دورية أكاديمية
Adapting the Segment Anything Model for Volumetric X-ray Data-Sets of Arbitrary Sizes
العنوان: | Adapting the Segment Anything Model for Volumetric X-ray Data-Sets of Arbitrary Sizes |
---|---|
المؤلفون: | Roland Gruber, Steffen Rüger, Thomas Wittenberg |
المصدر: | Applied Sciences, Vol 14, Iss 8, p 3391 (2024) |
بيانات النشر: | MDPI AG, 2024. |
سنة النشر: | 2024 |
المجموعة: | LCC:Technology LCC:Engineering (General). Civil engineering (General) LCC:Biology (General) LCC:Physics LCC:Chemistry |
مصطلحات موضوعية: | instance segmentation, Segment Anything Model, computed tomography, non-destructive testing, neural networks, machine learning, Technology, Engineering (General). Civil engineering (General), TA1-2040, Biology (General), QH301-705.5, Physics, QC1-999, Chemistry, QD1-999 |
الوصف: | We propose a new approach for volumetric instance segmentation in X-ray Computed Tomography (CT) data for Non-Destructive Testing (NDT) by combining the Segment Anything Model (SAM) with tile-based Flood Filling Networks (FFN). Our work evaluates the performance of SAM on volumetric NDT data-sets and demonstrates its effectiveness to segment instances in challenging imaging scenarios. We implemented and evaluated techniques to extend the image-based SAM algorithm for the use with volumetric data-sets, enabling the segmentation of three-dimensional objects using FFN’s spatial adaptability. The tile-based approach for SAM leverages FFN’s capabilities to segment objects of any size. We also explore the use of dense prompts to guide SAM in combining segmented tiles for improved segmentation accuracy. Our research indicates the potential of combining SAM with FFN for volumetric instance segmentation tasks, particularly in NDT scenarios and segmenting large entities and objects. While acknowledging remaining limitations, our study provides insights and establishes a foundation for advancements in instance segmentation in NDT scenarios. |
نوع الوثيقة: | article |
وصف الملف: | electronic resource |
اللغة: | English |
تدمد: | 2076-3417 |
Relation: | https://www.mdpi.com/2076-3417/14/8/3391; https://doaj.org/toc/2076-3417 |
DOI: | 10.3390/app14083391 |
URL الوصول: | https://doaj.org/article/de5912aeb0f5489d9eddbdc134e9d01b |
رقم الأكسشن: | edsdoj.5912aeb0f5489d9eddbdc134e9d01b |
قاعدة البيانات: | Directory of Open Access Journals |
تدمد: | 20763417 |
---|---|
DOI: | 10.3390/app14083391 |