same structure on the same image there can be significant differences depending on the structure, image quality/modality and the region being defined. It is often desirable to estimate this type of aleatoric uncertainty in a segmentation model to help understand the region in which the true structure is likely to be positioned. Furthermore, obtaining these datasets is resource intensive so training such models using limited data may be required. With a small dataset size, differing patient anatomy is likely not well represented causing epistemic uncertainty which should also be estimated so it can be determined for which cases the model is effective or not. MethodsWe use a 3D probabilistic U-Net to train a model from which several segmentations can be sampled to estimate the range of uncertainty seen between multiple observers. To ensure that regions where observers disagree most are emphasised in model training, we expand the Generalised Evidence Lower Bound (ELBO) with a Constrained Optimisation (GECO) loss function with an additional contour loss term to give attention to this region. Ensemble and Monte-Carlo dropout (MCDO) uncertainty quantification methods are used during inference to estimate model confidence on an unseen case. We apply our methodology to two radiotherapy clinical trial datasets, a gastric cancer trial (TOPGEAR, TROG 08.08) and a post-prostatectomy prostate cancer trial (RAVES, TROG 08.03). Each dataset contains only 10 cases each for model development to segment the clinical target volume (CTV) which was defined by multiple observers on each case. An additional 50 cases are available as a hold-out dataset for each trial which had only one observer define the CTV structure on each case. Up to 50 samples were generated using the probabilistic model for each case in the hold-out dataset. To assess performance, each manually defined structure was matched to the closest matching sampled segmentation based on commonly used metrics. ResultsThe TOPGEAR CTV model achieved a Dice Similarity Coefficient (DSC) and Surface DSC (sDSC) of 0.7 and 0.43 respectively with the RAVES model achieving 0.75 and 0.71 respectively. Segmentation quality across cases in the hold-out datasets was variable however both the ensemble and MCDO uncertainty estimation approaches were able to accurately estimate model confidence with a p-value < 0.001 for both TOPGEAR and RAVES when comparing the DSC using the Pearson correlation coefficient. ConclusionsWe demonstrated that training auto-segmentation models which can estimate aleatoric and epistemic uncertainty using limited datasets is possible. Having the model estimate prediction confidence is important to understand for which unseen cases a model is likely to be useful.

A Two-branch Edge Guided Lightweight Network for infrared image saliency detection

In the dynamic landscape of saliency detection, convolutional neural networks have emerged as catalysts for innovation, but remain largely tailored for RGB imagery, falling short in the context of infrared images, particularly in memory-restricted environments. These existing approaches tend to overlook the wealth of contour information vital for a nuanced analysis of infrared images. Addressing this notable gap, we introduce the novel Two-branch Edge Guided Lightweight Network (TBENet), designed explicitly for the robust analysis of infrared image saliency detection. The main contributions of this paper are as follows. First, we formulate the saliency detection task as two subtasks, contour enhancement and foreground segmentation. Therefore, the TBENet is divided into two specialized branches: a contour prediction branch for extracting target contour and a saliency map generation branch for separating the foreground from the background. The first branch employs an encoder–decoder architecture to meticulously delineate object contours, serving as a guiding blueprint for the second branch. This latter segment adeptly integrates spatial and semantic data, creating a precise saliency map that is refined further by an innovative edge-weighted contour loss function. Second, to enhance feature integration capabilities, we propose depthwise multi-scale and multi-cue modules, facilitating sophisticated feature aggregation. Third, a high-level linear bottleneck module is devised to ensure the extraction of rich semantic information, and by replacing the standard convolution with the depthwise convolution, it is beneficial to reduce model complexity. Additional, we reduce the number of channels of the feature maps from each stage of the decoder to further enhance the lightweight of the model. Last, we construct a novel infrared ship dataset Small-IRShip to train and evaluate our proposed model. Experimental results on the homemade dataset Small-IRShip and two publicly available datasets, namely RGB-T and IRSTD-1k, demonstrate TBENet’s superior performance over state-of-the-art methods, affirming its effectiveness in harnessing edge information and incorporating advanced feature integration strategies.

SC-Net: Symmetrical conical network for colorectal pathology image segmentation

Background and ObjectiveImage segmentation of histopathology of colorectal cancer is a core task of computer aided medical image diagnosis system. Existing convolutional neural networks generally extract multi-scale information in linear flow structures by inserting multi-branch modules, which is difficult to extract heterogeneous semantic information under multi-level and different receptive field and tough to establish context dependency among different receptive field features. MethodsTo address these issues, we propose a symmetric spiral progressive feature fusion encoder-decoder network called the Symmetric Conical Network (SC-Net). First, we design a Multi-scale Feature Extraction Block (MFEB) matching with the Symmetric Conical Network to obtain multi-branch heterogeneous semantic information under different receptive fields, so as to enrich the diversity of extracted feature information. The encoder is composed of MFEB through spiral and multi-branch arrangement to enhance context dependence between different information flow. Secondly, the information loss of contour, color and others in high-level semantic information through causally stacking MFEB, the Feature Mapping Layer (FML) is designed to map low-level features to high-level semantic features along the down-sampling branch and solve the problem of insufficient global feature extraction in deep levels. ResultsThe SC-Net was evaluated on our self-constructed colorectal cancer dataset, a publicly available breast cancer dataset and a polyp dataset. The results revealed that the mDice of segmentation reached 0.8611, 0.7259 and 0.7144. We compare our model with the state-of-art semantic segmentation UNet++, PSPNet, Attention U-Net, R2U-Net and other advanced segmentation networks. The experimental results demonstrate that we achieve the most advanced performance. ConclusionsThe results indicate that the proposed SC-Net excels in segmenting H&E stained pathology images, effectively preserving morphological features and spatial information even in scenarios with weak texture, poor contrast, and variations in appearance.

Unveiling the language of scars: A patient-centric themed framework for comprehensive scar morphology

BackgroundScarring, a pervasive issue spanning across medical disciplines, lacks a comprehensive terminology for effective communication, patient engagement, and outcome assessment. Existing scar classification systems are constrained by specific pathologies, physician-centric features, and inadequately account for emerging technologies. This study refrains from proposing yet another classification system and instead revisits the foundational language of scar morphology through a theme analysis of primary patient complaints. MethodData encompassing five years of a high-volume scar practice was analysed. Primary complaints were aggregated into collective descriptors and further organized into theme domains. The resulting hierarchical map of presenting complaints revealed five key domains: Loss of Function, Contour, Texture, Vector, and Colour Presenting complaints were codified into 42 items, which were then categorised into 14 collective descriptor terms. The latter were in turn organised into five overarching themes. ResultLoss of Function, accounting for 10% of primary concerns, signifies reduced function attributed solely to the scar. Contour, encompassing 41% of concerns, pertains to scar height, shape, and depth. Texture, representing 12% of concerns, denotes tactile variations such as hardness, roughness, and moisture. Vector, comprising 13% of concerns, refers to scar tissue tension and associated distortions. Colour, the concern in 24% of cases, encompasses variations in pigmentation, vascularity, and exogenous pigments. DiscussionStandardized terminology enhances patient care, communication, and research. This study underscores the fundamental question of "what bothers the patient," reviving a patient-centred approach to scar management. By prioritizing themes based on patient complaints, this study innovatively integrates function, aesthetics, and patient experience. In conclusion, this study pioneers a paradigm shift in scar management by presenting a patient-driven theme framework that offers a common language for healthcare professionals and patients. Embracing this language harmonizes scar treatment, fosters innovation, and transforms scars from silent reminders into stories of resilience and healing.

ReenactArtFace: Artistic Face Image Reenactment.

Large-scale datasets and deep generative models have enabled impressive progress in human face reenactment. Existing solutions for face reenactment have focused on processing real face images through facial landmarks by generative models. Different from real human faces, artistic human faces (e.g., those in paintings, cartoons, etc.) often involve exaggerated shapes and various textures. Therefore, directly applying existing solutions to artistic faces often fails to preserve the characteristics of the original artistic faces (e.g., face identity and decorative lines along face contours) due to the domain gap between real and artistic faces. To address these issues, we present ReenactArtFace, the first effective solution for transferring the poses and expressions from human videos to various artistic face images. We achieve artistic face reenactment in a coarse-to-fine manner. First, we perform 3D artistic face reconstruction, which reconstructs a textured 3D artistic face through a 3D morphable model (3DMM) and a 2D parsing map from an input artistic image. The 3DMM can not only rig the expressions better than facial landmarks but also render images under different poses/expressions as coarse reenactment results robustly. However, these coarse results suffer from self-occlusions and lack contour lines. Second, we thus perform artistic face refinement by using a personalized conditional adversarial generative model (cGAN) fine-tuned on the input artistic image and the coarse reenactment results. For high-quality refinement, we propose a contour loss to supervise the cGAN to faithfully synthesize contour lines. Quantitative and qualitative experiments demonstrate that our method achieves better results than the existing solutions.

AFUNet With Active Contour Loss for Water Body Detection in SAR Imagery

AFUNet With Active Contour Loss for Water Body Detection in SAR Imagery

Study of multistep Dense U-Net-based automatic segmentation for head MRI scans.

Despite extensive efforts to obtain accurate segmentation of magnetic resonance imaging (MRI) scans of a head, it remains challenging primarily due to variations in intensity distribution, which depend on the equipment and parameters used. The goal of this study is to evaluate the effectiveness of an automatic segmentation method for head MRI scans using a multistep Dense U-Net (MDU-Net) architecture. The MDU-Net-based method comprises two steps. The first step is to segment the scalp, skull, and whole brain from head MRI scans using a convolutional neural network (CNN). In the first step, a hybrid network is used to combine 2.5D Dense U-Net and 3D Dense U-Net structure. This hybrid network acquires logits in three orthogonal planes (axial, coronal, and sagittal) using 2.5D Dense U-Nets and fuses them by averaging. The resultant fused probability map with head MRI scans then serves as the input to a 3D Dense U-Net. In this process, different ratios of active contour loss and focal loss are applied. The second step is to segment the cerebrospinal fluid (CSF), white matter, and gray matter from extracted brain MRI scans using CNNs. In the second step, the histogram of the extracted brain MRI scans is standardized and then a 2.5D Dense U-Net is used to further segment the brain's specific tissues using the focal loss. A dataset of 100 head MRI scans from an OASIS-3 dataset was used for training, internal validation, and testing, with ratios of 80%, 10%, and 10%, respectively. Using the proposed approach, we segmented the head MRI scans into five areas (scalp, skull, CSF, white matter, and gray matter) and evaluated the segmentation results using the Dice similarity coefficient (DSC) score, Hausdorff distance (HD), and the average symmetric surface distance (ASSD) as evaluation metrics. We compared these results with those obtained using the Res-U-Net, Dense U-Net, U-Net++, Swin-Unet, and H-Dense U-Net models. The MDU-Net model showed DSC values of 0.933, 0.830, 0.833, 0.953, and 0.917 in the scalp, skull, CSF, white matter, and gray matter, respectively. The corresponding HD values were 2.37, 2.89, 2.13, 1.52, and 1.53mm, respectively. The ASSD values were 0.50, 1.63, 1.28, 0.26, and 0.27mm, respectively. Comparing these results with other models revealed that the MDU-Net model demonstrated the best performance in terms of the DSC values for the scalp, CSF, white matter, and gray matter. When compared with the H-Dense U-Net model, which showed the highest performance among the other models, the MDU-Net model showed substantial improvements in the HD view, particularly in the gray matter region, with a difference of approximately 9%. In addition, in terms of the ASSD, the MDU-Net model outperformed the H-Dense U-Net model, showing an approximately 7% improvements in the white matter and approximately 9% improvements in the gray matter. Compared with existing models in terms of DSC, HD, and ASSD, the proposed MDU-Net model demonstrated the best performance on average and showed its potential to enhance the accuracy of automatic segmentation for head MRI scans.

Segmentation of cardiac infarction in delayed-enhancement MRI using probability map and transformers-based neural networks

Background and Objective: Automatic segmentation of myocardial infarction is of great clinical interest for the quantitative evaluation of myocardial infarction (MI). Late Gadolinium Enhancement cardiac MRI (LGE-MRI) is commonly used in clinical practice to quantify MI, which is crucial for clinical diagnosis and treatment of cardiac diseases. However, the segmentation of infarcted tissue in LGE-MRI is highly challenging due to its high anisotropy and inhomogeneities.Methods: The innovative aspect of our work lies in the utilization of a probability map of the healthy myocardium to guide the localization of infarction, as well as the combination of 2D U-Net and U-Net transformers to achieve the final segmentation. Instead of employing a binary segmentation map, we propose using a probability map of the normal myocardium, obtained through a dedicated 2D U-Net. To leverage spatial information, we employ a U-Net transformers network where we incorporate the probability map into the original image as an additional input. Then, To address the limitations of U-Net in segmenting accurately the contours, we introduce an adapted loss function.Results: Our method has been evaluated on the 2020 MICCAI EMIDEC challenge dataset, yielding competitive results. Specifically, we achieved a Dice score of 92.94% for the myocardium and 92.36% for the infarction. These outcomes highlight the competitiveness of our approach.Conclusion: In the case of the infarction class, our proposed method outperforms state-of-the-art techniques across all metrics evaluated in the challenge, establishing its superior performance in infarction segmentation. This study further reinforces the importance of integrating a contour loss into the segmentation process.

CAU-Net: An Improved Attention U-Net for CT Head and Neck Organs at Risk Contouring

Segmentation of head and neck (H&N) organs at risk (OARs) is an intricate process, we propose Contest- extractor Attention U-Net (CAU-Net) to improve the segmentation accuracy of OARs contours by addressing the problem of limited accuracy of 2D segmentation algorithms in current radiotherapy techniques. A total of 60 patients from CSTRO2019's H&N dataset containing 22 organs, were available to train and evaluate a prototype deep learning-based normal tissue 2D auto-segmentation algorithm. Our CAU-Net is based on U-Net, by using the edge attention module to enhance the boundary representation, the null convolution block in the context extraction module to encode high-level semantic feature information, and the convolution of the sensory field to assign to different targets. A Dice loss function combine contour loss function was used in training the models. The contour loss function was improved to segment the target regions by the weights of different organ occurrences and the region assignment of false positives and false negatives to accurately predict the boundary structure. The OARs were delineated by a single experienced physician. A subset of 10 cases was withheld from training and used for validation. On those, we set three different deep-learning networks trained with CSTRO and compared them to the gold data: A) CAU-Net, B) nnUNet, and C) UNet++. To test its applicability, we used another public H&N dataset Public Domain Database for Computational Anatomy (PDDCA) containing 8 organs with 47 patients, among which 10 cases were used for validation: D) CAU-Net with the PDDCA, E) UNet2022 with the PDDCA. The Dice similarity coefficient (DSC) was used to measure the overlap between the results of the gold data and the automated segmentations. The average DSC scores for method A, B, and C across all OARs in the 10 evaluation cases were 0.67±0.08, 0.58±0.11 and 0.62±0.12, respectively. The difference in mean DSC scores was significant (p<0.05). The A/B difference was significant in Lens-L, Lens-R and Pituitary. Method A scored the highest DSC in all OARs except for the Spinal Cord, Mandible-L and Mandible-R. 16 OARs showed DSC≥0.6 on CSTRO. Method D, and E achieved 0.84±0.10 and 0.83±0.09 average DSC respectively. All OARs showed DSC≥0.7 on PDDCA. The CAU-Net proposed by us achieved better results than the baseline network for H&N OAR segmentation. This new development will provide the possibility of H&N organ segmentation and rapid diagnosis of radiotherapy. All the networks trained with PDDCA scored higher than CSTRO. Auto segmentation results can differ significantly when the same algorithm is trained on data from different institutions.

Clinicopathologic Profile and Surgical Modalities in Mandibular Ameloblastoma: A Descriptive Study.

Ameloblastoma is a benign neoplasm composed of epithelial tissue with invasive and infiltrative behavior at the local level and a high recurrence rate, with various histopathologic patterns and clinical forms. Approximately 85% of conventional ameloblastomas occur in the mandible, most often in the body, angle, and ascending ramus area. The treatment modalities include both conservative and radical treatments. Postoperative follow-up is most important in the treatment of ameloblastoma. To describe the clinicopathologic profile of mandibular ameloblastoma in patients undergoing different surgical modalities. The primary objective was to describe the clinicopathologic profile and surgical management of mandibular ameloblastoma in patients aged ≥18 years, who had reported to a tertiary dental care center for follow-up during the study period. The secondary objective was to describe the distribution of comorbidities associated with different surgical modalities and reconstructive methods. A total of 34 patients with mandibular ameloblastoma who underwent various surgical modalities between 2011 and 2021 were studied. Information was collected using a predesigned proforma and statistically analyzed. Thirty-four review cases of ameloblastoma were included in the study. The patients were analyzed concerning age, sex, site, size, clinical presentation, radiographic pattern, histopathologic subtype, type of surgery, and associated comorbidities. Most cases of mandibular ameloblastoma involve the age of 16 to 55 years. The mean age of occurrence was found to be 35.5±13.2. A female preponderance, a tumor size range of 2 to 4cm, a multicystic variant, involvement of the mandibular body in the premolar-molar area, root resorption, cortical perforation, and a follicular type of histopathologic pattern were the common presentations. Isolated anterior tumors restricted to the incisor/canine region were not found. The common surgical modalities undertaken were conservative methods such as enucleation, and chemical cauterization, and radical methods such as marginal mandibulectomy and segmental resection. Reconstruction using a titanium plate or free fibular graft was performed in the indicated cases. The common comorbidities included difficulty in chewing and loss of facial contour. Recurrence after surgical treatment was rare. Only 9% of cases developed a recurrence within 5 years. No recurrence was noted in cases treated with radical treatment, whereas 50% of cases treated with conservative methods showed recurrence. The age of occurrence, site, and size of the tumor, cortical perforation, root resorption, histopathologic type, and radiographic patterns are widely considered factors in devising a treatment plan for mandibular ameloblastoma. However, there may be rare instances where these tumors behave differently regardless of their innocuous clinicopathologic presentation. Surgical procedures such as segmental resection and marginal mandibulectomy were found to be promising for the eradication of the tumor, and prevention of recurrences and metastasis. However, conservative measures such as enucleation and chemical cauterization were fraught with an increased risk of tumor recurrence and metastasis. Future studies with a larger sample size should focus on the clinicopathologic characteristics of ameloblastoma to elucidate its varied behavior and develop newer and advanced treatment modalities that would provide better surgical and postsurgical outcomes in affected patients.

Changes in the microscopic organisation of rat adrenal glands under the influence of Vipera berus berus venom

Snakebite envenoming is a common but neglected public health problem worldwide. Annual mortality as a result of snakebites exceeds 138,000. The organs of the endocrine system are among the first to react to the effects of snake and viper toxins. Under these conditions, the adrenal glands are involved in the pathological process and contribute to the formation of the adaptation syndrome, undergoing complex structural changes. The research aims to study the changes in the microscopic organization of the adrenal glands of rats under the influence of Vipera berus berus venom. Experimental studies were carried out on white non-linear male rats. The animals were conditionally divided into a control and an experimental group of 10 individuals. Experimental rats were injected intraperitoneally in a saline solution with a semi-lethal dose (LD50) (1.576 mg/g-1) of Vipera berus berus venom. Animals of the control group were injected intraperitoneally with only saline solution. Rats were removed from the experiment 24 hours after exposure to the venom and anaesthetized by decapitation. Adrenal gland samples were taken for microscopic examination. Fixation of the material and preparation of paraffin blocks were carried out according to generally accepted methods. Histological preparations of the adrenal glands were stained with hematoxylin and eosin. Histological preparations were studied using an SEO SСAN light microscope. Under the influence of Vipera berus berus venom in zona glomerulosa of the adrenal cortex, moderately pronounced pathological changes were found, including vacuolization and granularity of the cytoplasm of endocrinocytes, loss of precise contours of nuclei, their hyperchromasia, expansion of lumens of sinusoidal capillaries, accumulation of erythrocytes in them. Under these conditions, zona fasciculata is characterized by significant cell granularity and perinuclear edema. Less pronounced structural organization changes were noted in the zona reticularis of the adrenal cortex. Endocrinocytes of this zone had small sizes, eosinophilic cytoplasm and dark nuclei. In the medulla of the adrenal glands, the cells were large in size and had indistinct contours, the cytoplasm was characterized by basophilic granularity, and the nuclei were light due to the predominance of euchromatin. The most pronounced effect of Vipera berus berus venom was on the zona glomerulosa and zona fasciculata of the adrenal cortex; most of the morphological signs of pathology in which were caused by a violation of protein metabolism in the cells of the parenchymal and stromal elements of this organ.

A Fully Convolutional Network with Waterfall Atrous Spatial Pooling and Localized Active Contour Loss for Fish Segmentation

Accurate measurements and statistics of fish data are important for sustainable development of aqua-enviroment and marine fisheries. For data measurements and statistics, automatic segmentation of fish is one of key tasks. The fish segmentation however is a challenging task due to arterfacts in underwater images. In this study, we introduce a deep-learning approach, namely FCN-WRN-WASP for automatic fish segmentation from the underwater images. In particular, we introduce a computational-efficient variation called Waterfall Atrous Spatial Pooling (WASP) module into a Fully convolutional network with Wide ResNet baseline. We also proposed a loss function inspired from active contour approach that can exploit the local intensity information from the input image. The approach has been validated on the DeepFish data and the SIUM data set. The results are promissing for fish segmentation, with higher Intersection over Union (IoU) scores compared to state of the arts. The evaluation results showed that the incorporation of the image based active contour loss helps increase the segmentation performance. In addition, the use of the WASP in the architecture is effective especially for forground fish segmentation.

Practical application of the facial fat compartments and the line of ligaments concept in achieving the lifting effect in the lower face region in female patients.

Practical application of the facial fat compartments and the line of ligaments concept in achieving the lifting effect in the lower face region in female patients.

MP05-03 DIFFERENCES IN PAPILLARY MORPHOLOGY BETWEEN BLACK AND WHITE STONE FORMERS

You have accessJournal of UrologyCME1 Apr 2023MP05-03 DIFFERENCES IN PAPILLARY MORPHOLOGY BETWEEN BLACK AND WHITE STONE FORMERS Luke Reynolds, Clark Judge, Julia Margason, India Skinner, Elaine Worcester, Frederick Coe, and Anna Zisman Luke ReynoldsLuke Reynolds More articles by this author , Clark JudgeClark Judge More articles by this author , Julia MargasonJulia Margason More articles by this author , India SkinnerIndia Skinner More articles by this author , Elaine WorcesterElaine Worcester More articles by this author , Frederick CoeFrederick Coe More articles by this author , and Anna ZismanAnna Zisman More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003216.03AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Nephrolithiasis is common and incidence is increasing faster among Blacks (B) compared to Whites (W). Recent evidence suggests that many stone formers (SF) form calcium oxalate stones on the base of a Randall plaque (RP), but this has only been studied in W SF. We sought to compare the renal papillary anatomy of B and W to improve our understanding of stone pathogenesis in the two groups. METHODS: SF undergoing ureteroscopy for the treatment of symptomatic and asymptomatic stone disease were prospectively enrolled. Patients with a systemic or anatomic cause for stone disease were excluded. Race was self-identified. Two blinded independent reviewers who had undergone standardized training on papillary grading used digital videos from ureteroscopy to assign scores of 0, 1, or 2 for plugging, plaque, pitting, and loss of contour. Scores were averaged across all papillae graded per kidney for each category, as well as the combined total score, and compared using Mann-Whitney U test. ANCOVA models were used to evaluate differences in these scores with adjustments for sex, age, BMI, and recurrence status (RS). RESULTS: Thirty-three B and 47 W patients were enrolled. Age was similar between groups but B had higher BMI (Table 1). The majority of patients were recurrent SF (66% W/83% B). B had significantly lower scores for plugging and plaque, as well as lower total scores (Table 1, Figure 1). In multivariate models, race was the only significant factor contributing to RP score, while race, age, and RS were significant for plugging. For total score, race and RS were significant contributors, and there was no interaction between race and RS. CONCLUSIONS: This study is the first to describe the papillary anatomy of B SF. Compared to W SF, B have significantly less RP and tubular plugging, suggesting potentially different mechanisms for stone formation. Source of Funding: P01 DK056788 (Worcester, Coe, Zisman) © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e44 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Luke Reynolds More articles by this author Clark Judge More articles by this author Julia Margason More articles by this author India Skinner More articles by this author Elaine Worcester More articles by this author Frederick Coe More articles by this author Anna Zisman More articles by this author Expand All Advertisement PDF downloadLoading ...

Determinants of renal papillary appearance in kidney stone formers: An in-depth examination

The aim of this study is to investi-gate the association between the urinary metabolic milieu and kidney stone recurrence with a validated papillary evaluation score (PPLA). We prospectively enrolled 30 stone for-mers who underwent retrograde intrarenal surgery procedures. Visual inspection of the accessible renal papillae was performed to calculate PPLA score, based on the characterization of ductal plugging, surface pitting, loss of papillary contour and Randall's plaque extension. Stone compositions, 24h urine collections and kidney stone events during follow-up were collected. Relative supersaturation ratios (RSS) for calcium oxalate (CaOx), brushite and uric acid were calculated using EQUIL-2. PPLA score > 3 was defined as high. Median follow-up period was 11 months (5, 34). PPLA score was inversely correlated with BMI (OR 0.59, 95% CI 0.38, 0.91, p = 0.018), type 2 diabetes (OR 0.04, 95% CI 0.003, 0.58, p = 0.018) and history of recurrent kidney stones (OR 0.17, 95%CI 0.04, 0.75, p = 0.019). The associations between PPLA score, diabetes and BMI were not confirmed after excluding patients with uric acid stones. Higher PPLA score was associated with lower odds of new kidney stone events during follow-up (OR 0.15, 95% CI 0.02, 1.00, p = 0.05). No other significant correla-tions were found. Our results confirm the lack of efficacy of PPLA score in phenotyping patients affected by kidney stone disease or in predicting the risk of stone recurrence. Larger, long-term studies need to be performed to clarify the role of PPLA on the risk of stone recurrence.

Pulmonary arteries segmentation from CT images using PA-Net with attention module and contour loss.

Pulmonary embolism is a kind of cardiovascular disease that threatens human life and health. Since pulmonary embolism exists in the pulmonary artery, improving the segmentation accuracy of pulmonary artery is the key to the diagnosis of pulmonary embolism. Traditional medical image segmentation methods have limited effectiveness in pulmonary artery segmentation. In recent years, deep learning methods have been gradually adopted to solve complex problems in the field of medical image segmentation. Due to the irregular shape of the pulmonary artery and the adjacent-complex tissues, the accuracy of the existing pulmonary artery segmentation methods based on deep learning needs to be improved. Therefore, the purpose of this paper is to develop a segmentation network, which can obtain higher segmentation accuracy and further improve the diagnosis effect. In this study, the pulmonary artery segmentation performance from the network model and loss function is improved, proposing a pulmonary artery segmentation network (PA-Net) to segment the pulmonary artery region from 2D CT images. Reverse Attention and edge attention are used to enhance the expression ability of the boundary. In addition, to better use feature information, the channel attention module is introduced in the decoder to highlight the important channel features and suppress the unimportant channels. Due to blurred boundaries, pixels near the boundaries of the pulmonary artery may be difficult to segment. Therefore, a new contour loss function based on the active contour model is proposed in this study to segment the target region by assigning dynamic weights to false positive and false negative regions and accurately predict the boundary structure. The experimental results show that the segmentation accuracy of this proposed method is significantly improved in comparison with state-of-the-art segmentation methods, and the Dice coefficient is 0.938±0.035, which is also confirmed from the 3D reconstruction results. Our proposed method can accurately segment pulmonary artery structure. This new development will provide the possibility for further rapid diagnosis of pulmonary artery diseases such as pulmonary embolism. Code is available at https://github.com/Yuanyan19/PA-Net.