Prolonged Electrocardiogram (ECG) monitoring through the Internet of Medical Things (IoMT) is vital for cardiac diagnosis yet generates prohibitive data volumes, posing significant challenges to storage and transmission. However, conventional ECG compression paradigms have plateaued, failing to push compression ratios higher under stringent fidelity constraints. To address these limitations, we propose an end-to-end architecture that synergizes a multi-granularity temporal-convolutional auto-encoder with Residual Vector Quantization (RVQ). The design introduces three complementary components: (1) RVQ integrated in the encoder-decoder pipeline to boost compression ratios; (2) a codebook-projection layer that increases codebook utilization and reconstruction fidelity; (3) periodicity-aware modeling that captures intrinsic ECG dynamics and further suppresses distortion. Extensive experiments on the MIT-BIH Arrhythmia Database show that the proposed method attains a compression ratio of 88× and Quality Score (QS) of 42.7, while keeping the Percentage Root Mean Difference (PRD) at 2.36% and the Percentage Root mean Difference Normalized (PRDN) at 17.56%, clearly surpassing existing techniques. Generalization is further assessed via zero-shot evaluation on the PhysioNet-2017 dataset. Overall, this paper presents an effective end-to-end compression framework, and experimental results corroborate its efficacy.

Using text prompts has been proven helpful in improving medical segmentation performance. However, text-prompted segmentation of the pulmonary infectious areas is a challenging task, for two major reasons: (i) the infected area is prone to misjudgment, resulting in under-segmentation or over-segmentation, (ii) full medical prompts are expensive, especially during real-world during testing, so missing medical note modality often occurs. To address these issues, we propose a new method for Prompt Learning with Missing Modalities for Medical Segmentation (MMPL-Seg). Specifically, based on the UNet-like encoder-decoder framework, we first introduce a Modality Reconstruction and Fusion module (MRF), which is suitable for both complete and incomplete modalities. Based on joint training of two branches of image-only and image-text pairs, this module enables image-only samples to also have latent semantic information in the test phase. In addition, we use the Dynamic Convolution Layer (DyConv) to achieve dynamic fusion of deep image-text features into shallow edge layers. To validate our idea, we conduct a series of experiments on the QaTa-COV19 multi-modality dataset. Experiments on the QaTa-COV19 dataset demonstrated that our model outperforms state-of-the-art approaches under complete and missing modality scenarios, proving its high performance and robustness.