Intracerebral hemorrhage (ICH) is a life-threatening stroke that requires precise segmentation for effective treatment. To aid in diagnosing ICH, various deep learning-based methods have been proposed. However, these methods face challenges posed by irregular patterns and low-contrast boundaries in ICH images. In this paper, we introduce a novel conditional diffusion-based segmentation approach for ICH segmentation. Our framework leverages ResNet18 and a Transformer Block to enhance conditional feature extraction, as well as cross-attention mechanisms to align global and local features between the conditional and diffusion branches. Experiment results on the Instance2022 dataset show an improvement exceeding 10% in the Dice coefficient and IoU score, compared to the baseline diffusion-based model, MedSegDiffv2. More impressively, more than 20% improvement is achieved in terms of both the Dice coefficient and IoU score in cross-dataset evaluations on two benchmarks, i.e., the BHSD and PhysioNet, demonstrating excellent generalizability to unseen data.

Gait speed is an important indicator of human health. Monitoring patients' gait speed can help doctors assess the recovery process, but traditional clinician observation fails to track in home scenarios. Compared to vision-based and wearable approaches, radio frequency signals offer an easily deployable and light free solution protecting user privacy in home scenarios. Therefore, we proposed a millimeter-wave (mmWave) system to accurately extract walking periods from collected trials and calculate gait speeds. To evaluate the robustness and reliability of our system and determine the optimal mounting position, we collected data from 5 volunteers with normal walking speeds and imitated various abnormal gait patterns and walking speeds. The results show that the mmWave device mounted near the ground outperforms across all volunteers than the one mounted near the ceiling, achieving an average estimation error of 0.02 m/s in abnormal gait evaluations.

Object detection plays a pivotal role in various fields, for example, a smart traffic system relies on the detected results for decision-making. However, existing studies predominately utilize optical camera and LiDAR, which exhibit limitations in adverse outdoor environments, such as foggy weather. To address these challenges, millimeter-waves (mmWaves) attract researchers’ attention to detect objects in severe conditions since they can work effectively in low-visibility conditions and overcome small obstacles. Yet, previous mmWave-based works have shown limited performance, such as no shape information for objects. Therefore, we design and implement a two-stage system, mmBox , to accurately predict bounding boxes with depth for vehicles and pedestrians, which first generates heatmaps in different dimensions and then leverages a deep learning model to extract features for predictions. To evaluate the performance of mmBox , we collected real-world mmWave reflections from urban traffic intersections and dense-fog environments. The extensive evaluation metrics show remarkable accuracy and the low latency of our model.

Millimeter-wave technology's unique advantages, in-cluding low-light functionality, cost-effectiveness, and penetration of small objects, make it perfect for outdoor object detection. But traditional methods like likelihood clustering have faced challenges in determining target objects' extent and distance. This work presents mmBox, a two-stage system tailored for precise bounding boxes of vehicles and pedestrians outdoors. We assess mmBox's effectiveness through extensive testing in outdoor street scenes using multiple metrics.

Millimeter wave (mmWave) 3D imaging has been applied for point cloud data (PCD) generation due to its valuable attributes, such as working under low light, compact size, and low-cost. However, past works have focused on transforming millimeter wave reflection signals into other data structures, like polar images and coarse PCDs before applying neural network to produce dense PCDs. Those algorithms will filter some useful features. To address this issue, our paper proposes an innovative prototype: mmWaveNet, a deep learning model that directly uses reflection signals as input and generates high-quality PCDs. We have experimentally evaluated mmWaveNet in a large indoor environment.