NGS of brush cytology samples improves the detection of high-grade dysplasia and cholangiocarcinoma in patients with primary sclerosing cholangitis: A retrospective and prospective study.

BACKGROUND: Biliary dysplasia, a precursor of cholangiocarcinoma (CCA), is a common complication of primary sclerosing cholangitis. Patients with high-grade dysplasia (HGD) or early CCA who have received oncological treatment are candidates for liver transplantation. The preoperative diagnosis of CCA or HGD is challenging, and the sensitivity of biliary brush cytology (BC) is limited. METHODS: By using next-generation sequencing (NGS), we retrospectively analyzed archived tissue samples (n=62) obtained from explanted liver tissue and CCA samples to identify oncogenic mutations that occur during primary sclerosing cholangitis carcinogenesis. BC samples were prospectively collected from patients with primary sclerosing cholangitis (n=97) referred for endoscopic retrograde cholangiography to measure the diagnostic utility of NGS combined with BC compared with traditional cytology alone. RESULTS: Mutations in KRAS, GNAS, FLT3, RNF43, TP53, ATRX, and SMAD4 were detected in archived CCA or HGD samples. KRAS, GNAS, TP53, CDKN2A, FBXW7, BRAF, and ATM mutations were detected in prospectively collected brush samples from patients with histologically verified CCA or HGD. One patient with low-grade dysplasia in the explanted liver had KRAS and GNAS mutations in brush sample. No mutations were observed in brush samples or archived tissues in liver transplantation cases without biliary neoplasia. While KRAS mutations are common in biliary neoplasms, they were also observed in patients without biliary neoplasia during surveillance. CONCLUSIONS: In summary, NGS of BC samples increased the sensitivity of detecting biliary neoplasia compared with traditional cytology. Performing NGS on BC samples may help diagnose HGD or early CCA, benefiting the timing of liver transplantation.

Deep learning quantification reveals a fundamental prognostic role for ductular reaction in biliary atresia.

BACKGROUND: We aimed to quantify ductular reaction (DR) in biliary atresia using a neural network in relation to underlying pathophysiology and prognosis. METHODS: Image-processing neural network model was applied to 259 cytokeratin-7-stained native liver biopsies of patients with biliary atresia and 43 controls. The model quantified total proportional DR (DR%) composed of portal biliary epithelium (BE%) and parenchymal intermediate hepatocytes (PIH%). The results were related to clinical data, Sirius Red-quantified liver fibrosis, serum biomarkers, and bile acids. RESULTS: In total, 2 biliary atresia biopsies were obtained preoperatively, 116 at Kasai portoenterostomy (KPE) and 141 during post-KPE follow-up. DR% (8.3% vs. 5.9%, p=0.045) and PIH% (1.3% vs. 0.6%, p=0.004) were increased at KPE in patients remaining cholestatic postoperatively. After KPE, patients with subsequent liver transplantation or death showed an increase in DR% (7.9%-9.9%, p = 0.04) and PIH% (1.6%-2.4%, p = 0.009), whereas patients with native liver survival (NLS) showed decreasing BE% (5.5%-3.0%, p = 0.03) and persistently low PIH% (0.9% vs. 1.3%, p = 0.11). In Cox regression, high DR predicted inferior NLS both at KPE [DR% (HR = 1.05, p = 0.01), BE% (HR = 1.05, p = 0.03), and PIH% (HR = 1.13, p = 0.005)] and during follow-up [DR% (HR = 1.08, p<0.0001), BE% (HR = 1.58, p = 0.001), and PIH% (HR = 1.04, p = 0.008)]. DR% correlated with Sirius red-quantified liver fibrosis at KPE (R = 0.47, p<0.0001) and follow-up (R = 0.27, p = 0.004). A close association between DR% and serum bile acids was observed at follow-up (R = 0.61, p<0.001). Liver fibrosis was not prognostic for NLS at KPE (HR = 1.00, p = 0.96) or follow-up (HR = 1.01, p = 0.29). CONCLUSIONS: DR predicted NLS in different disease stages before transplantation while associating with serum bile acids after KPE.

Programmed death-ligand 1 and tumor-infiltrating lymphocytes (TILs) - low TIL density may predict poorer long-term prognosis in T1 laryngeal cancer.

We evaluated the prognostic role of programmed death-ligand 1 (PD-L1) and tumor-infiltrating lymphocytes (TILs) in T1 glottic laryngeal squamous cell carcinoma (LSCC). T1 glottic LSCC patients (n = 174) treated at five Finnish university hospitals between 2003 and 2013 were included. Tissue microarray (TMA) blocks were used for PD-L1 immunohistochemistry. TILs were scored from intratumoral and stromal regions in whole tissue sections. Of 174 patients, 92 (53%) had negative, 66 (38%) intermediate, and 16 (9%) high PD-L1 levels. Of 80 patients whose TILs were analyzed, 50 (63%) had low and 30 (38%) high stromal TIL density. Patients with a local recurrence or a new primary tumor of the larynx had lower TIL density than had other patients (p = 0.047). High PD-L1 expression with low stromal TIL density was associated with inferior 5-year disease-specific survival (85% vs. 100%, p = 0.02). In conclusion, in patients treated for T1 glottic LSCC, low stromal TIL density was associated with local recurrences and new primary tumors of the larynx. High PD-L1 expression with low stromal TIL density may be associated with worse survival in T1 glottic LSCC.

The role of serology, liver function tests and imaging in screening of primary sclerosing cholangitis: the HelPSCreen score.

OBJECIVES: At present, no sensitive or specific screening test exists for primary sclerosing cholangitis (PSC). PSC screening is mainly based on elevated alkaline phosphatase (ALP) in patients with inflammatory bowel disease (IBD). We aimed to produce a screening score based on laboratory tests to predict the likelihood of PSC. Moreover, we evaluated the additional roles of liver histology and magnetic resonance cholangiopancreatography (MRCP) in the diagnosis of PSC. MATERIALS AND METHODS: The data of 385 patients who came for their first endoscopic retrograde cholangiography (ERC) to confirm PSC diagnosis were retrieved from the PSC registry of the Helsinki University Hospital. Overall, 69 patients referred for ERC with suspected PSC, in whom PSC was excluded by ERC or liver biopsy and MRCP, served as controls. We included patients' demographics and 13 laboratory test results in the analysis. Variables with significant odds ratios were selected for multivariate logistic regression, which was used to create a novel scoring system for PSC. The presence of IBD, serum perinuclear anti-neutrophil cytoplasmic antibodies, and ALP levels demonstrated the highest predictive value for PSC. A score was assigned for each statistically significant predictor. RESULTS: The optimal cut-off point for the score was ≥3, with an AUC of 0.83 (95%CI: 0.78-0.88). The addition of liver histology or MRCP findings to the score did not add a predictive value. CONCUSIONS: In conclusion, we created a novel, simple scoring system to screen the probability of PSC. The HelPSCreen-score may help to assess the disease prevalence and to target further investigations in patients suspected of PSC.

Deep Learning-Based Image Analysis of Liver Steatosis in Mouse Models.

The incidence of nonalcoholic fatty liver disease is a continuously growing health problem worldwide, along with obesity. Therefore, novel methods to both efficiently study the manifestation of nonalcoholic fatty liver disease and to analyze drug efficacy in preclinical models are needed. The present study developed a deep neural network-based model to quantify microvesicular and macrovesicular steatosis in the liver on hematoxylin-eosin-stained whole slide images, using the cloud-based platform, Aiforia Create. The training data included a total of 101 whole slide images from dietary interventions of wild-type mice and from two genetically modified mouse models with steatosis. The algorithm was trained for the following: to detect liver parenchyma, to exclude the blood vessels and any artefacts generated during tissue processing and image acquisition, to recognize and differentiate the areas of microvesicular and macrovesicular steatosis, and to quantify the recognized tissue area. The results of the image analysis replicated well the evaluation by expert pathologists and correlated well with the liver fat content measured by EchoMRI ex vivo, and the correlation with total liver triglycerides was notable. In conclusion, the developed deep learning-based model is a novel tool for studying liver steatosis in mouse models on paraffin sections and, thus, can facilitate reliable quantification of the amount of steatosis in large preclinical study cohorts.

Automated image analysis of keratin 7 staining can predict disease outcome in primary sclerosing cholangitis.

BACKGROUND AND AIMS: Primary sclerosing cholangitis (PSC) is a chronic cholestatic liver disease that obstructs the bile ducts and causes liver cirrhosis and cholangiocarcinoma. Efficient surrogate markers are required to measure disease progression. The cytokeratin 7 (K7) load in a liver specimen is an independent prognostic indicator that can be measured from digitalized slides using artificial intelligence (AI)-based models. METHODS: A K7-AI model 2.0 was built to measure the hepatocellular K7 load area of the parenchyma, portal tracts, and biliary epithelium. K7-stained PSC liver biopsy specimens (n = 295) were analyzed. A compound endpoint (liver transplantation, liver-related death, and cholangiocarcinoma) was applied in Kaplan-Meier survival analysis to measure AUC values and positive likelihood ratios for each histological variable detected by the model. RESULTS: The K7-AI model 2.0 was a better prognostic tool than plasma alkaline phosphatase, the fibrosis stage evaluated by Nakanuma classification, or K7 score evaluated by a pathologist based on the AUC values of measured variables. A combination of parameters, such as portal tract volume and area of K7-positive hepatocytes analyzed by the model, produced an AUC of 0.81 for predicting the compound endpoint. Portal tract volume measured by the model correlated with the histological fibrosis stage. CONCLUSIONS: The K7 staining of histological liver specimens in PSC provides significant information on disease outcomes through objective and reproducible data, including variables that cannot be measured by a human pathologist. The K7-AI model 2.0 could serve as a prognostic tool for clinical endpoints and as a surrogate marker in drug trials.

Novel histological scoring for predicting disease outcome in primary sclerosing cholangitis.

BACKGROUND: Primary sclerosing cholangitis (PSC) is a progressive cholestatic liver disease that may lead to liver cirrhosis or cholangiocarcinoma. Liver histology and fibrosis stage are predictive markers of disease progression, and histological cirrhosis is defined as a significant endpoint. PSC-specific histological scoring methods are lacking at present. We aimed to develop a tailored classification system for PSC, the PSC histoscore, based on histological features associated with disease progression. METHODS: In total, 300 PSC patients diagnosed between 1988 and 2018 were enrolled; their data were collected from the PSC registry (Helsinki University Hospital), and liver specimens were obtained from the Biobank of Helsinki. Five histological features included in the adapted Nakanuma scoring system and three additional parameters typical for PSC histology were evaluated and compared with the clinical and laboratory data. A compound endpoint consisting of liver transplantation, development of cholangiocarcinoma, or death was used as outcome measurement. RESULTS: Stage (fibrosis, bile duct loss, ductular reaction, and chronic cholestasis) and grade (portal inflammation, portal edema, hepatitis activity, and cholangitis activity) parameters were found to be independent predictive risk factors for the compound endpoint (P < 0.001). High disease grade (2-6) and stage (2-4) better correlated with clinical endpoints when evaluated with the PSC histoscore system compared to the adapted Nakanuma classification. The risk for disease progression in sequential endoscopic retrograde cholangiography (ERC) examinations was increased with elevated total PSC histoscores. CONCLUSION: The PSC histoscore is a novel histological classification system for PSC. Our findings support the applicability of liver histology as a marker for disease progression.

Chronic cholestasis detection by a novel tool: automated analysis of cytokeratin 7-stained liver specimens.

BACKGROUND: 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). METHODS: 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. RESULTS: The K7-AI model results (K7%area) correlated with the human K7 score (0.896; p < 2.2e- 16). In addition, K7%area correlated with stage of PSC (Metavir 0.446; p < 1.849e- 10 and Nakanuma 0.424; p < 4.23e- 10) and with plasma alkaline phosphatase (P-ALP) levels (0.369, p < 5.749e- 5). CONCLUSIONS: 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.