An artificial intelligence ultrasound system’s ability to distinguish benign from malignant follicular-patterned lesions
ObjectivesTo evaluate the application value of a generally trained artificial intelligence (AI) automatic diagnosis system in the malignancy diagnosis of follicular-patterned thyroid lesions (FPTL), including follicular thyroid carcinoma (FTC), adenomatoid hyperplasia nodule (AHN) and follicular thy...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-10-01
|
| Series: | Frontiers in Endocrinology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fendo.2022.981403/full |
| _version_ | 1811192265947742208 |
|---|---|
| author | Dong Xu Dong Xu Dong Xu Dong Xu Yuan Wang Hao Wu Wenliang Lu Wanru Chang Jincao Yao Meiying Yan Chanjuan Peng Chen Yang Liping Wang Liping Wang Lei Xu Lei Xu Lei Xu |
| author_facet | Dong Xu Dong Xu Dong Xu Dong Xu Yuan Wang Hao Wu Wenliang Lu Wanru Chang Jincao Yao Meiying Yan Chanjuan Peng Chen Yang Liping Wang Liping Wang Lei Xu Lei Xu Lei Xu |
| author_sort | Dong Xu |
| collection | DOAJ |
| description | ObjectivesTo evaluate the application value of a generally trained artificial intelligence (AI) automatic diagnosis system in the malignancy diagnosis of follicular-patterned thyroid lesions (FPTL), including follicular thyroid carcinoma (FTC), adenomatoid hyperplasia nodule (AHN) and follicular thyroid adenoma (FTA) and compare the diagnostic performance with radiologists of different experience levels.MethodsWe retrospectively reviewed 607 patients with 699 thyroid nodules that included 168 malignant nodules by using postoperative pathology as the gold standard, and compared the diagnostic performances of three radiologists (one junior, two senior) and that of AI automatic diagnosis system in malignancy diagnosis of FPTL in terms of sensitivity, specificity and accuracy, respectively. Pairwise t-test was used to evaluate the statistically significant difference.ResultsThe accuracy of the AI system in malignancy diagnosis was 0.71, which was higher than the best radiologist in this study by a margin of 0.09 with a p-value of 2.08×10-5. Two radiologists had higher sensitivity (0.84 and 0.78) than that of the AI system (0.69) at the cost of having much lower specificity (0.35, 0.57 versus 0.71). One senior radiologist showed balanced sensitivity and specificity (0.62 and 0.54) but both were lower than that of the AI system.ConclusionsThe generally trained AI automatic diagnosis system can potentially assist radiologists for distinguishing FTC from other FPTL cases that share poorly distinguishable ultrasonographical features. |
| first_indexed | 2024-04-11T23:49:35Z |
| format | Article |
| id | doaj.art-3d9722e9330c40c99408e6d82ec0f9cf |
| institution | Directory Open Access Journal |
| issn | 1664-2392 |
| language | English |
| last_indexed | 2024-04-11T23:49:35Z |
| publishDate | 2022-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Endocrinology |
| spelling | doaj.art-3d9722e9330c40c99408e6d82ec0f9cf2022-12-22T03:56:31ZengFrontiers Media S.A.Frontiers in Endocrinology1664-23922022-10-011310.3389/fendo.2022.981403981403An artificial intelligence ultrasound system’s ability to distinguish benign from malignant follicular-patterned lesionsDong Xu0Dong Xu1Dong Xu2Dong Xu3Yuan Wang4Hao Wu5Wenliang Lu6Wanru Chang7Jincao Yao8Meiying Yan9Chanjuan Peng10Chen Yang11Liping Wang12Liping Wang13Lei Xu14Lei Xu15Lei Xu16Department of Ultrasonography, The Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital), Institute of Basic Medicine and Cancer, Chinese Academy of Sciences, Hangzhou, ChinaUltrasound Branch, Zhejiang Society for Mathematical Medicine, Hangzhou, ChinaKey Laboratory of Head & Neck Cancer Translational Research of Zhejiang Province, Zhejiang Provincial Research Center for Cancer Intelligent Diagnosis and Molecular Technology, Hangzhou, ChinaShanghai Tenth People’s Hospital, Tongji University School of Medicine, Shanghai, ChinaSchool of Mathematical Sciences, Zhejiang University, Hangzhou, ChinaDepartment of Ultrasound, The Second Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou, ChinaSchool of Mathematical Sciences, Zhejiang University, Hangzhou, ChinaSchool of Mathematical Sciences, Zhejiang University, Hangzhou, ChinaDepartment of Ultrasonography, The Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital), Institute of Basic Medicine and Cancer, Chinese Academy of Sciences, Hangzhou, ChinaDepartment of Ultrasonography, The Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital), Institute of Basic Medicine and Cancer, Chinese Academy of Sciences, Hangzhou, ChinaDepartment of Ultrasonography, The Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital), Institute of Basic Medicine and Cancer, Chinese Academy of Sciences, Hangzhou, ChinaDepartment of Ultrasonography, The Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital), Institute of Basic Medicine and Cancer, Chinese Academy of Sciences, Hangzhou, ChinaDepartment of Ultrasonography, The Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital), Institute of Basic Medicine and Cancer, Chinese Academy of Sciences, Hangzhou, ChinaUltrasound Branch, Zhejiang Society for Mathematical Medicine, Hangzhou, ChinaUltrasound Branch, Zhejiang Society for Mathematical Medicine, Hangzhou, ChinaGroup of Computational Imaging and Digital Medicine, Zhejiang Qiushi Institute for Mathematical Medicine, Hangzhou, ChinaGroup of Intelligent Medical Devices, South and North Lake Institute for Medical Artificial Intelligence, Haiyan, ChinaObjectivesTo evaluate the application value of a generally trained artificial intelligence (AI) automatic diagnosis system in the malignancy diagnosis of follicular-patterned thyroid lesions (FPTL), including follicular thyroid carcinoma (FTC), adenomatoid hyperplasia nodule (AHN) and follicular thyroid adenoma (FTA) and compare the diagnostic performance with radiologists of different experience levels.MethodsWe retrospectively reviewed 607 patients with 699 thyroid nodules that included 168 malignant nodules by using postoperative pathology as the gold standard, and compared the diagnostic performances of three radiologists (one junior, two senior) and that of AI automatic diagnosis system in malignancy diagnosis of FPTL in terms of sensitivity, specificity and accuracy, respectively. Pairwise t-test was used to evaluate the statistically significant difference.ResultsThe accuracy of the AI system in malignancy diagnosis was 0.71, which was higher than the best radiologist in this study by a margin of 0.09 with a p-value of 2.08×10-5. Two radiologists had higher sensitivity (0.84 and 0.78) than that of the AI system (0.69) at the cost of having much lower specificity (0.35, 0.57 versus 0.71). One senior radiologist showed balanced sensitivity and specificity (0.62 and 0.54) but both were lower than that of the AI system.ConclusionsThe generally trained AI automatic diagnosis system can potentially assist radiologists for distinguishing FTC from other FPTL cases that share poorly distinguishable ultrasonographical features.https://www.frontiersin.org/articles/10.3389/fendo.2022.981403/fullthyroid adenomasadenocarcinomasfollicularultrasonographyartificial intelligence |
| spellingShingle | Dong Xu Dong Xu Dong Xu Dong Xu Yuan Wang Hao Wu Wenliang Lu Wanru Chang Jincao Yao Meiying Yan Chanjuan Peng Chen Yang Liping Wang Liping Wang Lei Xu Lei Xu Lei Xu An artificial intelligence ultrasound system’s ability to distinguish benign from malignant follicular-patterned lesions Frontiers in Endocrinology thyroid adenomas adenocarcinomas follicular ultrasonography artificial intelligence |
| title | An artificial intelligence ultrasound system’s ability to distinguish benign from malignant follicular-patterned lesions |
| title_full | An artificial intelligence ultrasound system’s ability to distinguish benign from malignant follicular-patterned lesions |
| title_fullStr | An artificial intelligence ultrasound system’s ability to distinguish benign from malignant follicular-patterned lesions |
| title_full_unstemmed | An artificial intelligence ultrasound system’s ability to distinguish benign from malignant follicular-patterned lesions |
| title_short | An artificial intelligence ultrasound system’s ability to distinguish benign from malignant follicular-patterned lesions |
| title_sort | artificial intelligence ultrasound system s ability to distinguish benign from malignant follicular patterned lesions |
| topic | thyroid adenomas adenocarcinomas follicular ultrasonography artificial intelligence |
| url | https://www.frontiersin.org/articles/10.3389/fendo.2022.981403/full |
| work_keys_str_mv | AT dongxu anartificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT dongxu anartificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT dongxu anartificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT dongxu anartificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT yuanwang anartificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT haowu anartificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT wenlianglu anartificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT wanruchang anartificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT jincaoyao anartificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT meiyingyan anartificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT chanjuanpeng anartificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT chenyang anartificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT lipingwang anartificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT lipingwang anartificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT leixu anartificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT leixu anartificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT leixu anartificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT dongxu artificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT dongxu artificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT dongxu artificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT dongxu artificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT yuanwang artificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT haowu artificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT wenlianglu artificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT wanruchang artificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT jincaoyao artificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT meiyingyan artificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT chanjuanpeng artificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT chenyang artificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT lipingwang artificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT lipingwang artificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT leixu artificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT leixu artificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions AT leixu artificialintelligenceultrasoundsystemsabilitytodistinguishbenignfrommalignantfollicularpatternedlesions |