Rechercher
image du produit
Lancet Oncology, The

S'abonner

Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images: a retrospective, multicohort, diagnostic study - 04/02/19

Doi : 10.1016/S1470-2045(18)30762-9 
Xiangchun Li, ProfPhD a, *, †, Sheng Zhang, ProfMD b, *, †, Qiang Zhang, MD c, *, Xi Wei, MD b, *, Yi Pan, MD d, Jing Zhao, MD b, Xiaojie Xin, MD b, Chunxin Qin, MD g, Xiaoqing Wang, MD b, Jianxin Li, MD h, Fan Yang, MD b, Yanhui Zhao, MD i, Meng Yang, PhD e, Qinghua Wang, MS e, Zhiming Zheng, MD j, Xiangqian Zheng, MD j, Xiangming Yang, MD k, Christopher T Whitlow, MD l, Metin Nafi Gurcan, ProfPhD m, Lun Zhang, ProfMD c, Xudong Wang, MD c, Boris C Pasche, ProfMD n, Ming Gao, ProfMD f, Wei Zhang, ProfPhD n, †, Kexin Chen, ProfMD e, ⁎, †
a Tianjin Cancer Institute, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy of Tianjin, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, Tianjin, China 
b Department of Diagnostic and Therapeutic Ultrasonography, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy of Tianjin, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, Tianjin, China 
c Department of Maxillofacial and Otorhinolaryngology Oncology, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy of Tianjin, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, Tianjin, China 
d Department of Pathology, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy of Tianjin, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, Tianjin, China 
e Department of Epidemiology and Biostatistics, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy of Tianjin, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, Tianjin, China 
f Department of Thyroid and Neck Cancer, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy of Tianjin, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, Tianjin, China 
g Department of Thyroid and Breast Surgery, Weihai Municipal Hospital, Shandong, China 
h Department of Ultrasonography, Weihai Municipal Hospital, Shandong, China 
i Department of Ultrasonography, Affiliated Hospital of Chifeng University, Inner Mongolia, China 
j Department of Ultrasonography, Integrated Traditional Chinese and Western Medicine Hospital, Jilin, China 
k Department of Ultrasonography, Dezhou Municiple Hospital, Shandong, China 
l Departments of Radiology and Biomedical Engineering, Wake Forest School of Medicine, Winston-Salem, NC, USA 
m Center for Biomedical Informatics Department of Internal Medicine, Wake Forest School of Medicine, Winston-Salem, NC, USA 
n Wake Forest Baptist Comprehensive Cancer Center, Wake Forest Baptist Medical Center, Department of Cancer Biology, Wake Forest School of Medicine, Winston-Salem, NC, USA 

* Correspondence to: Prof Kexin Chen, Department of Epidemiology and Biostatistics, Tianjin Medical University Cancer Institute and Hospital, Tianjin 300060, China Department of Epidemiology and Biostatistics Tianjin Medical University Cancer Institute and Hospital Tianjin 300060 China

Summary

Background

The incidence of thyroid cancer is rising steadily because of overdiagnosis and overtreatment conferred by widespread use of sensitive imaging techniques for screening. This overall incidence growth is especially driven by increased diagnosis of indolent and well-differentiated papillary subtype and early-stage thyroid cancer, whereas the incidence of advanced-stage thyroid cancer has increased marginally. Thyroid ultrasound is frequently used to diagnose thyroid cancer. The aim of this study was to use deep convolutional neural network (DCNN) models to improve the diagnostic accuracy of thyroid cancer by analysing sonographic imaging data from clinical ultrasounds.

Methods

We did a retrospective, multicohort, diagnostic study using ultrasound images sets from three hospitals in China. We developed and trained the DCNN model on the training set, 131 731 ultrasound images from 17 627 patients with thyroid cancer and 180 668 images from 25 325 controls from the thyroid imaging database at Tianjin Cancer Hospital. Clinical diagnosis of the training set was made by 16 radiologists from Tianjin Cancer Hospital. Images from anatomical sites that were judged as not having cancer were excluded from the training set and only individuals with suspected thyroid cancer underwent pathological examination to confirm diagnosis. The model’s diagnostic performance was validated in an internal validation set from Tianjin Cancer Hospital (8606 images from 1118 patients) and two external datasets in China (the Integrated Traditional Chinese and Western Medicine Hospital, Jilin, 741 images from 154 patients; and the Weihai Municipal Hospital, Shandong, 11 039 images from 1420 patients). All individuals with suspected thyroid cancer after clinical examination in the validation sets had pathological examination. We also compared the specificity and sensitivity of the DCNN model with the performance of six skilled thyroid ultrasound radiologists on the three validation sets.

Findings

Between Jan 1, 2012, and March 28, 2018, ultrasound images for the four study cohorts were obtained. The model achieved high performance in identifying thyroid cancer patients in the validation sets tested, with area under the curve values of 0·947 (95% CI 0·935–0·959) for the Tianjin internal validation set, 0·912 (95% CI 0·865–0·958) for the Jilin external validation set, and 0·908 (95% CI 0·891–0·925) for the Weihai external validation set. The DCNN model also showed improved performance in identifying thyroid cancer patients versus skilled radiologists. For the Tianjin internal validation set, sensitivity was 93·4% (95% CI 89·6–96·1) versus 96·9% (93·9–98·6; p=0·003) and specificity was 86·1% (81·1–90·2) versus 59·4% (53·0–65·6; p<0·0001). For the Jilin external validation set, sensitivity was 84·3% (95% CI 73·6–91·9) versus 92·9% (84·1–97·6; p=0·048) and specificity was 86·9% (95% CI 77·8–93·3) versus 57·1% (45·9–67·9; p<0·0001). For the Weihai external validation set, sensitivity was 84·7% (95% CI 77·0–90·7) versus 89·0% (81·9–94·0; p=0·25) and specificity was 87·8% (95% CI 81·6–92·5) versus 68·6% (60·7–75·8; p<0·0001).

Interpretation

The DCNN model showed similar sensitivity and improved specificity in identifying patients with thyroid cancer compared with a group of skilled radiologists. The improved technical performance of the DCNN model warrants further investigation as part of randomised clinical trials.

Funding

The Program for Changjiang Scholars and Innovative Research Team in University in China, and National Natural Science Foundation of China.

Le texte complet de cet article est disponible en PDF.

Plan


© 2019  Elsevier Ltd. Tous droits réservés.
Ajouter à ma bibliothèque Retirer de ma bibliothèque Imprimer
Export

    Export citations

  • Fichier

    •

  • Contenu

    •

Vol 20 - N° 2

P. 193-201 - février 2019 Retour au numéro
Article précédent Article précédent
  • Insulin potentiation therapy for cancer?
  • Tristan M Sissung, Keith T Schmidt, William D Figg
| Article suivant Article suivant
  • PET-adapted treatment for newly diagnosed advanced Hodgkin lymphoma (AHL2011): a randomised, multicentre, non-inferiority, phase 3 study
  • René-Olivier Casasnovas, Reda Bouabdallah, Pauline Brice, Julien Lazarovici, Hervé Ghesquieres, Aspasia Stamatoullas, Jehan Dupuis, Anne-Claire Gac, Thomas Gastinne, Bertrand Joly, Krimo Bouabdallah, Emmanuelle Nicolas-Virelizier, Pierre Feugier, Franck Morschhauser, Richard Delarue, Hassan Farhat, Philippe Quittet, Alina Berriolo-Riedinger, Adrian Tempescul, Véronique Edeline, Hervé Maisonneuve, Luc-Matthieu Fornecker, Thierry Lamy, Alain Delmer, Peggy Dartigues, Laurent Martin, Marc André, Nicolas Mounier, Alexandra Traverse-Glehen, Michel Meignan

Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.

Déjà abonné à cette revue ?

Accès rapides

Mon compte

Aide & support

Plateformes Elsevier Masson

Déclaration CNIL

EM-CONSULTE.COM est déclaré à la CNIL, déclaration n° 1286925.

En application de la loi nº78-17 du 6 janvier 1978 relative à l'informatique, aux fichiers et aux libertés, vous disposez des droits d'opposition (art.26 de la loi), d'accès (art.34 à 38 de la loi), et de rectification (art.36 de la loi) des données vous concernant. Ainsi, vous pouvez exiger que soient rectifiées, complétées, clarifiées, mises à jour ou effacées les informations vous concernant qui sont inexactes, incomplètes, équivoques, périmées ou dont la collecte ou l'utilisation ou la conservation est interdite.
Les informations personnelles concernant les visiteurs de notre site, y compris leur identité, sont confidentielles.
Le responsable du site s'engage sur l'honneur à respecter les conditions légales de confidentialité applicables en France et à ne pas divulguer ces informations à des tiers.

Tout le contenu de ce site: Copyright © 2024 Elsevier, ses concédants de licence et ses contributeurs. Tout les droits sont réservés, y compris ceux relatifs à l'exploration de textes et de données, a la formation en IA et aux technologies similaires. Pour tout contenu en libre accès, les conditions de licence Creative Commons s'appliquent.