Vladimir Eduardovich Vanushko

Papillary thyroid microcarcinomas (PTMCs) account for about 30% of papillary thyroid cancer cases, and the BRAF V600E mutation is one of the driver mutations in the development of papillary thyroid carcinomas. However, traditional molecular diagnostic methods are time-consuming and costly, highlighting the need for alternative approaches, such as machine learning-based analysis of histopathological images. Objective. To evaluate the feasibility of using a Multiple-Instance Learning (MIL) model to predict BRAF status in PTMC patients based on histopathological whole-slide images without explicit region-of-interest annotation. Material and methods. The study included histopathological scans from surgical specimens of 93 PTMC patients (age range 24—72 years, median 48 years) operated between 01.01.2022 and 01.09.2023. BRAF V600E status was determined by Real-Time PCR. For classification, an MIL model (CLAM) with pretrained feature extractors (CTransPath and Virchow) was used. Model performance was assessed using ROC-AUC with 5-fold cross-validation (10 repeats). Results. The BRAF V600E mutation was detected in 62 patients and absent in 31. The highest ROC-AUC (0.83; 95% CI: 0.61—1.00) was achieved using Virchow features with 20% top-attention region filtering. For CTransPath, ROC-AUC was 0.79 (95% CI: 0.60—0.95) with 5% region filtering. Conclusion. The MIL model shows promise for predicting BRAF status in PTMCs from histopathological images, particularly when using Virchow-derived features.

Fine-needle aspiration biopsy of thyroid nodules frequently yields indeterminate results, leading to unnecessary diagnostic surgeries. We evaluated a targeted plasma proteomics approach to differentiate benign follicular thyroid adenoma (FTA) from malignant papillary thyroid carcinoma (PTC). Using LC-MRM mass spectrometry with stable isotope-labeled standards (SIS), we quantified a multiplex protein panel in plasma samples from 267 patients. The analytical workflow incorporated an MS-based assessment of preanalytical hemolysis to prevent bias associated with thyroid-related blood composition changes and multiple rounds of randomization allowed assessment of batch effects. While previously proposed low-abundance thyroid cancer markers were rarely detected in the cohort, a signature of high-abundance plasma proteins successfully stratified the patients. The malignant PTC phenotype was characterized by a significant increase in apolipoprotein A1 and myosin-9, along with elevated CD14 and kininogen-1. Benign FTA was associated with higher levels of acute-phase proteins, including ceruloplasmin and complement C1q subunit C. Simple PCRE model with 20 parameters based on 4 major plasma proteins allowed to build a classifier with specificity that can be adjusted with regard to epidemiology and medical resource. This study establishes a foundational mass spectrometry-based framework that utilizes systemic proteomic profiles to differentiate underlying pathologies and improve clinical decision-making regarding patient management. By enabling additional stratification of patients with Bethesda IV cytology, who are otherwise frequently subjected to unwarranted diagnostic operations, this multiplex MS approach provides a potential non-invasive triage tool to reduce unnecessary surgical interventions for indeterminate thyroid nodules.

Papillary Microcarcinoma of the Thyroid Gland (PMTC) is the most common type of malignant thyroid neoplasm, characterized by its small size and generally favorable prognosis. The increased detection rate of PMTC is associated with advancements in high-precision diagnostic methods such as ultrasound and fine-needle aspiration biopsy. Diagnostic approaches include the use of the EU-TIRADS and Bethesda systems for risk assessment, as well as the analysis of molecular markers, such as BRAF gene mutations and promising studies on the role of microRNAs in predicting tumor progression.Optimal management of patients with PMTC requires an individualized therapeutic approach due to differences in disease progression. This article analyzes current diagnostic and treatment methods for PMTC, including the use of molecular-genetic markers, minimally invasive technologies, and active surveillance strategies, with an emphasis on a personalized approach to prognosis and therapy.

Tumors of the thyroid gland are extremely common. The incidence of malignant thyroid neoplasms has increased rapidly in recent decades, although it is unclear whether this is a true increase or the result of widespread use of screening ultrasound. The standard diagnostic procedure for determining the risk of malignancy and indications for surgical treatment of thyroid neoplasms is fine-needle aspiration biopsy followed by cytologic examination of the cellular aspirate. Despite the fact that in the majority of cases it is possible to make a differential diagnosis between thyroid cancer and benign thyroid masses, there is a diagnostic problem with intermediate categories of cytologic findings according to Bethesda, which makes it necessary to search for alternative solutions. This determines the need to expand preoperative diagnostic possibilities. One of the key directions of work on its realization is the study of proteomic data in various thyroid pathologies. The study of the proteome of thyroid tumors opens the possibility of identifying specific protein markers or mechanisms that play a key role in the oncogenesis and metastasis of thyroid tumors, as well as potential targets for new methods of diagnosis and treatment of these diseases. All this determines the relevance and practical importance of studying thyroid pathology at the molecular level, taking into account the potential of proteins as markers.

The preoperative diagnostics of medullary thyroid carcinoma (MTC), including the measuring of the blood calcitonin level, has a number of limitations. Particular focus has recently been placed on the role of miRNAs in the development of various malignant tumors; a comparative analysis of accuracy of the existing methods for MTC diagnosis with a novel diagnosis method, evaluation of the miRNA-375 expression level, was performed in this study. The expression level of miRNA-375 in cytology samples from 555 patients with the known histological diagnosis, including 41 patients with confirmed postoperative diagnosis of MTC, was assessed. The diagnostic parameters of the basal calcitonin level, calcitonin in wash-out fluid from the FNAB needle, and miRNA-375 were compared. An assessment of the miRNA-375 expression level made it possible to detect all the MTC samples with a 100% accuracy among all the 555 cytology specimens, as well as in non-informative FNAB specimens, and specimens from the ipsilateral thyroid lobe. Parameters such as sensitivity, specificity, PPV, and NPV were 100%. The miRNA-375 level, unlike calcitonin, does not correlate with tumor volume, so it does not have the so-called “gray zone”. An assessment of the miRNA-375 expression allows one to accurately distinguish MTC from other malignant and benign thyroid tumors.

The article presents a draft of clinical recommendations for the diagnosis and treatment of differentiated thyroid cancer in adult patients, which provides a modern examination algorithm, discusses the basic principles of laboratory, instrumental diagnostics and treatment approaches.

The article presents a draft of clinical recommendations for the diagnosis and treatment of medullary thyroid cancer in adult patients, which provides a modern examination algorithm, discusses the basic principles of laboratory, instrumental diagnostics and treatment approaches.

Проект федеральных клинических рекомендаций по диагностике и лечению амиодарон-индуцированной дисфункции щитовидной железы

Differentiated thyroid cancer Дифференцированный рак щитовидной железы

I.M. Sechenov First Moscow State Medical University (Sechenov University), Moscow, Russia; Endocrinology Research Centre, Moscow, Russia Thyroid cancer is the most common endocrine gland cancer. In the last few decades, the molecular diagnostics for thyroid tumors have been widely researched. It is one of the few cancers whose incidence has increased in recent years from microcarcinomas to common, large forms, in all age groups, from children to the elder people. Most researches focus on the genetic basis, since our current knowledge of the genetic background of various forms of thyroid cancer is far from being complete. Molecular and genetic research has several main directions: firstly, differential diagnosis of thyroid tumors, secondly, the prognostic value of detected mutations in thyroid cancer, and thirdly, targeted therapy for aggressive or radioactive iodine-resistant forms of thyroid cancer. In this review, we wanted to update our understanding and describe the prevailing advances in molecular genetics of thyroid cancer, focusing on the main genes associated with the pathology and their potential application in clinical practice.