Artificial intelligence defines protein-based classification of thyroid nodules

A hot and cold tumor‑related prognostic signature for stage II colorectal cancer

Globally, colorectal cancer (CRC) is one of the most lethal and prevalent malignancies. Based on the presence of immune cell infiltration in the tumor microenvironment, CRC can be divided into immunologically 'hot' or 'cold' tumors, which in turn leads to the differential efficacy of immunotherapy. However, the immune characteristics of hot and cold CRC tumors remain largely elusive, prompting further investigation of their properties regarding the tumor microenvironment. In the present study, a predictive model was developed based on the differential expression of proteins between cold and hot CRC tumors. First, the differentially expressed proteins (DEPs) were identified using digital spatial profiling and mass spectrometry-based proteomics analysis, and the pathway features of the DEPs were analyzed using functional enrichment analysis. A novel eight-gene signature prognostic risk model was developed (IDO1, MAT1A, NPEPL1, NT5C, PTGR2, RPL29, TMEM126A and TUBB4B), which was validated using data obtained from The Cancer Genome Atlas. The results revealed that the risk score of the eight-gene signature acted as an independent prognostic indicator in patients with stage II CRC (T3-4N0M0). It was also found that a high-risk score in the eight-gene signature was associated with high immune cell infiltration in patients with CRC. Taken together, these findings revealed some of the differential immune characteristics of hot and cold CRC tumors, and an eight-gene signature prognostic risk model was developed, which may serve as an independent prognostic indicator for patients with stage II CRC (T3-4N0M0).

Deep convolutional neural network model ResNeSt for discrimination of papillary thyroid carcinomas and benign nodules in thyroid nodules diagnosed as atypia of undetermined significance

Background

A deep convolutional neural network (DCNN) model was employed for the differentiation of thyroid nodules diagnosed as atypia of undetermined significance (AUS) according to the 2023 Bethesda System for Reporting Thyroid Cytopathology (TBSRTC). The aim of this study was to investigate the efficiency of ResNeSt in improving the diagnostic accuracy of fine-needle aspiration (FNA) biopsy.

Methods

Fragmented images were used to train and test DCNN models. A training dataset was built from 1,330 samples diagnosed as papillary thyroid carcinoma (PTC) or benign nodules, and a test dataset was built from 173 samples diagnosed as AUS. ResNeSt was trained and tested to provide a differentiation. With regard to AUS samples, the characteristics of the cell nuclei were compared using the Wilcoxon test.

Results

The ResNeSt model achieved an accuracy of 92.49% (160/173) on fragmented images and 84.78% (39/46) from a patient wise viewpoint in discrimination of PTC and benign nodules in AUS nodules. The sensitivity and specificity of ResNeSt model were 95.79% and 88.46%. The κ value between ResNeSt and the pathological results was 0.847 (P<0.001). With regard to the cell nuclei of AUS nodules, both area and perimeter of malignant nodules were larger than those of benign ones, which were 2,340.00 (1,769.00, 2,807.00) vs. 1,941.00 (1,567.50, 2,455.75), P<0.001 and 190.46 (167.64, 208.46) vs. 171.71 (154.95, 193.65), P<0.001, respectively. The grayscale (0 for black, 255 for white) of malignant lesions was lower than that of benign ones, which was 37.52 (31.41, 46.67) vs. 45.84 (31.88, 57.36), P <0.001, indicating nuclear staining of malignant lesions were deeper than benign ones.

Conclusions

In summary, the DCNN model ResNeSt showed great potential in discriminating thyroid nodules diagnosed as AUS. Among those nodules, malignant nodules showed larger and more deeply stained nuclei than benign nodules.

Deciphering the progression of fine-needle aspiration: A bibliometric analysis of thyroid nodule research

This study aims to dissect the evolution and pivotal shifts in Fine-Needle Aspiration (FNA) research for thyroid nodules over the past 2 decades, focusing on delineating key technological advancements and their impact on clinical practice. A comprehensive bibliometric analysis was conducted on 5418 publications from the Web of Science Core Collection database (2000-2023). Publications were rigorously selected based on their contributions to the advancement of FNA techniques and their influence on thyroid nodule management practices. Our analysis uncovered significant breakthroughs, most notably the incorporation of ultrasound and molecular diagnostics in FNA, which have markedly elevated diagnostic accuracy. A pivotal shift was identified towards minimally invasive post-FNA treatments, such as Radiofrequency Ablation, attributable to these diagnostic advancements. Additionally, the emergence of AI-assisted cytology represents a frontier in precision diagnostics, promising enhanced disease identification. The geographical analysis pinpointed the United States, Italy, and China as key contributors, with the United States leading in both publication volume and citation impact. This bibliometric analysis sheds light on the transformative progression in FNA practices for thyroid nodules, characterized by innovative diagnostic technologies and a trend towards patient-centric treatment approaches. The findings underscore the need for further research into AI integration and global practice standardization. Future explorations should focus on the practical application of these advancements in diverse healthcare settings and their implications for global thyroid nodule management.

Proteostatic reactivation of the developmental transcription factor TBX3 drives BRAF/MAPK-mediated tumorigenesis

MAPK pathway-driven tumorigenesis, often induced by BRAFV600E, relies on epithelial dedifferentiation. However, how lineage differentiation events are reprogrammed remains unexplored. Here, we demonstrate that proteostatic reactivation of developmental factor, TBX3, accounts for BRAF/MAPK-mediated dedifferentiation and tumorigenesis. During embryonic development, BRAF/MAPK upregulates USP15 to stabilize TBX3, which orchestrates organogenesis by restraining differentiation. The USP15-TBX3 axis is reactivated during tumorigenesis, and Usp15 knockout prohibits BRAFV600E-driven tumor development in a Tbx3-dependent manner. Deleting Tbx3 or Usp15 leads to tumor redifferentiation, which parallels their overdifferentiation tendency during development, exemplified by disrupted thyroid folliculogenesis and elevated differentiation factors such as Tpo, Nis, Tg. The clinical relevance is highlighted in that both USP15 and TBX3 highly correlates with BRAFV600E signature and poor tumor prognosis. Thus, USP15 stabilized TBX3 represents a critical proteostatic mechanism downstream of BRAF/MAPK-directed developmental homeostasis and pathological transformation, supporting that tumorigenesis largely relies on epithelial dedifferentiation achieved via embryonic regulatory program reinitiation.

An individualized protein-based prognostic model to stratify pediatric patients with papillary thyroid carcinoma

Pediatric papillary thyroid carcinomas (PPTCs) exhibit high inter-tumor heterogeneity and currently lack widely adopted recurrence risk stratification criteria. Hence, we propose a machine learning-based objective method to individually predict their recurrence risk. We retrospectively collect and evaluate the clinical factors and proteomes of 83 pediatric benign (PB), 85 pediatric malignant (PM) and 66 adult malignant (AM) nodules, and quantify 10,426 proteins by mass spectrometry. We find 243 and 121 significantly dysregulated proteins from PM vs. PB and PM vs. AM, respectively. Function and pathway analyses show the enhanced activation of the inflammatory and immune system in PM patients compared with the others. Nineteen proteins are selected to predict recurrence using a machine learning model with an accuracy of 88.24%. Our study generates a protein-based personalized prognostic prediction model that can stratify PPTC patients into high- or low-recurrence risk groups, providing a reference for clinical decision-making and individualized treatment.

Plasma proteomic characterization of colorectal cancer patients with FOLFOX chemotherapy by integrated proteomics technology

BACKGROUND

Colorectal Cancer (CRC) is a prevalent form of cancer, and the effectiveness of the main postoperative chemotherapy treatment, FOLFOX, varies among patients. In this study, we aimed to identify potential biomarkers for predicting the prognosis of CRC patients treated with FOLFOX through plasma proteomic characterization.

METHODS

Using a fully integrated sample preparation technology SISPROT-based proteomics workflow, we achieved deep proteome coverage and trained a machine learning model from a discovery cohort of 90 CRC patients to differentiate FOLFOX-sensitive and FOLFOX-resistant patients. The model was then validated by targeted proteomics on an independent test cohort of 26 patients.

RESULTS

We achieved deep proteome coverage of 831 protein groups in total and 536 protein groups in average for non-depleted plasma from CRC patients by using a Orbitrap Exploris 240 with moderate sensitivity. Our results revealed distinct molecular changes in FOLFOX-sensitive and FOLFOX-resistant patients. We confidently identified known prognostic biomarkers for colorectal cancer, such as S100A4, LGALS1, and FABP5. The classifier based on the biomarker panel demonstrated a promised AUC value of 0.908 with 93% accuracy. Additionally, we established a protein panel to predict FOLFOX effectiveness, and several proteins within the panel were validated using targeted proteomic methods.

CONCLUSIONS

Our study sheds light on the pathways affected in CRC patients treated with FOLFOX chemotherapy and identifies potential biomarkers that could be valuable for prognosis prediction. Our findings showed the potential of mass spectrometry-based proteomics and machine learning as an unbiased and systematic approach for discovering biomarkers in CRC.

Circulating small extracellular vesicle-based miRNA classifier for follicular thyroid carcinoma: a diagnostic study

BACKGROUND

The diagnosis of follicular thyroid carcinoma (FTC) prior to surgery remains a major challenge in the clinic.

METHODS

This multicentre diagnostic study involved 41 and 150 age- and sex-matched patients in the training cohort and validation cohort, respectively. The diagnostic properties of circulating small extracellular vesicle (sEV)-associated and cell-free RNAs were compared by RNA sequencing in the training cohort. Subsequently, using a quantitative real-time polymerase chain reaction (qRT‒PCR) assay, high-quality candidates were identified to construct an RNA classifier for FTC and verified in the validation cohort. The parallel expression, stability and influence of the RNA classifier on surgical strategy were also investigated.

RESULTS

The diagnostic properties of sEV long RNAs, cell-free long RNAs and sEV microRNAs (miRNAs) were comparable and superior to those of cell-free miRNAs in RNA sequencing. Given the clinical application, the circulating sEV miRNA (CirsEV-miR) classifier was developed from five miRNAs based on qRT‒PCR data, which could well identify FTC patients (area under curve [AUC] of 0.924 in the training cohort and 0.844 in the multicentre validation cohort). Further tests revealed that the CirsEV-miR score was significantly correlated with the tumour burden, and the levels of sEV miRNAs were also higher in sEVs from the FTC cell line, organoid and tissue. Additionally, circulating sEV miRNAs remained constant after different treatments, and the addition of the CirsEV-miR classifier as a biomarker improves the current surgical strategy.

CONCLUSIONS

The CirsEV-miR classifier could serve as a noninvasive, convenient, specific and stable auxiliary test to help diagnose FTC following ultrasonography.

Risk stratification of papillary thyroid cancers using multidimensional machine learning

BACKGROUND

Papillary thyroid cancer (PTC) is one of the most common endocrine malignancies with different risk levels. However, preoperative risk assessment of PTC is still a challenge in the worldwide. Here, the authors first report a Preoperative Risk Assessment Classifier for PTC (PRAC-PTC) by multidimensional features including clinical indicators, immune indices, genetic feature, and proteomics.

MATERIALS AND METHODS

The 558 patients collected from June 2013 to November 2020 were allocated to three groups: the discovery set [274 patients, 274 formalin-fixed paraffin-embedded (FFPE)], the retrospective test set (166 patients, 166 FFPE), and the prospective test set (118 patients, 118 fine-needle aspiration). Proteomic profiling was conducted by FFPE and fine-needle aspiration tissues from the patients. Preoperative clinical information and blood immunological indices were collected. The BRAFV600E mutation were detected by the amplification refractory mutation system.

RESULTS

The authors developed a machine learning model of 17 variables based on the multidimensional features of 274 PTC patients from a retrospective cohort. The PRAC-PTC achieved areas under the curve (AUC) of 0.925 in the discovery set and was validated externally by blinded analyses in a retrospective cohort of 166 PTC patients (0.787 AUC) and a prospective cohort of 118 PTC patients (0.799 AUC) from two independent clinical centres. Meanwhile, the preoperative predictive risk effectiveness of clinicians was improved with the assistance of PRAC-PTC, and the accuracies reached at 84.4% (95% CI: 82.9-84.4) and 83.5% (95% CI: 82.2-84.2) in the retrospective and prospective test sets, respectively.

CONCLUSION

This study demonstrated that the PRAC-PTC that integrating clinical data, gene mutation information, immune indices, high-throughput proteomics and machine learning technology in multicentre retrospective and prospective clinical cohorts can effectively stratify the preoperative risk of PTC and may decrease unnecessary surgery or overtreatment.

Integrated proteomic and metabolomic analysis of plasma reveals regulatory pathways and key elements in thyroid cancer

Thyroid cancer (TC) is the most common endocrine malignancy with increasing incidence in recent years. Fine-needle aspiration biopsy (FNAB), as a gold standard for the initial evaluation of thyroid nodules, fails to cover all the cytopathologic conditions resulting in overdiagnosis. There is an urgent need for a better classification of thyroid cancer from benign thyroid nodules (BTNs). Here, data independent acquisition (DIA)-based proteomics and untargeted metabolomics in plasma samples of 10 patients with TC and 15 patients with BTNs were performed. Key proteins and metabolites were identified specific to TC, and an independent cohort was used to validate the potential biomarkers using enzyme-linked immunosorbent assay (ELISA). In total, 1429 proteins and 1172 metabolites were identified. Principal component analysis showed a strong overlap at the proteomic level and a significant discrimination at the metabolomic level between the two groups, indicating a more drastic disturbance in the metabolome of thyroid cancer. Integrated analysis of proteomics and metabolomics shows glycerophospholipid metabolism and arachidonic acid metabolism as key regulatory pathways. Furthermore, a multi-omics biomarker panel was developed consisting of LCAT, GPX3 and leukotriene B4. Based on the AUC value for the discovery set, the classification performance was 0.960. The AUC value of the external validation set was 0.930. Altogether, our results will contribute to the clinical application of potential biomarkers in the diagnosis of thyroid cancer.

The performance of deep learning on thyroid nodule imaging predicts thyroid cancer: A systematic review and meta-analysis of epidemiological studies with independent external test sets

BACKGROUND AND AIMS

It is still controversial whether deep learning (DL) systems add accuracy to thyroid nodule imaging classification based on the recent available evidence. We conducted this study to analyze the current evidence of DL in thyroid nodule imaging diagnosis in both internal and external test sets.

METHODS

Until the end of December 2022, PubMed, IEEE, Embase, Web of Science, and the Cochrane Library were searched. We included primary epidemiological studies using externally validated DL techniques in image-based thyroid nodule appraisal. This systematic review was registered on PROSPERO (CRD42022362892).

RESULTS

We evaluated evidence from 17 primary epidemiological studies using externally validated DL techniques in image-based thyroid nodule appraisal. Fourteen studies were deemed eligible for meta-analysis. The pooled sensitivity, specificity, and area under the curve (AUC) of these DL algorithms were 0.89 (95% confidence interval 0.87-0.90), 0.84 (0.82-0.86), and 0.93 (0.91-0.95), respectively. For the internal validation set, the pooled sensitivity, specificity, and AUC were 0.91 (0.89-0.93), 0.88 (0.85-0.91), and 0.96 (0.93-0.97), respectively. In the external validation set, the pooled sensitivity, specificity, and AUC were 0.87 (0.85-0.89), 0.81 (0.77-0.83), and 0.91 (0.88-0.93), respectively. Notably, in subgroup analyses, DL algorithms still demonstrated exceptional diagnostic validity.

CONCLUSIONS

Current evidence suggests DL-based imaging shows diagnostic performances comparable to clinicians for differentiating thyroid nodules in both the internal and external test sets.

Insight of novel biomarkers for papillary thyroid carcinoma through multiomics

Introduction

The overdiagnosing of papillary thyroid carcinoma (PTC) in China necessitates the development of an evidence-based diagnosis and prognosis strategy in line with precision medicine. A landscape of PTC in Chinese cohorts is needed to provide comprehensiveness.

Methods

6 paired PTC samples were employed for whole-exome sequencing, RNA sequencing, and data-dependent acquisition mass spectrum analysis. Weighted gene co-expression network analysis and protein-protein interactions networks were used to screen for hub genes. Moreover, we verified the hub genes' diagnostic and prognostic potential using online databases. Logistic regression was employed to construct a diagnostic model, and we evaluated its efficacy and specificity based on TCGA-THCA and GEO datasets.

Results

The basic multiomics landscape of PTC among local patients were drawn. The similarities and differences were compared between the Chinese cohort and TCGA-THCA cohorts, including the identification of PNPLA5 as a driver gene in addition to BRAF mutation. Besides, we found 572 differentially expressed genes and 79 differentially expressed proteins. Through integrative analysis, we identified 17 hub genes for prognosis and diagnosis of PTC. Four of these genes, ABR, AHNAK2, GPX1, and TPO, were used to construct a diagnostic model with high accuracy, explicitly targeting PTC (AUC=0.969/0.959 in training/test sets).

Discussion

Multiomics analysis of the Chinese cohort demonstrated significant distinctions compared to TCGA-THCA cohorts, highlighting the unique genetic characteristics of Chinese individuals with PTC. The novel biomarkers, holding potential for diagnosis and prognosis of PTC, were identified. Furthermore, these biomarkers provide a valuable tool for precise medicine, especially for immunotherapeutic or nanomedicine based cancer therapy.

Analyzing the glial proteome in Alzheimer's disease

INTRODUCTION

Alzheimer's disease (AD) is a neurodegenerative disorder characterized by progressive cognitive decline, memory loss, and changes in behavior. Accumulating evidence indicates that dysfunction of glial cells, including astrocytes, microglia, and oligodendrocytes, may contribute to the development and progression of AD. Large-scale analysis of glial proteins sheds light on their roles in cellular processes and diseases. In AD, glial proteomics has been utilized to understand glia-based pathophysiology and identify potential biomarkers and therapeutic targets.

AREA COVERED

In this review, we provide an updated overview of proteomic analysis of glia in the context of AD. Additionally, we discuss current challenges in the field, involving glial complexity and heterogeneity, and describe some cutting-edge proteomic technologies to address them.

EXPERT OPINION

Unbiased comprehensive analysis of glial proteomes aids our understanding of the molecular and cellular mechanisms of AD pathogenesis. These investigations highlight the crucial role of glial cells and provide novel insights into the mechanisms of AD pathology. A deeper understanding of the AD-related glial proteome could offer a repertoire of potential biomarkers and therapeutics. Further technical advancement of glial proteomics will enable us to identify proteins within individual cells and specific cell types, thus significantly enhancing our comprehension of AD pathogenesis.

Differential regional importance mapping for thyroid nodule malignancy prediction with potential to improve needle aspiration biopsy sampling reliability

Objective

Existing guidelines for ultrasound-guided fine-needle aspiration biopsy lack specifications on sampling sites, but the number of biopsies improves diagnostic reliability. We propose the use of class activation maps (CAMs) and our modified malignancy-specific heat maps that locate important deep representations of thyroid nodules for class predictions.

Methods

We applied adversarial noise perturbations to the segmented concentric "hot" nodular regions of equal sizes to differentiate regional importance for the malignancy diagnostic performances of an accurate ultrasound-based artificial intelligence computer-aided diagnosis (AI-CADx) system using 2,602 retrospectively collected thyroid nodules with known histopathological diagnosis.

Results

The AI system demonstrated high diagnostic performance with an area under the curve (AUC) value of 0.9302 and good nodule identification capability with a median dice coefficient >0.9 when compared to radiologists' segmentations. Experiments confirmed that the CAM-based heat maps reflect the differentiable importance of different nodular regions for an AI-CADx system to make its predictions. No less importantly, the hot regions in malignancy heat maps of ultrasound images in comparison with the inactivated regions of the same 100 malignant nodules randomly selected from the dataset had higher summed frequency-weighted feature scores of 6.04 versus 4.96 rated by radiologists with more than 15 years of ultrasound examination experience according to widely used ultrasound-based risk stratification American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS) in terms of nodule composition, echogenicity, and echogenic foci, excluding shape and margin attributes, which could only be evaluated on the whole rather than on the sub-nodular component levels. In addition, we show examples demonstrating good spatial correspondence of highlighted regions of malignancy heat map to malignant tumor cell-rich regions in hematoxylin and eosin-stained histopathological images.

Conclusion

Our proposed CAM-based ultrasonographic malignancy heat map provides quantitative visualization of malignancy heterogeneity within a tumor, and it is of clinical interest to investigate in the future its usefulness to improve fine-needle aspiration biopsy (FNAB) sampling reliability by targeting potentially more suspicious sub-nodular regions.

Prospects of Testing Diurnal Profiles of Expressions of TSH-R and Circadian Clock Genes in Thyrocytes for Identification of Preoperative Biomarkers for Thyroid Carcinoma

Thyroid Nodules (TN) are frequent but mostly benign, and postoperative rate of benign TN attains the values from 70% to 90%. Therefore, there is an urgent need for identification of reliable preoperative diagnosis markers for patients with indeterminate thyroid cytology. In this study, an earlier unexplored design of research on preoperative biomarkers for thyroid malignancies was proposed. Evaluation of reported results of studies addressing the links of thyroid cancer to the circadian clockwork dysfunctions and abnormal activities of Thyroid-Stimulating Hormone (TSH) and its receptor (TSH-R) suggested diagnostic significance of such links. However, there is still a gap in studies of interrelationships between diurnal profiles of expression of circadian clock genes and TSH-R in indeterminate thyroid tissue exposed to different concentrations of TSH. These interrelationships might be investigated in future in vitro experiments on benign and malignant thyrocytes cultivated under normal and challenged TSH levels. Their design requires simultaneous measurement of diurnal profiles of expression of both circadian clock genes and TSH-R. Experimental results might help to bridge previous studies of preoperative biomarkers for thyroid carcinoma exploring diagnostic value of diurnal profiles of serum TSH levels, expression of TSH-R, and expression of circadian clock genes.