A Multiscale Connected UNet for the Segmentation of Lung Cancer Cells in Pathology Sections Stained Using Rapid On-Site Cytopathological Evaluation.

Am J Pathol

Key Laboratory of Biomedical Information Engineering of Ministry of Education, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, China. Electronic address:

Published: September 2024

Lung cancer is an increasingly serious health problem worldwide, and early detection and diagnosis are crucial for successful treatment. With the development of artificial intelligence and the growth of data volume, machine learning techniques can play a significant role in improving the accuracy of early detection in lung cancer. This study proposes a deep learning-based segmentation algorithm for rapid on-site cytopathological evaluation (ROSE) to enhance the diagnostic efficiency of endobronchial ultrasound-guided transbronchial needle aspiration biopsy (EBUS-TBNA) during surgery. By utilizing the CUNet3+ network model, cell clusters, including cancer cell clusters, can be accurately segmented in ROSE-stained pathological sections. The model demonstrated high accuracy, with an F1-score of 0.9604, recall of 0.9609, precision of 0.9654, and accuracy of 0.9834 on the internal testing data set. It also achieved an area under the receiver-operating characteristic curve of 0.9972 for cancer identification. The proposed algorithm saved time for on-site diagnosis, improved EBUS-TBNA efficiency, and outperformed classical segmentation algorithms in accurately identifying lung cancer cell clusters in ROSE-stained images. It effectively reduced over-segmentation, decreased network parameters, and enhanced computational efficiency, making it suitable for real-time patient evaluation during surgical procedures.

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ajpath.2024.05.011DOI Listing

Publication Analysis

Top Keywords

lung cancer
16
cell clusters
12
rapid on-site
8
on-site cytopathological
8
cytopathological evaluation
8
early detection
8
cancer cell
8
cancer
6
multiscale connected
4
connected unet
4

Similar Publications

Background: Chronic kidney disease (CKD) is a progressive condition that arises from diverse etiological factors, resulting in structural alterations and functional impairment of the kidneys. We aimed to establish the Anoikis-related gene signature in CKD by bioinformatics analysis.

Methods: We retrieved 3 datasets from the Gene Expression Omnibus (GEO) database to obtain differentially expressed genes (DEGs), followed by Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis, Gene Set Enrichment Analysis (GSEA) and Gene Set Variation Analysis (GSVA) of them, which were intersected with Anoikis-related genes (ARGs) to derive Anoikis-related differentially expressed genes (ARDEGs).

View Article and Find Full Text PDF

Primary malignant melanoma of the lung; a case report and literature review.

Respir Med Case Rep

December 2024

Division of Pulmonary Disease and Critical Care Medicine, University of Kentucky College of Medicine, Bowling Green, KY, USA.

Primary pulmonary malignant melanoma is an extremely rare non-epithelial malignancy. Literature is merely limited to a few anecdotal case reports. Herein we present a case of a 74-year-old female who was diagnosed with primary malignant melanoma of the lung.

View Article and Find Full Text PDF

Background: The Arp2/3 complex is a key regulator of tumor metastasis, and targeting its subunits offers potential for anti-metastatic therapy. However, the expression profiles, prognostic relevance, and diagnostic value of its subunits across cancers remain poorly understood. This study aims to investigate the clinical relevance of Arp2/3 complex subunits, particularly ARPC1A, in pan-cancer, and to further analyze the potential biological mechanisms of ARPC1A, as well as its association with immune infiltration and chemotherapy drug sensitivity.

View Article and Find Full Text PDF

In this article, we report the first case of a 61-year-old woman who was diagnosed with both nodules and cystic lesions in her lungs. The lung nodules were diagnosed as ALK-positive histiocytosis (APH) carrying an gene fusion, which microscopically displayed a mixed morphology of foamy cells, spindle cells, and Touton's giant cells. Immunohistochemistry showed expression of CD163, CD68, and ALK, while fluorescence hybridization (FISH) with second-generation sequencing (NGS) showed the ALK gene fusion with the FLCN gene variant.

View Article and Find Full Text PDF

Cancer-associated fibroblast-derived exosomal FAM83F regulates KIF23 expression to promote the malignant progression and reduce radiosensitivity in non-small cell lung cancer.

Cytotechnology

April 2025

Chongqing Key Laboratory of Translational Research for Cancer Metastasis and Individualized Treatment, Chongqing Cancer Institute, Chongqing Cancer Hospital, Chongqing University Cancer Hospital, Chongqing, 400030 China.

Unlabelled: Cancer-associated fibroblasts (CAFs) have been shown to play a crucial role in the progression of non-small cell lung cancer (NSCLC). Exosomes derived from CAFs have emerged as important mediators of intercellular communication in the tumor microenvironment, contributing to cancer progression. Therefore, it is essential to further investigate the mechanisms by which CAF-derived exosomes regulate NSCLC.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!