E-submission
Search
- Page Path
- HOME > Search
Original Articles
- Diagnosis of invasive encapsulated follicular variant papillary thyroid carcinoma by protein-based machine learning
- Truong Phan-Xuan Nguyen, Minh-Khang Le, Sittiruk Roytrakul, Shanop Shuangshoti, Nakarin Kitkumthorn, Somboon Keelawat
- Received July 23, 2024 Accepted September 14, 2024 Published online October 24, 2024
- DOI: https://doi.org/10.4132/jptm.2024.09.14 [Epub ahead of print]
- 361 View
- 62 Download
-
Abstract
PDF
Supplementary Material - Background
Although the criteria for follicular-pattern thyroid tumors are well-established, diagnosing these lesions remains challenging in some cases. In the recent World Health Organization Classification of Endocrine and Neuroendocrine Tumors (5th edition), the invasive encapsulated follicular variant of papillary thyroid carcinoma was reclassified as its own entity. It is crucial to differentiate this variant of papillary thyroid carcinoma from low-risk follicular pattern tumors due to their shared morphological characteristics. Proteomics holds significant promise for detecting and quantifying protein biomarkers. We investigated the potential value of a protein biomarker panel defined by machine learning for identifying the invasive encapsulated follicular variant of papillary thyroid carcinoma, initially using formalin- fixed paraffin-embedded samples.
Methods
We developed a supervised machine-learning model and tested its performance using proteomics data from 46 thyroid tissue samples.
Results
We applied a random forest classifier utilizing five protein biomarkers (ZEB1, NUP98, C2C2L, NPAP1, and KCNJ3). This classifier achieved areas under the curve (AUCs) of 1.00 and accuracy rates of 1.00 in training samples for distinguishing the invasive encapsulated follicular variant of papillary thyroid carcinoma from non-malignant samples. Additionally, we analyzed the performance of single-protein/gene receiver operating characteristic in differentiating the invasive encapsulated follicular variant of papillary thyroid carcinoma from others within The Cancer Genome Atlas projects, which yielded an AUC > 0.5.
Conclusions
We demonstrated that integration of high-throughput proteomics with machine learning can effectively differentiate the invasive encapsulated follicular variant of papillary thyroid carcinoma from other follicular pattern thyroid tumors.
- Significance of p53, cyclin D1 and c-myc Expressions in Thyroid Tumors.
- Zhuhu Li, Ho Jong Jeon, Mi Ja Lee
- Korean J Pathol. 2004;38(1):29-34.
- 1,684 View
- 19 Download
-
Abstract
PDF
- BACKGROUND
The G1/S phase proteins of the cell cycle play critical roles in tumorigenesis and tumor progression. Our aim was to investigate the significance of p53, cyclin D1 and c-myc expressions in thyroid tumors.
METHODS
The expressions of these proteins were examined in 217 cases of thyroid tumors and tissues using immunohistochemistry. The results were correlated with lymph node metastasis.
RESULTS
p53 expression was seen in 75.5, 47.5, 66.7, and 50% of papillary carcinomas (PC), follicular carcinomas (FC), undifferentiated carcinomas (UC) and follicular adenomas (FA), respectively. There was a significant difference between these expressions in these tumors and the results in nodular hyperplasia (NH) and normal tissues. Cyclin D1 expression was noted in 80.0, 68.4, 66.7, 61.1 and 79.5% of PC, FC, UC, FA and NH, respectively. c-myc expression was seen in 80.0, 94.2, 66.7, 66.7 and 52.3% of PC, FC, UC, FA and NH, respectively. There was a significant association between the expressions in these tumors and the results in normal tissues. The expressions of p53, cyclin D1 and c-myc were not correlated with lymph node metastasis.
CONCLUSIONS
These findings suggest the expressions of p53, cyclin D1 and c-myc may act in the early stage, and participates in tumorigenesis and promoting cell growth.
- Immunohistochemical Study on the Proliferative Activity of Human Thyroid Tumors.
- Myoung Jae Kang, Young Jin Jeong, Woo Sung Moon, Myoung Ja Jeong, Joo Heon Kim, Dong Geun Lee, Ho Yeul Choi, Sang Ho Kim
- Korean J Pathol. 1995;29(1):77-84.
- 1,794 View
- 15 Download
-
Abstract
PDF
- For the estimation of the proliferative activity, related to the biologic behaviour, malignant potential, and prognosis, of human thyroid tumors, PCNA(proliferating cell nuclear antigen) immunohistochemical staining was performed on paraffin-embedded sections of 9 normal thyroid tissues, 9 adenomatous goiters, 9 follicular adenomas, 4 Hurthle cell tumors, 12 papillary carcinomas, 4 follicular carcinomas, and 3 anaplastic carcinomas. The results were as follows: 1) The PCNA labeling indices in adenomatous goiter, follicular adenoma, and Hurthle cell tumor were 1.1, 1.5, and 2.4, respectively. They were significantly higher than the labeling index in normal thyroid. 2) The PCNA labeling indices in papillary carcinoma and follicular carcinoma were 3.5 and 4.4, respectively. They were significantly higher than the labeling indices in adenomatous goiter and follicular adenoma, but there was no significant difference between papillary and follicular carcinoma. 3) The PCNA labeling index in anaplastic carcinoma, 14.1, was significantly higher than those in benign and other malignant tumors. According to the results, the PCNA labeling index was well correlated with the malignant potential of a tumor. So the PCNA immunohistochemical staining is thought to be a useful method for the evaluation of the malignant potential and prognosis of a tumor.
First
Prev
