Deep Learning Classification and Quantification of Pejorative and Nonpejorative Architectures in Resected Hepatocellular Carcinoma from Digital Histopathologic Images.

Liver resection is one of the best treatments for small hepatocellular carcinoma (HCC), but post-resection recurrence is frequent. Biotherapies have emerged as an efficient adjuvant treatment, making the identification of patients at high risk of recurrence critical. Microvascular invasion (mVI), poor differentiation, pejorative macrotrabecular architectures, and vessels encapsulating tumor clusters architectures are the most accurate histologic predictors of recurrence, but their evaluation is time-consuming and imperfect. A supervised deep learning-based approach with ResNet34 on 680 whole slide images (WSIs) from 107 liver resection specimens allowed us to build an algorithm for the identification and quantification of these pejorative architectures. This model achieved an accuracy of 0.864 at patch level and 0.823 at WSI level. To assess its robustness, it was validated on an external cohort of 29 HCCs from another hospital, with an accuracy of 0.787 at WSI level, affirming its generalization capabilities. Moreover, the largest connected areas of the pejorative architectures extracted from the model were positively correlated to the presence of mVI and the number of tumor emboli. These results suggest that the identification of pejorative architectures could be an efficient surrogate of mVI and have a strong predictive value for the risk of recurrence. This study is the first step in the construction of a composite predictive algorithm for early post-resection recurrence of HCC, including artificial intelligence-based features.

Primary liver cancer classification from routine tumour biopsy using weakly supervised deep learning.

Background & Aims: The diagnosis of primary liver cancers (PLCs) can be challenging, especially on biopsies and for combined hepatocellular-cholangiocarcinoma (cHCC-CCA). We automatically classified PLCs on routine-stained biopsies using a weakly supervised learning method. Method: We selected 166 PLC biopsies divided into training, internal and external validation sets: 90, 29 and 47 samples, respectively. Two liver pathologists reviewed each whole-slide hematein eosin saffron (HES)-stained image (WSI). After annotating the tumour/non-tumour areas, tiles of 256x256 pixels were extracted from the WSIs and used to train a ResNet18 neural network. The tumour/non-tumour annotations served as labels during training, and the network's last convolutional layer was used to extract new tumour tile features. Without knowledge of the precise labels of the malignancies, we then applied an unsupervised clustering algorithm. Results: Pathological review classified the training and validation sets into hepatocellular carcinoma (HCC, 33/90, 11/29 and 26/47), intrahepatic cholangiocarcinoma (iCCA, 28/90, 9/29 and 15/47), and cHCC-CCA (29/90, 9/29 and 6/47). In the two-cluster model, Clusters 0 and 1 contained mainly HCC and iCCA histological features. The diagnostic agreement between the pathological diagnosis and the two-cluster model predictions (major contingent) in the internal and external validation sets was 100% (11/11) and 96% (25/26) for HCC and 78% (7/9) and 87% (13/15) for iCCA, respectively. For cHCC-CCA, we observed a highly variable proportion of tiles from each cluster (cluster 0: 5-97%; cluster 1: 2-94%). Conclusion: Our method applied to PLC HES biopsy could identify specific morphological features of HCC and iCCA. Although no specific features of cHCC-CCA were recognized, assessing the proportion of HCC and iCCA tiles within a slide could facilitate the identification of cHCC-CCA. Impact and implications: The diagnosis of primary liver cancers can be challenging, especially on biopsies and for combined hepatocellular-cholangiocarcinoma (cHCC-CCA). We automatically classified primary liver cancers on routine-stained biopsies using a weakly supervised learning method. Our model identified specific features of hepatocellular carcinoma and intrahepatic cholangiocarcinoma. Despite no specific features of cHCC-CCA being recognized, the identification of hepatocellular carcinoma and intrahepatic cholangiocarcinoma tiles within a slide could facilitate the diagnosis of primary liver cancers, and particularly cHCC-CCA.

Urgent Liver Transplantation for Acute Liver Failure in Pregnant Women: The Optimum Timing for Delivery.

BACKGROUND: The occurrence of acute liver failure (ALF) in pregnant women due to an etiology unrelated to pregnancy (pregALF) that leads to liver transplantation (LT) has rarely been reported. The objective was to report the outcome of pregnant women and fetus and propose a strategy for the timing of delivery and of LT in these patients. METHODS: Five consecutive pregnant patients with ALF were admitted to our center between 1986 and 2018 and underwent an LT. A systematic review of case reports concerning patients with pregALF who underwent LT was extracted from the literature. RESULTS: Three with gestational ages (GA) at admission of 15, 22, and 31 weeks of gestation (WG) were transplanted after delivery (n = 1) or intrauterine demise (n = 2) and 2 with GA of 16 and 23 WG before delivery. One infant survived in each group. Among the 32 cases published previously, 11 (34%) had been transplanted after delivery (median GA:31 [28-33]); 10 of these 11 infants were alive at birth. The other 21 mothers were transplanted before delivery (GA:21 WG [18-22]). The median GA at delivery was 30 WG [27.75-37]. Twelve of 21 infants were alive at birth. One-year survival among the ALF patients in our series and in the literature was 100%. Overall, the perinatal survival rate was low (64.8%). CONCLUSIONS: In pregnant patients presenting with ALF not related to the pregnancy, the LT lifesaving procedure had an excellent outcome. Overall, 65% of the infants were alive at delivery with major mortality in those fetus <22 WG despite continued pregnancy.

Evaluation of perfusion CT and dual-energy CT for predicting microvascular invasion of hepatocellular carcinoma.

PURPOSE: Evaluation of perfusion CT and dual-energy CT (DECT) quantitative parameters for predicting microvascular invasion (MVI) of hepatocellular carcinoma (HCC) prior to surgery. METHODS: This prospective single-center study included fifty-six patients (44 men; median age 67; range 31-84) who provided written informed consent. Inclusion criteria were (1) treatment-naïve patients with a diagnosis of HCC, (2) an indication for hepatic resection, and (3) available arterial DECT phase and perfusion CT (GE revolution HD-GSI). Iodine concentrations (IC), arterial density (AD), and 9 quantitative perfusion parameters for HCC were correlated to pathological results. Radiological parameters based principal component analysis (PCA), corroborated by unsupervised heatmap classification, was meant to deliver a model for predicting MVI in HCC. Survival analysis was performed using univariable log-rank test and multivariable Cox model, both censored at time of relapse. RESULTS: 58 HCC lesions were analyzed (median size 42.3 mm; range of 20-140). PCA showed that the radiological model was predictive of tumor grade (p = 0.01), intratumoral MVI (p = 0.004), peritumoral MVI (p = 0.04), MTM (macrotrabecular-massive) subtype (p = 0.02), and capsular invasion (p = 0.02) in HCC. Heatmap classification of HCC showed tumor heterogeneity, stratified into three main clusters according to the risk of relapse. Survival analysis confirmed that permeability surface-area product (PS) was the only significant independent parameter, among all quantitative tumoral CT parameters, for predicting a risk of relapse (Cox p value = 0.004). CONCLUSION: A perfusion CT and DECT-based quantitative imaging profile can provide a diagnosis of histological MVI in HCC. PS is an independent parameter for relapse. CLINICAL TRIALS: ClinicalTrials.gov: NCT03754192.

Advanced epithelioid hemangioendothelioma of the liver: could lenvatinib offer a bridge treatment to liver transplantation?

In this article, we describe the case of a 34-year-old woman presenting a multifocal and metastatic epithelioid hemangioendothelioma (HEHE) of the liver. Under classical chemotherapy using cyclophosphamide, there was a fast tumor progression in liver and extra-hepatic metastatic sites (lungs and mediastinal lymph node). Taking into account the patient's age and the natural history of the HEHE, our goal was to try to bring her to liver transplantation (LT) and lenvatinib was an acceptable candidate for this reason. Shortly after the initiation of lenvatinib before LT and surgery, we observed the enlargement of large devascularized necrotic areas in most of the liver HEHE masses, suggesting a good response. The patient was finally transplanted 6 months after initiation of lenvatinib treatment. Eight months after LT, progression occurred (ascites, peritoneal recurrence, and mediastinal lymph node). After restarting lenvatinib, ascites disappeared and the lymph node decreased in size, suggesting a good response, more than 1 year after her transplantation. This is the first case report to our knowledge that illustrates the benefit of lenvatinib as a neoadjuvant bridge until LT for a multifocal and metastatic HEHE. In addition, this drug has also shown a benefit in term of disease control after a late recurrence of the tumor. We suggest that lenvatinib should be proposed as a bridge to the LT for nonresectable HEHE. Moreover, this drug was also beneficial in the treatment of late recurrence after LT. The absence of pharmacologic interactions between classical immunosuppressive drugs and lenvatinib may allow its use as an early adjuvant approach when the risk of recurrence is high. The strength of our case consists in the long follow-up and the innovative message allowing changing palliative strategies into curative ones in case of advanced HEHE.

Four-Year Experience of Digital Slide Telepathology for Intraoperative Frozen Section Consultations in a Two-Site French Academic Department of Pathology.

OBJECTIVES: To share our experience with digital slide telepathology for intraoperative frozen section consultations (IOCs) and to describe its evolution over time by reporting performance metrics and addressing organizational and economic aspects. METHODS: Since 2013, a technician has been alone at the surgical site. At the other site, the pathologist opens the digital slide from a local server via the intranet. Three periods were compared: a 6-month period of conventional IOC (period 1), a 24-month period of telepathology at 6 months after implementation (period 2), and a 12-month period of telepathology at 3.5 years after implementation (period 3). RESULTS: In total, 87 conventional IOCs and 464 and 313 IOCs on digital slides were performed respectively during periods 1, 2, and 3; mean turnaround time was 27, 36, and 38 minutes, respectively, and there were a mean number of 1.1, 1.1, and 1.3 slides, respectively, per IOC. Diagnostic accuracy was achieved in 95.4%, 92.7%, and 93.9%, respectively, of IOCs (not significant). The additional cost is in the same range as the cost of urgent transport by courier. CONCLUSIONS: Developing IOC with digital slides is a challenge but is necessary to optimize medical time in the current context of pathologist shortage and budget restrictions.

Liver transplantation in patients with liver failure related to exertional heatstroke.

BACKGROUND & AIMS: Severe acute liver injury is a grave complication of exertional heatstroke. Liver transplantation (LT) may be a therapeutic option, but the criteria for LT and the optimal timing of LT have not been clearly established. The aim of this study was to define the profile of patients who require transplantation in this context. METHODS: This was a multicentre, retrospective study of patients admitted with a diagnosis of exertional heatstroke-related severe acute liver injury with a prothrombin time (PT) of less than 50%. A total of 24 male patients were studied. RESULTS: Fifteen of the 24 patients (median nadir PT: 35% [29.5-40.5]) improved under medical therapy alone and survived. Nine of the 24 were listed for emergency LT. At the time of registration, the median PT was 10% (5-12) and all had numerous dysfunctional organs. Five patients (nadir PT: 12% [9-12]) were withdrawn from the list because of an elevation of PT values that mainly occurred between day 2 and day 3. Ultimately, 4 patients underwent transplantation as their PT persisted at <10%, 3 days (2.75-3.25) after the onset of exertional heatstroke, and they had more than 3 organ dysfunctions. Of these 4 patients, 3 were still alive 1 year later. Histological analysis of the 4 explanted livers demonstrated massive or sub-massive necrosis, and little potential for effective mitoses, characterised by a "mitonecrotic" appearance. CONCLUSION: The first-line treatment for exertional heatstroke-related severe acute liver injury is medical therapy. LT is only a rare alternative and such a decision should not be taken too hastily. A persistence of PT <10%, without any signs of elevation after a median period of 3  days following the onset of heatstroke, was the trigger that prompted LT, was the trigger adopted in order to decide upon LT. LAY SUMMARY: Acute liver injury due to heatstroke can progress to acute liver failure with organ dysfunction despite medical treatment; in such situations, liver transplantation (LT) may offer a therapeutic option. The classic criteria for LT appear to be poorly adapted to heatstroke-related acute liver failure. We confirmed thatmedication is the first-line therapy acute liver injury caused by heatstroke, with LT only rarely necessary. A decision to perform LT should not be made hastily. Fluctuations in prothrombin time and the patient's clinical status should be considered even in the event of severe liver failure.

18F-FDG Uptake in Well-Differentiated Neuroendocrine Tumors Correlates with Both Ki-67 and VHL Pathway Inactivation.

BACKGROUND: 18F-FDG-PET scan positivity correlates with poor prognosis in neuroendocrine neoplasms (NEN). Glucose transporter 1 (GLUT1) and carbonic anhydrase 9 (CA9) are markers of aggressiveness in tumors. Together with von Hippel-Lindau protein (pVHL), they are involved in tumor cell metabolism via the hypoxia-inducible factor signaling pathway. The aim of this study was to compare, in a series of well-differentiated neuroendocrine tumors (NET), the 18F-FDG uptake and expression of the proliferation markers Ki-67, GLUT1, CA9, and pVHL. PATIENTS AND METHODS: This retrospective study included 27 patients with well-differentiated NET. 18F-FDG-PET images were evaluated by the maximum standardized uptake value (SUVmax). GLUT1, CA9, and pVHL were analyzed by immunohistochemistry. RESULTS: The NET were of pancreatic (n = 19), midgut (n = 4), duodenal (n = 1), esophageal (n = 1), rectal (n = 1), and pulmonary (n = 1) origin. Eight, 11, and 8 tumors were grade 1, 2, and 3, respectively. The mean/median Ki-67 index was 15/10% (1-60). The mean/median SUVmax was 6.2/5.2 (1.4-18.7). SUVmax correlated with greater tumor size (p = 0.03), higher expression of Ki-67 (p = 0.04), and lower expression of pVHL (p = 0.008). In the group of 16 NET with a low proliferative index (Ki-67 index <10%), 5/6 (83%) of the tumors with a high SUVmax had decreased pVHL expression (p = 0.0013). CONCLUSION: This study confirms that 18F-FDG-PET uptake correlates with both tumor size and proliferation in well-differentiated NET, and it highlights a subset of low-grade but 18F-FDG-PET-positive NET related to sporadic inactivation of the VHL pathway.

[18F]FDG PET/CT predicts progression-free survival in patients with idiopathic pulmonary fibrosis.

BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is a devastating disease characterized by an unpredictable course. Prognostic markers and disease activity markers are needed. The purpose of this single-center retrospective study was to evaluate the prognostic value of lung fluorodeoxyglucose ([18F]-FDG) uptake assessed by standardized uptake value (SUV), metabolic lung volume (MLV) and total lesion glycolysis (TLG) in patients with IPF. METHODS: We included 27 IPF patients (IPF group) and 15 patients with a gastrointestinal neuroendocrine tumor without thoracic involvement (control group). We quantified lung SUV mean and SUV max, MLV and TLG and assessed clinical data, high-resolution CT (HRCT) fibrosis and ground-glass score; lung function; gender, age, physiology (GAP) stage at inclusion and during follow-up; and survival. RESULTS: Lung SUV mean and SUV max were higher in IPF patients than controls (p <0.00001). For patients with IPF, SUV mean, SUV max, MLV and TLG were correlated with severity of lung involvement as measured by a decline in forced vital capacity (FVC) and diffusing capacity of the lungs for carbon monoxide (DLCO) and increased GAP score. In a univariate and in a multivariate Cox proportional-hazards model, risk of death was increased although not significantly with high SUV mean. On univariate analysis, risk of death was significantly associated with high TLG and MLV, which disappeared after adjustment functional variables or GAP index. Increased MLV and TLG were independent predictors of death or disease progression during the 12 months after PET scan completion (for every 100-point increase in TLG, hazard ratio [HR]: 1.11 (95% CI 1.06; 1.36), p = 0.003; for every 100-point increase in MLV, HR: 1.20 (1.04; 1.19), p = 0.002). On multivariable analysis including TLG or MLV with age, FVC, and DLCO or GAP index, TLG and MLV remained associated with progression-free survival (HR: 1.1 [1.03; 1.22], p = 0.01; and 1.13 [1.0; 1.2], p = 0.005). CONCLUSION: FDG lung uptake may be a marker of IPF severity and predict progression-free survival for patients with IPF.

Acute Liver Failure/Injury Related to Drug Reaction With Eosinophilia and Systemic Symptoms: Outcomes and Prognostic Factors.

BACKGROUND: Drug reaction with eosinophilia and systemic symptoms (DRESS) is a rare severe adverse drug-induced reaction with multiorgan involvement. The outcome and prediction of those patients who develop severe acute liver injury (sALI) or acute liver failure (ALF) remain little known. METHODS: A multicenter retrospective study of patients admitted with a diagnosis of DRESS-related sALI or ALF. Histological review was performed on liver core biopsies from native livers. RESULTS: Sixteen patients (11 women, 5 men; mean age, 39±17.2 years) were classified as having definite (n=13) or probable (n=3) DRESS. At admission, 3 patients had hepatic encephalopathy; median levels of prothrombin time, INR, and total bilirubin were, respectively, 33% (Q1-Q3, 21-41), 2.74 (1.98-4.50), and 94 µmol/L (Q1-Q3, 39.5-243.5). Nine patients received corticosteroid therapy. Overall, 9 patients improved spontaneously and 7 worsened (liver transplantation [LT] (n=5), deceased (n=2)). Transplantation-free and post-LT survival was 56% and 60%, respectively. After LT, DRESS recurrence was observed in 3 of 5 patients. Systemic corticosteroid therapy was not significantly associated with a clinical improvement. In the multivariate analysis, factor V level less than 40% at day 0 and factor V levels of 40% or greater at admission but decreasing at day 2 were associated with worse outcome. Pathological findings (n=7) revealed atypical lymphoid infiltrates, Kupffer cell hyperplasia with erythrophagocytosis, and an inconstant presence of eosinophils. CONCLUSIONS: The spontaneous prognosis of patients with sALI/ALF due to DRESS is poor and was not improved by corticosteroid therapy. Histology is helpful to establish diagnosis. Dynamic variables regarding factor V values are predictive of a poor outcome.