Deep learning models for thyroid nodules diagnosis of fine-needle aspiration biopsy: a retrospective, prospective, multicentre study in China.

Accurately distinguishing between malignant and benign thyroid nodules through fine-needle aspiration cytopathology is crucial for appropriate therapeutic intervention. However, cytopathologic diagnosis is time consuming and hindered by the shortage of experienced cytopathologists. Reliable assistive tools could improve cytopathologic diagnosis efficiency and accuracy. We aimed to develop and test an artificial intelligence (AI)-assistive system for thyroid cytopathologic diagnosis according to the Thyroid Bethesda Reporting System. 11 254 whole-slide images (WSIs) from 4037 patients were used to train deep learning models. Among the selected WSIs, cell level was manually annotated by cytopathologists according to The Bethesda System for Reporting Thyroid Cytopathology (TBSRTC) guidelines of the second edition (2017 version). A retrospective dataset of 5638 WSIs of 2914 patients from four medical centres was used for validation. 469 patients were recruited for the prospective study of the performance of AI models and their 537 thyroid nodule samples were used. Cohorts for training and validation were enrolled between Jan 1, 2016, and Aug 1, 2022, and the prospective dataset was recruited between Aug 1, 2022, and Jan 1, 2023. The performance of our AI models was estimated as the area under the receiver operating characteristic (AUROC), sensitivity, specificity, accuracy, positive predictive value, and negative predictive value. The primary outcomes were the prediction sensitivity and specificity of the model to assist cyto-diagnosis of thyroid nodules. The AUROC of TBSRTC III+ (which distinguishes benign from TBSRTC classes III, IV, V, and VI) was 0·930 (95% CI 0·921-0·939) for Sun Yat-sen Memorial Hospital of Sun Yat-sen University (SYSMH) internal validation and 0·944 (0·929 - 0·959), 0·939 (0·924-0·955), 0·971 (0·938-1·000) for The First People's Hospital of Foshan (FPHF), Sichuan Cancer Hospital & Institute (SCHI), and The Third Affiliated Hospital of Guangzhou Medical University (TAHGMU) medical centres, respectively. The AUROC of TBSRTC V+ (which distinguishes benign from TBSRTC classes V and VI) was 0·990 (95% CI 0·986-0·995) for SYSMH internal validation and 0·988 (0·980-0·995), 0·965 (0·953-0·977), and 0·991 (0·972-1·000) for FPHF, SCHI, and TAHGMU medical centres, respectively. For the prospective study at SYSMH, the AUROC of TBSRTC III+ and TBSRTC V+ was 0·977 and 0·981, respectively. With the assistance of AI, the specificity of junior cytopathologists was boosted from 0·887 (95% CI 0·8440-0·922) to 0·993 (0·974-0·999) and the accuracy was improved from 0·877 (0·846-0·904) to 0·948 (0·926-0·965). 186 atypia of undetermined significance samples from 186 patients with BRAF mutation information were collected; 43 of them harbour the BRAFV600E mutation. 91% (39/43) of BRAFV600E-positive atypia of undetermined significance samples were identified as malignant by the AI models. In this study, we developed an AI-assisted model named the Thyroid Patch-Oriented WSI Ensemble Recognition (ThyroPower) system, which facilitates rapid and robust cyto-diagnosis of thyroid nodules, potentially enhancing the diagnostic capabilities of cytopathologists. Moreover, it serves as a potential solution to mitigate the scarcity of cytopathologists. Guangdong Science and Technology Department. For the Chinese translation of the abstract see Supplementary Materials section.

Wang J ，Zheng N ，Wan H ，Yao Q ，Jia S ，Zhang X ，Fu S ，Ruan J ，He G ，Chen X ，Li S ，Chen R ，Lai B ，Wang J ，Jiang Q ，Ouyang N ，Zhang Y ... -  《The Lancet Digital Health》

BRAF V600E mutation and the Bethesda System for Reporting Thyroid Cytopathology of fine-needle aspiration biopsy for distinguishing benign from malignant thyroid nodules.

The Bethesda System for Reporting Thyroid Cytopathology (TBSRTC) predicts the risk of malignancy for the different categories of the ultrasound-guided fine-needle aspiration biopsy (FNAB). The objective of this study is to investigate the efficiencies of the v-raf murine sarcoma viral oncogene homolog B1 (BRAF) V600E mutation test and the TBSRTC categories in distinguishing between benign and malignant thyroid nodules. In this study, 362 ultrasound-guided fine-needle aspiration (FNA) samples from 344 patients aged from 17 to 76 years old were retrospectively reviewed. The patients were classified into six groups (I-VI) according to the TBSRTC system. The amplification refractory mutation system-polymerase chain reaction (ARMS-PCR) was used to evaluate the BRAF V600E mutation level in total 362 samples. Among of the 344 patients, 128 patients (131 thyroid nodules) who underwent surgeries were followed by histopathological examination. The predictive values of the BRAF V600E mutation test and TBSRTC categories were evaluated in these 131 thyroid nodules. The median ages of the patients in the TBSRTC IV-VI group were smaller than those in the TBSRTC I-III groups. The proportion of nodules over 1 cm was larger than it in the TBSRTC IV group compared to the other groups. Significant differences in BRAF V600E mutation were observed (P < .001) among these six groups. The sensitivity (89.57%) for the detection of malignant thyroid nodules, negative predictive value (NPV; 45.45%) for the detection of benign nodules, and accuracy (86.26%) for distinguishing between benign and malignant thyroid nodules increased by combining the BRAF V600E mutation test and TBSRTC system when compared with the BRAF V600E mutation test and TBSRTC system respectively. The BRAF V600E mutation test alone demonstrated the increased positive predictive value (PPV; 98.91%) and specificity (93.75%) for the detection of malignant thyroid nodules compared to the TBSRTC method (alone or in combination with the BRAF V600E method). In summary, significant differences in age, nodule diameter, and BRAF V600E mutation were noted among the six categories of the TBSRTC system. The combination of the BRAF V600E mutation test and TBSRTC system demonstrated increases in the NPV, sensitivity, and accuracy, while the BRAF V600E method proved superiority to the TBSRTC system with regard to the PPV and specificity.

Sheng D ，Yu X ，Li H ，Zhang M ，Chen J ... -  《-》

Deep learning-based artificial intelligence model to assist thyroid nodule diagnosis and management: a multicentre diagnostic study.

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. 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. 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%. The ThyNet-assisted strategy can significantly improve the diagnostic performance of radiologists and help reduce unnecessary fine needle aspirations for thyroid nodules. National Natural Science Foundation of China and Guangzhou Science and Technology Project.

Peng S ，Liu Y ，Lv W ，Liu L ，Zhou Q ，Yang H ，Ren J ，Liu G ，Wang X ，Zhang X ，Du Q ，Nie F ，Huang G ，Guo Y ，Li J ，Liang J ，Hu H ，Xiao H ，Liu Z ，Lai F ，Zheng Q ，Wang H ，Li Y ，Alexander EK ，Wang W ，Xiao H ... -  《The Lancet Digital Health》

Improved Diagnostic Accuracy of Thyroid Fine-Needle Aspiration Cytology with Artificial Intelligence Technology.

Lee Y ，Alam MR ，Park H ，Yim K ，Seo KJ ，Hwang G ，Kim D ，Chung Y ，Gong G ，Cho NH ，Yoo CW ，Chong Y ，Choi HJ ... -  《-》

The combination of ACR-Thyroid Imaging Reporting and Data system and The Bethesda System for Reporting Thyroid Cytopathology in the evaluation of thyroid nodules-An institutional experience.

The Bethesda System for Reporting Thyroid Cytopathology (TBSRTC) is widely utilised by cytopathologists. The American College of Radiology (ACR) has also proposed a thyroid imaging reporting and data system (TIRADS) to classify thyroid nodules and guide their selection for fine needle aspiration (FNA). The current study aimed to analyse the usefulness of TBSRTC in thyroid cytology reporting, to examine its histological correlation with TIRADS, and to compare the management of lesions in each cytological category in our institute to the TBSRTC recommendations. A retrospective study was performed on all thyroid FNAs from a 2-year period at a tertiary care centre. Histological correlations of TBSRTC and ACR TIRADS were examined for cases with surgical follow-up, and the risk of malignancy in each TBSRTC category, and sensitivity and specificity of FNA and TIRADS, were calculated. A total of 337 thyroid FNAs were examined, with histological follow-up in 99 cases. Risk of malignancy in categories I-VI was 9.5%, 2.3%, 0.0, 8%, 87.5% and 100.0%, respectively. The sensitivity, specificity, positive predictive value, and negative predictive value of FNA were 60.0%, 99.0%, 85.7%, and 97.5%, respectively, while those values for thyroid ultrasound were 90.3%, 72.2%, 92.9% and 65%, respectively. The study substantiates the usefulness of TBSRTC in arriving at a more precise diagnosis. Hurthle cell lesions with atypia were the common cause of misdiagnosis. The combination of TIRADS and TBSRTC aids in better stratification of thyroid nodules and in decision making for management of lesions.

Sakthisankari S ，Vidhyalakshmi S ，Shanthakumari S ，Devanand B ，Nagul U ... -  《-》