Dataset Information

Machine-learning-based diagnosis of thyroid fine-needle aspiration biopsy synergistically by Papanicolaou staining and refractive index distribution.

ABSTRACT: We developed a machine learning algorithm (MLA) that can classify human thyroid cell clusters by exploiting both Papanicolaou staining and intrinsic refractive index (RI) as correlative imaging contrasts and evaluated the effects of this combination on diagnostic performance. Thyroid fine-needle aspiration biopsy (FNAB) specimens were analyzed using correlative optical diffraction tomography, which can simultaneously measure both, the color brightfield of Papanicolaou staining and three-dimensional RI distribution. The MLA was designed to classify benign and malignant cell clusters using color images, RI images, or both. We included 1535 thyroid cell clusters (benign: malignancy = 1128:407) from 124 patients. Accuracies of MLA classifiers using color images, RI images, and both were 98.0%, 98.0%, and 100%, respectively. As information for classification, the nucleus size was mainly used in the color image; however, detailed morphological information of the nucleus was also used in the RI image. We demonstrate that the present MLA and correlative FNAB imaging approach has the potential for diagnosing thyroid cancer, and complementary information from color and RI images can improve the performance of the MLA.

SUBMITTER: Lee YK

PROVIDER: S-EPMC10276805 | biostudies-literature | 2023 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine-learning-based diagnosis of thyroid fine-needle aspiration biopsy synergistically by Papanicolaou staining and refractive index distribution.

Lee Young Ki YK Ryu Dongmin D Kim Seungwoo S Park Juyeon J Park Seog Yun SY Ryu Donghun D Lee Hayoung H Lim Sungbin S Min Hyun-Seok HS Park YongKeun Y Lee Eun Kyung EK

Scientific reports 20230617 1

We developed a machine learning algorithm (MLA) that can classify human thyroid cell clusters by exploiting both Papanicolaou staining and intrinsic refractive index (RI) as correlative imaging contrasts and evaluated the effects of this combination on diagnostic performance. Thyroid fine-needle aspiration biopsy (FNAB) specimens were analyzed using correlative optical diffraction tomography, which can simultaneously measure both, the color brightfield of Papanicolaou staining and three-dimensio ...[more]

PMID: 37330568

Similar Datasets

Project description:Although thyroid fine-needle aspiration (FNA) and core needle biopsy (CNB) are commonly utilized modalities in the evaluation of thyroid nodules, metastatic tumors to the thyroid are only rarely encountered. We aspired to determine the incidence and primary origin of metastases to the thyroid at our institution and to examine their clinicopathologic and cytomorphologic features.A search of our database was undertaken to review all thyroid FNA and/or CNB examined between January 2004 and December 2013.During our 10 year study period, 7497 patients underwent 13,182 FNA and/or CNB. Four hundred sixty one (6%) patients were diagnosed with neoplasms. Only five (1.1%) were found to have metastatic tumors to the thyroid involving three females and two males. Two were diagnosed by FNA, one by CNB, and two by both FNA and CNB, with rapid on-site evaluation (ROSE) employed in all cases. The primary malignancies in the five cases were pulmonary and nasopharyngeal squamous cell carcinomas, renal cell carcinoma, pancreatic adenocarcinoma, and olfactory neuroblastoma. The cytomorphologic features of these metastases to the thyroid aided in their distinction from primary thyroid carcinoma. Two of these metastases, a renal cell carcinoma and pancreatic adenocarcinoma, were the first clinical manifestations of cancer.Metastases to the thyroid diagnosed by FNA and/or CNB are exceedingly rare in our institution, comprising only 0.04% of total FNA/CNB and only 1.1% of all thyroid neoplasms. We report the first known case of metastatic olfactory neuroblastoma to the thyroid diagnosed by aspiration cytology. In addition, an occult primary may present as a thyroid mass on FNA or CNB as occurred with two of our cases. FNA/CNB proved to be highly effective in the diagnosis of metastases to the thyroid, with ROSE proving valuable in assuring specimen adequacy. Thyroid FNA and CNB demonstrated great utility in the setting of metastatic disease, obviating the need for more invasive procedures.

Dataset Information

Machine-learning-based diagnosis of thyroid fine-needle aspiration biopsy synergistically by Papanicolaou staining and refractive index distribution.

Publications

Machine-learning-based diagnosis of thyroid fine-needle aspiration biopsy synergistically by Papanicolaou staining and refractive index distribution.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets