RESUMEN
This article aims to solve the video object segmentation (VOS) task in a scribble-supervised manner, in which VOS models are not only initialized with sparse target scribbles for inference but also trained by sparse scribble annotations. Thus, the annotation burdens for both initialization and training can be substantially lightened. The difficulties of scribble-supervised VOS lie in two aspects: 1) it demands a strong reasoning ability to carefully segment the target given only a sparse initial target scribble and 2) it necessitates learning dense prediction from sparse scribble annotations during training, requiring powerful learning capability. In this work, we propose a reliability-guided hierarchical memory network (RHMNet) for this task, which segments the target in a stepwise expanding strategy w.r.t. the memory reliability level. To be specific, RHMNet maintains a reliability-guided memory bank. It first uses the high-reliability memory to locate the region with high reliability belonging to the target, i.e., highly similar to the initial target scribble. Then, it expands the located high-reliability region to the entire target conditioned on the region itself and all existing memories. In addition, we propose a scribble-supervised learning mechanism to facilitate the model learning for dense prediction. It exploits the pixel-level relations within a single frame and the instance-level variations across multiple frames to take full advantage of the scribble annotations in sequence training samples. The favorable performance on four popular benchmarks demonstrates that our method is promising. Our project is available at: https://github.com/mkg1204/RHMNet-for-SSVOS.
RESUMEN
Estrogen receptor ß (ERß) plays critical roles in thyroid cancer progression. However, its role in thyroid cancer stem cell maintenance remains elusive. Here, we report that ERß is overexpressed in papillary thyroid cancer stem cells (PTCSCs), whereas ablation of ERß decreases stemness-related factors expression, diminishes ALDH+ cell populations, and suppresses sphere formation ability and tumor growth. Screening estrogen-responsive lncRNAs in PTC spheroid cells, we find that lncRNA-H19 is highly expressed in PTCSCs and PTC tissue specimens, which is correlated with poor overall survival. Mechanistically, estradiol (E2) significantly promotes H19 transcription via ERß and elevates H19 expression. Silencing of H19 inhibits E2-induced sphere formation ability. Furthermore, H19 acting as a competitive endogenous RNA sequesters miRNA-3126-5p to reciprocally release ERß expression. ERß depletion reverses H19-induced stem-like properties upon E2 treatment. Appropriately, ERß is upregulated in PTC tissue specimens. Notably, aspirin attenuates E2-induced cancer stem-like traits through decreasing both H19 and ERß expression. Collectively, our findings reveal that ERß-H19 positive feedback loop has a compelling role in PTCSC maintenance under E2 treatment and provides a potential therapeutic targeting strategy for PTC.