# Tracked 3D Ultrasound and Deep Neural Network-based Thyroid Segmentation reduce Interobserver Variability in Thyroid Volumetry

arXiv: https://arxiv.org/abs/2108.10118 · HTML: https://mlsanity.com/paper/2108.10118/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 35 references that are in the map.
- First posted on arXiv 10 Aug 2021.

## Builds on (most cited first, 2 of 2)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [QuickNAT: A Fully Convolutional Network for Quick and Accurate Segmentation of Neuroanatomy](https://mlsanity.com/paper/1801.04161/) (2018)

## Built on by (most cited first, 29 of 29)

- [ScribblePrompt: Fast and Flexible Interactive Segmentation for Any Biomedical Image](https://mlsanity.com/paper/2312.07381/) (2023)
- [nnInteractive: Redefining 3D Promptable Segmentation](https://mlsanity.com/paper/2503.08373/) (2025)
- [Learning General-Purpose Biomedical Volume Representations using Randomized Synthesis](https://mlsanity.com/paper/2411.02372/) (2024)
- [Ultra-NeRF: Neural Radiance Fields for Ultrasound Imaging](https://mlsanity.com/paper/2301.10520/) (2023)
- [UltraSam: A Foundation Model for Ultrasound using Large Open-Access Segmentation Datasets](https://mlsanity.com/paper/2411.16222/) (2024)
- [Tyche: Stochastic In-Context Learning for Medical Image Segmentation](https://mlsanity.com/paper/2401.13650/) (2024)
- [USF-MAE: Ultrasound Self-Supervised Foundation Model with Masked Autoencoding](https://mlsanity.com/paper/2510.22990/) (2025)
- [MultiverSeg: Scalable Interactive Segmentation of Biomedical Imaging Datasets with In-Context Guidance](https://mlsanity.com/paper/2412.15058/) (2024)
- [S3M: Scalable Statistical Shape Modeling through Unsupervised Correspondences](https://mlsanity.com/paper/2304.07515/) (2023)
- [Diffusion as Sound Propagation: Physics-inspired Model for Ultrasound Image Generation](https://mlsanity.com/paper/2407.05428/) (2024)
- [U2-BENCH: Benchmarking Large Vision-Language Models on Ultrasound Understanding](https://mlsanity.com/paper/2505.17779/) (2025)
- [MedicoSAM: Robust Improvement of SAM for Medical Imaging](https://mlsanity.com/paper/2501.11734/) (2025)
- [LOTUS: Learning to Optimize Task-based US representations](https://mlsanity.com/paper/2307.16021/) (2023)
- [HoloPOCUS: Portable Mixed-Reality 3D Ultrasound Tracking, Reconstruction and Overlay](https://mlsanity.com/paper/2308.13823/) (2023)
- [On the Localization of Ultrasound Image Slices within Point Distribution Models](https://mlsanity.com/paper/2309.00372/) (2023)
- [The Missing Piece: A Case for Pre-Training in 3D Medical Object Detection](https://mlsanity.com/paper/2509.15947/) (2025)
- [Comparing SAM 2 and SAM 3 for Zero-Shot Segmentation of 3D Medical Data](https://mlsanity.com/paper/2511.21926/) (2025)
- [UMind-VL: A Generalist Ultrasound Vision-Language Model for Unified Grounded Perception and Comprehensive Interpretation](https://mlsanity.com/paper/2511.22256/) (2025)
- [US-JEPA: A Joint Embedding Predictive Architecture for Ultrasound](https://mlsanity.com/paper/2602.19322/) (2026)
- [Deep Spectral Methods for Unsupervised Ultrasound Image Interpretation](https://mlsanity.com/paper/2408.02043/) (2024)
- [PointVoxelFormer -- Reviving point cloud networks for 3D medical imaging](https://mlsanity.com/paper/2412.17390/) (2024)
- [UltraSAM3: A Concept-Driven Foundation Model for Universal Ultrasound Image Segmentation](https://mlsanity.com/paper/2607.29200/) (2026)
- [UltraG-Bench: A Multi-task Benchmark for assessing Large Vision-Language Models on Pixel-level Evidence Grounding in Ultrasound](https://mlsanity.com/paper/2609.30928/) (2026)
- [Can ultrasound confidence maps predict sonographers' labeling variability?](https://mlsanity.com/paper/2308.09433/) (2023)
- [Pancakes: Consistent Multi-Protocol Image Segmentation Across Biomedical Domains](https://mlsanity.com/paper/2512.13534/) (2025)
- [A Unified Platform and Quality Assurance Framework for 3D Ultrasound Reconstruction with Robotic, Optical, and Electromagnetic Tracking](https://mlsanity.com/paper/2603.20077/) (2026)
- [UltraG-Ray: Physics-Based Gaussian Ray Casting for Novel Ultrasound View Synthesis](https://mlsanity.com/paper/2603.29022/) (2026)
- [SLIP: Segmentation with Low-latency Interactive Prompting for 3D Medical Images](https://mlsanity.com/paper/2607.22332/) (2026)
- [Infrared Imaging Empowered by Artificial Intelligence for Pediatric Skeletal Triage: A Narrative Review and Future Perspectives](https://mlsanity.com/paper/2607.24727/) (2026)

## Abstract (arXiv)

Background: Thyroid volumetry is crucial in diagnosis, treatment and monitoring of thyroid diseases. However, conventional thyroid volumetry with 2D ultrasound is highly operator-dependent. This study compares 2D ultrasound and tracked 3D ultrasound with an automatic thyroid segmentation based on a deep neural network regarding inter- and intraobserver variability, time and accuracy. Volume reference was MRI. Methods: 28 healthy volunteers were scanned with 2D and 3D ultrasound as well as by MRI. Three physicians (MD 1, 2, 3) with different levels of experience (6, 4 and 1 a) performed three 2D ultrasound and three tracked 3D ultrasound scans on each volunteer. In the 2D scans the thyroid lobe volumes were calculated with the ellipsoid formula. A convolutional deep neural network (CNN) segmented the 3D thyroid lobes automatically. On MRI (T1 VIBE sequence) the thyroid was manually segmented by an experienced medical doctor. Results: The CNN was trained to obtain a dice score of 0.94. The interobserver variability comparing two MDs showed mean differences for 2D and 3D respectively of 0.58 ml to 0.52 ml (MD1 vs. 2), -1.33 ml to -0.17 ml (MD1 vs. 3) and -1.89 ml to -0.70 ml (MD2 vs. 3). Paired samples t-tests showed significant differences in two comparisons for 2D and none for 3D. Intraobsever variability was similar for 2D and 3D ultrasound. Comparison of ultrasound volumes and MRI volumes by paired samples t-tests showed a significant difference for the 2D volumetry of all MDs, and no significant difference for 3D ultrasound. Acquisition time was significantly shorter for 3D ultrasound. Conclusion: Tracked 3D ultrasound combined with a CNN segmentation significantly reduces interobserver variability in thyroid volumetry and increases the accuracy of the measurements with shorter acquisition times.