Assessment of encoder-decoder-based segmentation models for thyroid ultrasound images

Yadav, Niranjan; Dass, Rajeshwar; Virmani, Jitendra

doi:10.1007/s11517-023-02849-4

Cited by 6 publications

(2 citation statements)

References 107 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the currently retrieved research, many models, such as U-net, ACU2E-net, BPAT-UNet, FCG-net, SK UNet++, etc. [ 5 – 10 ], were used in the form of encoding and decoding for target segmentation of nodules or entities in ultrasound thyroid. As displayed in Table 1 , Chen et al [ 6 ] combined U-net with traditional algorithms to obtain the original data, and super-pixel processed data and Sobel edge processed images were merged as the training data as a complement to enhance the segmentation of thyroid entities.…”

Section: Related Workmentioning

confidence: 99%

Three-dimensional visualization of thyroid ultrasound images based on multi-scale features fusion and hierarchical attention

Mi,

Wang,

Feng

et al. 2024

BioMed Eng OnLine

View full text Add to dashboard Cite

Background Ultrasound three-dimensional visualization, a cutting-edge technology in medical imaging, enhances diagnostic accuracy by providing a more comprehensive and readable portrayal of anatomical structures compared to traditional two-dimensional ultrasound. Crucial to this visualization is the segmentation of multiple targets. However, challenges like noise interference, inaccurate boundaries, and difficulties in segmenting small structures exist in the multi-target segmentation of ultrasound images. This study, using neck ultrasound images, concentrates on researching multi-target segmentation methods for the thyroid and surrounding tissues. Method We improved the Unet++ to propose PA-Unet++ to enhance the multi-target segmentation accuracy of the thyroid and its surrounding tissues by addressing ultrasound noise interference. This involves integrating multi-scale feature information using a pyramid pooling module to facilitate segmentation of structures of various sizes. Additionally, an attention gate mechanism is applied to each decoding layer to progressively highlight target tissues and suppress the impact of background pixels. Results Video data obtained from 2D ultrasound thyroid serial scans served as the dataset for this paper.4600 images containing 23,000 annotated regions were divided into training and test sets at a ratio of 9:1, the results showed that: compared with the results of U-net++, the Dice of our model increased from 78.78% to 81.88% (+ 3.10%), the mIOU increased from 73.44% to 80.35% (+ 6.91%), and the PA index increased from 92.95% to 94.79% (+ 1.84%). Conclusions Accurate segmentation is fundamental for various clinical applications, including disease diagnosis, treatment planning, and monitoring. This study will have a positive impact on the improvement of 3D visualization capabilities and clinical decision-making and research in the context of ultrasound image.

show abstract

Section: Related Workmentioning

confidence: 99%

Three-dimensional visualization of thyroid ultrasound images based on multi-scale features fusion and hierarchical attention

Mi,

Wang,

Feng

et al. 2024

BioMed Eng OnLine

View full text Add to dashboard Cite

show abstract

“…The goal of segmentation is to separate the areas of interest, in this case, the thyroid tumor, from the surrounding tissues in medical images. This can be done manually by an expert radiologist, or it can be automated using machine learning algorithms [64,65]. Segmentation is a crucial step in medical image analysis because it helps to accurately determine the location, size, and shape of the tumor, which are vital parameters for diagnosis, treatment planning, and prognosis prediction.…”

Section: O2 Segmentationmentioning

confidence: 99%

AI in Thyroid Cancer Diagnosis: Techniques, Trends, and Future Directions

Habchi,

Himeur,

Kheddar

et al. 2023

Systems

View full text Add to dashboard Cite

Artificial intelligence (AI) has significantly impacted thyroid cancer diagnosis in recent years, offering advanced tools and methodologies that promise to revolutionize patient outcomes. This review provides an exhaustive overview of the contemporary frameworks employed in the field, focusing on the objective of AI-driven analysis and dissecting methodologies across supervised, unsupervised, and ensemble learning. Specifically, we delve into techniques such as deep learning, artificial neural networks, traditional classification, and probabilistic models (PMs) under supervised learning. With its prowess in clustering and dimensionality reduction, unsupervised learning (USL) is explored alongside ensemble methods, including bagging and potent boosting algorithms. The thyroid cancer datasets (TCDs) are integral to our discussion, shedding light on vital features and elucidating feature selection and extraction techniques critical for AI-driven diagnostic systems. We lay out the standard assessment criteria across classification, regression, statistical, computer vision, and ranking metrics, punctuating the discourse with a real-world example of thyroid cancer detection using AI. Additionally, this study culminates in a critical analysis, elucidating current limitations and delineating the path forward by highlighting open challenges and prospective research avenues. Through this comprehensive exploration, we aim to offer readers a panoramic view of AI’s transformative role in thyroid cancer diagnosis, underscoring its potential and pointing toward an optimistic future.

show abstract

Deep Learning‐Based Segmentation and Risk Stratification for Gastrointestinal Stromal Tumors in Transabdominal Ultrasound Imaging

Zhuo,

Chen,

Guo

et al. 2024

J of Ultrasound Medicine

View full text Add to dashboard Cite

PurposeTo develop a deep neural network system for the automatic segmentation and risk stratification prediction of gastrointestinal stromal tumors (GISTs).MethodsA total of 980 ultrasound (US) images from 245 GIST patients were retrospectively collected. These images were randomly divided (6:2:2) into a training set, a validation set, and an internal test set. Additionally, 188 US images from 47 prospective GIST patients were collected to evaluate the segmentation and diagnostic performance of the model. Five deep learning‐based segmentation networks, namely, UNet, FCN, DeepLabV3+, Swin Transformer, and SegNeXt, were employed, along with the ResNet 18 classification network, to select the most suitable network combination. The performance of the segmentation models was evaluated using metrics such as the intersection over union (IoU), Dice similarity coefficient (DSC), recall, and precision. The classification performance was assessed based on accuracy and the area under the receiver operating characteristic curve (AUROC).ResultsAmong the compared models, SegNeXt‐ResNet18 exhibited the best segmentation and classification performance. On the internal test set, the proposed model achieved IoU, DSC, precision, and recall values of 82.1, 90.2, 91.7, and 88.8%, respectively. The accuracy and AUC for GIST risk prediction were 87.4 and 92.0%, respectively. On the external test set, the segmentation models exhibited IoU, DSC, precision, and recall values of 81.0, 89.5, 92.8, and 86.4%, respectively. The accuracy and AUC for GIST risk prediction were 86.7 and 92.5%, respectively.ConclusionThis two‐stage SegNeXt‐ResNet18 model achieves automatic segmentation and risk stratification prediction for GISTs and demonstrates excellent segmentation and classification performance.

show abstract

Assessment of encoder-decoder-based segmentation models for thyroid ultrasound images

Cited by 6 publications

References 107 publications

Three-dimensional visualization of thyroid ultrasound images based on multi-scale features fusion and hierarchical attention

Three-dimensional visualization of thyroid ultrasound images based on multi-scale features fusion and hierarchical attention

AI in Thyroid Cancer Diagnosis: Techniques, Trends, and Future Directions

Deep Learning‐Based Segmentation and Risk Stratification for Gastrointestinal Stromal Tumors in Transabdominal Ultrasound Imaging

Contact Info

Product

Resources

About