Objective
Thyroid carcinoma is one of the most common diseases with an increasing incidence
worldwide in recent years. In clinical diagnosis, medical practitioners normally take
a preliminary thyroid nodule grading so that highly suspected thyroid nodules can
be taken into the fine-needle aspiration (FNA) biopsy to evaluate the malignancy.
However, subjective misinterpretations might lead to ambiguous risk stratification
of thyroid nodules and unnecessary FNA biopsy.
Methods
We propose a thyroid carcinoma auxiliary diagnosis method for fine-needle aspiration
biopsy evaluation. Through integration of several deep learning models into a multibranch
network for thyroid nodule risk stratification in the Thyroid Imaging Reporting and
Data System (TIRADS) with pathological features and cascading of a discriminator,
our proposed method provides an intelligent auxiliary diagnosis to assist medical
practitioners in determining the necessity for further FNA.
Discussion
Experimental results revealed that not only was the rate at which nodules are falsely
diagnosed as malignant nodules effectively reduced, which avoids the unnecessary high
cost and pain of aspiration biopsy, but also previously missing detected cases were
identified with high possibility. By comparing the physicians’ diagnosis alone with
machine-assisted diagnosis, physicians' diagnostic performance improved with the aid
of our proposed method, illustrating that our model can be very helpful in clinical
practice.
Conclusion
Our proposed method might help medical practitioners avoid subjective interpretations
and inter-observer variability. For patients, reliable diagnosis is provided and unnecessary
painful diagnostics can be avoided. In other superficial organs such as metastatic
lymph nodes and salivary gland tumors, the proposed method might also provide a reliable
auxiliary diagnosis for risk stratification.
Keywords
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Ultrasound in Medicine and BiologyAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Sixty years of CA: a cancer journal for clinicians.CA Cancer J Clin. 2010; 60: 345-350
- The application value of CDFI and SMI combined with serological markers in distinguishing benign and malignant thyroid nodules.Clin Transl Oncol. 2022; 24: 2200-2209
- Thyroid incidentalomas: epidemiology, risk stratification with ultrasound and workup.Eur Thyroid J. 2014; 3: 154-163
- Treatment of thyroid cancer based on risk groups.J Surg Oncol. 2006; 94: 683-691
- Outcomes of incidentally discovered thyroid nodules referred to a high-volume head and neck surgeon.Head Neck. 2014; 36: 126-129
- Thyroid incidentaloma.Best Pract Res Clin Endocrinol Metab. 2012; 26: 83-96
- Review of factors related to the thyroid cancer epidemic.Int J Endocrinol. 2017; 2017: 1-9
- An improved deep learning approach for detection of thyroid papillary cancer in ultrasound images.Sci Rep. 2018; 8: 1-12
- Evaluating thyroid nodules: predicting and selecting malignant nodules for fine-needle aspiration (FNA) cytology.Insights Imaging. 2013; 4: 617-624
- A primer on deep learning in genomics.Nat Genet. 2019; 51: 12-18
- Deep learning in the biomedical applications: recent and future status.Appl Sci. 2019; 9: 1526
- Regularization of neural networks using DropConnect.PMLR. 2013; 28: 1058-1066
- A pre-trained convolutional neural network based method for thyroid nodule diagnosis.Ultrasonics. 2017; 73: 221-230
- Thyroid nodule classification in ultrasound images by fine-tuning deep convolutional neural network.J Digital Imaging. 2017; 30: 477-486
- Learning from weakly-labeled clinical data for automatic thyroid nodule classification in ultrasound images.in: 2018 25th IEEE International Conference on Image Processing (ICIP), Athens, Greece, New York: IEEE2018: 3114-3118
- Automatic diagnosis for thyroid nodules in ultrasound images by deep neural networks.Medical Image Analysis. 2020; 61101665
- Automatic thyroid nodule recognition and diagnosis in ultrasound imaging with the YOLOv2 neural network.World J Surg Oncol. 2019; 17: 1-9
- Deep residual learning for image recognition.in: Proceedings, 2016 IEEE Conference on Computer Vision and Pattern Recognition, New York: IEEE2016: 770-778
- Semantic consistency generative adversarial network for cross-modality domain adaptation in ultrasound thyroid nodule classification.Appl Intell. 2022; 99: 1-15
- Cross-modal domain adaptation for text-based regularization of image semantics in image retrieval systems.Comput Vision Image Understand. 2014; 124: 123-135
- Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images: a retrospective, multicohort, diagnostic study.Lancet Oncol. 2019; 20: 193-201
- YOLO9000: Better, faster, stronger.in: Proceedings, IEEE Conference on Computer Vision and Pattern Recognition, New York: IEEE2017: 6517-6525
- Ultrasound image analysis using deep learning algorithm for the diagnosis of thyroid nodules.Medicine. 2019; 98: e15133
- Automatic removal of manually induced artefacts in ultrasound images of thyroid gland.in: Proceedings, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), New York: IEEE2013: 3399-3402
Tzutalin LI. LabelImg, <https://github.com/tzutalin/labelImg>; 2015 [accessed 22.10.2021].
- MobileNets for flower classification using TensorFlow.in: Proceedings, 2017 International Conference on Big Data, IoT and Data Science (BID), Pune, India, New York: IEEE2017: 154-158
- Efficientnet: rethinking model scaling for convolutional neural networks.PMLR. 2019; 97: 6105-6114
- Mobilenetv2: inverted residuals and linear bottlenecks.in: Proceedings, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, New York: IEEE2018: 4510-4520
- Squeeze-and-excitation networks.in: Proceedings, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, New York: IEEE2018: 7132-7141
- Mnasnet: platform-aware neural architecture search for mobile.in: Proceedings, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New York: IEEE2019: 2820-2828
- Ensemble learning: a survey.WIREs. 2018; 8: e1249
- Deep learning-based computer-aided diagnosis system for localization and diagnosis of metastatic lymph nodes on ultrasound: a pilot study.Thyroid. 2018; 28: 1332-1338
Article info
Publication history
Published online: February 14, 2023
Accepted:
January 1,
2023
Received in revised form:
December 22,
2022
Received:
May 8,
2022
Identification
Copyright
© 2023 World Federation for Ultrasound in Medicine & Biology. All rights reserved.
