Machine Learning Streamlines the Morphometric Characterization and Multiclass Segmentation of Nuclei in Different Follicular Thyroid Lesions: Everything in a NUTSHELL.

Autor:	L'Imperio V; School of Medicine and Surgery, University of Milano-Bicocca, Milan, Italy; Department of Pathology, Fondazione IRCCS San Gerardo dei Tintori, Monza, Italy., Coelho V; Department of Informatics, Systems and Communication, University of Milano-Bicocca, Milan, Italy., Cazzaniga G; School of Medicine and Surgery, University of Milano-Bicocca, Milan, Italy; Department of Pathology, Fondazione IRCCS San Gerardo dei Tintori, Monza, Italy., Papetti DM; Department of Informatics, Systems and Communication, University of Milano-Bicocca, Milan, Italy., Del Carro F; School of Medicine and Surgery, University of Milano-Bicocca, Milan, Italy; Department of Pathology, Fondazione IRCCS San Gerardo dei Tintori, Monza, Italy., Capitoli G; School of Medicine and Surgery, University of Milano-Bicocca, Milan, Italy; Bicocca Bioinformatics Biostatistics and Bioimaging Research Centre-B4, University of Milano-Bicocca, Milan, Italy., Marino M; Department of Informatics, Systems and Communication, University of Milano-Bicocca, Milan, Italy., Ceku J; School of Medicine and Surgery, University of Milano-Bicocca, Milan, Italy; Department of Pathology, Fondazione IRCCS San Gerardo dei Tintori, Monza, Italy., Fusco N; Division of Pathology, European Institute of Oncology IRCCS, Milan, Italy; Department of Oncology and Hematology-Oncology, University of Milan, Milan, Italy., Ivanova M; Division of Pathology, European Institute of Oncology IRCCS, Milan, Italy., Gianatti A; Department of Pathology, ASST Papa Giovanni XXIII, Bergamo, Italy., Nobile MS; Bicocca Bioinformatics Biostatistics and Bioimaging Research Centre-B4, University of Milano-Bicocca, Milan, Italy; Department of Environmental Sciences, Informatics and Statistics, Ca' Foscari University of Venice, Venice, Italy., Galimberti S; School of Medicine and Surgery, University of Milano-Bicocca, Milan, Italy; Bicocca Bioinformatics Biostatistics and Bioimaging Research Centre-B4, University of Milano-Bicocca, Milan, Italy; Biostatistics and Clinical Epidemiology, Fondazione IRCCS San Gerardo Dei Tintori, Monza, Italy., Besozzi D; Department of Informatics, Systems and Communication, University of Milano-Bicocca, Milan, Italy; Bicocca Bioinformatics Biostatistics and Bioimaging Research Centre-B4, University of Milano-Bicocca, Milan, Italy. Electronic address: daniela.besozzi@unimib.it., Pagni F; School of Medicine and Surgery, University of Milano-Bicocca, Milan, Italy; Department of Pathology, Fondazione IRCCS San Gerardo dei Tintori, Monza, Italy. Electronic address: fabio.pagni@unimib.it.
Jazyk:	angličtina
Zdroj:	Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc [Mod Pathol] 2024 Dec; Vol. 37 (12), pp. 100608. Date of Electronic Publication: 2024 Sep 05.
DOI:	10.1016/j.modpat.2024.100608
Abstrakt:	The diagnostic assessment of thyroid nodules is hampered by the persistence of uncertainty in borderline cases and further complicated by the inclusion of noninvasive follicular tumor with papillary-like nuclear features (NIFTP) as a less aggressive alternative to papillary thyroid carcinoma (PTC). In this setting, computational methods might facilitate the diagnostic process by unmasking key nuclear characteristics of NIFTP. The main aims of this work were to (1) identify morphometric features of NIFTP and PTC that are interpretable for the human eye and (2) develop a deep learning model for multiclass segmentation as a support tool to reduce diagnostic variability. Our findings confirmed that nuclei in NIFTP and PTC share multiple characteristics, setting them apart from hyperplastic nodules (HP). The morphometric analysis identified 15 features that can be translated into nuclear alterations readily understandable by pathologists, such as a remarkable internuclear homogeneity for HP in contrast to a major complexity in the chromatin texture of NIFTP and to the peculiar pattern of nuclear texture variability of PTC. A few NIFTP cases with available next-generation sequencing data were also analyzed to initially explore the impact of RAS-related mutations on nuclear morphometry. Finally, a pixel-based deep learning model was trained and tested on whole-slide images of NIFTP, PTC, and HP cases. The model, named NUTSHELL (NUclei from Thyroid tumors Segmentation to Highlight Encapsulated Low-malignant Lesions), successfully detected and classified the majority of nuclei in all whole-slide image tiles, showing comparable results with already well-established pathology nuclear scores. NUTSHELL provides an immediate overview of NIFTP areas and can be used to detect microfoci of PTC within extensive glandular samples or identify lymph node metastases. NUTSHELL can be run inside WSInfer with an easy rendering in QuPath, thus facilitating the democratization of digital pathology. (Copyright © 2024 The Authors. Published by Elsevier Inc. All rights reserved.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu