To address the challenges faced by current brain midline segmentation techniques, such as insufficient accuracy and poor segmentation continuity, this paper proposes a deep learning network model based on a two-stage framework. On the first stage of the model, prior knowledge of the feature consistency of adjacent brain midline slices under normal and pathological conditions is utilized. Associated midline slices are selected through slice similarity analysis, and a novel feature weighting strategy is adopted to collaboratively fuse the overall change characteristics and spatial information of these associated slices, thereby enhancing the feature representation of the brain midline in the intracranial region. On the second stage, the optimal path search strategy for the brain midline is employed based on the network output probability map, which effectively addresses the problem of discontinuous midline segmentation. The method proposed in this paper achieved satisfactory results on the CQ500 dataset provided by the Center for Advanced Research in Imaging, Neurosciences and Genomics, New Delhi, India. The Dice similarity coefficient (DSC), Hausdorff distance (HD), average symmetric surface distance (ASSD), and normalized surface Dice (NSD) were 67.38 ± 10.49, 24.22 ± 24.84, 1.33 ± 1.83, and 0.82 ± 0.09, respectively. The experimental results demonstrate that the proposed method can fully utilize the prior knowledge of medical images to effectively achieve accurate segmentation of the brain midline, providing valuable assistance for subsequent identification of the brain midline by clinicians.
Automatic classification of medical questions is of great significance in improving the quality and efficiency of online medical services, and belongs to the task of intent recognition. Joint entity recognition and intent recognition perform better than single task models. Currently, most publicly available medical text intent recognition datasets lack entity annotation, and manual annotation of these entities requires a lot of time and manpower. To solve this problem, this paper proposes a medical text classification model, bidirectional encoder representation based on transformer-recurrent convolutional neural network-entity-label-semantics (BRELS), which integrates medical entity label semantics. This model firstly utilizes an adaptive fusion mechanism to absorb prior knowledge of medical entity labels, achieving local feature enhancement. Then in global feature extraction, a lightweight recurrent convolutional neural network (LRCNN) is used to suppress parameter growth while preserving the original semantics of the text. The ablation and comparison experiments are conducted on three public medical text intent recognition datasets to validate the performance of the model. The results show that F1 score reaches 87.34%, 81.71%, and 77.74% on each dataset, respectively. The results show that the BRELS model can effectively identify and understand medical terminology, thereby effectively identifying users’ intentions, which can improve the quality and efficiency of online medical services.
Magnetic resonance imaging plays a crucial role in the diagnosis and management of ischemic stroke. Accurate segmentation of stroke lesions holds significant clinical value in assisting the formulation of individualized interventional treatment plans and objectively assessing patient prognosis. To address the challenges of blurred and irregularly shaped ischemic stroke lesions with random locations, this study proposes a prior knowledge-guided and multi-level edge feature fusion shifted window Transformer-based U-Net with encoder representations (PMSwin UNETR). First, based on the distribution characteristics of stroke lesions, a lesion distribution probability map is generated to guide the segmentation network in focusing on areas prone to lesions. Second, a multi-level edge feature extraction module is employed to enrich edge features. Finally, a soft-clDice loss function is introduced to directly learn lesion boundaries, enhancing edge segmentation accuracy. The effectiveness of PMSwin UNETR was validated using the 2022 Ischemic Stroke Lesion Segmentation Challenge (ISLES2022) dataset, with results showing Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and recall rates of 82.43%, 3.768 8, and 82.45%, respectively, outperforming other mainstream segmentation algorithms. This study demonstrates that the proposed PMSwin UNETR model effectively improves ischemic stroke lesion segmentation, providing important references and application value for precise clinical diagnosis and intelligent medical imaging research in stroke.