Artificial Intelligence for Thyroid Nodule Characterization: Where Are We Standing?

Sorrenti, Salvatore; Dolcetti, Vincenzo; Radziņa, Maija; Bellini, Maria Irene; Frezza, Fabrizio; Munir, Khushboo; Grani, Giorgio; Durante, Cosimo; D’Andrea, Vito; David, Emanuele; Calò, Pietro Giorgio; Lori, Eleonora; Cantisani, Vito

doi:10.3390/cancers14143357

Cited by 53 publications

(40 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thyroid cancer (TC) is one of the most rapidly increasing malignancies in Western countries, with an annual incidence rate of 5.4% in men and 6.5% in women (1). Much of this rise is largely due to early detection using more sensitive diagnostic procedures, including Artificial Intelligence, performed for other medical reasons and able to identify incidental small thyroid nodules, otherwise missed (2)(3)(4). Certain risk factors for TC are female sex, family history of TC, radiation exposure, lymphocytic thyroiditis, and reduced iodine intake (5,6).…”

Section: Introductionmentioning

confidence: 99%

Thyroid and renal cancers: A bidirectional association

Bellini

Lori

Forte³

et al. 2022

Front. Oncol.

Self Cite

View full text Add to dashboard Cite

There is a deep interrelation between the thyroid gland and the kidney parenchyma, with dysfunction of the first leading to significant changes in renal metabolism and vice versa. Given the recognition of cancer as a systemic disease, the raise of thyroid tumors and the common association of several malignancies, such as breast cancer, prostate cancer, colorectal cancer, and other, with an increased risk of kidney disease, public health alert for these conditions is warranted. A systematic review of the current evidence on the bidirectional relationship between thyroid and renal cancers was conducted including 18 studies, highlighting patient’s characteristics, histology, time for secondary malignancy to develop from the first diagnosis, treatment, and follow-up. A total of 776 patients were identified; median age was 64 years (range: 7–76 years). Obesity and family history were identified as the most common risk factors, and genetic susceptibility was suggested with a potential strong association with Cowden syndrome. Controversy on chemo and radiotherapy effects was found, as not all patients were previously exposed to these treatments. Men were more likely to develop kidney cancer after a primary thyroid malignancy, with 423/776 (54%) experiencing renal disease secondarily. Median time after the first malignancy was 5.2 years (range: 0–20 years). With the advancement of current oncological therapy, the prognosis for thyroid cancer patients has improved, although there has been a corresponding rise in the incidence of multiple secondary malignancy within the same population, particularly concerning the kidney. Surgery can achieve disease-free survival, if surveillance follow-up allows for an early localized form, where radical treatment is recommended.

show abstract

Section: Introductionmentioning

confidence: 99%

Thyroid and renal cancers: A bidirectional association

Bellini

Lori

Forte³

et al. 2022

Front. Oncol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Compared to traditional statistical methods such as logistic regression, machine learning enables more interactions between variables and outcomes to be found. However, to our knowledge, studies on employing machine learning for predicting LLNM in PTC patients are still absent ( 11 ). In fact, establishing a robust predictive model for PTC would help clinicians stratify high-risk patients for intensive treatment and propose candidates for active follow-up.…”

Section: Introductionmentioning

confidence: 99%

Machine learning-based dynamic prediction of lateral lymph node metastasis in patients with papillary thyroid cancer

Lai

Fan²,

Zhu³

et al. 2022

Front. Endocrinol.

View full text Add to dashboard Cite

ObjectiveTo develop a web-based machine learning server to predict lateral lymph node metastasis (LLNM) in papillary thyroid cancer (PTC) patients.MethodsClinical data for PTC patients who underwent primary thyroidectomy at our hospital between January 2015 and December 2020, with pathologically confirmed presence or absence of any LLNM finding, were retrospectively reviewed. We built all models from a training set (80%) and assessed them in a test set (20%), using algorithms including decision tree, XGBoost, random forest, support vector machine, neural network, and K-nearest neighbor algorithm. Their performance was measured against a previously established nomogram using area under the receiver operating characteristic curve (AUC), decision curve analysis (DCA), precision, recall, accuracy, F1 score, specificity, and sensitivity. Interpretable machine learning was used for identifying potential relationships between variables and LLNM, and a web-based tool was created for use by clinicians.ResultsA total of 1135 (62.53%) out of 1815 PTC patients enrolled in this study experienced LLNM episodes. In predicting LLNM, the best algorithm was random forest. In determining feature importance, the AUC reached 0.80, with an accuracy of 0.74, sensitivity of 0.89, and F1 score of 0.81. In addition, DCA showed that random forest held a higher clinical net benefit. Random forest identified tumor size, lymph node microcalcification, age, lymph node size, and tumor location as the most influentials in predicting LLNM. And the website tool is freely accessible at http://43.138.62.202/.ConclusionThe results showed that machine learning can be used to enable accurate prediction for LLNM in PTC patients, and that the web tool allowed for LLNM risk assessment at the individual level.

show abstract

“…AI assisted imaging diagnosis is the fastest growing and most widely used field in clinical practice. AI assisted ultrasound diagnosis can realize intelligent ultrasound prenatal examination ( 22 ), intelligent cardiac ultrasound examination ( 23 ), intelligent diagnosis of thyroid nodules ( 9 – 12 ) and breast nodules ( 24 ), etc. It has become increasingly mature and has the uniqueness of non-invasive, convenient and reproducible.…”

Section: Discussionmentioning

confidence: 99%

“…Thyroid gland has become the precursor of AI development in the field of ultrasound due to its unique superficial position and relatively easy to collect standard images ( 25 ). AI ultrasound intelligent auxiliary diagnosis system based on static ultrasound images can realize automatic delineation of nodules, morphological recognition, benign and malignant discrimination, and has high diagnostic value for the judgment of benign and malignant thyroid nodules ( 9 – 12 ). On this basis, dynamic AI uses super large-scale convolution neural network (CNN) and deep learning technology to establish an artificial intelligence aided diagnosis model for benign and malignant thyroid nodules based on CNN to automatically extract image features.…”

Section: Discussionmentioning

confidence: 99%

“…A study has shown that about 20% of 25445 biopsy tissue samples were pathologically diagnosed as atypical lesions with unknown significance or could not be determined as malignant, with an average malignant risk of 15.9% and 75.2% respectively ( 8 ). With the joint application of artificial intelligence (AI) technology and medical imaging data, static AI ultrasound intelligent auxiliary diagnosis system was generated and used to diagnose thyroid nodules, which can improve the diagnostic efficiency while ensuring the accuracy ( 9 – 12 ). However, static AI can only diagnose a single view of nodules, and cannot judge the nature of nodules in real time.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Identification of benign and malignant thyroid nodules based on dynamic AI ultrasound intelligent auxiliary diagnosis system

Wang

Wan

et al. 2022

Front. Endocrinol.

View full text Add to dashboard Cite

BackgroundDynamic artificial intelligence (AI) ultrasound intelligent auxiliary diagnosis system (Dynamic AI) is a joint application of AI technology and medical imaging data, which can perform a real-time synchronous dynamic analysis of nodules. The aim of this study is to investigate the value of dynamic AI in differentiating benign and malignant thyroid nodules and its guiding significance for treatment strategies.MethodsThe data of 607 patients with 1007 thyroid nodules who underwent surgical treatment were reviewed and analyzed, retrospectively. Dynamic AI was used to differentiate benign and malignant nodules. The diagnostic efficacy of dynamic AI was evaluated by comparing the results of dynamic AI examination, preoperative fine needle aspiration cytology (FNAC) and postoperative pathology of nodules with different sizes and properties in patients of different sexes and ages.ResultsThe sensitivity, specificity and accuracy of dynamic AI in the diagnosis of thyroid nodules were 92.21%, 83.20% and 89.97%, respectively, which were highly consistent with the postoperative pathological results (kappa = 0.737, p < 0.001). There is no statistical difference in accuracy between people with different ages and sexes and nodules of different sizes, which showed the good stability. The accuracy of dynamic AI in malignant nodules (92.21%) was significantly higher than that in benign nodules (83.20%) (p < 0.001). The specificity and positive predictive value were significantly higher, and the misdiagnosis rate was significantly lower in dynamic AI than that of preoperative ultrasound ACR TI-RADS (p < 0.001). The accuracy of dynamic AI in nodules with diameter ≤ 0.50 cm was significantly higher than that of preoperative ultrasound (p = 0.044). Compared with FNAC, the sensitivity (96.58%) and accuracy (94.06%) of dynamic AI were similar.ConclusionsThe dynamic AI examination has high diagnostic value for benign and malignant thyroid nodules, which can effectively assist surgeons in formulating scientific and reasonable individualized diagnosis and treatment strategies for patients.

show abstract

Artificial Intelligence for Thyroid Nodule Characterization: Where Are We Standing?

Cited by 53 publications

References 72 publications

Thyroid and renal cancers: A bidirectional association

Thyroid and renal cancers: A bidirectional association

Machine learning-based dynamic prediction of lateral lymph node metastasis in patients with papillary thyroid cancer

Identification of benign and malignant thyroid nodules based on dynamic AI ultrasound intelligent auxiliary diagnosis system

Contact Info

Product

Resources

About