Department of Pathology, University of Helsinki and Helsinki University Hospital, Haartmaninkatu 3, 00290, Helsinki, Finland.
Aiforia Technologies Oy, Tukholmankatu 8, 000290, Helsinki, Finland.
Diagn Pathol. 2021 May 6;16(1):41. doi: 10.1186/s13000-021-01102-6.
The objective was to build a novel method for automated image analysis to locate and quantify the number of cytokeratin 7 (K7)-positive hepatocytes reflecting cholestasis by applying deep learning neural networks (AI model) in a cohort of 210 liver specimens. We aimed to study the correlation between the AI model's results and disease progression. The cohort of liver biopsies which served as a model of chronic cholestatic liver disease comprised of patients diagnosed with primary sclerosing cholangitis (PSC).
In a cohort of patients with PSC identified from the PSC registry of the University Hospital of Helsinki, their K7-stained liver biopsy specimens were scored by a pathologist (human K7 score) and then digitally analyzed for K7-positive hepatocytes (K7%area). The digital analysis was by a K7-AI model created in an Aiforia Technologies cloud platform. For validation, values were human K7 score, stage of disease (Metavir and Nakunuma fibrosis score), and plasma liver enzymes indicating clinical cholestasis, all subjected to correlation analysis.
The K7-AI model results (K7%area) correlated with the human K7 score (0.896; p < 2.2e). In addition, K7%area correlated with stage of PSC (Metavir 0.446; p < 1.849e and Nakanuma 0.424; p < 4.23e) and with plasma alkaline phosphatase (P-ALP) levels (0.369, p < 5.749e).
The accuracy of the AI-based analysis was comparable to that of the human K7 score. Automated quantitative image analysis correlated with stage of PSC and with P-ALP. Based on the results of the K7-AI model, we recommend K7 staining in the assessment of cholestasis by means of automated methods that provide fast (9.75 s/specimen) quantitative analysis.
本研究旨在建立一种新的自动化图像分析方法，通过应用深度学习神经网络（AI 模型）在 210 例肝标本中定位和量化反映胆汁淤积的角蛋白 7（K7）阳性肝细胞数量。我们旨在研究 AI 模型结果与疾病进展的相关性。该肝活检队列作为慢性胆汁淤积性肝病模型，由赫尔辛基大学医院原发性硬化性胆管炎（PSC）登记处诊断的患者组成。
在赫尔辛基大学医院 PSC 登记处鉴定的 PSC 患者队列中，他们的 K7 染色肝活检标本由病理学家（人类 K7 评分）进行评分，然后进行 K7 阳性肝细胞（K7%area）的数字分析。数字分析由 Aiforia 技术云平台创建的 K7-AI 模型完成。为了验证，对人类 K7 评分、疾病分期（Metavir 和 Nakunuma 纤维化评分）和指示临床胆汁淤积的血浆肝酶进行相关性分析。
K7-AI 模型结果（K7%area）与人类 K7 评分（0.896；p<2.2e）相关。此外，K7%area 与 PSC 分期（Metavir 0.446；p<1.849e 和 Nakunuma 0.424；p<4.23e）和血浆碱性磷酸酶（P-ALP）水平（0.369，p<5.749e）相关。
基于人工智能的分析准确性可与人类 K7 评分相媲美。自动化定量图像分析与 PSC 分期和 P-ALP 相关。基于 K7-AI 模型的结果，我们建议在评估胆汁淤积时使用 K7 染色，通过提供快速（9.75s/specimen）定量分析的自动化方法。
