Lesions In Region Research Articles

A Novel Deep Learning Model for Breast Tumor Ultrasound Image Classification with Lesion Region Perception.

Multi-task learning (MTL) methods are widely applied in breast imaging for lesion area perception and classification to assist in breast cancer diagnosis and personalized treatment. A typical paradigm of MTL is the shared-backbone network architecture, which can lead to information sharing conflicts and result in the decline or even failure of the main task's performance. Therefore, extracting richer lesion features and alleviating information-sharing conflicts has become a significant challenge for breast cancer classification. This study proposes a novel Multi-Feature Fusion Multi-Task (MFFMT) model to effectively address this issue. Firstly, in order to better capture the local and global feature relationships of lesion areas, a Contextual Lesion Enhancement Perception (CLEP) module is designed, which integrates channel attention mechanisms with detailed spatial positional information to extract more comprehensive lesion feature information. Secondly, a novel Multi-Feature Fusion (MFF) module is presented. The MFF module effectively extracts differential features that distinguish between lesion-specific characteristics and the semantic features used for tumor classification, and enhances the common feature information of them as well. Experimental results on two public breast ultrasound imaging datasets validate the effectiveness of our proposed method. Additionally, a comprehensive study on the impact of various factors on the model's performance is conducted to gain a deeper understanding of the working mechanism of the proposed framework.

MASDF-Net: A Multi-Attention Codec Network with Selective and Dynamic Fusion for Skin Lesion Segmentation.

Automated segmentation algorithms for dermoscopic images serve as effective tools that assist dermatologists in clinical diagnosis. While existing deep learning-based skin lesion segmentation algorithms have achieved certain success, challenges remain in accurately delineating the boundaries of lesion regions in dermoscopic images with irregular shapes, blurry edges, and occlusions by artifacts. To address these issues, a multi-attention codec network with selective and dynamic fusion (MASDF-Net) is proposed for skin lesion segmentation in this study. In this network, we use the pyramid vision transformer as the encoder to model the long-range dependencies between features, and we innovatively designed three modules to further enhance the performance of the network. Specifically, the multi-attention fusion (MAF) module allows for attention to be focused on high-level features from various perspectives, thereby capturing more global contextual information. The selective information gathering (SIG) module improves the existing skip-connection structure by eliminating the redundant information in low-level features. The multi-scale cascade fusion (MSCF) module dynamically fuses features from different levels of the decoder part, further refining the segmentation boundaries. We conducted comprehensive experiments on the ISIC 2016, ISIC 2017, ISIC 2018, and PH2 datasets. The experimental results demonstrate the superiority of our approach over existing state-of-the-art methods.

MAPPNet: A Multi-Scale Attention Pyramid Pooling Network for Dental Calculus Segmentation

Dental diseases are among the most prevalent diseases globally, and accurate segmentation of dental calculus images plays a crucial role in periodontal disease diagnosis and treatment planning. However, the current methods are not stable and reliable enough due to the variable morphology of dental calculus and the blurring of the boundaries between the dental edges and the surrounding tissues; therefore, our hope is to propose an accurate and reliable calculus segmentation algorithm to improve the efficiency of clinical detection. We propose a multi-scale attention pyramid pooling network (MAPPNet) to enhance the performance of dental calculus segmentation. The network incorporates a multi-scale fusion strategy in both the encoder and decoder, forming a model with a dual-ended multi-scale structure. This design, in contrast to employing a multi-scale fusion scheme at a single end, enables more effective capturing of features from diverse scales. Furthermore, the attention pyramid pooling module (APPM) reconstructs the features on this map by leveraging a spatial-first and channel-second attention mechanism. APPM enables the network to adaptively adjust the weights of different locations and channels in the feature map, thereby enhancing the perception of important regions and key features. Experimental evaluation of our collected dental calculus segmentation dataset demonstrates the superior performance of MAPPNet, which achieves an intersection-over-union of 81.46% and an accuracy rate of 98.35%. Additionally, on two publicly available datasets, ISIC2018 (skin lesion dataset) and Kvasir-SEG (gastrointestinal polyp segmentation dataset), MAPPNet achieved an intersection-over-union of 76.48% and 91.38%, respectively. These results validate the effectiveness of our proposed network in accurately segmenting lesion regions and achieving high accuracy rates, surpassing many existing segmentation methods.

Adaptive edge prior-based deep attention residual network for low-dose CT image denoising

Improving the diagnostic quality of low-dose CT (LDCT) images relies on effective noise removal. Recent advancements have highlighted the widespread use of deep residual networks for LDCT image denoising. These networks possess properties that aid in preserving image integrity and optimizing model performance. However, the denoising process faces challenges due to the complex patterns and intensity similarities between edge details and lesion regions. To address this issue, this paper introduces a novel approach called the cross-scale attentional residual network (RCANet), which utilizes an adaptive edge prior for LDCT image denoising. The adaptive edge prior enhances the denoising network’s ability to retain image boundary features and uniqueness. To distinguish subtle differences between LDCT image edge details and lesion areas, a cross-scale mapping dual-element module (CMDM) is designed to preserve rich edge texture information during model training. To prevent over-smoothing of denoised results, a compound loss function is proposed, combining MSE loss and multi-scale attention residual perception loss. To validate the effectiveness of the method, experiments were conducted on the AAPM-Mayo Clinic LDCT Grand Challenge dataset. The results demonstrate that RCANet surpasses state-of-the-art residual structure-based network models and performs comparably to leading denoising algorithms.

Texture feature-aware consistency for semi-supervised honeycomb lung lesion segmentation

Accurate segmentation of honeycomb lung lesions from lung CT images is crucial for the clinical diagnosis of a wide range of lung diseases. Existing semi-supervised segmentation methods ignore the rich texture feature information in honeycomb lung CT images, resulting in inaccurate predictions in the lesion region. Therefore, this paper proposes a semi-supervised honeycomb lung lesion segmentation framework using texture feature-aware consistency. The framework consists of a shared encoder, a main decoder, and three auxiliary decoders. The different outputs produced by the decoders are used to compute the Grey Level Co-occurrence Matrix and extract texture features, respectively, and further to compute the loss of texture feature-aware consistency. In pseudo-labeling supervision, the uncertainty of each output is computed to bootstrap the pseudo-labeling supervision loss. For the small lesion recognition omission problem, a pseudo-label refinement module is constructed to reuse the multi-scale features of the encoder, focusing on small-scale lesions, and refining the pseudo-labels. Experimental results show that the proposed method outperforms other methods in the honeycomb lung segmentation task, achieving a Dice coefficient of 77.62 using 20% labeled data. Additionally, experiments on publicly available datasets further demonstrate the generalizability of the proposed method. The code is available at https://github.com/Oran9er/TFC-Net-main.

Mapping stroke outcomes: A review of brain connectivity atlases.

The brain connectivity-based atlas is a promising tool for understanding neural communication pathways in the brain, gaining relevance in predicting personalized outcomes for various brain pathologies. This critical review examines the robustness of the brain connectivity-based atlas for predicting post-stroke outcomes. A comprehensive literature search was conducted from 2012 to May 2023 across PubMed, Scopus, EMBASE, EBSCOhost, and Medline databases. Twenty-one studies were screened, and through analysis of these studies, we identified 18 brain connectivity atlases employed by the studies for lesion analysis in their predictions. The brain atlases were assessed for study cohorts, connectivity measures, identified brain regions, atlas applications, and limitations. Based on the analysis of these studies, most atlases were based on diffusion tensor imaging and resting-state functional magnetic resonance imaging (MRI). Studies predicting post-stroke functional outcomes relied on the atlases for multivariate lesion analysis and region of interest identification, often employing atlases derived from young, healthy populations. Current brain connectivity-based atlases for stroke applications lack standardized methods to define and map brain connectivity across atlases and cover sensorimotor functional connectivity to a limited extent. In conclusion, this review highlights the need to develop more comprehensive, robust, and adaptable brain connectivity-based atlases specifically tailored to post-stroke populations.

ESFPNet: Efficient Stage-Wise Feature Pyramid on Mix Transformer for Deep Learning-Based Cancer Analysis in Endoscopic Video.

For patients at risk of developing either lung cancer or colorectal cancer, the identification of suspect lesions in endoscopic video is an important procedure. The physician performs an endoscopic exam by navigating an endoscope through the organ of interest, be it the lungs or intestinal tract, and performs a visual inspection of the endoscopic video stream to identify lesions. Unfortunately, this entails a tedious, error-prone search over a lengthy video sequence. We propose a deep learning architecture that enables the real-time detection and segmentation of lesion regions from endoscopic video, with our experiments focused on autofluorescence bronchoscopy (AFB) for the lungs and colonoscopy for the intestinal tract. Our architecture, dubbed ESFPNet, draws on a pretrained Mix Transformer (MiT) encoder and a decoder structure that incorporates a new Efficient Stage-Wise Feature Pyramid (ESFP) to promote accurate lesion segmentation. In comparison to existing deep learning models, the ESFPNet model gave superior lesion segmentation performance for an AFB dataset. It also produced superior segmentation results for three widely used public colonoscopy databases and nearly the best results for two other public colonoscopy databases. In addition, the lightweight ESFPNet architecture requires fewer model parameters and less computation than other competing models, enabling the real-time analysis of input video frames. Overall, these studies point to the combined superior analysis performance and architectural efficiency of the ESFPNet for endoscopic video analysis. Lastly, additional experiments with the public colonoscopy databases demonstrate the learning ability and generalizability of ESFPNet, implying that the model could be effective for region segmentation in other domains.

Sub retinal pigment epithelium hyporeflective spaces preceding large drusen collapse.

To describe and study hyporeflective sub retinal pigment epithelium (RPE) spaces in large drusen and drusenoid pigment epithelial detachment prior to collapse. Retrospective longitudinal study which enrolled patients with large and very large drusen due to intermediate age-related macular degeneration (AMD). The following optical coherence tomography (OCT) parameters were assessed: Drusen size (maximum width and height), OCT biomarkers of RPE atrophy, presence of intraretinal and subretinal fluid (IRF, SRF), acquired vitelliform lesion and sub RPE regions of hyporeflectivity within the PED compartment. Of the 50 eyes from 41 patients (mean age of 77.1 ± 9 years, 78% women) with large and very large drusen, 16 eyes progressed to collapse. Eyes with sub RPE hyporeflective spaces (n=8 eyes, 50%) were associated with greater drusen width and height than eyes without sub RPE hyporeflective spaces. At the collapse visit, eyes with sub RPE hyporeflective spaces displayed poorer visual acuity and greater iRORA (incomplete RPE outer retinal atrophy) and cRORA (complete RORA) length than eyes without sub RPE hyporeflective spaces (p=0.004 and p=0.04, respectively). Sub RPE hyporeflective spaces are a novel OCT finding of large and very large drusen that collapse to atrophy. Progressive RPE dysfunction and failure may lead to reduced drusenoid material formation and progressive degenerative hydration of the large drusen prior to collapse, but this awaits confirmation with histopathological analysis.

Novel Deep CNNs Explore Regions, Boundaries, and Residual Learning for COVID-19 Infection Analysis in Lung CT.

COVID-19 poses a global health crisis, necessitating precise diagnostic methods for timely containment. However, accurately delineating COVID-19-affected regions in lung CT scans is challenging due to contrast variations and significant texture diversity. In this regard, this study introduces a novel two-stage classification and segmentation CNN approach for COVID-19 lung radiological pattern analysis. A novel Residual-BRNet is developed to integrate boundary and regional operations with residual learning, capturing key COVID-19 radiological homogeneous regions, texture variations, and structural contrast patterns in the classification stage. Subsequently, infectious CT images undergo lesion segmentation using the newly proposed RESeg segmentation CNN in the second stage. The RESeg leverages both average and max-pooling implementations to simultaneously learn region homogeneity and boundary-related patterns. Furthermore, novel pixel attention (PA) blocks are integrated into RESeg to effectively address mildly COVID-19-infected regions. The evaluation of the proposed Residual-BRNet CNN in the classification stage demonstrates promising performance metrics, achieving an accuracy of 97.97%, F1-score of 98.01%, sensitivity of 98.42%, and MCC of 96.81%. Meanwhile, PA-RESeg in the segmentation phase achieves an optimal segmentation performance with an IoU score of 98.43% and a dice similarity score of 95.96% of the lesion region. The framework's effectiveness in detecting and segmenting COVID-19 lesions highlights its potential for clinical applications.

Asymptotic multilayer pooled transformer based strategy for medical assistance in developing countries

With the continuous progress of medical imaging technology, pathology images have become an important basis for doctors to judge the condition. However, pathology images have problems such as large numbers, large sizes, and complex backgrounds, which make the task of manual recognition exceptionally difficult. The use of computer-aided diagnosis technology can improve the diagnostic accuracy of medical image recognition. Transformer model-based methods have made great progress in the field of medical image recognition, but the self-attention mechanism in them has high computational complexity. Although single-layer pooling can reduce the computational cost, the strategy is prone to feature loss, and too many self-attention operations can exacerbate the distraction problem. Based on this, this study proposes an asymptotic multilayer pooling transformer-based pathology image assistance strategy in medical decision-making systems. First, we pre-process the pathology images with denoising and enhancement to accurately capture the detailed features of the lesion region. Then the asymptotic multilayer pooling transformer pyramid structure (PMPSNet) is used to identify cell nuclei. In the self-focused module, a multilayer pooling operation is employed to simplify the sequence and efficiently capture contextual features. In addition, the strategy utilizes a pyramid encoder to obtain multi-scale feature maps and a novel multilayer perceptual structure to limit the attention interference problem. The results show that our proposed PMPSNet-L model achieves a DSC value of 0.822, which is about 1.4 % better than the second-ranked model, and the IoU value reaches up to 0.702. In addition, our PMPSNet-S maintains a relatively lightweight parameter size of about 14.49 million, which is considerably lower than the existing segmentation models. Our proposed method not only achieves higher segmentation accuracy but also has fewer model parameters and lower computational complexity.

A frequency selection network for medical image segmentation

Existing medical image segmentation methods may only consider feature extraction and information processing in spatial domain, or lack the design of interaction between frequency information and spatial information, or ignore the semantic gaps between shallow and deep features, and lead to inaccurate segmentation results. Therefore, in this paper, we propose a novel frequency selection segmentation network (FSSN), which achieves more accurate lesion segmentation by fusing local spatial features and global frequency information, better design of feature interactions, and suppressing low correlation frequency components for mitigating semantic gaps. Firstly, we propose a global-local feature aggregation module (GLAM) to simultaneously capture multi-scale local features in the spatial domain and exploits global frequency information in the frequency domain, and achieves complementary fusion of local details features and global frequency information. Secondly, we propose a feature filter module (FFM) to mitigate semantic gaps when we conduct cross-level features fusion, and makes FSSN discriminatively determine which frequency information should be preserved for accurate lesion segmentation. Finally, in order to make better use of local information, especially the boundary of lesion region, we employ deformable convolution (DC) to extract pertinent features in the local range, and makes our FSSN can focus on relevant image contents better. Extensive experiments on two public benchmark datasets show that compared with representative medical image segmentation methods, our FSSN can obtain more accurate lesion segmentation results in terms of both objective evaluation indicators and subjective visual effects with fewer parameters and lower computational complexity.

Interactive Skin Lesion Segmentation Considering Behavioral Preference in Clicking

Interactive Medical Image Segmentation (IMIS) aims to improve the accuracy of image segmentation by incorporating human guidance, primarily through click‐based interactions. IMIS for skin lesion segmentation is a challenging task because the edges of lesion regions on the skin are often ambiguous, and training IMIS models requires the generation of pseudo‐clicks to simulate human clicks. Most previous methods generate pseudo‐clicks by sampling from the entire mis‐segmented region. However, such clicks are inconsistent with human behavior, resulting in performance degradation, particularly for skin lesion segmentation. In this study, we address this issue by integrating human preference into the process of generating pseudo clicks to train the segmentation model, which is simple yet effective. Specifically, through a user study, we find that people are more inclined to click on larger mis‐segmented regions during interactive segmentation. Inspired by this, a roulette selection strategy is used to generate the pseudo‐clicks based on the area of the mis‐segmented subregions. Our proposed method, BehaviorClick, can be easily integrated with existing interactive segmentation models to improve the performance. The accuracy improvement on four dermoscopic datasets under six state‐of‐the‐art interactive segmentation methods is confirmed, which demonstrates the generalizability and effectiveness of our approach. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

A two-stage image enhancement and dynamic feature aggregation framework for gastroscopy image segmentation

Accurate and reliable automatic segmentation of lesion areas in gastroscopy images can assist endoscopists in making diagnoses and reduce the possibility of missed or incorrect diagnoses. This paper presents a two-stage framework for segmenting gastroscopy images, which aims to improve the accuracy of medical image segmentation tasks using limited datasets. The proposed framework consists of two stages: the Image Enhancement Stage and the Lesion Segmentation Stage. First, in the Image Enhancement Stage, an image enhancement solution called TDC-Enhance is proposed to enrich the original small-scale gastroscopy image dataset. This solution performs Texture Enhancement, Detail Enhancement, and Color Enhancement on the original images. Then, in the Lesion Segmentation Stage, a multi-path automatic segmentation network for gastroscopy images, named DynaSiam, is introduced. DynaSiam comprises a Dependent Encoder, a Shared Encoder, and a Fusion Decoder. It learns feature information related to the lesion region by encoding the different enhanced images obtained in the Image Enhancement Stage as inputs to the multi-path network. Additionally, a Dynamic Feature Interaction (DFI) block is designed to capture and learn deeper image information, thereby improving the segmentation performance of the model. The experimental results show that the proposed method achieves a 90.80% mIoU, 92.71% Dice coefficient and 96.31% Accuracy. Other performance metrics also indicate the best performance, suggesting that the proposed model has significant potential for clinical analysis and diagnosis. Code and implementation details can be found on GitHub: https://github.com/kyasulee/DynaSiam.

A three-dimensional quantitative assessment on bony growth and symmetrical recovery of mandible after decompression for unicystic ameloblastoma

Unicystic ameloblastoma (UAM) of the jaw can be effectively reduced in volume through decompression, which promotes bone regeneration and restores jaw symmetry. This study quantitatively evaluated changes in mandible volume and symmetry following decompression of mandibular UAM. This study included 17 patients who underwent surgical decompression followed by second-stage curettage for mandibular UAM. Preoperative and postoperative three-dimensional computed tomography (CT) images were collected. Bone volume and the area of cortical perforation were measured to assess bone growth during decompression. Mandibular volumetric symmetry was analyzed by calculating the volumetric ratio of the two sides of the mandible. Twelve pairs of landmarks were identified on the surface of the lesion regions, and their coordinates were used to calculate the mean asymmetry index (AI) of the mandible. Paired t-tests and the Mann–Whitney U test were used for statistical analysis, with p < 0.05 considered indicative of statistical significance. The mean duration of decompression was 9.41 ± 3.28 months. The mean bone volume increased by 8.07 ± 2.41%, and cortical perforation recovery was 71.97 ± 14.99%. The volumetric symmetry of the mandible improved significantly (p < 0.05), and a statistically significant decrease in AI was observed (p < 0.05). In conclusion, UAM decompression enhances bone growth and symmetry recovery of the mandible. The present evaluation technique is clinically useful for quantitatively assessing mandibular asymmetry.

HST-MRF: Heterogeneous Swin Transformer With Multi-Receptive Field for Medical Image Segmentation.

The Transformer has been successfully used in medical image segmentation due to its excellent long-range modeling capabilities. However, patch segmentation is necessary when building a Transformer class model. This process ignores the tissue structure features within patch, resulting in the loss of shallow representation information. In this study, we propose a Heterogeneous Swin Transformer with Multi-Receptive Field (HST-MRF) model that fuses patch information from different receptive fields to solve the problem of loss of feature information caused by patch segmentation. The heterogeneous Swin Transformer (HST) is the core module, which achieves the interaction of multi-receptive field patch information through heterogeneous attention and passes it to the next stage for progressive learning, thus complementing the patch structure information. We also designed a two-stage fusion module, multimodal bilinear pooling (MBP), to assist HST in further fusing multi-receptive field information and combining low-level and high-level semantic information for accurate localization of lesion regions. In addition, we developed adaptive patch embedding (APE) and soft channel attention (SCA) modules to retain more valuable information when acquiring patch embedding and filtering channel features, respectively, thereby improving model segmentation quality. We evaluated HST-MRF on multiple datasets for polyp, skin lesion and breast ultrasound segmentation tasks. Experimental results show that our proposed method outperforms state-of-the-art models and can achieve superior performance. Furthermore, we verified the effectiveness of each module and the benefits of multi-receptive field segmentation in reducing the loss of structural information through ablation experiments and qualitative analysis.

Pulmonary PET /CT image instance segmentation based on dense interactive feature fusion Mask RCNN

There are some problems in positron emission tomography/ computed tomography (PET/CT) lung images, such as little information of feature pixels in lesion regions, complex and diverse shapes, and blurred boundaries between lesions and surrounding tissues, which lead to inadequate extraction of tumor lesion features by the model. To solve the above problems, this paper proposes a dense interactive feature fusion Mask RCNN (DIF-Mask RCNN) model. Firstly, a feature extraction network with cross-scale backbone and auxiliary structures was designed to extract the features of lesions at different scales. Then, a dense interactive feature enhancement network was designed to enhance the lesion detail information in the deep feature map by interactively fusing the shallowest lesion features with neighboring features and current features in the form of dense connections. Finally, a dense interactive feature fusion feature pyramid network (FPN) network was constructed, and the shallow information was added to the deep features one by one in the bottom-up path with dense connections to further enhance the model's perception of weak features in the lesion region. The ablation and comparison experiments were conducted on the clinical PET/CT lung image dataset. The results showed that the APdet, APseg, APdet_s and APseg_s indexes of the proposed model were 67.16%, 68.12%, 34.97% and 37.68%, respectively. Compared with Mask RCNN (ResNet50), APdet and APseg indexes increased by 7.11% and 5.14%, respectively. DIF-Mask RCNN model can effectively detect and segment tumor lesions. It provides important reference value and evaluation basis for computer-aided diagnosis of lung cancer.

TLTNet: A novel transscale cascade layered transformer network for enhanced retinal blood vessel segmentation

Extracting global and local feature information is still challenging due to the problems of retinal blood vessel medical images like fuzzy edge features, noise, difficulty in distinguishing between lesion regions and background information, and loss of low-level feature information, which leads to insufficient extraction of feature information. To better solve these problems and fully extract the global and local feature information of the image, we propose a novel transscale cascade layered transformer network for enhanced retinal blood vessel segmentation, which consists of an encoder and a decoder and is connected between the encoder and decoder by a transscale transformer cascade module. Among them, the encoder consists of a local–global transscale transformer module, a multi-head layered transscale adaptive embedding module, and a local context(LCNet) module. The transscale transformer cascade module learns local and global feature information from the first three layers of the encoder, and multi-scale dependent features, fuses the hierarchical feature information from the skip connection block and the channel-token interaction fusion block, respectively, and inputs it to the decoder. The decoder includes a decoding module for the local context network and a transscale position transformer module to input the local and global feature information extracted from the encoder with retained key position information into the decoding module and the position embedding transformer module for recovery and output of the prediction results that are consistent with the input feature information. In addition, we propose an improved cross-entropy loss function based on the difference between the deterministic observation samples and the prediction results with the deviation distance, which is validated on the DRIVE and STARE datasets combined with the proposed network model based on the dual transformer structure in this paper, and the segmentation accuracies are 97.26% and 97.87%, respectively. Compared with other state-of-the-art networks, the results show that the proposed network model has a significant competitive advantage in improving the segmentation performance of retinal blood vessel images.

Multi-grained contrastive representation learning for label-efficient lesion segmentation and onset time classification of acute ischemic stroke

Ischemic lesion segmentation and the time since stroke (TSS) onset classification from paired multi-modal MRI imaging of unwitnessed acute ischemic stroke (AIS) patients is crucial, which supports tissue plasminogen activator (tPA) thrombolysis decision-making. Deep learning methods demonstrate superiority in TSS classification. However, they often overfit task-irrelevant features due to insufficient paired labeled data, resulting in poor generalization. We observed that unpaired data are readily available and inherently carry task-relevant cues, but are less often considered and explored. Based on this, in this paper, we propose to fully excavate the potential of unpaired unlabeled data and use them to facilitate the downstream AIS analysis task. We first analyze the utility of features at the varied grain and propose a multi-grained contrastive learning (MGCL) framework to learn task-related prior representations from both coarse-grained and fine-grained levels. The former can learn global prior representations to enhance the location ability for the ischemic lesions and perceive the healthy surroundings, while the latter can learn local prior representations to enhance the perception ability for semantic relation between the ischemic lesion and other health regions. To better transfer and utilize the learned task-related representation, we designed a novel multi-task framework to simultaneously achieve ischemic lesion segmentation and TSS classification with limited labeled data. In addition, a multi-modal region-related feature fusion module is proposed to enable the feature correlation and synergy between multi-modal deep image features for more accurate TSS decision-making. Extensive experiments on the large-scale multi-center MRI dataset demonstrate the superiority of the proposed framework. Therefore, it is promising that it helps better stroke evaluation and treatment decision-making.

Adenoid Cystic Carcinoma of the Nasopharynx: A Retrospective Study of 12 Cases.

Objective: This study aimed to describe the experience of a single institution in China in treating adenoid cystic carcinoma of the nasopharynx. Methods: We reviewed the previous literature and conducted a retrospective analysis of 12 patients who diagnosed with nasopharyngeal adenoid cystic carcinoma (NACC) in clinical data, treatment, and follow-up data during 2019 to 2021. Results: Patients ranged in age from 32 to 68 years (mean 40.7 years, median 48.5 years), with a male to female ratio of 5:7. Most of our patients have T4a and T4b diseases (50% and 25%, respectively). A quarter of patients develop distant metastases. Among the 12 patients, 7 of them have positive margins under the microscope (7/12, 58.3%). The chief clinical manifestations were epistaxis, facial swelling, facial pain, headache ear stuffy, and hearing loss. If the tumors involved with cavernous sinus, brain stem infiltrated, and internal carotid artery circumvented, patients will undertake routine enhanced magnetic resonance imaging with Magnetic Resonance Angiography/Magnetic Resonance Venogram (MRA/MRV) to clearly show the lesion region. All patients underwent endoscopic endonasal approach. Fifty percent of patients received radiotherapy and 25% of patients received chemotherapy. None of the patients was lost and the follow-up time ranged from 16 to 45 months. The mean and median follow-up were 2.08 and 1.58 years. Two patients were dead of distant metastasis within 18 and 20 months after the surgery, and another patient with recurrent NACC died of hemorrhage. Conclusion: NACC is a rare malignant tumor that occurs in the nasopharynx, which can grow along the nerve, destroy the bone of the skull base, and metastasize to other organs. Up to now, there is no standard treatment. Our results show that endoscopic sinus surgery is a better choice for advanced or recurrent NACC.

Data-Driven Analysis Reveals Cortical Infarction Patterns Correlated With Inflammation and Prognosis: A Retrospective, Multicenter Cohort Study.

We aim to identify the distinct lesion patterns and regions associated with functional outcome and inflammation in patients with acute ischemic stroke, and investigate whether the association between lesion patterns and functional outcome was mediated by inflammation. We performed nonnegative matrix factorization to derived low-dimensional lesion patterns (atoms), and Bayesian linear regression models were applied to explore the associations of lesion patterns with inflammatory factors including high-sensitivity C-reactive protein and interleukin-6, as well as functional outcome (defined as modified Rankin Scale score at 3 months). The difference distribution mean and 95% highest probability density interval (HPDI) were calculated. Mediation analysis was used to examine the mediating effects of inflammation on the relationships between lesion patterns and functional outcome. Seven lesion patterns were derived from 5914 patients with acute ischemic stroke. Lesion patterns distributed in the cortical regions were associated with inflammatory response, including atom 1 (interleukin-6: mean, 0.113 [95% HPDI, 0.073-0.162]; high-sensitivity C-reactive protein: mean, 0.082 [95% HPDI, 0.038-0.123]) and atom 4 (interleukin-6: mean, 0.113 [95% HPDI, 0.071-0.167]; high-sensitivity C-reactive protein: mean, 0.108 [95% HPDI, 0.058-0.165]). These lesion patterns were also significantly associated with functional outcome (atom 1: mean, 1.958 [95% HPDI, 1.538-2.383]; atom 4: mean, 2.245 [95% HPDI, 1.773-2.741]). Mediation analysis suggested that interleukin-6 explained 15.34% and 7.47% in the association of atom 1 and atom 4 with functional outcome, respectively. Certain lesion patterns that are associated with both inflammation and functional outcome of acute ischemic stroke, especially cortical infarction, may play a role in functional outcome through modulating inflammatory reactions.