Uni4Eye++: A General Masked Image Modeling Multi-modal Pre-training Framework for Ophthalmic Image Classification and Segmentation.

A large-scale labeled dataset is a key factor for the success of supervised deep learning in most ophthalmic image analysis scenarios. However, limited annotated data is very common in ophthalmic image analysis, since manual annotation is time-consuming and labor-intensive. Self-supervised learning (SSL) methods bring huge opportunities for better utilizing unlabeled data, as they do not require massive annotations. To utilize as many unlabeled ophthalmic images as possible, it is necessary to break the dimension barrier, simultaneously making use of both 2D and 3D images as well as alleviating the issue of catastrophic forgetting. In this paper, we propose a universal self-supervised Transformer framework named Uni4Eye++ to discover the intrinsic image characteristic and capture domain-specific feature embedding in ophthalmic images. Uni4Eye++ can serve as a global feature extractor, which builds its basis on a Masked Image Modeling task with a Vision Transformer architecture. On the basis of our previous work Uni4Eye, we further employ an image entropy guided masking strategy to reconstruct more-informative patches and a dynamic head generator module to alleviate modality confusion. We evaluate the performance of our pre-trained Uni4Eye++ encoder by fine-tuning it on multiple downstream ophthalmic image classification and segmentation tasks. The superiority of Uni4Eye++ is successfully established through comparisons to other state-of-the-art SSL pre-training methods. Our code is available at Github1.

Dual-Targeted Zeolitic Imidazolate Frameworks Drug Delivery System Reversing Cisplatin Resistance to Treat Resistant Ovarian Cancer.

Objective: Ovarian cancer cells are prone to acquire tolerance to chemotherapeutic agents, which seriously affects clinical outcomes. The development of novel strategies to enhance the targeting of chemotherapeutic agents to overcome drug resistance and minimize side effects is significant for improving the clinical outcomes of ovarian cancer patients. Methods: We employed folic acid (FA)-modified ZIF-90 nanomaterials (FA-ZIF-90) to deliver the chemotherapeutic drug, cisplatin (DDP), via dual targeting to improve its targeting to circumvent cisplatin resistance in ovarian cancer cells, especially by targeting mitochondria. FA-ZIF-90/DDP could rapidly release DDP in response to dual stimulation of acidity and ATP in tumor cells. Results: FA-ZIF-90/DDP showed good blood compatibility. It was efficiently taken up by human ovarian cancer cisplatin-resistant cells A2780/DDP and aggregated in the mitochondrial region. FA-ZIF-90/DDP significantly inhibited the mitochondrial activity and metastatic ability of A2780/DDP cells. In addition, it effectively induced apoptosis in A2780/DDP cells and overcame cisplatin resistance. In vivo experiments showed that FA-ZIF-90/DDP increased the accumulation of DDP in tumor tissues and significantly inhibited tumor growth. Conclusion: FA-modified ZIF-90 nanocarriers can improve the tumor targeting and anti-tumor effects of chemotherapeutic drugs, reduce toxic side effects, and are expected to be a novel therapeutic strategy to reverse drug resistance in ovarian cancer.

Chirally Selective and Switchable Luminescence from Achiral Quantum Emitters on Suspended Twisted Stacking Metasurfaces.

Dynamic control of circularly polarized photoluminescence has aroused great interest in quantum optics and nanophotonics. Chiral plasmonic metasurfaces enable the manipulation of the polarization state via plasmon-photon coupling. However, current plasmonic light-emitting metasurfaces for effective deterministic modulation of spin-dependent emission at near-infrared wavelengths are underexplored in terms of dissymmetry and tunability. Here, we demonstrate a microfluidic hybrid emitting system of a suspended twisted stacking metasurface coated with PbS quantum dots. The suspended metasurface is fabricated with a single step of electron beam exposure, exhibiting a strong optical chirality of 309° µm-1 with a thickness of less than λ/10 at key spectral locations. With significant chiral-selective interactions, enhanced photoluminescence is achieved with strong dissymmetry in circular polarization. The dissymmetry factor of the induced circularly polarized emission can reach 1.54. More importantly, altering the refractive index of the surrounding medium at the bottom surface of the metasurface can effectively manipulate the chiroptical responses of the hybrid system, hence leading to chirality-reversed emission. This active hybrid emitting system could be a resultful platform for chirality-switchable light emission from achiral quantum emitters, holding great potential for anticounterfeiting, biosensing, light sources, imaging, and displays.

Multifaceted Carbonized Metal-Organic Frameworks Synergize with Immune Checkpoint Inhibitors for Precision and Augmented Cuproptosis Cancer Therapy.

The discovery of cuproptosis, a copper-dependent mechanism of programmed cell death, has provided a way for cancer treatment. However, cuproptosis has inherent limitations, including potential cellular harm, the lack of targeting, and insufficient efficacy as a standalone treatment. Therefore, exogenously controlled combination treatments have emerged as key strategies for cuproptosis-based oncotherapy. In this study, a Cu2-xSe@cMOF nanoplatform was constructed for combined sonodynamic/cuproptosis/gas therapy. This platform enabled precise cancer cotreatment, with external control allowing the selective induction of cuproptosis in cancer cells. This approach effectively prevented cancer metastasis and recurrence. Furthermore, Cu2-xSe@cMOF was combined with the antiprogrammed cell death protein ligand-1 antibody (aPD-L1), and this combination maximized the advantages of cuproptosis and immune checkpoint therapy. Additionally, under ultrasound irradiation, the H2Se gas generated from Cu2-xSe@cMOF induced cytotoxicity in cancer cells. Further, it generated reactive oxygen species, which hindered cell survival and proliferation. This study reports an externally controlled system for cuproptosis induction that combines a carbonized metal-organic framework with aPD-L1 to enhance cancer treatment. This precision and reinforced cuproptosis cancer therapy platform could be valuable as an effective therapeutic agent to reduce cancer mortality and morbidity in the future.

Deciduous pulp tissue implantation into the root canal of mandibular incisor resulted in pulp revascularization: a case report with a 5-year follow-up.

To explore a new method to implant deciduous tooth pulp into the canal of young permanent teeth with necrotic pulps and apical periodontitis for the regenerative endodontic treatment of tooth no: 41 in a 7-year-old male. Briefly, 1.5% Sodium Hypochlorite (NaOCl) irrigation and calcium hydroxide-iodoform paste were used as root canal disinfectant at the first visit. After 2 weeks, the intracanal medication was removed, and the root canal was slowly rinsed with 17% Ethylene Diamine Tetraacetic Acid (EDTA), followed by flushing with 20 mL saline and then drying with paper points. Tooth no: 72 was extracted, and its pulp was extracted and subsequently implanted into the disinfected root canal along with induced apical bleeding. Calcium hydroxide iodoform paste was gently placed over the bleeding clot, and after forming a mineral trioxide aggregate (MTA) coronal barrier, the accessed cavities were restored using Z350 resin composite. The root developments were evaluated via radiographic imaging at 6 months, 1 year and 5 years after treatment. Imaging and clinical analysis showed closure of the apical foramen, thickening of the root canal wall, and satisfactory root length growth. Autologous transplantation might be useful to regenerate dental pulp in necrotic young permanent teeth.

JOINEDTrans: Prior guided multi-task transformer for joint optic disc/cup segmentation and fovea detection.

Deep learning-based image segmentation and detection models have largely improved the efficiency of analyzing retinal landmarks such as optic disc (OD), optic cup (OC), and fovea. However, factors including ophthalmic disease-related lesions and low image quality issues may severely complicate automatic OD/OC segmentation and fovea detection. Most existing works treat the identification of each landmark as a single task, and take into account no prior information. To address these issues, we propose a prior guided multi-task transformer framework for joint OD/OC segmentation and fovea detection, named JOINEDTrans. JOINEDTrans effectively combines various spatial features of the fundus images, relieving the structural distortions induced by lesions and other imaging issues. It contains a segmentation branch and a detection branch. To be noted, we employ an encoder with prior-learning in a vessel segmentation task to effectively exploit the positional relationship among vessel, OD/OC, and fovea, successfully incorporating spatial prior into the proposed JOINEDTrans framework. There are a coarse stage and a fine stage in JOINEDTrans. In the coarse stage, OD/OC coarse segmentation and fovea heatmap localization are obtained through a joint segmentation and detection module. In the fine stage, we crop regions of interest for subsequent refinement and use predictions obtained in the coarse stage to provide additional information for better performance and faster convergence. Experimental results demonstrate that JOINEDTrans outperforms existing state-of-the-art methods on the publicly available GAMMA, REFUGE, and PALM fundus image datasets. We make our code available at https://github.com/HuaqingHe/JOINEDTrans.

MyoFold: Joint myocardial tissue composition and wall motion quantification via a highly folded sequence.

PURPOSE: This study aims to develop and evaluate a novel cardiovascular MR sequence, MyoFold, designed for the simultaneous quantifications of myocardial tissue composition and wall motion. METHODS: MyoFold is designed as a 2D single breathing-holding sequence, integrating joint T1/T2 mapping and cine imaging. The sequence uses a 2-fold accelerated balanced SSFP (bSSFP) for data readout and incorporates electrocardiogram synchronization to align with the cardiac cycle. MyoFold initially acquires six single-shot inversion-recovery images, completed during the diastole of six successive heartbeats. T2 preparation (T2-prep) is applied to introduce T2 weightings for the last three images. Subsequently, over the following six heartbeats, segmented bSSFP is performed for the movie of the entire cardiac cycle, synchronized with an electrocardiogram. A neural network trained using numerical simulations of MyoFold is used for T1 and T2 calculations. MyoFold was validated through phantom and in vivo experiments, with comparisons made against MOLLI, SASHA, T2-prep bSSFP, and the conventional cine. RESULTS: In phantom studies, MyoFold exhibited a 10% overestimation in T1 measurements, whereas T2 measurements demonstrated high accuracy. In vivo experiments revealed that MyoFold T1 had comparable accuracy to SASHA and precision similar to MOLLI. MyoFold demonstrated good agreement with T2-prep bSSFP in myocardial T2 measurements. No significant differences were observed in the quantification of left-ventricle wall thickness and function between MyoFold and the conventional cine. CONCLUSION: MyoFold presents as a rapid, simple, and multitasking approach for quantitative cardiovascular MR examinations, offering simultaneous assessment of tissue composition and wall motion. The sequence's multitasking capabilities make it a promising tool for comprehensive cardiac evaluations in clinical settings.

Carbon-based Nanomaterials in Photothermal Therapy Guided by Photoacoustic Imaging: State of Knowledge and Recent Advances.

Carbon-based nanomaterials (CBNM)have been widely used in various fields due to their excellent physicochemical properties. In particular, in the area of tumor diagnosis and treatment, researchers have frequently reported them for their potential fluorescence, photoacoustic (PA), and ultrasound imaging performance, as well as their photothermal, photodynamic, sonodynamic, and other therapeutic properties. As the functions of CBNM are increasingly developed, their excellent imaging properties and superior tumor treatment effects make them extremely promising theranostic agents. This review aims to integrate the considered and researched information in a specific field of this research topic and systematically present, summarize, and comment on the efforts made by authoritative scholars. In this review, we summarized the work exploring carbon-based materials in the field of tumor imaging and therapy, focusing on PA imaging-guided photothermal therapy (PTT) and discussing their imaging and therapeutic mechanisms and developments. Finally, the current challenges and potential opportunities of carbon-based materials for PA imaging-guided PTT are presented, and issues that researchers should be aware of when studying CBNM are provided.

SSiT: Saliency-Guided Self-Supervised Image Transformer for Diabetic Retinopathy Grading.

Self-supervised Learning (SSL) has been widely applied to learn image representations through exploiting unlabeled images. However, it has not been fully explored in the medical image analysis field. In this work, Saliency-guided Self-Supervised image Transformer (SSiT) is proposed for Diabetic Retinopathy (DR) grading from fundus images. We novelly introduce saliency maps into SSL, with a goal of guiding self-supervised pre-training with domain-specific prior knowledge. Specifically, two saliency-guided learning tasks are employed in SSiT: 1) Saliency-guided contrastive learning is conducted based on the momentum contrast, wherein fundus images' saliency maps are utilized to remove trivial patches from the input sequences of the momentum-updated key encoder. Thus, the key encoder is constrained to provide target representations focusing on salient regions, guiding the query encoder to capture salient features. 2) The query encoder is trained to predict the saliency segmentation, encouraging the preservation of fine-grained information in the learned representations. To assess our proposed method, four publicly-accessible fundus image datasets are adopted. One dataset is employed for pre-training, while the three others are used to evaluate the pre-trained models' performance on downstream DR grading. The proposed SSiT significantly outperforms other representative state-of-the-art SSL methods on all downstream datasets and under various evaluation settings. For example, SSiT achieves a Kappa score of 81.88% on the DDR dataset under fine-tuning evaluation, outperforming all other ViT-based SSL methods by at least 9.48%.

The State-of-the-Art and Perspectives of Laser Ablation for Tumor Treatment.

Tumors significantly impact individuals' physical well-being and quality of life. With the ongoing advancements in optical technology, information technology, robotic technology, etc., laser technology is being increasingly utilized in the field of tumor treatment, and laser ablation (LA) of tumors remains a prominent area of research interest. This paper presents an overview of the recent progress in tumor LA therapy, with a focus on the mechanisms and biological effects of LA, commonly used ablation lasers, image-guided LA, and robotic-assisted LA. Further insights and future prospects are discussed in relation to these aspects, and the paper proposed potential future directions for the development of tumor LA techniques.

The LMIT: Light-mediated minimally-invasive theranostics in oncology.

Minimally-invasive diagnosis and therapy have gradually become the trend and research hotspot of current medical applications. The integration of intraoperative diagnosis and treatment is a development important direction for real-time detection, minimally-invasive diagnosis and therapy to reduce mortality and improve the quality of life of patients, so called minimally-invasive theranostics (MIT). Light is an important theranostic tool for the treatment of cancerous tissues. Light-mediated minimally-invasive theranostics (LMIT) is a novel evolutionary technology that integrates diagnosis and therapeutics for the less invasive treatment of diseased tissues. Intelligent theranostics would promote precision surgery based on the optical characterization of cancerous tissues. Furthermore, MIT also requires the assistance of smart medical devices or robots. And, optical multimodality lay a solid foundation for intelligent MIT. In this review, we summarize the important state-of-the-arts of optical MIT or LMIT in oncology. Multimodal optical image-guided intelligent treatment is another focus. Intraoperative imaging and real-time analysis-guided optical treatment are also systemically discussed. Finally, the potential challenges and future perspectives of intelligent optical MIT are discussed.

Simultaneous alignment and surface regression using hybrid 2D-3D networks for 3D coherent layer segmentation of retinal OCT images with full and sparse annotations.

Layer segmentation is important to quantitative analysis of retinal optical coherence tomography (OCT). Recently, deep learning based methods have been developed to automate this task and yield remarkable performance. However, due to the large spatial gap and potential mismatch between the B-scans of an OCT volume, all of them were based on 2D segmentation of individual B-scans, which may lose the continuity and diagnostic information of the retinal layers in 3D space. Besides, most of these methods required dense annotation of the OCT volumes, which is labor-intensive and expertise-demanding. This work presents a novel framework based on hybrid 2D-3D convolutional neural networks (CNNs) to obtain continuous 3D retinal layer surfaces from OCT volumes, which works well with both full and sparse annotations. The 2D features of individual B-scans are extracted by an encoder consisting of 2D convolutions. These 2D features are then used to produce the alignment displacement vectors and layer segmentation by two 3D decoders coupled via a spatial transformer module. Two losses are proposed to utilize the retinal layers' natural property of being smooth for B-scan alignment and layer segmentation, respectively, and are the key to the semi-supervised learning with sparse annotation. The entire framework is trained end-to-end. To the best of our knowledge, this is the first work that attempts 3D retinal layer segmentation in volumetric OCT images based on CNNs. Experiments on a synthetic dataset and three public clinical datasets show that our framework can effectively align the B-scans for potential motion correction, and achieves superior performance to state-of-the-art 2D deep learning methods in terms of both layer segmentation accuracy and cross-B-scan 3D continuity in both fully and semi-supervised settings, thus offering more clinical values than previous works.

Toward hippocampal volume measures on ultra-high field magnetic resonance imaging: a comprehensive comparison study between deep learning and conventional approaches.

The hippocampus is a complex brain structure that plays an important role in various cognitive aspects such as memory, intelligence, executive function, and path integration. The volume of this highly plastic structure is identified as one of the most important biomarkers of specific neuropsychiatric and neurodegenerative diseases. It has also been extensively investigated in numerous aging studies. However, recent studies on aging show that the performance of conventional approaches in measuring the hippocampal volume is still far from satisfactory, especially in terms of delivering longitudinal measures from ultra-high field magnetic resonance images (MRIs), which can visualize more boundary details. The advancement of deep learning provides an alternative solution to measuring the hippocampal volume. In this work, we comprehensively compared a deep learning pipeline based on nnU-Net with several conventional approaches including Freesurfer, FSL and DARTEL, for automatically delivering hippocampal volumes: (1) Firstly, we evaluated the segmentation accuracy and precision on a public dataset through cross-validation. Results showed that the deep learning pipeline had the lowest mean (L = 1.5%, R = 1.7%) and the lowest standard deviation (L = 5.2%, R = 6.2%) in terms of volume percentage error. (2) Secondly, sub-millimeter MRIs of a group of healthy adults with test-retest 3T and 7T sessions were used to extensively assess the test-retest reliability. Results showed that the deep learning pipeline achieved very high intraclass correlation coefficients (L = 0.990, R = 0.986 for 7T; L = 0.985, R = 0.983 for 3T) and very small volume percentage differences (L = 1.2%, R = 0.9% for 7T; L = 1.3%, R = 1.3% for 3T). (3) Thirdly, a Bayesian linear mixed effect model was constructed with respect to the hippocampal volumes of two healthy adult datasets with longitudinal 7T scans and one disease-related longitudinal dataset. It was found that the deep learning pipeline detected both the subtle and disease-related changes over time with high sensitivity as well as the mild differences across subjects. Comparison results from the aforementioned three aspects showed that the deep learning pipeline significantly outperformed the conventional approaches by large margins. Results also showed that the deep learning pipeline can better accommodate longitudinal analysis purposes.

Stroke analysis and recognition in functional near-infrared spectroscopy signals using machine learning methods.

Stroke is a high-incidence disease with high disability and mortality rates. It is a serious public health problem worldwide. Shortened onset-to-image time is very important for the diagnosis and treatment of stroke. Functional near-infrared spectroscopy (fNIRS) is a noninvasive monitoring tool with real-time, noninvasive, and convenient features. In this study, we propose an automatic classification framework based on cerebral oxygen saturation signals to identify patients with hemorrhagic stroke, patients with ischemic stroke, and normal subjects. The reflected fNIRS signals were used to detect the cerebral oxygen saturation and the relative value of oxygen and deoxyhemoglobin concentrations of the left and right frontal lobes. The wavelet time-frequency analysis-based features from these signals were extracted. Such features were used to analyze the differences in cerebral oxygen saturation signals among different types of stroke patients and healthy humans and were selected to train the machine learning models. Furthermore, an important analysis of the features was performed. The accuracy of the models trained was greater than 85%, and the accuracy of the models after data augmentation was greater than 90%, which is of great significance in distinguishing patients with hemorrhagic stroke or ischemic stroke. This framework has the potential to shorten the onset-to-diagnosis time of stroke.

The effects of cocaine use severity and abstinence on behavioral performance and neural processes of response inhibition.

Previous studies identified cerebral markers of response inhibition dysfunction in cocaine dependence. However, whether deficits in response inhibition vary with the severity of cocaine use or ameliorate during abstinence remain unclear. This study aimed to address these issues and the neural mechanisms supporting the individual variation. We examined the data of 67 individuals with cocaine dependence (CD) and 84 healthy controls (HC) who underwent functional magnetic resonance imaging during a stop-signal task (SST). The stop-signal reaction time (SSRT) was computed using the integration method, with a longer SSRT indicating poorer response inhibition. The results showed that, while CD and HC did not differ significantly in SSRT, years of cocaine use (YOC) and days of abstinence (DOA) were each positively and negatively correlated with the SSRT in CD. Whole-brain regressions of stop minus go success trials on SSRT revealed correlates in bilateral superior temporal gyrus (STG) in response inhibition across CD and HC. Further, mediation and path analyses revealed that YOC and DOA affected SSRT through the STG activities in CD. Together, the findings characterized the contrasting effects of cocaine use severity and abstinence on response inhibition as well as the neural processes that support these effects in cocaine dependence.

GAMMA challenge: Glaucoma grAding from Multi-Modality imAges.

Glaucoma is a chronic neuro-degenerative condition that is one of the world's leading causes of irreversible but preventable blindness. The blindness is generally caused by the lack of timely detection and treatment. Early screening is thus essential for early treatment to preserve vision and maintain life quality. Colour fundus photography and Optical Coherence Tomography (OCT) are the two most cost-effective tools for glaucoma screening. Both imaging modalities have prominent biomarkers to indicate glaucoma suspects, such as the vertical cup-to-disc ratio (vCDR) on fundus images and retinal nerve fiber layer (RNFL) thickness on OCT volume. In clinical practice, it is often recommended to take both of the screenings for a more accurate and reliable diagnosis. However, although numerous algorithms are proposed based on fundus images or OCT volumes for the automated glaucoma detection, there are few methods that leverage both of the modalities to achieve the target. To fulfil the research gap, we set up the Glaucoma grAding from Multi-Modality imAges (GAMMA) Challenge to encourage the development of fundus & OCT-based glaucoma grading. The primary task of the challenge is to grade glaucoma from both the 2D fundus images and 3D OCT scanning volumes. As part of GAMMA, we have publicly released a glaucoma annotated dataset with both 2D fundus colour photography and 3D OCT volumes, which is the first multi-modality dataset for machine learning based glaucoma grading. In addition, an evaluation framework is also established to evaluate the performance of the submitted methods. During the challenge, 1272 results were submitted, and finally, ten best performing teams were selected for the final stage. We analyse their results and summarize their methods in the paper. Since all the teams submitted their source code in the challenge, we conducted a detailed ablation study to verify the effectiveness of the particular modules proposed. Finally, we identify the proposed techniques and strategies that could be of practical value for the clinical diagnosis of glaucoma. As the first in-depth study of fundus & OCT multi-modality glaucoma grading, we believe the GAMMA Challenge will serve as an essential guideline and benchmark for future research.

YoloCurvSeg: You only label one noisy skeleton for vessel-style curvilinear structure segmentation.

Weakly-supervised learning (WSL) has been proposed to alleviate the conflict between data annotation cost and model performance through employing sparsely-grained (i.e., point-, box-, scribble-wise) supervision and has shown promising performance, particularly in the image segmentation field. However, it is still a very challenging task due to the limited supervision, especially when only a small number of labeled samples are available. Additionally, almost all existing WSL segmentation methods are designed for star-convex structures which are very different from curvilinear structures such as vessels and nerves. In this paper, we propose a novel sparsely annotated segmentation framework for curvilinear structures, named YoloCurvSeg. A very essential component of YoloCurvSeg is image synthesis. Specifically, a background generator delivers image backgrounds that closely match the real distributions through inpainting dilated skeletons. The extracted backgrounds are then combined with randomly emulated curves generated by a Space Colonization Algorithm-based foreground generator and through a multilayer patch-wise contrastive learning synthesizer. In this way, a synthetic dataset with both images and curve segmentation labels is obtained, at the cost of only one or a few noisy skeleton annotations. Finally, a segmenter is trained with the generated dataset and possibly an unlabeled dataset. The proposed YoloCurvSeg is evaluated on four publicly available datasets (OCTA500, CORN, DRIVE and CHASEDB1) and the results show that YoloCurvSeg outperforms state-of-the-art WSL segmentation methods by large margins. With only one noisy skeleton annotation (respectively 0.14%, 0.03%, 1.40%, and 0.65% of the full annotation), YoloCurvSeg achieves more than 97% of the fully-supervised performance on each dataset. Code and datasets will be released at https://github.com/llmir/YoloCurvSeg.

CHSNet: Automatic lesion segmentation network guided by CT image features for acute cerebral hemorrhage.

Stroke is a cerebrovascular disease that can lead to severe sequelae such as hemiplegia and mental retardation with a mortality rate of up to 40%. In this paper, we proposed an automatic segmentation network (CHSNet) to segment the lesions in cranial CT images based on the characteristics of acute cerebral hemorrhage images, such as high density, multi-scale, and variable location, and realized the three-dimensional (3D) visualization and localization of the cranial lesions after the segmentation was completed. To enhance the feature representation of high-density regions, and capture multi-scale and up-down information on the target location, we constructed a convolutional neural network with encoding-decoding backbone, Res-RCL module, Atrous Spatial Pyramid Pooling, and Attention Gate. We collected images of 203 patients with acute cerebral hemorrhage, constructed a dataset containing 5998 cranial CT slices, and conducted comparative and ablation experiments on the dataset to verify the effectiveness of our model. Our model achieved the best results on both test sets with different segmentation difficulties, test1: Dice = 0.918, IoU = 0.853, ASD = 0.476, RVE = 0.113; test2: Dice = 0.716, IoU = 0.604, ASD = 5.402, RVE = 1.079. Based on the segmentation results, we achieved 3D visualization and localization of hemorrhage in CT images of stroke patients. The study has important implications for clinical adjuvant diagnosis.