RSV: Robotic Sonography for Thyroid Volumetry

Zielke, John; Eilers, Christine; Busam, Benjamin; Navab, Nassir; Wendler, Thomas

doi:10.1109/lra.2022.3146542

Cited by 15 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To summarize the results on thyroid volumetry, the best performing method with respect to the DSC was the CNN (DSC = 0.87), and the lowest performance was obtained with the GC (DSC = 0.67), both reported by Poudel et al In terms of RVE in 2D US, we observed a high variability ranging from a RVE of 3.74 ± 2.00 % (Chang et al) to a RVE of 26.95 ± 14.95 % (Krönke et al) (▶ Table 4). 3D US appears to improve the accuracy of thyroid volumetry (RVE < 5 %) which has been also confirmed in an experimental robotic ultrasound setup [58]. However, the current literature is too limited to draw a definite conclusion.…”

Section: Thyroid Volumetrymentioning

confidence: 62%

Artificial Intelligence-powered automatic volume calculation in medical images – available tools, performance and challenges for nuclear medicine

Wendler,

Kreissl,

Schemmer

et al. 2023

Nuklearmedizin

Self Cite

View full text Add to dashboard Cite

Volumetry is crucial in oncology and endocrinology, for diagnosis, treatment planning, and evaluating response to therapy for several diseases. The integration of Artificial Intelligence (AI) and Deep Learning (DL) has significantly accelerated the automatization of volumetric calculations, enhancing accuracy and reducing variability and labor. In this review, we show that a high correlation has been observed between Machine Learning (ML) methods and expert assessments in tumor volumetry; Yet, it is recognized as more challenging than organ volumetry. Liver volumetry has shown progression in accuracy with a decrease in error. If a relative error below 10 % is acceptable, ML-based liver volumetry can be considered reliable for standardized imaging protocols if used in patients without major anomalies. Similarly, ML-supported automatic kidney volumetry has also shown consistency and reliability in volumetric calculations. In contrast, AI-supported thyroid volumetry has not been extensively developed, despite initial works in 3D ultrasound showing promising results in terms of accuracy and reproducibility. Despite the advancements presented in the reviewed literature, the lack of standardization limits the generalizability of ML methods across diverse scenarios. The domain gap, i. e., the difference in probability distribution of training and inference data, is of paramount importance before clinical deployment of AI, to maintain accuracy and reliability in patient care. The increasing availability of improved segmentation tools is expected to further incorporate AI methods into routine workflows where volumetry will play a more prominent role in radionuclide therapy planning and quantitative follow-up of disease evolution.

show abstract

Section: Thyroid Volumetrymentioning

confidence: 62%

Artificial Intelligence-powered automatic volume calculation in medical images – available tools, performance and challenges for nuclear medicine

Wendler,

Kreissl,

Schemmer

et al. 2023

Nuklearmedizin

Self Cite

View full text Add to dashboard Cite

show abstract

“…Notably, the thyroid lobe may not be visible based on the location predicted by skeletal data (Fig. 2b), because the anatomy of the neck varies greatly in different populations [30]. Consequently, we added the fine-tuning step to further locate the thyroid lobe.…”

Section: Thyroid Search and Probe Orientation Optimizationmentioning

confidence: 99%

“…So far, autonomous OPS are still challenging. It often requires either accurate knowledge of the image features, such as the moments or intensity-based methods, or a 3D US probe [19,30,31]. A popular YOLO object detection model was introduced to detect the presence of suspicious nodules in the image [44].…”

Section: Fully Autonomous Out-of-plane Ultrasound Imagingmentioning

confidence: 99%

“…In terms of robots at level 1, vision servo technology allows the robot to automatically track desired image features and compensate for unwanted participant motion during teleoperation, thereby partially reducing operator burden and user dependency in acquisition [23][24][25][26]. Most existing autonomous systems are still at level 2 [27][28][29][30], which rely on experts to design the acquisition procedure. Although some systems can reach level 3 (i.e., [31][32][33][34]), their clinical feasibility must be investigated further and compared with robotic assistant systems.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Fully Autonomous Robotic Ultrasound System for Thyroid Scanning

Su¹,

Liu

Ren

et al. 2023

Preprint

View full text Add to dashboard Cite

The current thyroid ultrasound relies heavily on the experience of the sonographer and radiologist, which would be physically and cognitively exhausting. Here we report a novel fully autonomous robotic ultrasound system (FARUS) that can scan thyroid regions without human assistance. In this application, human skeleton point recognition, image segmentation, and force feedback are used to solve the problem of thyroid localization. The orientation of the ultrasound probe is adjusted via Bayesian optimization. By using FARUS, both transverse and longitudinal scanning of thyroid tissue can be performed, as well as real-time thyroid nodule detection with artificial intelligence (AI) algorithms. Experimental results on human participants demonstrate that FARUS can perform high-quality ultrasound scans in comparison with manual scans obtained by clinicians.

show abstract

“…Most solutions deploy a Cartesian impedance controller with direct force control along threedimensional (3D) surfaces, as e.g., in [9]. Many investigate different approaches to visual servoing based on US data for image quality optimisation [10], interaction force adjustment [11], or automated US scanning of the thyroid [12]. Usually, purely autonomous execution is considered, and external imaging and tracking systems are used for registration and surface reconstruction.…”

Section: Introductionmentioning

confidence: 99%

Toward Safe and Collaborative Robotic Ultrasound Tissue Scanning in Neurosurgery

Dyck,

Weld,

Klodmann

et al. 2024

IEEE Trans. Med. Robot. Bionics

View full text Add to dashboard Cite

Intraoperative ultrasound imaging is used to facilitate safe brain tumour resection. However, due to challenges with image interpretation and the physical scanning, this tool has yet to achieve widespread adoption in neurosurgery. In this paper, we introduce the components and workflow of a novel, versatile robotic platform for intraoperative ultrasound tissue scanning in neurosurgery. An RGB-D camera attached to the robotic arm allows for automatic object localisation with ArUco markers, and 3D surface reconstruction as a triangular mesh using the ImFusion Suite software solution. Impedance controlled guidance of the US probe along arbitrary surfaces, represented as a mesh, enables collaborative US scanning, i.e., autonomous, teleoperated and hands-on guided data acquisition. A preliminary experiment evaluates the suitability of the conceptual workflow and system components for probe landing on a custom-made softtissue phantom. Further assessment in future experiments will be necessary to prove the effectiveness of the presented platform.

show abstract

RSV: Robotic Sonography for Thyroid Volumetry

Cited by 15 publications

References 15 publications

Artificial Intelligence-powered automatic volume calculation in medical images – available tools, performance and challenges for nuclear medicine

Artificial Intelligence-powered automatic volume calculation in medical images – available tools, performance and challenges for nuclear medicine

A Fully Autonomous Robotic Ultrasound System for Thyroid Scanning

Toward Safe and Collaborative Robotic Ultrasound Tissue Scanning in Neurosurgery

Contact Info

Product

Resources

About