Department of Pathology, Cancer Hospital, Chinese Academy of Medical Sciences (CHCAMS), Beijing, China.
Division of Medical Technology Development, Hangzhou Zhiwei Information & Technology Ltd., Hangzhou, Hangzhou, China.
Acta Cytol. 2021;65(4):335-341. doi: 10.1159/000510474. Epub 2020 Oct 6.
Urine cytology plays an important role in diagnosing urothelial carcinoma (UC). However, urine cytology interpretation is subjective and difficult. Morphogo (ALAB, Boston, MA, USA), equipped with automatic acquisition and scanning, optical focusing, and automatic classification with convolutional neural network has been developed for bone marrow aspirate smear analysis of hematopoietic diseases. The goal of this preliminary study was to determine the feasibility of developing a machine learning algorithm on Morphogo for identifying abnormal urothelial cells in urine cytology slides.
Thirty-seven achieved abnormal urine cytology slides from cases with the diagnosis of atypical urothelial cells and above (suspicions or positive for UC) were obtained from 1 hospital. A pathologist (J.R.) reviewed the slides and manually selected and annotated representative cells to feed into Morphogo with following categories: benign (urothelial cells, squamous cells, degenerated cells, and inflammatory cells), atypical cells, and suspicious cells. Initial validation of the algorithm was performed on a subset of the original 37 cases. Urine samples from additional 12 unknown cases with various histological diagnoses (6 cases of high-grade urothelial carcinoma (HGUC), 1 case of low-grade urothelial carcinoma (LGUC), 1 case of prostate adenocarcinoma, 1 case of renal cell carcinoma, and 4 cases of non-neoplastic conditions) were collected from another hospital for initial blind testing.
A total of 1,910 benign and 1,978 abnormal (atypical and suspicious) cells from 37 slides were annotated for developing and training of the algorithm. This algorithm was validated on 27 slides that resulted in identification of at least 1 abnormal cell per slide, with a total of 200 abnormal cells, and an average of 7.4 cells per slide. Of the 12 unknown cases tested, the original cytology was positive for tumor cells in 2 HGUC samples. Morphogo was abnormal (atypical or suspicious) for 6 samples from patients with UC, including one with LGUC and one with prostate adenocarcinoma.
Morphogo machine learning algorithm is capable of identifying abnormal urothelial cells. Further validation studies with a larger number of urine samples will be needed to determine if it can be used to assist the cytological diagnosis of UC.
尿液细胞学在诊断尿路上皮癌（UC）方面发挥着重要作用。然而，尿液细胞学的解释具有主观性且困难。Morphogo（ALAB，波士顿，MA，美国）配备了自动采集和扫描、光学聚焦以及基于卷积神经网络的自动分类功能，已被开发用于骨髓抽吸涂片分析血液病。本初步研究的目的是确定在 Morphogo 上开发机器学习算法以识别尿液细胞学涂片上异常尿路上皮细胞的可行性。
从 1 家医院获得了 37 例诊断为非典型尿路上皮细胞及以上（UC 可疑或阳性）的异常尿液细胞学涂片。一名病理学家（J.R.）对这些涂片进行了回顾，并手动选择和标记有代表性的细胞，然后将其输入 Morphogo，分类为良性（尿路上皮细胞、鳞状细胞、退化细胞和炎症细胞）、非典型细胞和可疑细胞。最初对原始 37 例中的一部分进行了算法验证。从另一家医院收集了另外 12 例未知病例的尿液样本，这些病例的组织学诊断各不相同（6 例高级别尿路上皮癌（HGUC）、1 例低级别尿路上皮癌（LGUC）、1 例前列腺腺癌、1 例肾细胞癌和 4 例非肿瘤性疾病），用于初始盲法测试。
对 37 张涂片的 1910 个良性细胞和 1978 个异常（非典型和可疑）细胞进行了注释，以开发和培训算法。该算法在 27 张涂片上进行了验证，每张涂片至少识别出 1 个异常细胞，总共 200 个异常细胞，平均每张涂片 7.4 个细胞。在测试的 12 个未知病例中，有 2 例 HGUC 样本的原始细胞学检查为肿瘤细胞阳性。Morphogo 对 6 例 UC 患者的样本呈异常（非典型或可疑），包括 1 例 LGUC 和 1 例前列腺腺癌。
Morphogo 机器学习算法能够识别异常尿路上皮细胞。需要进一步开展更大数量的尿液样本验证研究，以确定它是否可用于辅助 UC 的细胞学诊断。
