Noninvasive Follicular Thyroid Neoplasm with Papillary-like Nuclear Features (NIFTP): Tumour Entity with a Short History. A Review on Challenges in Our Microscopes, Molecular and Ultrasonographic Profile

Can the analysis of chromatin texture and nuclear fractal dimensions serve as effective means to distinguish non-invasive follicular thyroid neoplasm with papillary-like nuclear features from other malignancies with follicular pattern in the thyroid?: a study

OBJECTIVE

Thyroid carcinoma ranks as the 9th most prevalent global cancer, accounting for 586,202 cases and 43,636 deaths in 2020. Computerized image analysis, utilizing artificial intelligence algorithms, emerges as a potential tool for tumor evaluation.

AIM

This study aims to assess and compare chromatin textural characteristics and nuclear dimensions in follicular neoplasms through gray-level co-occurrence matrix (GLCM), fractal, and morphometric analysis.

METHOD

A retrospective cross-sectional study involving 115 thyroid malignancies, specifically 49 papillary thyroid carcinomas with follicular morphology, was conducted from July 2021 to July 2023. Ethical approval was obtained, and histopathological examination, along with image analysis, was performed using ImageJ software.

RESULTS

A statistically significant difference was observed in contrast (2.426 (1.774-3.412) vs 2.664 (1.963-3.610), p = .002), correlation (1.202 (1.071-1.298) vs 0.892 (0.833-0.946), p = .01), and ASM (0.071 (0.090-0.131) vs 0.044 (0.019-0.102), p = .036) between NIFTP and IFVPTC. However, morphometric parameters did not yield statistically significant differences among histological variants.

CONCLUSION

Computerized image analysis, though promising in subtype discrimination, requires further refinement and integration with traditional diagnostic parameters. The study suggests potential applications in scenarios where conventional histopathological assessment faces limitations due to limited tissue availability. Despite limitations such as a small sample size and a retrospective design, the findings contribute to understanding thyroid carcinoma characteristics and underscore the need for comprehensive evaluations integrating various diagnostic modalities.

BRAF mutation, selected miRNAs and genes expression in primary papillary thyroid carcinomas and local lymph node metastases

Mutations in cancer-related genes are now known to be accompanied by epigenetic events in carcinogenesis by modification of the regulatory pathways and expression of genes involved in the pathobiology. Such cancer-related mutations, miRNAs and gene expression may be promising molecular markers of the most common papillary thyroid carcinoma (PTC). However, there are limited data on their relationships. The aim of this study was to analyse the interactions between BRAF mutations, selected microRNAs (miR-21, miR-34a, miR-146b, and miR-9) and the expression of selected genes (LGALS3, NKX2-1, TACSTD2, TPO) involved in the pathogenesis of PTC. The study cohort included 60 primary papillary thyroid carcinomas (PTC) that were classified as classical (PTC/C; n=50) and invasive follicular variant (PTC/F; n=10), and 40 paired lymph node metastases (LNM). BRAF mutation status in primary and recurrent/persistent papillary thyroid carcinomas was determined. The mutation results were compared both between primary and metastatic cancer tissue, and between BRAF mutation status and selected genes and miRNA expression in primary PTC. Furthermore, miRNAs and gene expression were compared between primary PTCs and non-neoplastic tissue, and local lymph node metastatic tumor, respectively. All studied markers showed several significant mutual interactions and contexts. In conclusion, to the best our knowledge, this is the first integrated study of BRAF mutational status, the expression levels of mRNAs of selected genes and miRNAs in primary PTC, and paired LNM.

FFPE++: Improving the quality of formalin-fixed paraffin-embedded tissue imaging via contrastive unpaired image-to-image translation

Formalin-fixation and paraffin-embedding (FFPE) is a technique for preparing and preserving tissue specimens that has been utilized in histopathology since the late 19th century. This process is further complicated by FFPE preparation steps such as fixation, processing, embedding, microtomy, staining, and coverslipping, which often results in artifacts due to the complex histological and cytological characteristics of a tissue specimen. The term "artifacts" includes, but is not limited to, staining inconsistencies, tissue folds, chattering, pen marks, blurring, air bubbles, and contamination. The presence of artifacts may interfere with pathological diagnosis in disease detection, subtyping, grading, and choice of therapy. In this study, we propose FFPE++, an unpaired image-to-image translation method based on contrastive learning with a mixed channel-spatial attention module and self-regularization loss that drastically corrects the aforementioned artifacts in FFPE tissue sections. Turing tests were performed by 10 board-certified pathologists with more than 10 years of experience. These tests which were performed for ovarian carcinoma, lung adenocarcinoma, lung squamous cell carcinoma, and papillary thyroid carcinoma, demonstrate the clear superiority of the proposed method in many clinical aspects compared with standard FFPE images. Based on the qualitative experiments and feedback from the Turing tests, we believe that FFPE++ can contribute to substantial diagnostic and prognostic accuracy in clinical pathology in the future and can also improve the performance of AI tools in digital pathology. The code and dataset are publicly available at https://github.com/DeepMIALab/FFPEPlus.

Three-dimensional nuclear architecture distinguishes thyroid cancer histotypes

Molecular markers can serve as diagnostic tools to support pathological analysis in thyroid neoplasms. However, because the same markers can be observed in some benign thyroid lesions, additional approaches are necessary to differentiate thyroid tumor subtypes, prevent overtreatment and tailor specific clinical management. This applies particularly to the recently described variant of thyroid cancer referred to as noninvasive follicular thyroid neoplasm with papillary-like nuclear features (NIFTP). This variant has an estimated prevalence of 4.4% to 9.1% of all papillary thyroid carcinomas worldwide. We studied 60 thyroid lesions: 20 classical papillary thyroid carcinoma (CPTC), 20 follicular variant of PTC (FVPTC) and 20 NIFTP. We examined morphological and molecular features to identify parameters that can differentiate NIFTP from the other PTC subtypes. When blindly investigating the nuclear architecture of thyroid neoplasms, we observed that NIFTP has significantly longer telomeres than CPTC and FVPTC. Super-resolved 3D-structured illumination microscopy demonstrated that NIFTP is heterogeneous and that its nuclei contain more densely packed DNA and smaller interchromatin spaces than CPTC and FVPTC, a pattern that resembles normal thyroid tissue. These data are consistent with the observed indolent biological behavior and favorable prognosis associated with NIFTP, which lacks BRAFV600E mutations. Of note, next-generation thyroid oncopanel sequencing was unable to distinguish the thyroid cancer histotypes in our study cohort. In summary, our data suggest that 3D nuclear architecture can be a powerful analytical tool to diagnose and guide clinical management of NIFTP.

Non-invasive follicular thyroid neoplasm with papillary-like nuclear feature: clinical, pathological, and molecular update 5 years after the nomenclature revision

The term non-invasive follicular thyroid neoplasm with papillary-like nuclear features (NIFTP) was proposed in 2016 and incorporated as a new entity in the World Health Organization (WHO) classification of tumours of endocrine organs in 2017. Since then, there has been debate regarding the histological criteria for the diagnosis, the need for molecular studies or the risk of lymph node metastasis or recurrence associated with this entity. Over the years, the concept of NIFTP evolved, now including both small (<1 cm) and large (>4 cm) tumours and oncocytic lesions. On the other hand, recent data on NIFTP in the setting of thyroid follicular nodular disease or frequent coexistence of malignant tumours raised concerns regarding the follow-up of these patients. Today, both pathologists and clinicians still face several challenges in the diagnosis, treatment, and follow-up of patients with NIFTP.

Trends in AI-powered Classification of Thyroid Neoplasms Based on Histopathology Images - a Systematic Review

Background

Assessment of thyroid nodules histopathology using AI is crucial for an accurate diagnosis. This systematic review analyzes recent works employing deep learning approaches for classifying thyroid nodules based on histopathology images, evaluating their performance, and identifying limitations.

Methods

Eligibility criteria focused on peer-reviewed English papers published in the last 5 years, applying deep learning to categorize thyroid histopathology images. The PubMed database was searched using relevant keyword combinations.

Results

Out of 103 articles, 11 studies met inclusion criteria. They used convolutional neural networks to classify thyroid neoplasm. Most studies aimed for basic tumor subtyping; however, 3 studies targeted the prediction of tumor-associated mutation. Accuracy ranged from 77% to 100%, with most over 90%.

Discussion

The findings from our analysis reveal the effectiveness of deep learning in identifying discriminative morphological patterns from histopathology images, thus enhancing the accuracy of thyroid nodule histopathological classification. Key limitations were small sample sizes, subjective annotation, and limited dataset diversity. Further research with larger diverse datasets, model optimization, and real-world validation is essential to translate these tools into clinical practice.