The Segment Anything Model (SAM) is a recently proposed prompt-based segmentation model in a generic zero-shot segmentation approach. With the zero-shot segmentation capacity, SAM achieved impressive flexibility and precision on various segmentation tasks. However, the current pipeline requires manual prompts during the inference stage, which is still resource intensive for biomedical image segmentation. In this paper, instead of using prompts during the inference stage, we introduce a pipeline that utilizes the SAM, called all-in-SAM, through the entire AI development workflow (from annotation generation to model finetuning) without requiring manual prompts during the inference stage. Specifically, SAM is first employed to generate pixel-level annotations from weak prompts (e.g., points, bounding box). Then, the pixel-level annotations are used to finetune the SAM segmentation model rather than training from scratch. Our experimental results reveal two key findings: 1) the proposed pipeline surpasses the state-of-the-art (SOTA) methods in a nuclei segmentation task on the public Monuseg dataset, and 2) the utilization of weak and few annotations for SAM finetuning achieves competitive performance compared to using strong pixel-wise annotated data.
more »
« less
Segment Anything Model (SAM) for Digital Pathology: Assess Zero-shot Segmentation on Whole Slide Imaging
The segment anything model (SAM) was released as a foundation model for image segmentation. The promptable segmentation model was trained by over 1 billion masks on 11M licensed and privacy-respecting images. The model supports zero-shot image segmentation with various seg- mentation prompts (e.g., points, boxes, masks). It makes the SAM attractive for medical image analysis, especially for digital pathology where the training data are rare. In this study, we eval- uate the zero-shot segmentation performance of SAM model on representative segmentation tasks on whole slide imaging (WSI), including (1) tumor segmentation, (2) non-tumor tissue segmen- tation, (3) cell nuclei segmentation. Core Results: The results suggest that the zero-shot SAM model achieves remarkable segmentation performance for large connected objects. However, it does not consistently achieve satisfying performance for dense instance object segmentation, even with 20 prompts (clicks/boxes) on each image. We also summarized the identified limitations for digital pathology: (1) image resolution, (2) multiple scales, (3) prompt selection, and (4) model fine-tuning. In the future, the few-shot fine-tuning with images from downstream pathological seg- mentation tasks might help the model to achieve better performance in dense object segmentation.
more »
« less
- Award ID(s):
- 2040462
- PAR ID:
- 10447851
- Date Published:
- Journal Name:
- Medical Imaging with Deep Learning (MIDL)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Recent advances in object segmentation have demonstrated that deep neural networks excel at object segmentation for specific classes in color and depth images. However, their performance is dictated by the number of classes and objects used for training, thereby hindering generalization to never seen objects or zero-shot samples. To exacerbate the problem further, object segmentation using image frames rely on recognition and pattern matching cues. Instead, we utilize the ‘active’ nature of a robot and their ability to ‘interact’ with the environment to induce additional geometric constraints for segmenting zero-shot samples. In this paper, we present the first framework to segment unknown objects in a cluttered scene by repeatedly ‘nudging’ at the objects and moving them to obtain additional motion cues at every step using only a monochrome monocular camera. We call our framework NudgeSeg. These motion cues are used to refine the segmentation masks. We successfully test our approach to segment novel objects in various cluttered scenes and provide an extensive study with image and motion segmentation methods. We show an impressive average detection rate of over 86% on zero-shot objects.more » « less
-
Sketch-to-image synthesis method transforms a simple abstract black-and-white sketch into an image. Most sketch-to-image synthesis methods generate an image in an end-to-end manner, leading to generate a non-satisfactory result. The reason is that, in end-to-end models, the models generate images directly from the input sketches. Thus, with very abstract and complicated sketches, the models might struggle in generating naturalistic images due to the simultaneous focus on both factors: overall shape and fine-grained details. In this paper, we propose to divide the problem into subproblems. To this end, an intermediate output, which is a semantic mask map, is first generated from the input sketch via an instance and semantic segmentation. In the instance segmentation stage, the objects' sizes might be modified depending on the surrounding environment and their respective size prior to reflect reality and produce more realistic images. In the semantic seg-mentation stage, a background segmentation is first constructed based on the context of the detected objects. Various natural scenes are implemented for both indoor and outdoor scenes. Following this, a foreground segmentation process is commenced, where each detected object is semantically added into the constructed segmented background. Then, in the next stage, an image-to-image translation model is leveraged to convert the semantic mask map into a colored image. Finally, a post-processing stage is incorporated to further enhance the image result. Extensive experiments demonstrate the superiority of our proposed method over state-of-the-art methods.more » « less
-
This paper assesses trending AI foundation models, especially emerging computer vision foundation models and their performance in natural landscape feature segmentation. While the term foundation model has quickly garnered interest from the geospatial domain, its definition remains vague. Hence, this paper will first introduce AI foundation models and their defining characteristics. Built upon the tremendous success achieved by Large Language Models (LLMs) as the foundation models for language tasks, this paper discusses the challenges of building foundation models for geospatial artificial intelligence (GeoAI) vision tasks. To evaluate the performance of large AI vision models, especially Meta’s Segment Anything Model (SAM), we implemented different instance segmentation pipelines that minimize the changes to SAM to leverage its power as a foundation model. A series of prompt strategies were developed to test SAM’s performance regarding its theoretical upper bound of predictive accuracy, zero-shot performance, and domain adaptability through fine-tuning. The analysis used two permafrost feature datasets, ice-wedge polygons and retrogressive thaw slumps because (1) these landform features are more challenging to segment than man-made features due to their complicated formation mechanisms, diverse forms, and vague boundaries; (2) their presence and changes are important indicators for Arctic warming and climate change. The results show that although promising, SAM still has room for improvement to support AI-augmented terrain mapping. The spatial and domain generalizability of this finding is further validated using a more general dataset EuroCrops for agricultural field mapping. Finally, we discuss future research directions that strengthen SAM’s applicability in challenging geospatial domains.more » « less
-
Training a referring expression comprehension (ReC) model for a new visual domain requires collecting referring expressions, and potentially corresponding bounding boxes, for images in the domain. While large-scale pre-trained models are useful for image classification across domains, it remains unclear if they can be applied in a zero-shot manner to more complex tasks like ReC. We present ReCLIP, a simple but strong zero-shot baseline that repurposes CLIP, a state-of-the-art large-scale model, for ReC. Motivated by the close connection between ReC and CLIP’s contrastive pre-training objective, the first component of ReCLIP is a region-scoring method that isolates object proposals via cropping and blurring, and passes them to CLIP. However, through controlled experiments on a synthetic dataset, we find that CLIP is largely incapable of performing spatial reasoning off-the-shelf. We reduce the gap between zero-shot baselines from prior work and supervised models by as much as 29% on RefCOCOg, and on RefGTA (video game imagery), ReCLIP’s relative improvement over supervised ReC models trained on real images is 8%.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
