Diagnosing thyroid nodules with atypia of undetermined significance/follicular lesion of undetermined significance cytology with the deep convolutional neural network
Abstract To compare the diagnostic performances of physicians and a deep convolutional neural network (CNN) predicting malignancy with ultrasonography images of thyroid nodules with atypia of undetermined significance (AUS)/follicular lesion of undetermined significance (FLUS) results on fine-needle...
Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/123d2a86c3da4deeb87fbe58d55bf840 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:123d2a86c3da4deeb87fbe58d55bf840 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:123d2a86c3da4deeb87fbe58d55bf8402021-12-02T17:13:16ZDiagnosing thyroid nodules with atypia of undetermined significance/follicular lesion of undetermined significance cytology with the deep convolutional neural network10.1038/s41598-021-99622-02045-2322https://doaj.org/article/123d2a86c3da4deeb87fbe58d55bf8402021-10-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-99622-0https://doaj.org/toc/2045-2322Abstract To compare the diagnostic performances of physicians and a deep convolutional neural network (CNN) predicting malignancy with ultrasonography images of thyroid nodules with atypia of undetermined significance (AUS)/follicular lesion of undetermined significance (FLUS) results on fine-needle aspiration (FNA). This study included 202 patients with 202 nodules ≥ 1 cm AUS/FLUS on FNA, and underwent surgery in one of 3 different institutions. Diagnostic performances were compared between 8 physicians (4 radiologists, 4 endocrinologists) with varying experience levels and CNN, and AUS/FLUS subgroups were analyzed. Interobserver variability was assessed among the 8 physicians. Of the 202 nodules, 158 were AUS, and 44 were FLUS; 86 were benign, and 116 were malignant. The area under the curves (AUCs) of the 8 physicians and CNN were 0.680–0.722 and 0.666, without significant differences (P > 0.05). In the subgroup analysis, the AUCs for the 8 physicians and CNN were 0.657–0.768 and 0.652 for AUS, 0.469–0.674 and 0.622 for FLUS. Interobserver agreements were moderate (k = 0.543), substantial (k = 0.652), and moderate (k = 0.455) among the 8 physicians, 4 radiologists, and 4 endocrinologists. For thyroid nodules with AUS/FLUS cytology, the diagnostic performance of CNN to differentiate malignancy with US images was comparable to that of physicians with variable experience levels.Inyoung YounEunjung LeeJung Hyun YoonHye Sun LeeMi-Ri KwonJuhee MoonSunyoung KangSeul Ki KwonKyong Yeun JungYoung Joo ParkDo Joon ParkSun Wook ChoJin Young KwakNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Medicine R Science Q |
| spellingShingle |
Medicine R Science Q Inyoung Youn Eunjung Lee Jung Hyun Yoon Hye Sun Lee Mi-Ri Kwon Juhee Moon Sunyoung Kang Seul Ki Kwon Kyong Yeun Jung Young Joo Park Do Joon Park Sun Wook Cho Jin Young Kwak Diagnosing thyroid nodules with atypia of undetermined significance/follicular lesion of undetermined significance cytology with the deep convolutional neural network |
| description |
Abstract To compare the diagnostic performances of physicians and a deep convolutional neural network (CNN) predicting malignancy with ultrasonography images of thyroid nodules with atypia of undetermined significance (AUS)/follicular lesion of undetermined significance (FLUS) results on fine-needle aspiration (FNA). This study included 202 patients with 202 nodules ≥ 1 cm AUS/FLUS on FNA, and underwent surgery in one of 3 different institutions. Diagnostic performances were compared between 8 physicians (4 radiologists, 4 endocrinologists) with varying experience levels and CNN, and AUS/FLUS subgroups were analyzed. Interobserver variability was assessed among the 8 physicians. Of the 202 nodules, 158 were AUS, and 44 were FLUS; 86 were benign, and 116 were malignant. The area under the curves (AUCs) of the 8 physicians and CNN were 0.680–0.722 and 0.666, without significant differences (P > 0.05). In the subgroup analysis, the AUCs for the 8 physicians and CNN were 0.657–0.768 and 0.652 for AUS, 0.469–0.674 and 0.622 for FLUS. Interobserver agreements were moderate (k = 0.543), substantial (k = 0.652), and moderate (k = 0.455) among the 8 physicians, 4 radiologists, and 4 endocrinologists. For thyroid nodules with AUS/FLUS cytology, the diagnostic performance of CNN to differentiate malignancy with US images was comparable to that of physicians with variable experience levels. |
| format |
article |
| author |
Inyoung Youn Eunjung Lee Jung Hyun Yoon Hye Sun Lee Mi-Ri Kwon Juhee Moon Sunyoung Kang Seul Ki Kwon Kyong Yeun Jung Young Joo Park Do Joon Park Sun Wook Cho Jin Young Kwak |
| author_facet |
Inyoung Youn Eunjung Lee Jung Hyun Yoon Hye Sun Lee Mi-Ri Kwon Juhee Moon Sunyoung Kang Seul Ki Kwon Kyong Yeun Jung Young Joo Park Do Joon Park Sun Wook Cho Jin Young Kwak |
| author_sort |
Inyoung Youn |
| title |
Diagnosing thyroid nodules with atypia of undetermined significance/follicular lesion of undetermined significance cytology with the deep convolutional neural network |
| title_short |
Diagnosing thyroid nodules with atypia of undetermined significance/follicular lesion of undetermined significance cytology with the deep convolutional neural network |
| title_full |
Diagnosing thyroid nodules with atypia of undetermined significance/follicular lesion of undetermined significance cytology with the deep convolutional neural network |
| title_fullStr |
Diagnosing thyroid nodules with atypia of undetermined significance/follicular lesion of undetermined significance cytology with the deep convolutional neural network |
| title_full_unstemmed |
Diagnosing thyroid nodules with atypia of undetermined significance/follicular lesion of undetermined significance cytology with the deep convolutional neural network |
| title_sort |
diagnosing thyroid nodules with atypia of undetermined significance/follicular lesion of undetermined significance cytology with the deep convolutional neural network |
| publisher |
Nature Portfolio |
| publishDate |
2021 |
| url |
https://doaj.org/article/123d2a86c3da4deeb87fbe58d55bf840 |
| work_keys_str_mv |
AT inyoungyoun diagnosingthyroidnoduleswithatypiaofundeterminedsignificancefollicularlesionofundeterminedsignificancecytologywiththedeepconvolutionalneuralnetwork AT eunjunglee diagnosingthyroidnoduleswithatypiaofundeterminedsignificancefollicularlesionofundeterminedsignificancecytologywiththedeepconvolutionalneuralnetwork AT junghyunyoon diagnosingthyroidnoduleswithatypiaofundeterminedsignificancefollicularlesionofundeterminedsignificancecytologywiththedeepconvolutionalneuralnetwork AT hyesunlee diagnosingthyroidnoduleswithatypiaofundeterminedsignificancefollicularlesionofundeterminedsignificancecytologywiththedeepconvolutionalneuralnetwork AT mirikwon diagnosingthyroidnoduleswithatypiaofundeterminedsignificancefollicularlesionofundeterminedsignificancecytologywiththedeepconvolutionalneuralnetwork AT juheemoon diagnosingthyroidnoduleswithatypiaofundeterminedsignificancefollicularlesionofundeterminedsignificancecytologywiththedeepconvolutionalneuralnetwork AT sunyoungkang diagnosingthyroidnoduleswithatypiaofundeterminedsignificancefollicularlesionofundeterminedsignificancecytologywiththedeepconvolutionalneuralnetwork AT seulkikwon diagnosingthyroidnoduleswithatypiaofundeterminedsignificancefollicularlesionofundeterminedsignificancecytologywiththedeepconvolutionalneuralnetwork AT kyongyeunjung diagnosingthyroidnoduleswithatypiaofundeterminedsignificancefollicularlesionofundeterminedsignificancecytologywiththedeepconvolutionalneuralnetwork AT youngjoopark diagnosingthyroidnoduleswithatypiaofundeterminedsignificancefollicularlesionofundeterminedsignificancecytologywiththedeepconvolutionalneuralnetwork AT dojoonpark diagnosingthyroidnoduleswithatypiaofundeterminedsignificancefollicularlesionofundeterminedsignificancecytologywiththedeepconvolutionalneuralnetwork AT sunwookcho diagnosingthyroidnoduleswithatypiaofundeterminedsignificancefollicularlesionofundeterminedsignificancecytologywiththedeepconvolutionalneuralnetwork AT jinyoungkwak diagnosingthyroidnoduleswithatypiaofundeterminedsignificancefollicularlesionofundeterminedsignificancecytologywiththedeepconvolutionalneuralnetwork |
| _version_ |
1718381362558271488 |