{"ID":2851989,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.18213","arxiv_id":"2510.18213","title":"EMA-SAM: Exponential Moving-average for SAM-based PTMC Segmentation","abstract":"Papillary thyroid microcarcinoma (PTMC) is increasingly managed with radio-frequency ablation (RFA), yet accurate lesion segmentation in ultrasound videos remains difficult due to low contrast, probe-induced motion, and heat-related artifacts. The recent Segment Anything Model 2 (SAM-2) generalizes well to static images, but its frame-independent design yields unstable predictions and temporal drift in interventional ultrasound. We introduce \\textbf{EMA-SAM}, a lightweight extension of SAM-2 that incorporates a confidence-weighted exponential moving average pointer into the memory bank, providing a stable latent prototype of the tumour across frames. This design preserves temporal coherence through probe pressure and bubble occlusion while rapidly adapting once clear evidence reappears. On our curated PTMC-RFA dataset (124 minutes, 13 patients), EMA-SAM improves \\emph{maxDice} from 0.82 (SAM-2) to 0.86 and \\emph{maxIoU} from 0.72 to 0.76, while reducing false positives by 29\\%. On external benchmarks, including VTUS and colonoscopy video polyp datasets, EMA-SAM achieves consistent gains of 2--5 Dice points over SAM-2. Importantly, the EMA pointer adds \\textless0.1\\% FLOPs, preserving real-time throughput of $\\sim$30\\,FPS on a single A100 GPU. These results establish EMA-SAM as a robust and efficient framework for stable tumour tracking, bridging the gap between foundation models and the stringent demands of interventional ultrasound. Codes are available here \\hyperref[code {https://github.com/mdialameh/EMA-SAM}.","short_abstract":"Papillary thyroid microcarcinoma (PTMC) is increasingly managed with radio-frequency ablation (RFA), yet accurate lesion segmentation in ultrasound videos remains difficult due to low contrast, probe-induced motion, and heat-related artifacts. The recent Segment Anything Model 2 (SAM-2) generalizes well to static image...","url_abs":"https://arxiv.org/abs/2510.18213","url_pdf":"https://arxiv.org/pdf/2510.18213v1","authors":"[\"Maryam Dialameh\",\"Hossein Rajabzadeh\",\"Jung Suk Sim\",\"Hyock Ju Kwon\"]","published":"2025-10-21T01:30:27Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":607948,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2851989,"paper_url":"https://arxiv.org/abs/2510.18213","paper_title":"EMA-SAM: Exponential Moving-average for SAM-based PTMC Segmentation","repo_url":"https://github.com/mdialameh/EMA-SAM","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}