AI Article Synopsis

Article Abstract

Background: The incidence rate of thyroid nodules has reached 65%, but only 5-15% of these modules are malignant. Therefore, accurately determining the benign and malignant nature of thyroid nodules can prevent unnecessary treatment. We aimed to develop a deep-learning (DL) radiomics model based on ultrasound (US), explore its diagnostic efficacy for benign and malignant thyroid nodules, and verify whether it improved the diagnostic level of physicians.

Methods: We retrospectively included 1,076 thyroid nodules from 817 patients at three institutions. The radiomics and DL features of the US images were extracted and used to construct radiomics signature (Rad_sig) and deep-learning signature (DL_sig). A Pearson correlation analysis and least absolute shrinkage and selection operator (LASSO) regression analysis were used for feature selection. Clinical US semantic signature (C_US_sig) was constructed based on clinical information and US semantic features. Next, a combined model was constructed based on the above three signatures in the form of a nomogram. The model was constructed using a development set (institution 1: 719 nodules), and the model was evaluated using two external validation sets (institution 2: 74 nodules, and institution 3: 283 nodules). The performance of the model was assessed using decision curve analysis (DCA) and calibration curves. Furthermore, the C_US_sigs of junior physicians, senior physicians, and expers were constructed. The DL radiomics model was used to assist the physicians with different levels of experience in the interpretation of thyroid nodules.

Results: In the development and validation sets, the combined model showed the highest performance, with areas under the curve (AUCs) of 0.947, 0.917, and 0.929, respectively. The DCA results showed that the comprehensive nomogram had the best clinical utility. The calibration curves indicated good calibration for all models. The AUCs for distinguishing between benign and malignant thyroid nodules by junior physicians, senior physicians, and experts were 0.714-0.752, 0.740-0.824, and 0.891-0.908, respectively; however, with the assistance of DL radiomics, the AUCs reached 0.858-0.923, 0.888-0.944, and 0.912-0.919, respectively.

Conclusions: The nomogram based on DL radiomics had high diagnostic efficacy for thyroid nodules, and DL radiomics could assist physicians with different levels of experience to improve their diagnostic level.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11320491PMC
http://dx.doi.org/10.21037/qims-23-1597DOI Listing

Publication Analysis

Top Keywords

thyroid nodules
28
diagnostic level
12
benign malignant
12
nodules
10
deep-learning radiomics
8
based ultrasound
8
thyroid
8
radiomics model
8
diagnostic efficacy
8
malignant thyroid
8

Similar Publications

Renal cell carcinoma metastasis to the thyroid gland: a case report.

J Med Case Rep

December 2024

Laboratory of Pathology Pathology, "CSD Health Care", Kiev, Ukraine.

Background: In this article, we report a case of renal cell carcinoma metastasis to the thyroid gland. Occult lesions of the thyroid were treated with a thyroidectomy. The case history presented below describes the patient's pathway and subsequent results.

View Article and Find Full Text PDF

Background: With increased early detection efforts, surgery for early-stage lung cancer is expected to rise. Pafolacianine is the first FDA approved targeted optical imaging agent indicated as an adjunct for intraoperative identification of malignant and nonmalignant pulmonary lesions in adult patients with known or suspected cancer in the lung.

Methods: This is a retrospective review of the malignant and nonmalignant lesions identified by pafolacianine with intraoperative molecular imaging (IMI) in the multi-center Phase 2 and Phase 3 ELUCIDATE clinical trials.

View Article and Find Full Text PDF
Article Synopsis
  • The study investigates the role of ultrasound-guided fine-needle aspiration biopsy (FNAB) in diagnosing thyroid nodules larger than 3 cm, emphasizing its significance for treatment decisions.* -
  • Researchers reviewed patient records from 2018 to 2023, focusing on those who underwent thyroid surgery, categorizing them by nodule size to analyze FNAB outcomes.* -
  • Results indicated that larger nodules (≥4 cm) had a higher rate of malignancy and more false negatives in FNAB, stressing the need for careful evaluation in surgical planning.*
View Article and Find Full Text PDF

Background: Night work includes working between 10 pm and 6 am, which has known effects on people's health. One of the hormones influenced by the circadian rhythm is thyroid stimulating hormone (TSH).

Objective: Considering the effects of night shift-work on the thyroid gland, the purpose of this study was to investigate the relationship between thyroid nodules and night shift-work among the employees of Yazd Electricity Company.

View Article and Find Full Text PDF

Background And Aims: Thyroid cancer, a prevalent endocrine malignancy, often presents as thyroid nodules, whose benign or malignant nature is challenging to determine. This study aims to identify circulating miRNA panels that may distinguish between benign nodules, papillary thyroid cancer, and normal thyroid conditions, building on extensive research into miRNAs as potential thyroid cancer biomarkers.

Materials And Methods: As a cross-sectional case-control study the study revealed the quantification of the 17-miRNA panel was evaluated using qRT-PCR method on 60 blood samples, comprising 25 patients diagnosed with PTC, 24 patients with benign lesions, and 11 healthy controls.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!