Department of Pathology and Laboratory Medicine, University of Miami Health System, Miami, FL, USA.
Department of Pathology, University of Pittsburgh Medical Center, Pittsburgh, PA, USA.
Cytopathology. 2020 Sep;31(5):426-431. doi: 10.1111/cyt.12829. Epub 2020 May 20.
Distinguishing small cell lung carcinoma (SCLC) from large cell neuroendocrine carcinoma (LCNEC) in cytology is challenging. Our aim was to design a deep learning algorithm for classifying high-grade neuroendocrine carcinomas in fine needle aspirations.
Archival cytology cases of high-grade neuroendocrine carcinoma (17 small cell, 13 large cell, 10 mixed/unclassifiable) were retrieved. Each case included smears (Diff-Quik® and Papanicolaou stains) and cell block or concomitant core biopsies (haematoxylin and eosin [H&E] stain). All slides (n = 114) were scanned at 40× magnification, randomised and split into training (11 large, nine small) and test (two large, eight small, 10 mixed) groups. Tumour was annotated using QuPath and exported as JPEG image tiles. Three distinct deep learning convolutional neural networks, one for each preparation/stain, were designed to classify each tile and provide an overall diagnosis for each slide.
The H&E-trained algorithm correctly classified 7/8 (87.5%) SCLC cases and 2/2 (100%) LCNEC cases. The Papanicolaou stain algorithm correctly classified 6/7 (85.7%) SCLC. and 1/1 (100%) LCNEC cases. The algorithm trained on Diff-Quik® stained images correctly classified 7/8 (87.5%) SCLC and 1/1 (100%) LCNEC cases.
Using open source software, it was feasible to design a deep learning algorithm to distinguish between SCLC and LCNEC. The algorithm showed high precision in distinguishing between these two categories on H&E sectioned material and direct smears. Although the dataset was limited, our deep learning models show promising results in the classification of LCNEC and SCLC. Additional work using a larger dataset is necessary to improve the algorithm's performance.
在细胞学中区分小细胞肺癌（SCLC）和大细胞神经内分泌癌（LCNEC）具有挑战性。我们的目的是设计一种深度学习算法，用于分类细针抽吸的高级神经内分泌癌。
回顾性检索高级神经内分泌癌（17 例小细胞、13 例大细胞、10 例混合/无法分类）的存档细胞学病例。每个病例包括涂片（Diff-Quik®和巴氏染色）和细胞块或伴随的核心活检（苏木精和伊红[H&E]染色）。所有载玻片（n=114）均以 40×放大倍数扫描，随机分为训练组（11 例大细胞，9 例小细胞）和测试组（2 例大细胞，8 例小细胞，10 例混合）。使用 QuPath 对肿瘤进行注释，并以 JPEG 图像块的形式导出。设计了三个不同的深度学习卷积神经网络，分别用于每种制备/染色，以对每个图像块进行分类，并为每个载玻片提供总体诊断。
H&E 训练的算法正确分类了 8/8（87.5%）例 SCLC 病例和 2/2（100%）例 LCNEC 病例。巴氏染色算法正确分类了 6/7（85.7%）例 SCLC 病例和 1/1（100%）例 LCNEC 病例。在 Diff-Quik®染色图像上训练的算法正确分类了 8/8（87.5%）例 SCLC 病例和 1/1（100%）例 LCNEC 病例。
使用开源软件，设计一种深度学习算法来区分 SCLC 和 LCNEC 是可行的。该算法在 H&E 切片和直接涂片上对这两种类型的区分具有很高的准确性。尽管数据集有限，但我们的深度学习模型在 LCNEC 和 SCLC 的分类中显示出有希望的结果。需要使用更大的数据集来改进算法的性能。
