The field of ultrasound imaging and analysis is experiencing significant advancements, driven by innovative approaches in probe pose estimation, image segmentation, and machine learning. Researchers are exploring cost-effective and versatile solutions for precise 3D ultrasound imaging, such as leveraging lightweight cameras and visual servoing in simulated environments. Additionally, weakly supervised segmentation frameworks are being developed to reduce the burden of extensive pixel-level annotations, achieving performance comparable to fully supervised counterparts. The integration of clinician-in-the-loop AI pipelines is also enhancing reproducibility, prognostic accuracy, and clinical trust in lung cancer CT-based prognosis. Noteworthy papers include: Freehand 3D Ultrasound Imaging: Sim-in-the-Loop Probe Pose Optimization via Visual Servoing, which proposes a cost-effective solution for precise 3D US imaging. Uncertainty-Aware Extreme Point Tracing for Weakly Supervised Ultrasound Image Segmentation, which achieves performance comparable to fully supervised counterparts while reducing annotation cost. Click, Predict, Trust: Clinician-in-the-Loop AI Segmentation for Lung Cancer CT-Based Prognosis, which develops a clinician-in-the-loop DL pipeline to enhance reproducibility and prognostic accuracy. ZACH-ViT: A Zero-Token Vision Transformer with ShuffleStrides Data Augmentation for Robust Lung Ultrasound Classification, which introduces a novel Vision Transformer variant for robust lung ultrasound classification. Towards Objective Obstetric Ultrasound Assessment: Contrastive Representation Learning for Fetal Movement Detection, which proposes a self-supervised learning framework for fetal movement detection. Dynamic Weight Adjustment for Knowledge Distillation: Leveraging Vision Transformer for High-Accuracy Lung Cancer Detection and Real-Time Deployment, which presents a novel approach for lung cancer classification using dynamic fuzzy logic-driven knowledge distillation.