Pathological Changes Discover Network: Discover the Pathological Changes of Perivascular Dermatitis by Semi-supervised Learning

Computed tomography image reconstruction using stacked U-Net

Anomaly-guided weakly supervised lesion segmentation on retinal OCT images

The current Synthetic Aperture Radar (SAR) target detection methods based on Convolutional Neural Network (CNN) rely on a large amount of slice-level labeled train samples. However, it takes a lot of labor and material resources to label the SAR images at slice-level. Compared to label samples at slice-level, it is easier to label them at image-level. The image-level label indicates whether the image contains the target of interest or not. In this paper, a semi-supervised SAR image target detection method based on CNN is proposed by using a small number of slice-level labeled samples and a large number of image-level labeled samples. The target detection network of this method consists of region proposal network and detection network. Firstly, the target detection network is trained using the slice-level labeled samples. After training convergence, the output slices constitute the candidate region set. Then, the image-level labeled clutter samples are input into the network and then the negative slices of the output are added to the candidate region set. Next, the image-level labeled target samples are input into the network as well. After selecting the positive and negative slices in the output of the network, they are added to the candidate region set. Finally, the detection network is trained using the updated candidate region set. The processes of updating candidate region set and training detection network alternate until convergence. The experimental results based on the measured data demonstrate that the performance of the proposed method is similar to the fully supervised training method using a much larger set of slice-level samples.

IntroductionFast, accurate, and automatic analysis of histopathological images using digital image processing and deep learning technology is a necessary task. Conventional histopathological image analysis algorithms require the manual design of features, while deep learning methods can achieve fast prediction and accurate analysis, but rely on the drive of a large amount of labeled data.MethodsIn this work, we introduce WSSS-CRAM a weakly-supervised semantic segmentation that can obtain detailed pixel-level labels from image-level annotated data. Specifically, we use a discriminative activation strategy to generate category-specific image activation maps via class labels. The category-specific activation maps are then post-processed using conditional random fields to obtain reliable regions that are directly used as ground-truth labels for the segmentation branch. Critically, the two steps of the pseudo-label acquisition and training segmentation model are integrated into an end-to-end model for joint training in this method.ResultsThrough quantitative evaluation and visualization results, we demonstrate that the framework can predict pixel-level labels from image-level labels, and also perform well when testing images without image-level annotations.DiscussionFuture, we consider extending the algorithm to different pathological datasets and types of tissue images to validate its generalization capability.

IntroductionThe aim of the study was to explore the effect of aminoguanidine cream on the skin tissue microenvironment in diabetic rats.Material and methodsA total of 51 healthy male Sprague Dawley (SD) rats were randomly divided into three groups: the diabetes group (n = 18), the aminoguanidine group (n = 18) and the control group (n = 15). Rats in the diabetes group and aminoguanidine group were injected with 65 mg/kg streptozotocin to induce the diabetes model, and in the control group with citrate buffer. After successful induction of diabetes, the back hair of all rats was stripped by barium sulfide, and the aminoguanidine group was treated with aminoguanidine cream using disinfected cotton swabs twice every day for 40 days, while the diabetes and control groups were treated with the cream matrix. The pathological changes of skin were observed by HE staining, while the content of inflammatory cytokines (TNF-α, IL-8, ICAM and IL-1α) and the antioxidant indexes (T-AOC, GSH-PX, MPO MDA H2O2) were examined using commercial kits.ResultsAfter 40 days of treatment, the diabetes group manifested tissue lesions, whereas the aminoguanidine group seemed normal. Compared with the diabetes group, the content of inflammatory cytokines TNF-α, IL-8, ICAM and IL-1α was dramatically lower in the aminoguanidine group. T-AOC in all groups underwent dramatic changes and returned to normal finally. The activities of GSH-PX and MPO and content of H2O2 in the diabetes group were all higher than those in the aminoguanidine group.ConclusionsAminoguanidine may have a good systemic effect on alleviating the pathological changes of skin tissue in diabetic rats, which may be attributed to the regulation of GSH-PX, TNF-α, IL-8, ICAM and IL-1α.

Deep learning techniques have shown great potential in medical image processing, particularly through accurate and reliable image segmentation on magnetic resonance imaging (MRI) scans or computed tomography (CT) scans, which allow the localization and diagnosis of lesions. However, training these segmentation models requires a large number of manually annotated pixel-level labels, which are time-consuming and labor-intensive, in contrast to image-level labels that are easier to obtain. It is imperative to resolve this problem through weakly-supervised semantic segmentation models using image-level labels as supervision since it can significantly reduce human annotation efforts. Most of the advanced solutions exploit class activation mapping (CAM). However, the original CAMs rarely capture the precise boundaries of lesions. In this study, we propose the strategy of multi-scale inference to refine CAMs by reducing the detail loss in single-scale reasoning. For segmentation, we develop a novel model named Mixed-UNet, which has two parallel branches in the decoding phase. The results can be obtained after fusing the extracted features from two branches. We evaluate the designed Mixed-UNet against several prevalent deep learning-based segmentation approaches on our dataset collected from the local hospital and public datasets. The validation results demonstrate that our model surpasses available methods under the same supervision level in the segmentation of various lesions from brain imaging.

Rethinking masked image modelling for medical image representation

Accurate segmentation of Optical Coherence Tomography (OCT) images is crucial for diagnosing and monitoring retinal diseases. However, the labor-intensive nature of pixel-level annotation limits the scalability of supervised learning for large datasets. Weakly Supervised Semantic Segmentation (WSSS) offers a promising alternative by using weaker forms of supervision, such as image-level labels, to reduce the annotation burden. Despite its advantages, weak supervision inherently carries limited information. We propose a novel WSSS framework with only image-level labels for OCT lesion segmentation that integrates structural and text-driven guidance to produce high-quality, pixel-level pseudo labels. The framework employs two visual processing modules: one that processes the original OCT images and another that operates on layer segmentations augmented with anomalous signals, enabling the model to associate lesions with their corresponding anatomical layers. Complementing these visual cues, we leverage large-scale pretrained models to provide two forms of textual guidance: label-derived descriptions that encode local semantics, and domain-agnostic synthetic descriptions that, although expressed in natural image terms, capture spatial and relational semantics useful for generating globally consistent representations. By fusing these visual and textual features in a multi-modal framework, our method aligns semantic meaning with structural relevance, thereby improving lesion localization and segmentation performance. Experiments on three OCT datasets demonstrate state-of-the-art results, highlighting its potential to advance diagnostic accuracy and efficiency in medical imaging.

The existing Synthetic Aperture Radar (SAR) image target detection methods based on convolutional neural networks (CNNs) have achieved remarkable performance, but these methods require a large number of target-level labeled training samples to train the network. Moreover, some clutter is very similar to targets in SAR images with complex scenes, making the target detection task very difficult. Therefore, a SAR target detection network based on a semi-supervised learning and attention mechanism is proposed in this paper. Since the image-level label simply marks whether the image contains the target of interest or not, which is easier to be labeled than the target-level label, the proposed method uses a small number of target-level labeled training samples and a large number of image-level labeled training samples to train the network with a semi-supervised learning algorithm. The proposed network consists of a detection branch and a scene recognition branch with a feature extraction module and an attention module shared between these two branches. The feature extraction module can extract the deep features of the input SAR images, and the attention module can guide the network to focus on the target of interest while suppressing the clutter. During the semi-supervised learning process, the target-level labeled training samples will pass through the detection branch, while the image-level labeled training samples will pass through the scene recognition branch. During the test process, considering the help of global scene information in SAR images for detection, a novel coarse-to-fine detection procedure is proposed. After the coarse scene recognition determining whether the input SAR image contains the target of interest or not, the fine target detection is performed on the image that may contain the target. The experimental results based on the measured SAR dataset demonstrate that the proposed method can achieve better performance than the existing methods.

Deep learning-based thyroid ultrasound image segmentation is of great importance in clinical diagnosis. The Weakly Supervised Semantic Segmentation (WSSS) models requiring only Image-level Labels (IL) reduce the dependence on pixel-level labels. However, due to the lack of position of the objects in image-level labels, WSSS methods with IL are generally based on Class Activation Map (CAM) that can locate the objects. Nowadays, channel attention, which is one of the effective tools to extract object features from images, has been widely used in semantic segmentation tasks. Unfortunately, due to the large differences in the size and discriminative features of thyroid nodules, the mainstream channel attention is unable to perform flexible feature extraction for nodules, leading to the problem of under-segmentation or over-segmentation in the predicted results of the model. To overcome this issue, we propose a dynamic channel attention network that can extract features of thyroid nodules adaptively, called the CAM-guided Adaptive Attention Network (CAANet). In detail, CAANet can pay different attention to the overall and discriminative features of nodules based on the information provided by CAM. Finally, to verify the effectiveness of our method, we perform experimental comparisons with recent WSSS methods and the mainstream channel attention methods on the thyroid ultrasound image dataset. The evaluation results show that our method has better performance improvement, with a mean Intersection over Union (IoU) of 52.713%.

Objective: To summarize the clinical and imaging features of linear scleroderma en coup de saber (LSCS) with central nervous system involvement in children. Methods: The clinical data(clinical manifestations and imaging features) of 6 children diagnosed with LSCS with central nervous system involvement who were admitted to Beijing Children's Hospital Affiliated to Capital Medical University from May 2019 to November 2021 were retrospectively analyzed. Results: The 6 patients were all female, aged 6.8 (3.3, 11.0) years at the time of diagnosis, and aged 3.0 (1.7, 4.1) years at the time of discovery of facial skin lesions. Facial skin lesions appeared before neurological symptoms in 5 cases, and neurological symptoms appeared 2 months before skin lesions in 1 case. All the patients had "sword wound" skin lesions on the forehead with alopecia. Neurological manifestations included epileptic seizures in 6 cases, focal neurological defects in 5 cases, and headaches in 2 cases. The intracranial lesions were all ipsilateral to the skin lesions. The magnetic resonance imaging (MRI) of 6 cases showed abnormal signals mainly involving white matter in 1 hemisphere, and 3 cases showed local encephalomalacia. The scattered low signal was observed in 5 cases on susceptibility weighted imaging. Localized brain parenchyma or leptomeninges enhancement was seen on Gadolinium-enhanced sequences in 5 cases. Scattered foci of calcification on the affected side were seen on cranial CT in 4 cases. Skin biopsy was performed in 2 cases. Part of the lesion of the brain was removed in 1 case, and the pathological findings suggested small vasculitis, which was consistent with skin pathological changes. All patients received symptomatic treatment with antiepileptic drugs. Oral prednisone combined with methotrexate was given in 4 cases, and 1 case was given oral prednisone only. One case was presumed to be in the resting stage of the disease due to significant cerebral atrophy in half of the brain, and only antiepileptic drugs were added. The patients were followed up for 6-36 months. The skin lesions of scleroderma and alopecia did not progress in 5 cases, and hemifacial atrophy was developed in 1 case, which was considered to be combined with Parry-Romberg syndrome. The seizures were controlled in 4 cases. One case had reduced seizure frequency but left hemiplegia. One patient still had intractable epilepsy and paroxysmal headache. Conclusions: LSCS with central nervous system involvement is more common in girls, with seizures and neurological defects as the main manifestations. Intracranial lesions are mostly ipsilateral to the skin lesions. Cerebral microbleeds, calcification, and encephalomalacia foci are common, and the pathological changes in skin and intracranial lesions are consistent with small-vessel vasculitis. Prednisone combined with methotrexate treatment has shown some efficacy, but some children remain with refractory epilepsy and neurological deficit symptoms.

White matter lesion (WML) segmentation applied to magnetic resonance imaging (MRI) scans of people with multiple sclerosis has been an area of extensive research in recent years. As with most tasks in medical imaging, deep learning (DL) methods have proven very effective and have quickly replaced existing methods. Despite the improvement offered by these networks, there are still shortcomings with these DL approaches. In this work, we compare several DL algorithms, as well as methods for ensembling the results of those algorithms, for performing MS lesion segmentation. An ensemble approach is shown to best estimate total WML and has the highest agreement with manual delineations.

Image dehazing has always been a challenging topic in image processing. The development of deep learning methods, especially the generative adversarial networks (GAN), provides a new way for image dehazing. In recent years, many deep learning methods based on GAN have been applied to image dehazing. However, GAN has two problems in image dehazing. Firstly, For haze image, haze not only reduces the quality of the image but also blurs the details of the image. For GAN network, it is difficult for the generator to restore the details of the whole image while removing the haze. Secondly, GAN model is defined as a minimax problem, which weakens the loss function. It is difficult to distinguish whether GAN is making progress in the training process. Therefore, we propose a guided generative adversarial dehazing network (GGADN). Different from other generation adversarial networks, GGADN adds a guided module on the generator. The guided module verifies the network of each layer of the generator. At the same time, the details of the map generated by each layer are strengthened. Network training is based on the pre-trained VGG feature model and L1-regularized gradient prior which is developed by new loss function parameters. From the dehazing results of synthetic images and real images, the proposed method is better than the state-of-the-art dehazing methods.

Nowadays, deep learning methods with high structural complexity and flexibility inevitably lean on the computational capability of the hardware. A platform with high-performance GPUs and large amounts of memory could support neural networks having large numbers of layers and kernels. However, naively pursuing high-cost hardware would probably drag the technical development of deep learning methods. In the article, we thus establish a new preprocessing method to reduce the computational complexity of the neural networks. Inspired by the band theory of solids in physics, we map the image space into a noninteraction physical system isomorphically and then treat image voxels as particle-like clusters. Then, we reconstruct the Fermi–Dirac distribution to be a correction function for the normalization of the voxel intensity and as a filter of insignificant cluster components. The filtered clusters at the circumstance can delineate the morphological heterogeneity of the image voxels. We used the BraTS 2019 datasets and the dimensional fusion U-net for the algorithmic validation, and the proposed Fermi–Dirac correction function exhibited comparable performance to other employed preprocessing methods. By comparing to the conventional z-score normalization function and the Gamma correction function, the proposed algorithm can save at least 38% of computational time cost under a low-cost hardware architecture. Even though the correction function of global histogram equalization has the lowest computational time among the employed correction functions, the proposed Fermi–Dirac correction function exhibits better capabilities of image augmentation and segmentation.

Video-based human action recognition is one of the most important and challenging areas of research in the field of computer vision. Human action recognition has found many pragmatic applications in video surveillance, human-computer interaction, entertainment, autonomous driving, etc. Owing to the recent development of deep learning methods for human action recognition, the performance of action recognition has significantly enhanced for challenging datasets. Deep learning techniques are mainly used for recognizing actions in images and videos comprising of Euclidean data. A recent development in deep learning methods is the extension of these techniques to non-Euclidean data or graph data with many nodes and edges. Human body skeleton resembles a graph, therefore, the graph convolutional network (GCN) is applicable to the non-Euclidean body skeleton. In the past few years, GCN has emerged as an important tool for skeleton-based action recognition. Therefore, we conduct a survey using GCN methods for action recognition. Herein, we present a comprehensive overview of recent GCN techniques for action recognition, propose a taxonomy for the categorization of GCN techniques for action recognition, carry out a detailed study of the benchmark datasets, enlist relevant resources and open-source codes, and finally provide an outline for future research directions and trends. To the best of authors' knowledge, this is the first survey for action recognition using GCN techniques.