paper-with-me

홈 › Papers

False Negative/Positive Control for SAM on Noisy Medical Images

2023-08-20 · Xing Yao, Han Liu, Dewei Hu, Daiwei Lu, Ange Lou, Hao Li, Ruining Deng, Gabriel Arenas, Baris Oguz, Nadav Schwartz, Brett C Byram, Ipek Oguz

The Segment Anything Model (SAM) is a recently developed all-range foundation model for image segmentation. It can use sparse manual prompts such as bounding boxes to generate pixel-level segmentation in natural images but struggles in medical images such as low-contrast, noisy ultrasound images. We propose a refined test-phase prompt augmentation technique designed to improve SAM's performance in medical image segmentation. The method couples multi-box prompt augmentation and an aleatoric uncertainty-based false-negative (FN) and false-positive (FP) correction (FNPC) strategy. We evaluate the method on two ultrasound datasets and show improvement in SAM's performance and robustness to inaccurate prompts, without the necessity for further training or tuning. Moreover, we present the Single-Slice-to-Volume (SS2V) method, enabling 3D pixel-level segmentation using only the bounding box annotation from a single 2D slice. Our results allow efficient use of SAM in even noisy, low-contrast medical images. The source code will be released soon.

📄 PDF Abstract BibTeX arXiv:2308.10382

Code (1)

xyimaging/fnpc 공식 구현 pytorch

Tasks

Image SegmentationMedical Image SegmentationSegmentationSemantic Segmentation

Methods 이 논문이 사용한 방법론

SAM 설명 없음

Similar Papers 제목 키워드 기반

Risk-Aware Robust Learning: Reducing Clinical Risk under Label Noise in Medical Image Classification

2026-04-26 · Maycon R. S. Pereira, Filipe R. Cordeiro arxiv

Noisy labels are a pervasive challenge in medical image classification, where annotation errors arise from inter-observer variability and diagnostic ambiguity. Although several noise-robust learning methods have been pro…

Medical Image ClassificationMedical Diagnosis

Noisy Positive-Unlabeled Learning with Self-Training for Speculative Knowledge Graph Reasoning

2023-06-13 · Ruijie Wang, Baoyu Li, Yichen Lu, Dachun Sun 외

This paper studies speculative reasoning task on real-world knowledge graphs (KG) that contain both \textit{false negative issue} (i.e., potential true facts being excluded) and \textit{false positive issue} (i.e., unrel…

Knowledge GraphsWorld Knowledge

Contrastive Language Prompting to Ease False Positives in Medical Anomaly Detection

2024-11-12 · YeongHyeon Park, Myung Jin Kim, Hyeong Seok Kim

A pre-trained visual-language model, contrastive language-image pre-training (CLIP), successfully accomplishes various downstream tasks with text prompts, such as finding images or localizing regions within the image. De…

Anomaly DetectionLanguage ModelingLanguage Modelling

Revisiting the Negative Data of Distantly Supervised Relation Extraction

2021-05-21 · ACL 2021 5 · Chenhao Xie, Jiaqing Liang, Jingping Liu, Chengsong Huang 외

Distantly supervision automatically generates plenty of training samples for relation extraction. However, it also incurs two major problems: noisy labels and imbalanced training data. Previous works focus more on reduci…

RelationRelation ExtractionSentence

Cross-modal Retrieval with Noisy Correspondence via Consistency Refining and Mining

2024-03-25 · IEEE Transactions on Image Processing 2024 3 · Xinran Ma, Mouxing Yang, Yunfan Li, Peng Hu 외

The success of existing cross-modal retrieval (CMR) methods heavily rely on the assumption that the annotated cross-modal correspondence is faultless. In practice, however, the correspondence of some pairs would be inevi…

Cross-Modal RetrievalCross-modal retrieval with noisy correspondenceGraph MatchingRetrieval