1
|
Sant VR, Radhachandran A, Ivezic V, Lee DT, Livhits MJ, Wu JX, Masamed R, Arnold CW, Yeh MW, Speier W. From Bench-to-Bedside: How Artificial Intelligence is Changing Thyroid Nodule Diagnostics, a Systematic Review. J Clin Endocrinol Metab 2024; 109:1684-1693. [PMID: 38679750 PMCID: PMC11180510 DOI: 10.1210/clinem/dgae277] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/30/2024] [Revised: 04/04/2024] [Accepted: 04/16/2024] [Indexed: 05/01/2024]
Abstract
CONTEXT Use of artificial intelligence (AI) to predict clinical outcomes in thyroid nodule diagnostics has grown exponentially over the past decade. The greatest challenge is in understanding the best model to apply to one's own patient population, and how to operationalize such a model in practice. EVIDENCE ACQUISITION A literature search of PubMed and IEEE Xplore was conducted for English-language publications between January 1, 2015 and January 1, 2023, studying diagnostic tests on suspected thyroid nodules that used AI. We excluded articles without prospective or external validation, nonprimary literature, duplicates, focused on nonnodular thyroid conditions, not using AI, and those incidentally using AI in support of an experimental diagnostic outside standard clinical practice. Quality was graded by Oxford level of evidence. EVIDENCE SYNTHESIS A total of 61 studies were identified; all performed external validation, 16 studies were prospective, and 33 compared a model to physician prediction of ground truth. Statistical validation was reported in 50 papers. A diagnostic pipeline was abstracted, yielding 5 high-level outcomes: (1) nodule localization, (2) ultrasound (US) risk score, (3) molecular status, (4) malignancy, and (5) long-term prognosis. Seven prospective studies validated a single commercial AI; strengths included automating nodule feature assessment from US and assisting the physician in predicting malignancy risk, while weaknesses included automated margin prediction and interobserver variability. CONCLUSION Models predominantly used US images to predict malignancy. Of 4 Food and Drug Administration-approved products, only S-Detect was extensively validated. Implementing an AI model locally requires data sanitization and revalidation to ensure appropriate clinical performance.
Collapse
Affiliation(s)
- Vivek R Sant
- Division of Endocrine Surgery, UT Southwestern Medical Center, Dallas, TX 75390, USA
| | - Ashwath Radhachandran
- Biomedical Artificial Intelligence Research Lab, UCLA Department of Bioengineering, Los Angeles, CA 90024, USA
| | - Vedrana Ivezic
- Biomedical Artificial Intelligence Research Lab, UCLA Department of Bioengineering, Los Angeles, CA 90024, USA
| | - Denise T Lee
- Department of Surgery, Icahn School of Medicine at Mount Sinai Hospital, New York, NY 10029, USA
| | - Masha J Livhits
- Section of Endocrine Surgery, UCLA David Geffen School of Medicine, Los Angeles, CA 90095, USA
| | - James X Wu
- Section of Endocrine Surgery, UCLA David Geffen School of Medicine, Los Angeles, CA 90095, USA
| | - Rinat Masamed
- Department of Radiology, University of California, Los Angeles, Los Angeles, CA 90095, USA
| | - Corey W Arnold
- Biomedical Artificial Intelligence Research Lab, UCLA Department of Bioengineering, Los Angeles, CA 90024, USA
| | - Michael W Yeh
- Section of Endocrine Surgery, UCLA David Geffen School of Medicine, Los Angeles, CA 90095, USA
| | - William Speier
- Biomedical Artificial Intelligence Research Lab, UCLA Department of Bioengineering, Los Angeles, CA 90024, USA
| |
Collapse
|
2
|
Wang Z, Wang X, Wang T, Qiu J, Lu W. Localization and Risk Stratification of Thyroid Nodules in Ultrasound Images Through Deep Learning. ULTRASOUND IN MEDICINE & BIOLOGY 2024; 50:882-887. [PMID: 38494413 DOI: 10.1016/j.ultrasmedbio.2024.02.013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/11/2023] [Revised: 01/03/2024] [Accepted: 02/20/2024] [Indexed: 03/19/2024]
Abstract
OBJECTIVE Deep learning algorithms have commonly been used for the differential diagnosis between benign and malignant thyroid nodules. The aim of the study described here was to develop an integrated system that combines a deep learning model and a clinical standard Thyroid Imaging Reporting and Data System (TI-RADS) for the simultaneous segmentation and risk stratification of thyroid nodules. METHODS Three hundred four ultrasound images from two independent sites with TI-RADS 4 thyroid nodules were collected. The edge connection and Criminisi algorithm were used to remove manually induced markers in ultrasound images. An integrated system based on TI-RADS and a mask region-based convolution neural network (Mask R-CNN) was proposed to stratify subclasses of TI-RADS 4 thyroid nodules and to segment thyroid nodules in the ultrasound images. Accuracy and the precision-recall curve were used to evaluate stratification performance, and the Dice similarity coefficient (DSC) between the segmentation of Mask R-CNN and the radiologist's contour was used to evaluate the segmentation performance of the model. RESULTS The combined approach could significantly enhance the performance of the proposed integrated system. Overall stratification accuracy of TI-RADS 4 thyroid nodules, mean average precision and mean DSC of the proposed model in the independent test set was 90.79%, 0.8579 and 0.83, respectively. Specifically, stratification accuracy values for TI-RADS 4a, 4b and 4c thyroid nodules were 95.83%, 84.21% and 77.78%, respectively. CONCLUSION An integrated system combining TI-RADS and a deep learning model was developed. The system can provide clinicians with not only diagnostic assistance from TI-RADS but also accurate segmentation of thyroid nodules, which improves the applicability of the system in clinical practice.
Collapse
Affiliation(s)
- Zhipeng Wang
- Department of Radiology, Second Affiliated Hospital of Shandong First Medical University, Tai'an, China; School of Radiology, Shandong First Medical University and Shandong Academy of Medical Sciences, Tai'an, China
| | - Xiuzhu Wang
- Department of Obstetrics, Tai'an City Central Hospital, Tai'an, China
| | - Ting Wang
- Department of Ultrasound, Zoucheng Maternity and Child Healthcare Hospital, Jining, China
| | - Jianfeng Qiu
- Department of Radiology, Second Affiliated Hospital of Shandong First Medical University, Tai'an, China; School of Radiology, Shandong First Medical University and Shandong Academy of Medical Sciences, Tai'an, China
| | - Weizhao Lu
- Department of Radiology, Second Affiliated Hospital of Shandong First Medical University, Tai'an, China.
| |
Collapse
|
3
|
Pozdeyev N, Dighe M, Barrio M, Raeburn C, Smith H, Fisher M, Chavan S, Rafaels N, Shortt JA, Lin M, Leu MG, Clark T, Marshall C, Haugen BR, Subramanian D, Crooks K, Gignoux C, Cohen T. Thyroid Cancer Polygenic Risk Score Improves Classification of Thyroid Nodules as Benign or Malignant. J Clin Endocrinol Metab 2024; 109:402-412. [PMID: 37683082 DOI: 10.1210/clinem/dgad530] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/01/2023] [Revised: 08/29/2023] [Accepted: 09/05/2023] [Indexed: 09/10/2023]
Abstract
CONTEXT Thyroid nodule ultrasound-based risk stratification schemas rely on the presence of high-risk sonographic features. However, some malignant thyroid nodules have benign appearance on thyroid ultrasound. New methods for thyroid nodule risk assessment are needed. OBJECTIVE We investigated polygenic risk score (PRS) accounting for inherited thyroid cancer risk combined with ultrasound-based analysis for improved thyroid nodule risk assessment. METHODS The convolutional neural network classifier was trained on thyroid ultrasound still images and cine clips from 621 thyroid nodules. Phenome-wide association study (PheWAS) and PRS PheWAS were used to optimize PRS for distinguishing benign and malignant nodules. PRS was evaluated in 73 346 participants in the Colorado Center for Personalized Medicine Biobank. RESULTS When the deep learning model output was combined with thyroid cancer PRS and genetic ancestry estimates, the area under the receiver operating characteristic curve (AUROC) of the benign vs malignant thyroid nodule classifier increased from 0.83 to 0.89 (DeLong, P value = .007). The combined deep learning and genetic classifier achieved a clinically relevant sensitivity of 0.95, 95% CI [0.88-0.99], specificity of 0.63 [0.55-0.70], and positive and negative predictive values of 0.47 [0.41-0.58] and 0.97 [0.92-0.99], respectively. AUROC improvement was consistent in European ancestry-stratified analysis (0.83 and 0.87 for deep learning and deep learning combined with PRS classifiers, respectively). Elevated PRS was associated with a greater risk of thyroid cancer structural disease recurrence (ordinal logistic regression, P value = .002). CONCLUSION Augmenting ultrasound-based risk assessment with PRS improves diagnostic accuracy.
Collapse
Affiliation(s)
- Nikita Pozdeyev
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
- Division of Endocrinology Metabolism and Diabetes, Department of Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
- University of Colorado Cancer Center, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Manjiri Dighe
- Department of Radiology, University of Washington, Seattle, WA 98195, USA
| | - Martin Barrio
- Division of GI, Trauma, and Endocrine Surgery, Department of Surgery, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Christopher Raeburn
- Division of GI, Trauma, and Endocrine Surgery, Department of Surgery, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Harry Smith
- Colorado Center for Personalized Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Matthew Fisher
- Colorado Center for Personalized Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Sameer Chavan
- Colorado Center for Personalized Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Nicholas Rafaels
- Colorado Center for Personalized Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Jonathan A Shortt
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
- Colorado Center for Personalized Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Meng Lin
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
- Colorado Center for Personalized Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Michael G Leu
- Information Technology Services, UW Medicine, Seattle, WA 98195, USA
- Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA 98195, USA
- Department of Pediatrics, University of Washington, Seattle, WA 98105, USA
- Division of Hospital Medicine, Seattle Children's Hospital, Seattle, WA 98105, USA
| | - Toshimasa Clark
- Department of Radiology, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Carrie Marshall
- Department of Pathology, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Bryan R Haugen
- Division of Endocrinology Metabolism and Diabetes, Department of Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
- University of Colorado Cancer Center, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | | | - Kristy Crooks
- Colorado Center for Personalized Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
- Department of Pathology, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Christopher Gignoux
- Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
- Colorado Center for Personalized Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
| | - Trevor Cohen
- Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA 98195, USA
| |
Collapse
|
4
|
Wang Y, Yu M, He M, Zhang G, Zhang L, Zhang B. Diagnostic value of a computer-assisted diagnosis system for the ultrasound features in thyroid nodules. ARCHIVES OF ENDOCRINOLOGY AND METABOLISM 2023; 68:e220501. [PMID: 37948567 PMCID: PMC10916796 DOI: 10.20945/2359-4292-2022-0501] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/04/2023] [Accepted: 03/15/2023] [Indexed: 11/12/2023]
Abstract
Objective To explore the diagnostic value of the TUIAS (SW_TH01/II) computer-aided diagnosis (CAD) software system for the ultrasound Thyroid Imaging Reporting and Data System (TI-RADS) features in thyroid nodules. Materials and methods This retrospective study enrolled patients with thyroid nodules in Shanghai East Hospital between January 2017 and October 2021. The novel CAD software (SW_TH01/II) and three sonographers performed a qualitative analysis of the ultrasound TI-RADS features in aspect ratio, margin irregularity, margin smoothness, calcification, and echogenicity of the thyroid nodules. Results A total of 225 patients were enrolled. The accuracy, sensitivity, and specificity of the CAD software in "aspect ratio" were 95.6%, 96.2%, and 95.4%, in "margin irregularity" were 90.7%, 90.5%, and 90.9%, in "margin smoothness" were 85.8%, 88.5%, and 83.0%, in "calcification" were 83.6%, 81.7%, and 82.0%, in "homogeneity" were 88.9%, 90.6%, and 82.2%, in "major echo" were 85.3%, 88.0%, and 85.4%, and in "contains very hypoechoic echo" were 92.0%, 90.0%, and 92.4%. The analysis time of the CAD software was significantly shorter than for the sonographers (2.7 ± 1.6 vs. 29.7 ± 12.7 s, P < 0.001). Conclusion The CAD system achieved high accuracy in describing thyroid nodule features. It might assist in clinical thyroid nodule analysis.
Collapse
Affiliation(s)
- Yiwei Wang
- Graduate School of Dalian Medical University, Dalian, Liaoning, China,
| | - Ming Yu
- Tend. AI Medical Technology, China
| | | | | | - Libo Zhang
- Shanghai East Hospital, Department of Ultrasound in Medicine, Shanghai, China
| | - Bo Zhang
- Shanghai East Hospital, Tongji University School of Medicine, Department of Ultrasound in Medicine, Shanghai, China
| |
Collapse
|
5
|
Yin A, Lu Y, Xu F, Zhao Y, Sun Y, Huang M, Li X. Study on diagnosis of thyroid nodules based on convolutional neural network. RADIOLOGIE (HEIDELBERG, GERMANY) 2023; 63:64-72. [PMID: 37074397 DOI: 10.1007/s00117-023-01137-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Accepted: 02/03/2023] [Indexed: 04/20/2023]
Abstract
OBJECTIVE An artificial intelligence (AI) algorithm based on convolutional neural networks was used in ultrasound diagnosis in order to evaluate its performance in judging the nature of thyroid nodules and nodule classification. METHODS A total of 105 patients with thyroid nodules confirmed by surgery or biopsy were retrospectively analyzed. The properties, characteristics, and classification of thyroid nodules were evaluated by sonographers and by AI to obtain combined diagnoses. Receiver operating characteristic curves were generated to evaluate the performance of AI, the sonographer, and their combined effort in diagnosing the nature of thyroid nodules and classifying their characteristics. In the diagnosis of thyroid nodules with solid components, hypoechoic appearance, indistinct borders, Anteroposterior/transverse diameter ratio > 1(A/T > 1), and calcification performed by sonographers and by AI, the properties exhibited statistically significant differences. RESULTS Sonographers had a sensitivity of 80.7%, specificity of 73.7%, accuracy of 79.0%, and area under the curve (AUC) of 0.751 in the diagnosis of benign and malignant thyroid nodules. AI had a sensitivity of 84.5%, specificity of 81.0%, accuracy of 84.7%, and AUC of 0.803. The combined AI and sonographer diagnosis had a sensitivity of 92.1%, specificity of 86.3%, accuracy of 91.7%, and AUC of 0.910. CONCLUSION The efficacy of a combined diagnosis for benign and malignant thyroid nodules is higher than that of an AI-based diagnosis alone or a sonographer-based diagnosis alone. The combined diagnosis can reduce unnecessary fine-needle aspiration biopsy procedures and better evaluate the necessity of surgery in clinical practice.
Collapse
Affiliation(s)
- AiTao Yin
- Dali university, 671003, Dali Yunnan, China
| | - YongPing Lu
- Department of Ultrasound, Affiliated Hospital of Yunnan University, 650000, Kunming Yunnan, China.
| | - Fei Xu
- Department of Ultrasound, Affiliated Hospital of Yunnan University, 650000, Kunming Yunnan, China
| | - YiFan Zhao
- Department of Ultrasound, Affiliated Hospital of Yunnan University, 650000, Kunming Yunnan, China
| | - Yue Sun
- Department of Ultrasound, Affiliated Hospital of Yunnan University, 650000, Kunming Yunnan, China
| | - Miao Huang
- Dali university, 671003, Dali Yunnan, China
| | - XiangBi Li
- Dali university, 671003, Dali Yunnan, China
| |
Collapse
|
6
|
戚 枫, 邱 敏, 魏 国. [Review on ultrasonographic diagnosis of thyroid diseases based on deep learning]. SHENG WU YI XUE GONG CHENG XUE ZA ZHI = JOURNAL OF BIOMEDICAL ENGINEERING = SHENGWU YIXUE GONGCHENGXUE ZAZHI 2023; 40:1027-1032. [PMID: 37879934 PMCID: PMC10600415 DOI: 10.7507/1001-5515.202302049] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Subscribe] [Scholar Register] [Received: 02/28/2023] [Revised: 07/30/2023] [Indexed: 10/27/2023]
Abstract
In recent years, the incidence of thyroid diseases has increased significantly and ultrasound examination is the first choice for the diagnosis of thyroid diseases. At the same time, the level of medical image analysis based on deep learning has been rapidly improved. Ultrasonic image analysis has made a series of milestone breakthroughs, and deep learning algorithms have shown strong performance in the field of medical image segmentation and classification. This article first elaborates on the application of deep learning algorithms in thyroid ultrasound image segmentation, feature extraction, and classification differentiation. Secondly, it summarizes the algorithms for deep learning processing multimodal ultrasound images. Finally, it points out the problems in thyroid ultrasound image diagnosis at the current stage and looks forward to future development directions. This study can promote the application of deep learning in clinical ultrasound image diagnosis of thyroid, and provide reference for doctors to diagnose thyroid disease.
Collapse
Affiliation(s)
- 枫源 戚
- 山东中医药大学 智能与信息工程学院(济南 250355)College of Intelligence and Information Engineering, Shandong University of Traditional Chinese Medicine, Jinan 250355, P. R. China
| | - 敏 邱
- 山东中医药大学 智能与信息工程学院(济南 250355)College of Intelligence and Information Engineering, Shandong University of Traditional Chinese Medicine, Jinan 250355, P. R. China
| | - 国辉 魏
- 山东中医药大学 智能与信息工程学院(济南 250355)College of Intelligence and Information Engineering, Shandong University of Traditional Chinese Medicine, Jinan 250355, P. R. China
| |
Collapse
|
7
|
Zhou L, Chang L, Li J, Long Q, Shao J, Zhu J, Liew AWC, Wei X, Zhang W, Yuan X. Aided diagnosis of thyroid nodules based on an all-optical diffraction neural network. Quant Imaging Med Surg 2023; 13:5713-5726. [PMID: 37711804 PMCID: PMC10498233 DOI: 10.21037/qims-23-98] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/25/2023] [Accepted: 07/12/2023] [Indexed: 09/16/2023]
Abstract
Background Thyroid cancer is the most common malignancy in the endocrine system, with its early manifestation being the presence of thyroid nodules. With the advantages of convenience, noninvasiveness, and a lack of radiation, ultrasound is currently the first-line screening tool for the clinical diagnosis of thyroid nodules. The use of artificial intelligence to assist diagnosis is an emerging technology. This paper proposes the use optical neural networks for potential application in the auxiliary diagnosis of thyroid nodules. Methods Ultrasound images obtained from January 2013 to December 2018 at the Institute and Hospital of Oncology, Tianjin Medical University, were included in a dataset. Patients who consecutively underwent thyroid ultrasound diagnosis and follow-up procedures were included. We developed an all-optical diffraction neural network to assist in the diagnosis of thyroid nodules. The network is composed of 5 diffraction layers and 1 detection plane. The input image is placed 10 mm away from the first diffraction layer. The input of the diffractive neural network is light at a wavelength of 632.8 nm, and the output of this network is determined by the amplitude and light intensity obtained from the detection region. Results The all-optical neural network was used to assist in the diagnosis of thyroid nodules. In the classification task of benign and malignant thyroid nodules, the accuracy of classification on the test set was 97.79%, with an area under the curve value of 99.8%. In the task of detecting thyroid nodules, we first trained the model to determine whether any nodules were present and achieved an accuracy of 84.92% on the test set. Conclusions Our study demonstrates the potential of all-optical neural networks in the field of medical image processing. The performance of the models based on optical neural networks is comparable to other widely used network models in the field of image classification.
Collapse
Affiliation(s)
- Lingxiao Zhou
- Nanophotonics Research Center, Institute of Microscale Optoelectronics, Shenzhen University, Shenzhen, China
| | - Luchen Chang
- Department of Diagnostic and Therapeutic Ultrasonography, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin’s Clinical Research Center for Cancer, Tianjin, China
| | - Jie Li
- Nanophotonics Research Center, Institute of Microscale Optoelectronics, Shenzhen University, Shenzhen, China
| | - Quanzhou Long
- Nanophotonics Research Center, Institute of Microscale Optoelectronics, Shenzhen University, Shenzhen, China
| | - Junjie Shao
- Nanophotonics Research Center, Institute of Microscale Optoelectronics, Shenzhen University, Shenzhen, China
| | - Jialin Zhu
- Department of Diagnostic and Therapeutic Ultrasonography, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin’s Clinical Research Center for Cancer, Tianjin, China
| | - Alan Wee-Chung Liew
- School of Information and Communication Technology, Griffith University, Queensland, Australia
| | - Xi Wei
- Department of Diagnostic and Therapeutic Ultrasonography, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin’s Clinical Research Center for Cancer, Tianjin, China
| | - Wanlong Zhang
- Nanophotonics Research Center, Institute of Microscale Optoelectronics, Shenzhen University, Shenzhen, China
| | - Xiaocong Yuan
- Nanophotonics Research Center, Institute of Microscale Optoelectronics, Shenzhen University, Shenzhen, China
- Research Center for Humanoid Sensing, Research Institute of Intelligent Sensing, Zhejiang Lab, Hangzhou, China
| |
Collapse
|
8
|
Toro-Tobon D, Loor-Torres R, Duran M, Fan JW, Singh Ospina N, Wu Y, Brito JP. Artificial Intelligence in Thyroidology: A Narrative Review of the Current Applications, Associated Challenges, and Future Directions. Thyroid 2023; 33:903-917. [PMID: 37279303 PMCID: PMC10440669 DOI: 10.1089/thy.2023.0132] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 06/08/2023]
Abstract
Background: The use of artificial intelligence (AI) in health care has grown exponentially with the promise of facilitating biomedical research and enhancing diagnosis, treatment, monitoring, disease prevention, and health care delivery. We aim to examine the current state, limitations, and future directions of AI in thyroidology. Summary: AI has been explored in thyroidology since the 1990s, and currently, there is an increasing interest in applying AI to improve the care of patients with thyroid nodules (TNODs), thyroid cancer, and functional or autoimmune thyroid disease. These applications aim to automate processes, improve the accuracy and consistency of diagnosis, personalize treatment, decrease the burden for health care professionals, improve access to specialized care in areas lacking expertise, deepen the understanding of subtle pathophysiologic patterns, and accelerate the learning curve of less experienced clinicians. There are promising results for many of these applications. Yet, most are in the validation or early clinical evaluation stages. Only a few are currently adopted for risk stratification of TNODs by ultrasound and determination of the malignant nature of indeterminate TNODs by molecular testing. Challenges of the currently available AI applications include the lack of prospective and multicenter validations and utility studies, small and low diversity of training data sets, differences in data sources, lack of explainability, unclear clinical impact, inadequate stakeholder engagement, and inability to use outside of the research setting, which might limit the value of their future adoption. Conclusions: AI has the potential to improve many aspects of thyroidology; however, addressing the limitations affecting the suitability of AI interventions in thyroidology is a prerequisite to ensure that AI provides added value for patients with thyroid disease.
Collapse
Affiliation(s)
- David Toro-Tobon
- Division of Endocrinology, Diabetes, Metabolism and Nutrition, Department of Medicine, Mayo Clinic, Rochester, Minnesota, USA
| | - Ricardo Loor-Torres
- Division of Endocrinology, Diabetes, Metabolism and Nutrition, Department of Medicine, Mayo Clinic, Rochester, Minnesota, USA
| | - Mayra Duran
- Division of Endocrinology, Diabetes, Metabolism and Nutrition, Department of Medicine, Mayo Clinic, Rochester, Minnesota, USA
| | - Jungwei W. Fan
- Department of Artificial Intelligence and Informatics, Mayo Clinic, Rochester, Minnesota, USA
| | - Naykky Singh Ospina
- Division of Endocrinology, Department of Medicine, University of Florida, Gainesville, Florida, USA
| | - Yonghui Wu
- Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida, Gainesville, Florida, USA
| | - Juan P. Brito
- Division of Endocrinology, Diabetes, Metabolism and Nutrition, Department of Medicine, Mayo Clinic, Rochester, Minnesota, USA
| |
Collapse
|
9
|
Lee JH, Kim YG, Ahn Y, Park S, Kong HJ, Choi JY, Kim K, Nam IC, Lee MC, Masuoka H, Miyauchi A, Kim S, Kim YA, Choe EK, Chai YJ. Investigation of optimal convolutional neural network conditions for thyroid ultrasound image analysis. Sci Rep 2023; 13:1360. [PMID: 36693894 PMCID: PMC9873643 DOI: 10.1038/s41598-023-28001-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/02/2022] [Accepted: 01/11/2023] [Indexed: 01/26/2023] Open
Abstract
Neural network models have been used to analyze thyroid ultrasound (US) images and stratify malignancy risk of the thyroid nodules. We investigated the optimal neural network condition for thyroid US image analysis. We compared scratch and transfer learning models, performed stress tests in 10% increments, and compared the performance of three threshold values. All validation results indicated superiority of the transfer learning model over the scratch model. Stress test indicated that training the algorithm using 3902 images (70%) resulted in a performance which was similar to the full dataset (5575). Threshold 0.3 yielded high sensitivity (1% false negative) and low specificity (72% false positive), while 0.7 gave low sensitivity (22% false negative) and high specificity (23% false positive). Here we showed that transfer learning was more effective than scratch learning in terms of area under curve, sensitivity, specificity and negative/positive predictive value, that about 3900 images were minimally required to demonstrate an acceptable performance, and that algorithm performance can be customized according to the population characteristics by adjusting threshold value.
Collapse
Affiliation(s)
- Joon-Hyop Lee
- Department of Surgery, Gachon University College of Medicine, Gil Medical Center, Inchon, Korea
| | - Young-Gon Kim
- Transdisciplinary Department of Medicine and Advanced Technology, Seoul National University Hospital, Seoul, Korea
| | - Youngbin Ahn
- Transdisciplinary Department of Medicine and Advanced Technology, Seoul National University Hospital, Seoul, Korea
| | - Seyeon Park
- Transdisciplinary Department of Medicine and Advanced Technology, Seoul National University Hospital, Seoul, Korea
| | - Hyoun-Joong Kong
- Transdisciplinary Department of Medicine and Advanced Technology, Seoul National University Hospital, Seoul, Korea
| | - June Young Choi
- Department of Surgery, Seoul National University Bundang Hospital, Seongnam-si, Gyeonggi-do, Korea
| | - Kwangsoon Kim
- Department of Surgery, College of Medicine, The Catholic University of Korea, Seoul, Korea
| | - Inn-Chul Nam
- Department of Otolaryngology-Head and Neck Surgery, College of Medicine, The Catholic University of Korea, Seoul, Korea
| | - Myung-Chul Lee
- Department of Otorhinolaryngology-Head and Neck Surgery, Korea Cancer Center Hospital, Korea Institute of Radiological and Medical Science, Seoul, Korea
| | | | | | - Sungwan Kim
- Transdisciplinary Department of Medicine and Advanced Technology, Seoul National University Hospital, Seoul, Korea
| | - Young A Kim
- Department of Pathology, Seoul Metropolitan Government Seoul National University Boramae Medical Center, Seoul, Korea
| | - Eun Kyung Choe
- Transdisciplinary Department of Medicine and Advanced Technology, Seoul National University Hospital, Seoul, Korea. .,Department of Surgery, Seoul National University Hospital Healthcare System Gangnam Center, Seoul, Korea.
| | - Young Jun Chai
- Transdisciplinary Department of Medicine and Advanced Technology, Seoul National University Hospital, Seoul, Korea. .,Department of Surgery, Seoul Metropolitan Government, Seoul National University Boramae Medical Center, 20 Boramaep-ro 5-gil, Dongjak-gu, Seoul, 07061, Korea.
| |
Collapse
|
10
|
The Use of Artificial Intelligence in the Diagnosis and Classification of Thyroid Nodules: An Update. Cancers (Basel) 2023; 15:cancers15030708. [PMID: 36765671 PMCID: PMC9913834 DOI: 10.3390/cancers15030708] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/04/2022] [Revised: 01/20/2023] [Accepted: 01/20/2023] [Indexed: 01/27/2023] Open
Abstract
The incidence of thyroid nodules diagnosed is increasing every year, leading to a greater risk of unnecessary procedures being performed or wrong diagnoses being made. In our paper, we present the latest knowledge on the use of artificial intelligence in diagnosing and classifying thyroid nodules. We particularly focus on the usefulness of artificial intelligence in ultrasonography for the diagnosis and characterization of pathology, as these are the two most developed fields. In our search of the latest innovations, we reviewed only the latest publications of specific types published from 2018 to 2022. We analyzed 930 papers in total, from which we selected 33 that were the most relevant to the topic of our work. In conclusion, there is great scope for the use of artificial intelligence in future thyroid nodule classification and diagnosis. In addition to the most typical uses of artificial intelligence in cancer differentiation, we identified several other novel applications of artificial intelligence during our review.
Collapse
|
11
|
Ensemble Learning of Multiple Models Using Deep Learning for Multiclass Classification of Ultrasound Images of Hepatic Masses. BIOENGINEERING (BASEL, SWITZERLAND) 2023; 10:bioengineering10010069. [PMID: 36671641 PMCID: PMC9854883 DOI: 10.3390/bioengineering10010069] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/24/2022] [Revised: 12/29/2022] [Accepted: 01/03/2023] [Indexed: 01/06/2023]
Abstract
Ultrasound (US) is often used to diagnose liver masses. Ensemble learning has recently been commonly used for image classification, but its detailed methods are not fully optimized. The purpose of this study is to investigate the usefulness and comparison of some ensemble learning and ensemble pruning techniques using multiple convolutional neural network (CNN) trained models for image classification of liver masses in US images. Dataset of the US images were classified into four categories: benign liver tumor (BLT) 6320 images, liver cyst (LCY) 2320 images, metastatic liver cancer (MLC) 9720 images, primary liver cancer (PLC) 7840 images. In this study, 250 test images were randomly selected for each class, for a total of 1000 images, and the remaining images were used as the training. 16 different CNNs were used for training and testing ultrasound images. The ensemble learning used soft voting (SV), weighted average voting (WAV), weighted hard voting (WHV) and stacking (ST). All four types of ensemble learning (SV, ST, WAV, and WHV) showed higher values of accuracy than the single CNN. All four types also showed significantly higher deep learning (DL) performance than ResNeXt101 alone. For image classification of liver masses using US images, ensemble learning improved the performance of DL over a single CNN.
Collapse
|
12
|
Chang L, Zhang Y, Zhu J, Hu L, Wang X, Zhang H, Gu Q, Chen X, Zhang S, Gao M, Wei X. An integrated nomogram combining deep learning, clinical characteristics and ultrasound features for predicting central lymph node metastasis in papillary thyroid cancer: A multicenter study. Front Endocrinol (Lausanne) 2023; 14:964074. [PMID: 36896175 PMCID: PMC9990492 DOI: 10.3389/fendo.2023.964074] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/08/2022] [Accepted: 02/10/2023] [Indexed: 02/23/2023] Open
Abstract
OBJECTIVE Central lymph node metastasis (CLNM) is a predictor of poor prognosis for papillary thyroid carcinoma (PTC) patients. The options for surgeon operation or follow-up depend on the state of CLNM while accurate prediction is a challenge for radiologists. The present study aimed to develop and validate an effective preoperative nomogram combining deep learning, clinical characteristics and ultrasound features for predicting CLNM. MATERIALS AND METHODS In this study, 3359 PTC patients who had undergone total thyroidectomy or thyroid lobectomy from two medical centers were enrolled. The patients were divided into three datasets for training, internal validation and external validation. We constructed an integrated nomogram combining deep learning, clinical characteristics and ultrasound features using multivariable logistic regression to predict CLNM in PTC patients. RESULTS Multivariate analysis indicated that the AI model-predicted value, multiple, position, microcalcification, abutment/perimeter ratio and US-reported LN status were independent risk factors predicting CLNM. The area under the curve (AUC) for the nomogram to predict CLNM was 0.812 (95% CI, 0.794-0.830) in the training cohort, 0.809 (95% CI, 0.780-0.837) in the internal validation cohort and 0.829(95%CI, 0.785-0.872) in the external validation cohort. Based on the analysis of the decision curve, our integrated nomogram was superior to other models in terms of clinical predictive ability. CONCLUSION Our proposed thyroid cancer lymph node metastasis nomogram shows favorable predictive value to assist surgeons in making appropriate surgical decisions in PTC treatment.
Collapse
Affiliation(s)
- Luchen Chang
- Department of Diagnostic and Therapeutic Ultrasonography, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin’s Clinical Research Center for Cancer, Tianjin, China
| | - Yanqiu Zhang
- Department of Diagnostic and Therapeutic Ultrasonography, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin’s Clinical Research Center for Cancer, Tianjin, China
| | - Jialin Zhu
- Department of Diagnostic and Therapeutic Ultrasonography, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin’s Clinical Research Center for Cancer, Tianjin, China
| | - Linfei Hu
- Department of Thyroid and Neck Cancer, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center of Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin’s Clinical Research Center for Cancer, Tianjin, China
| | - Xiaoqing Wang
- Department of Diagnostic and Therapeutic Ultrasonography, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin’s Clinical Research Center for Cancer, Tianjin, China
| | - Haozhi Zhang
- Department of Thyroid and Neck Cancer, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center of Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin’s Clinical Research Center for Cancer, Tianjin, China
| | - Qing Gu
- Department of Ultrasonography, Cangzhou Hospital of Integrated Traditional Chinese and Western Medicine of Hebei Province, Cangzhou, Hebei, China
| | - Xiaoyu Chen
- Department of Diagnostic and Therapeutic Ultrasonography, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin’s Clinical Research Center for Cancer, Tianjin, China
| | - Sheng Zhang
- Department of Diagnostic and Therapeutic Ultrasonography, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin’s Clinical Research Center for Cancer, Tianjin, China
| | - Ming Gao
- Department of Thyroid and Neck Cancer, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center of Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin’s Clinical Research Center for Cancer, Tianjin, China
- Department of Breast and Thyroid Surgery, Tianjin Union Medical Center, Tianjin, China
| | - Xi Wei
- Department of Diagnostic and Therapeutic Ultrasonography, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin’s Clinical Research Center for Cancer, Tianjin, China
- *Correspondence: Xi Wei,
| |
Collapse
|
13
|
Ding H, Zhang E, Fang F, Liu X, Zheng H, Yang H, Ge Y, Yang Y, Lin T. Automatic identification of benign pigmented skin lesions from clinical images using deep convolutional neural network. BMC Biotechnol 2022; 22:28. [PMID: 36217185 PMCID: PMC9552359 DOI: 10.1186/s12896-022-00755-5] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/13/2021] [Accepted: 08/26/2022] [Indexed: 11/10/2022] Open
Abstract
OBJECTIVE We aimed to develop a computer-aided detection (CAD) system for accurate identification of benign pigmented skin lesions (PSLs) from images captured using a digital camera or a smart phone. METHODS We collected a total of 12,836 clinical images which had been classified and location-labeled for training and validating. Four models were developed and validated; you only look once, v4 (YOLOv4), you only look once, v5 (YOLOv5), single shot multibox detector (SSD) and faster region-based convolutional neural networks (Faster R-CNN). The performance of the models was compared with three trained dermatologists, respectively. The accuracy of the best model was further tested and validated using smartphone-captured images. RESULTS The accuracies of YOLOv4, YOLOv5, SSD and Faster R-CNN were 0.891, 0.929, 0.852 and 0.874, respectively. The precision, sensitivity and specificity of YOLOv5 (the best model) were 0.956, 0.962 and 0.952, respectively. The accuracy of YOLOv5 model for images captured using a smart-phone was 0.905. The CAD based YOLOv5 system can potentially be used in clinical identification of PSLs. CONCLUSION We developed and validated a CAD system for automatic identification of benign PSLs using digital images. This approach may be used by non-dermatologists to easily diagnose by taking a photo of skin lesion and guide on management of PSLs.
Collapse
Affiliation(s)
- Hui Ding
- Department of Cosmetic Laser Surgery, Hospital for Skin Disease and Institute of Dermatology, Peking Union Medical College and Chinese Academy of Medical Sciences (CAMS), Nanjing, 210042, China
| | - Eejia Zhang
- Department of Cosmetic Laser Surgery, Hospital for Skin Disease and Institute of Dermatology, Peking Union Medical College and Chinese Academy of Medical Sciences (CAMS), Nanjing, 210042, China
| | - Fumin Fang
- Department of Cosmetic Laser Surgery, Hospital for Skin Disease and Institute of Dermatology, Peking Union Medical College and Chinese Academy of Medical Sciences (CAMS), Nanjing, 210042, China
| | - Xing Liu
- Department of Cosmetic Laser Surgery, Hospital for Skin Disease and Institute of Dermatology, Peking Union Medical College and Chinese Academy of Medical Sciences (CAMS), Nanjing, 210042, China
| | - Huiying Zheng
- Department of Cosmetic Laser Surgery, Hospital for Skin Disease and Institute of Dermatology, Peking Union Medical College and Chinese Academy of Medical Sciences (CAMS), Nanjing, 210042, China
| | - Hedan Yang
- Department of Cosmetic Laser Surgery, Hospital for Skin Disease and Institute of Dermatology, Peking Union Medical College and Chinese Academy of Medical Sciences (CAMS), Nanjing, 210042, China
| | - Yiping Ge
- Department of Cosmetic Laser Surgery, Hospital for Skin Disease and Institute of Dermatology, Peking Union Medical College and Chinese Academy of Medical Sciences (CAMS), Nanjing, 210042, China.
| | - Yin Yang
- Department of Cosmetic Laser Surgery, Hospital for Skin Disease and Institute of Dermatology, Peking Union Medical College and Chinese Academy of Medical Sciences (CAMS), Nanjing, 210042, China.
| | - Tong Lin
- Jiangsu Key Laboratory of Molecular Biology for Skin Diseases and STIs, Institute of Dermatology, Chinese Academy of Medical Sciences and Peking Union Medical College, Nanjing, 210042, China.
| |
Collapse
|
14
|
Sorrenti S, Dolcetti V, Radzina M, Bellini MI, Frezza F, Munir K, Grani G, Durante C, D’Andrea V, David E, Calò PG, Lori E, Cantisani V. Artificial Intelligence for Thyroid Nodule Characterization: Where Are We Standing? Cancers (Basel) 2022; 14:cancers14143357. [PMID: 35884418 PMCID: PMC9315681 DOI: 10.3390/cancers14143357] [Citation(s) in RCA: 37] [Impact Index Per Article: 18.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/09/2022] [Revised: 06/24/2022] [Accepted: 07/08/2022] [Indexed: 12/12/2022] Open
Abstract
Simple Summary In the present review, an up-to-date summary of the state of the art of artificial intelligence (AI) implementation for thyroid nodule characterization and cancer is provided. The opinion on the real effectiveness of AI systems remains controversial. Taking into consideration the largest and most scientifically valid studies, it is possible to state that AI provides results that are comparable or inferior to expert ultrasound specialists and radiologists. Promising data approve AI as a support tool and simultaneously highlight the need for a radiologist supervisory framework for AI provided results. Therefore, current solutions might be more suitable for educational purposes. Abstract Machine learning (ML) is an interdisciplinary sector in the subset of artificial intelligence (AI) that creates systems to set up logical connections using algorithms, and thus offers predictions for complex data analysis. In the present review, an up-to-date summary of the current state of the art regarding ML and AI implementation for thyroid nodule ultrasound characterization and cancer is provided, highlighting controversies over AI application as well as possible benefits of ML, such as, for example, training purposes. There is evidence that AI increases diagnostic accuracy and significantly limits inter-observer variability by using standardized mathematical algorithms. It could also be of aid in practice settings with limited sub-specialty expertise, offering a second opinion by means of radiomics and computer-assisted diagnosis. The introduction of AI represents a revolutionary event in thyroid nodule evaluation, but key issues for further implementation include integration with radiologist expertise, impact on workflow and efficiency, and performance monitoring.
Collapse
Affiliation(s)
- Salvatore Sorrenti
- Department of Surgical Sciences, “Sapienza” University of Rome, 00161 Rome, Italy; (S.S.); (V.D.); (E.L.)
| | - Vincenzo Dolcetti
- Department of Radiological, Anatomo-Pathological Sciences, “Sapienza” University of Rome, 00161 Rome, Italy; (V.D.); (V.C.)
| | - Maija Radzina
- Radiology Research Laboratory, Riga Stradins University, LV-1007 Riga, Latvia;
- Medical Faculty, University of Latvia, Diagnostic Radiology Institute, Paula Stradina Clinical University Hospital, LV-1007 Riga, Latvia
| | - Maria Irene Bellini
- Department of Surgical Sciences, “Sapienza” University of Rome, 00161 Rome, Italy; (S.S.); (V.D.); (E.L.)
- Correspondence:
| | - Fabrizio Frezza
- Department of Information Engineering, Electronics and Telecommunications, “Sapienza” University of Rome, 00184 Rome, Italy; (F.F.); (K.M.)
- Consorzio Nazionale Interuniversitario per le Telecomunicazioni (CNIT), Viale G.P. Usberti 181/A Sede Scientifica di Ingegneria-Palazzina 3, 43124 Parma, Italy
| | - Khushboo Munir
- Department of Information Engineering, Electronics and Telecommunications, “Sapienza” University of Rome, 00184 Rome, Italy; (F.F.); (K.M.)
| | - Giorgio Grani
- Department of Translational and Precision Medicine, “Sapienza” University of Rome, 00161 Rome, Italy; (G.G.); (C.D.); (E.D.)
| | - Cosimo Durante
- Department of Translational and Precision Medicine, “Sapienza” University of Rome, 00161 Rome, Italy; (G.G.); (C.D.); (E.D.)
| | - Vito D’Andrea
- Department of Surgical Sciences, “Sapienza” University of Rome, 00161 Rome, Italy; (S.S.); (V.D.); (E.L.)
| | - Emanuele David
- Department of Translational and Precision Medicine, “Sapienza” University of Rome, 00161 Rome, Italy; (G.G.); (C.D.); (E.D.)
| | - Pietro Giorgio Calò
- Department of Surgical Sciences, “Policlinico Universitario Duilio Casula”, University of Cagliari, 09042 Monserrato, Italy;
| | - Eleonora Lori
- Department of Surgical Sciences, “Sapienza” University of Rome, 00161 Rome, Italy; (S.S.); (V.D.); (E.L.)
| | - Vito Cantisani
- Department of Radiological, Anatomo-Pathological Sciences, “Sapienza” University of Rome, 00161 Rome, Italy; (V.D.); (V.C.)
| |
Collapse
|
15
|
Cleere EF, Davey MG, O’Neill S, Corbett M, O’Donnell JP, Hacking S, Keogh IJ, Lowery AJ, Kerin MJ. Radiomic Detection of Malignancy within Thyroid Nodules Using Ultrasonography-A Systematic Review and Meta-Analysis. Diagnostics (Basel) 2022; 12:diagnostics12040794. [PMID: 35453841 PMCID: PMC9027085 DOI: 10.3390/diagnostics12040794] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/24/2022] [Revised: 03/22/2022] [Accepted: 03/22/2022] [Indexed: 02/04/2023] Open
Abstract
Background: Despite investigation, 95% of thyroid nodules are ultimately benign. Radiomics is a field that uses radiological features to inform individualized patient care. We aimed to evaluate the diagnostic utility of radiomics in classifying undetermined thyroid nodules into benign and malignant using ultrasonography (US). Methods: A diagnostic test accuracy systematic review and meta-analysis was performed in accordance with PRISMA guidelines. Sensitivity, specificity, and area under curve (AUC) delineating benign and malignant lesions were recorded. Results: Seventy-five studies including 26,373 patients and 46,175 thyroid nodules met inclusion criteria. Males accounted for 24.6% of patients, while 75.4% of patients were female. Radiomics provided a pooled sensitivity of 0.87 (95% CI: 0.86−0.87) and a pooled specificity of 0.84 (95% CI: 0.84−0.85) for characterizing benign and malignant lesions. Using convolutional neural network (CNN) methods, pooled sensitivity was 0.85 (95% CI: 0.84−0.86) and pooled specificity was 0.82 (95% CI: 0.82−0.83); significantly lower than studies using non-CNN: sensitivity 0.90 (95% CI: 0.89−0.90) and specificity 0.88 (95% CI: 0.87−0.89) (p < 0.05). The diagnostic ability of radiologists and radiomics were comparable for both sensitivity (OR 0.98) and specificity (OR 0.95). Conclusions: Radiomic analysis using US provides a reproducible, reliable evaluation of undetermined thyroid nodules when compared to current best practice.
Collapse
Affiliation(s)
- Eoin F. Cleere
- The Lambe Institute for Translational Research, National University of Ireland, H91 YR71 Galway, Ireland; (M.G.D.); (A.J.L.); (M.J.K.)
- Department of Otolaryngology, Galway University Hospitals, H91 YR71 Galway, Ireland; (M.C.); (I.J.K.)
- Correspondence:
| | - Matthew G. Davey
- The Lambe Institute for Translational Research, National University of Ireland, H91 YR71 Galway, Ireland; (M.G.D.); (A.J.L.); (M.J.K.)
| | - Shane O’Neill
- Department of Breast and Endocrine Surgery, Galway University Hospitals, H91 YR71 Galway, Ireland;
| | - Mel Corbett
- Department of Otolaryngology, Galway University Hospitals, H91 YR71 Galway, Ireland; (M.C.); (I.J.K.)
| | - John P O’Donnell
- Department of Radiology, Galway University Hospitals, H91 YR71 Galway, Ireland;
| | - Sean Hacking
- Department of Pathology and Laboratory Medicine, Warren Alpert Medical School of Brown University, Providence, RI 02903, USA;
| | - Ivan J. Keogh
- Department of Otolaryngology, Galway University Hospitals, H91 YR71 Galway, Ireland; (M.C.); (I.J.K.)
| | - Aoife J. Lowery
- The Lambe Institute for Translational Research, National University of Ireland, H91 YR71 Galway, Ireland; (M.G.D.); (A.J.L.); (M.J.K.)
- Department of Breast and Endocrine Surgery, Galway University Hospitals, H91 YR71 Galway, Ireland;
| | - Michael J. Kerin
- The Lambe Institute for Translational Research, National University of Ireland, H91 YR71 Galway, Ireland; (M.G.D.); (A.J.L.); (M.J.K.)
- Department of Breast and Endocrine Surgery, Galway University Hospitals, H91 YR71 Galway, Ireland;
| |
Collapse
|
16
|
Deep learning-based artificial intelligence model to assist thyroid nodule diagnosis and management: a multicentre diagnostic study. LANCET DIGITAL HEALTH 2021; 3:e250-e259. [PMID: 33766289 DOI: 10.1016/s2589-7500(21)00041-8] [Citation(s) in RCA: 107] [Impact Index Per Article: 35.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/27/2020] [Revised: 02/01/2021] [Accepted: 02/21/2021] [Indexed: 02/06/2023]
Abstract
BACKGROUND Strategies for integrating artificial intelligence (AI) into thyroid nodule management require additional development and testing. We developed a deep-learning AI model (ThyNet) to differentiate between malignant tumours and benign thyroid nodules and aimed to investigate how ThyNet could help radiologists improve diagnostic performance and avoid unnecessary fine needle aspiration. METHODS ThyNet was developed and trained on 18 049 images of 8339 patients (training set) from two hospitals (the First Affiliated Hospital of Sun Yat-sen University, Guangzhou, China, and Sun Yat-sen University Cancer Center, Guangzhou, China) and tested on 4305 images of 2775 patients (total test set) from seven hospitals (the First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, China; the Sixth Affiliated Hospital of Sun Yat-sen University, Guangzhou, China; the Guangzhou Army General Hospital, Guangzhou, China; the Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, China; the First Affiliated Hospital of Sun Yat-sen University; Sun Yat-sen University Cancer Center; and the First Affiliated Hospital of Guangxi Medical University, Nanning, China) in three stages. All nodules in the training and total test set were pathologically confirmed. The diagnostic performance of ThyNet was first compared with 12 radiologists (test set A); a ThyNet-assisted strategy, in which ThyNet assisted diagnoses made by radiologists, was developed to improve diagnostic performance of radiologists using images (test set B); the ThyNet assisted strategy was then tested in a real-world clinical setting (using images and videos; test set C). In a simulated scenario, the number of unnecessary fine needle aspirations avoided by ThyNet-assisted strategy was calculated. FINDINGS The area under the receiver operating characteristic curve (AUROC) for accurate diagnosis of ThyNet (0·922 [95% CI 0·910-0·934]) was significantly higher than that of the radiologists (0·839 [0·834-0·844]; p<0·0001). Furthermore, ThyNet-assisted strategy improved the pooled AUROC of the radiologists from 0·837 (0·832-0·842) when diagnosing without ThyNet to 0·875 (0·871-0·880; p<0·0001) with ThyNet for reviewing images, and from 0·862 (0·851-0·872) to 0·873 (0·863-0·883; p<0·0001) in the clinical test, which used images and videos. In the simulated scenario, the number of fine needle aspirations decreased from 61·9% to 35·2% using the ThyNet-assisted strategy, while missed malignancy decreased from 18·9% to 17·0%. INTERPRETATION The ThyNet-assisted strategy can significantly improve the diagnostic performance of radiologists and help reduce unnecessary fine needle aspirations for thyroid nodules. FUNDING National Natural Science Foundation of China and Guangzhou Science and Technology Project.
Collapse
|
17
|
Wei X, Zhu J, Zhang H, Gao H, Yu R, Liu Z, Zheng X, Gao M, Zhang S. Visual Interpretability in Computer-Assisted Diagnosis of Thyroid Nodules Using Ultrasound Images. Med Sci Monit 2020; 26:e927007. [PMID: 32798214 PMCID: PMC7446277 DOI: 10.12659/msm.927007] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/06/2023] Open
Abstract
BACKGROUND The number of studies on deep learning in artificial intelligence (AI)-assisted diagnosis of thyroid nodules is increasing. However, it is difficult to explain what the models actually learn in artificial intelligence-assisted medical research. Our aim is to investigate the visual interpretability of the computer-assisted diagnosis of malignant and benign thyroid nodules using ultrasound images. MATERIAL AND METHODS We designed and implemented 2 experiments to test whether our proposed model learned to interpret the ultrasound features used by ultrasound experts to diagnose thyroid nodules. First, in an anteroposterior/transverse (A/T) ratio experiment, multiple models were trained by changing the A/T ratio of the original nodules, and their classification, accuracy, sensitivity, and specificity were tested. Second, in a visualization experiment, class activation mapping used global average pooling and a fully connected layer to visualize the neural network to show the most important features. We also examined the importance of data preprocessing. RESULTS The A/T ratio experiment showed that after changing the A/T ratio of the nodules, the accuracy of the neural network model was reduced by 9.24-30.45%, indicating that our neural network model learned the A/T ratio information of the nodules. The visual experiment results showed that the nodule margins had a strong influence on the prediction of the neural network. CONCLUSIONS This study was an active exploration of interpretability in the deep learning classification of thyroid nodules. It demonstrated the neural network-visualized model focused on irregular nodule margins and the A/T ratio to classify thyroid nodules.
Collapse
Affiliation(s)
- Xi Wei
- Department of Diagnostic and Therapeutic Ultrasonography, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center of Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Tianjin, China (mainland)
| | - Jialin Zhu
- Department of Diagnostic and Therapeutic Ultrasonography, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center of Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Tianjin, China (mainland)
| | - Haozhi Zhang
- Department of Thyroid and Neck Cancer, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center of Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Tianjin, China (mainland)
| | - Hongyan Gao
- Department of Ultrasonography, Tianjin Xiqing District Women and Children's Health and Family Planning Service Center, Tianjin, China (mainland)
| | - Ruiguo Yu
- College of Intelligence and Computing, Tianjin University, Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin Key Laboratory of Advanced Networking, Tianjin, China (mainland)
| | - Zhiqiang Liu
- College of Intelligence and Computing, Tianjin University, Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin Key Laboratory of Advanced Networking, Tianjin, China (mainland)
| | - Xiangqian Zheng
- Department of Thyroid and Neck Cancer, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center of Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Tianjin, China (mainland)
| | - Ming Gao
- Department of Thyroid and Neck Cancer, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center of Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Tianjin, China (mainland)
| | - Sheng Zhang
- Department of Diagnostic and Therapeutic Ultrasonography, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center of Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin's Clinical Research Center for Cancer, Tianjin, China (mainland)
| |
Collapse
|