Algorithmic transparency and interpretability measures improve radiologists' performance in BI-RADS 4 classification.

OBJECTIVE: To evaluate the perception of different types of AI-based assistance and the interaction of radiologists with the algorithm's predictions and certainty measures. METHODS: In this retrospective observer study, four radiologists were asked to classify Breast Imaging-Reporting and Data System 4 (BI-RADS4) lesions (n = 101 benign, n = 99 malignant). The effect of different types of AI-based assistance (occlusion-based interpretability map, classification, and certainty) on the radiologists' performance (sensitivity, specificity, questionnaire) were measured. The influence of the Big Five personality traits was analyzed using the Pearson correlation. RESULTS: Diagnostic accuracy was significantly improved by AI-based assistance (an increase of 2.8% ± 2.3%, 95 %-CI 1.5 to 4.0 %, p = 0.045) and trust in the algorithm was generated primarily by the certainty of the prediction (100% of participants). Different human-AI interactions were observed ranging from nearly no interaction to humanization of the algorithm. High scores in neuroticism were correlated with higher persuasibility (Pearson's r = 0.98, p = 0.02), while higher consciousness and change of accuracy showed an inverse correlation (Pearson's r = -0.96, p = 0.04). CONCLUSION: Trust in the algorithm's performance was mostly dependent on the certainty of the predictions in combination with a plausible heatmap. Human-AI interaction varied widely and was influenced by personality traits. KEY POINTS: • AI-based assistance significantly improved the diagnostic accuracy of radiologists in classifying BI-RADS 4 mammography lesions. • Trust in the algorithm's performance was mostly dependent on the certainty of the prediction in combination with a reasonable heatmap. • Personality traits seem to influence human-AI collaboration. Radiologists with specific personality traits were more likely to change their classification according to the algorithm's prediction than others.

Computed high-b-value high-resolution DWI improves solid lesion detection in IPMN of the pancreas.

OBJECTIVES: To examine the effect of high-b-value computed diffusion-weighted imaging (cDWI) on solid lesion detection and classification in pancreatic intraductal papillary mucinous neoplasm (IPMN), using endoscopic ultrasound (EUS) and histopathology as a standard of reference. METHODS: Eighty-two patients with known or suspected IPMN were retrospectively enrolled. Computed high-b-value images at b = 1000 s/mm2 were calculated from standard (b = 0, 50, 300, and 600 s/mm2) DWI images for conventional full field-of-view (fFOV, 3 × 3 × 4 mm3 voxel size) DWI. A subset of 39 patients received additional high-resolution reduced-field-of-view (rFOV, 2.5 × 2.5 × 3 mm3 voxel size) DWI. In this cohort, rFOV cDWI was compared against fFOV cDWI additionally. Two experienced radiologists evaluated (Likert scale 1-4) image quality (overall image quality, lesion detection and delineation, fluid suppression within the lesion). In addition, quantitative image parameters (apparent signal-to-noise ratio (aSNR), apparent contrast-to-noise ratio (aCNR), contrast ratio (CR)) were assessed. Diagnostic confidence regarding the presence/absence of diffusion-restricted solid nodules was assessed in an additional reader study. RESULTS: High-b-value cDWI at b = 1000 s/mm2 outperformed acquired DWI at b = 600 s/mm2 regarding lesion detection, fluid suppression, aCNR, CR, and lesion classification (p = < .001-.002). Comparing cDWI from fFOV and rFOV revealed higher image quality in high-resolution rFOV-DWI compared to conventional fFOV-DWI (p ≤ .001-.018). High-b-value cDWI images were rated non-inferior to directly acquired high-b-value DWI images (p = .095-.655). CONCLUSIONS: High-b-value cDWI may improve the detection and classification of solid lesions in IPMN. Combining high-resolution imaging and high-b-value cDWI may further increase diagnostic precision. CLINICAL RELEVANCE STATEMENT: This study shows the potential of computed high-resolution high-sensitivity diffusion-weighted magnetic resonance imaging for solid lesion detection in pancreatic intraductal papillary mucinous neoplasia (IPMN). The technique may enable early cancer detection in patients under surveillance. KEY POINTS: • Computed high-b-value diffusion-weighted imaging (cDWI) may improve the detection and classification of intraductal papillary mucinous neoplasms (IPMN) of the pancreas. • cDWI calculated from high-resolution imaging increases diagnostic precision compared to cDWI calculated from conventional-resolution imaging. • cDWI has the potential to strengthen the role of MRI for screening and surveillance of IPMN, particularly in view of the rising incidence of IPMNs combined with now more conservative therapeutic approaches.

A deep learning model enables accurate prediction and quantification of pulmonary edema from chest X-rays.

BACKGROUND: A quantitative assessment of pulmonary edema is important because the clinical severity can range from mild impairment to life threatening. A quantitative surrogate measure, although invasive, for pulmonary edema is the extravascular lung water index (EVLWI) extracted from the transpulmonary thermodilution (TPTD). Severity of edema from chest X-rays, to date is based on the subjective classification of radiologists. In this work, we use machine learning to quantitatively predict the severity of pulmonary edema from chest radiography. METHODS: We retrospectively included 471 X-rays from 431 patients who underwent chest radiography and TPTD measurement within 24 h at our intensive care unit. The EVLWI extracted from the TPTD was used as a quantitative measure for pulmonary edema. We used a deep learning approach and binned the data into two, three, four and five classes increasing the resolution of the EVLWI prediction from the X-rays. RESULTS: The accuracy, area under the receiver operating characteristic curve (AUROC) and Mathews correlation coefficient (MCC) in the binary classification models (EVLWI < 15, ≥ 15) were 0.93 (accuracy), 0.98 (AUROC) and 0.86(MCC). In the three multiclass models, the accuracy ranged between 0.90 and 0.95, the AUROC between 0.97 and 0.99 and the MCC between 0.86 and 0.92. CONCLUSION: Deep learning can quantify pulmonary edema as measured by EVLWI with high accuracy.

Improved detection rates and treatment planning of head and neck cancer using dual-layer spectral CT.

PURPOSE: The aim of this study was to evaluate the advantages of dual-layer spectral CT (DLSCT) in detection and staging of head and neck cancer (HNC) as well as the imaging of tumour margins and infiltration depth compared to conventional contrast enhanced CT (CECT). MATERIALS AND METHODS: Thirty-nine patients with a proven diagnosis of HNC were examined with a DLSCT scanner and retrospectively analysed. An age-matched healthy control group of the same size was used. Images were acquired in the venous phase. Virtual monoenergetic 40keV-equivalent (MonoE40) images were compared to CECT-images. Diagnostic confidence for tumour identification and margin detection was rated independently by four experienced observers. The steepness of the Hounsfield unit (HU)-increase at the tumour margin was analysed. External carotid artery branch image reconstructions were performed and their contrast compared to conventional arterial phase imaging. Means were compared using a Student's t-test. ANOVA was used for multiple comparisons. RESULTS: MonoE40 images were superior to CECT-images in tumour detection and margin delineation. MonoE40 showed significantly higher attenuation differences between tumour and healthy tissue compared to CECT-images (p < 0.001). The HU-increase at the boundary of the tumour was significantly steeper in MonoE40 images compared to CECT-images (p < 0.001). Iodine uptake in the tumour was significantly higher compared to healthy tissue (p < 0.001). MonoE40 compared to conventional images allowed visualisation of external carotid artery branches from the venous phase in a higher number of cases (87% vs. 67%). CONCLUSION: DLSCT enables improved detection of primary and recurrent head and neck cancer and quantification of tumour iodine uptake. Improved contrast of MonoE40 compared to conventional reconstructions enables higher diagnostic confidence concerning tumour margin detection and vessel identification. KEY POINTS: • Sensitivity concerning tumour detection are higher using dual-layer spectral-CT than conventional CT. • Lesion to background contrast in DLSCT is significantly higher than in CECT. • DLSCT provides sufficient contrast for evaluation of external carotid artery branches.

Qualitative and Quantitative Comparison of Respiratory Triggered Reduced Field-of-View (FOV) Versus Full FOV Diffusion Weighted Imaging (DWI) in Pancreatic Pathologies.

RATIONALE AND OBJECTIVES: To investigate the effects of a reduced field-of-view (rFOV) acquisition in diffusion-weighted magnetic resonance imaging of the pancreas. MATERIALS AND METHODS: We enrolled 153 patients who underwent routine clinical MRI work-up including respiratory-triggered diffusion-weighted single-shot echo-planar imaging (DWI) with full field-of-view (fFOV, 3 × 3 × 4 mm3 voxel size) and reduced field-of-view (rFOV, 2.5 × 2.5 × 3 mm3 voxel size) for suspected pancreatic pathology. Two experienced radiologists were asked to subjectively rate (Likert Scale 1-4) image quality (overall image quality, lesion conspicuity, anatomical detail, artifacts). In addition, quantitative image parameters were assessed (apparent diffusion coefficient, apparent signal to noise ratio, apparent contrast to noise ratio [CNR]). RESULTS: All subjective metrics of image quality were rated in favor of rFOV DWI images compared to fFOV DWI images with substantial-to-high inter-rater reliability. Calculated ADC values of normal pancreas, pancreatic pathologies and reference tissues revealed no differences between both sequences. Whereas the apparent signal to noise ratio was higher in fFOV images, apparent CNR was higher in rFOV images. CONCLUSION: rFOV DWI provides higher image quality and apparent CNR values, favorable in the analysis of pancreatic pathologies.

Prediction of Tumor Cellularity in Resectable PDAC from Preoperative Computed Tomography Imaging.

BACKGROUND: PDAC remains a tumor entity with poor prognosis and a 5-year survival rate below 10%. Recent research has revealed invasive biomarkers, such as distinct molecular subtypes, predictive for therapy response and patient survival. Non-invasive prediction of individual patient outcome however remains an unresolved task. METHODS: Discrete cellularity regions of PDAC resection specimen (n = 43) were analyzed by routine histopathological work up. Regional tumor cellularity and CT-derived Hounsfield Units (HU, n = 66) as well as iodine concentrations were regionally matched. One-way ANOVA and pairwise t-tests were performed to assess the relationship between different cellularity level in conventional, virtual monoenergetic 40 keV (monoE 40 keV) and iodine map reconstructions. RESULTS: A statistically significant negative correlation between regional tumor cellularity in histopathology and CT-derived HU from corresponding image regions was identified. Radiological differentiation was best possible in monoE 40 keV CT images. However, HU values differed significantly in conventional reconstructions as well, indicating the possibility of a broad clinical application of this finding. CONCLUSION: In this study we establish a novel method for CT-based prediction of tumor cellularity for in-vivo tumor characterization in PDAC patients.

[18F]FDG PET/MRI enables early chemotherapy response prediction in pancreatic ductal adenocarcinoma.

PURPOSE: In this prospective exploratory study, we evaluated the feasibility of [18F]fluorodeoxyglucose ([18F]FDG) PET/MRI-based chemotherapy response prediction in pancreatic ductal adenocarcinoma at two weeks upon therapy onset. MATERIAL AND METHODS: In a mixed cohort, seventeen patients treated with chemotherapy in neoadjuvant or palliative intent were enrolled. All patients were imaged by [18F]FDG PET/MRI before and two weeks after onset of chemotherapy. Response per RECIST1.1 was then assessed at 3 months [18F]FDG PET/MRI-derived parameters (MTV50%, TLG50%, MTV2.5, TLG2.5, SUVmax, SUVpeak, ADCmax, ADCmean and ADCmin) were assessed, using multiple t-test, Man-Whitney-U test and Fisher's exact test for binary features. RESULTS: At 72 ± 43 days, twelve patients were classified as responders and five patients as non-responders. An increase in ∆MTV50% and ∆ADC (≥ 20% and 15%, respectively) and a decrease in ∆TLG50% (≤ 20%) at 2 weeks after chemotherapy onset enabled prediction of responders and non-responders, respectively. Parameter combinations (∆TLG50% and ∆ADCmax or ∆MTV50% and ∆ADCmax) further improved discrimination. CONCLUSION: Multiparametric [18F]FDG PET/MRI-derived parameters, in particular indicators of a change in tumor glycolysis and cellularity, may enable very early chemotherapy response prediction. Further prospective studies in larger patient cohorts are recommended to their clinical impact.

Combined DCE-MRI- and FDG-PET enable histopathological grading prediction in a rat model of hepatocellular carcinoma.

PURPOSE: To test combined dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and 18F-FDG positron emission tomography (FDG-PET)-derived parameters for prediction of histopathological grading in a rat Diethyl Nitrosamine (DEN)-induced hepatocellular carcinoma (HCC) model. METHODS: 15 male Wistar rats, aged 10 weeks were treated with oral DEN 0.01 % in drinking water and monitored until HCCs were detectable. DCE-MRI and PET were performed consecutively on small animal scanners. 38 tumors were identified and manually segmented based on HCC-specific contrast enhancement patterns. Grading (G2/3: 24 tumors, G1:14 tumors) alongside other histopathological parameters, tumor volume, contrast agent and 18F-FDG uptake metrics were noted. Class imbalance was addressed using SMOTE and collinearity was removed using hierarchical clustering and principal component analysis. A logistic regression model was fit separately to the individual parameter groups (DCE-MRI-derived, PET-derived, tumor volume) and the combined parameters. RESULTS: The combined model using all imaging-derived parameters achieved a mean ± STD sensitivity of 0.88 ± 0.16, specificity of 0.70 ± 0.20 and AUC of 0.90 ± 0.03. No correlation was found between tumor grading and tumor volume, morphology, necrosis, extracellular matrix, immune cell infiltration or underlying liver fibrosis. CONCLUSION: A combination of DCE-MRI- and 18F-FDG-PET-derived parameters provides high accuracy for histopathological grading of hepatocellular carcinoma in a relevant translational model system.

Multiparametric Modelling of Survival in Pancreatic Ductal Adenocarcinoma Using Clinical, Histomorphological, Genetic and Image-Derived Parameters.

RATIONALE: Pancreatic ductal adenocarcinoma (PDAC) remains a tumor entity of exceptionally poor prognosis, and several biomarkers are under current investigation for the prediction of patient prognosis. Many studies focus on promoting newly developed imaging biomarkers without a rigorous comparison to other established parameters. To assess the true value and leverage the potential of all efforts in this field, a multi-parametric evaluation of the available biomarkers for PDAC survival prediction is warranted. Here we present a multiparametric analysis to assess the predictive value of established parameters and the added contribution of newly developed imaging features such as biomarkers for overall PDAC patient survival. METHODS: 103 patients with resectable PDAC were retrospectively enrolled. Clinical and histopathological data (age, sex, chemotherapy regimens, tumor size, lymph node status, grading and resection status), morpho-molecular and genetic data (tumor morphology, molecular subtype, tp53, kras, smad4 and p16 genetics), image-derived features and the combination of all parameters were tested for their prognostic strength based on the concordance index (CI) of multivariate Cox proportional hazards survival modelling after unsupervised machine learning preprocessing. RESULTS: The average CIs of the out-of-sample data were: 0.63 for the clinical and histopathological features, 0.53 for the morpho-molecular and genetic features, 0.65 for the imaging features and 0.65 for the combined model including all parameters. CONCLUSIONS: Imaging-derived features represent an independent survival predictor in PDAC and enable the multiparametric, machine learning-assisted modelling of postoperative overall survival with a high performance compared to clinical and morpho-molecular/genetic parameters. We propose that future studies systematically include imaging-derived features to benchmark their additive value when evaluating biomarker-based model performance.

Image-Based Molecular Phenotyping of Pancreatic Ductal Adenocarcinoma.

To bridge the translational gap between recent discoveries of distinct molecular phenotypes of pancreatic cancer and tangible improvements in patient outcome, there is an urgent need to develop strategies and tools informing and improving the clinical decision process. Radiomics and machine learning approaches can offer non-invasive whole tumor analytics for clinical imaging data-based classification. The retrospective study assessed baseline computed tomography (CT) from 207 patients with proven pancreatic ductal adenocarcinoma (PDAC). Following expert level manual annotation, Pyradiomics was used for the extraction of 1474 radiomic features. The molecular tumor subtype was defined by immunohistochemical staining for KRT81 and HNF1a as quasi-mesenchymal (QM) vs. non-quasi-mesenchymal (non-QM). A Random Forest machine learning algorithm was developed to predict the molecular subtype from the radiomic features. The algorithm was then applied to an independent cohort of histopathologically unclassifiable tumors with distinct clinical outcomes. The classification algorithm achieved a sensitivity, specificity and ROC-AUC (area under the receiver operating characteristic curve) of 0.84 ± 0.05, 0.92 ± 0.01 and 0.93 ± 0.01, respectively. The median overall survival for predicted QM and non-QM tumors was 16.1 and 20.9 months, respectively, log-rank-test p = 0.02, harzard ratio (HR) 1.59. The application of the algorithm to histopathologically unclassifiable tumors revealed two groups with significantly different survival (8.9 and 39.8 months, log-rank-test p < 0.001, HR 4.33). The machine learning-based analysis of preoperative (CT) imaging allows the prediction of molecular PDAC subtypes highly relevant for patient survival, allowing advanced pre-operative patient stratification for precision medicine applications.

Intensive Care Risk Estimation in COVID-19 Pneumonia Based on Clinical and Imaging Parameters: Experiences from the Munich Cohort.

The evolving dynamics of coronavirus disease 2019 (COVID-19) and the increasing infection numbers require diagnostic tools to identify patients at high risk for a severe disease course. Here we evaluate clinical and imaging parameters for estimating the need of intensive care unit (ICU) treatment. We collected clinical, laboratory and imaging data from 65 patients with confirmed COVID-19 infection based on polymerase chain reaction (PCR) testing. Two radiologists evaluated the severity of findings in computed tomography (CT) images on a scale from 1 (no characteristic signs of COVID-19) to 5 (confluent ground glass opacities in over 50% of the lung parenchyma). The volume of affected lung was quantified using commercially available software. Machine learning modelling was performed to estimate the risk for ICU treatment. Patients with a severe course of COVID-19 had significantly increased interleukin (IL)-6, C-reactive protein (CRP), and leukocyte counts and significantly decreased lymphocyte counts. The radiological severity grading was significantly increased in ICU patients. Multivariate random forest modelling showed a mean ± standard deviation sensitivity, specificity and accuracy of 0.72 ± 0.1, 0.86 ± 0.16 and 0.80 ± 0.1 and a receiver operating characteristic-area under curve (ROC-AUC) of 0.79 ± 0.1. The need for ICU treatment is independently associated with affected lung volume, radiological severity score, CRP, and IL-6.

Acceleration of chemical shift encoding-based water fat MRI for liver proton density fat fraction and T2* mapping using compressed sensing.

OBJECTIVES: To evaluate proton density fat fraction (PDFF) and T2* measurements of the liver with combined parallel imaging (sensitivity encoding, SENSE) and compressed sensing (CS) accelerated chemical shift encoding-based water-fat separation. METHODS: Six-echo Dixon imaging was performed in the liver of 89 subjects. The first acquisition variant used acceleration based on SENSE with a total acceleration factor equal to 2.64 (acquisition labeled as SENSE). The second acquisition variant used acceleration based on a combination of CS with SENSE with a total acceleration factor equal to 4 (acquisition labeled as CS+SENSE). Acquisition times were compared between acquisitions and proton density fat fraction (PDFF) and T2*-values were measured and compared separately for each liver segment. RESULTS: Total scan duration was 14.5 sec for the SENSE accelerated image acquisition and 9.3 sec for the CS+SENSE accelerated image acquisition. PDFF and T2* values did not differ significantly between the two acquisitions (paired Mann-Whitney and paired t-test P>0.05 in all cases). CS+SENSE accelerated acquisition showed reduced motion artifacts (1.1%) compared to SENSE acquisition (12.3%). CONCLUSION: CS+SENSE accelerates liver PDFF and T2*mapping while retaining the same quantitative values as an acquisition using only SENSE and reduces motion artifacts.

Camera-based respiratory triggering improves the image quality of 3D magnetic resonance cholangiopancreatography.

PURPOSE: To evaluate the performance of a novel camera-based breathing navigation system in respiratory-triggered (CRT) 3D-magnetic resonance cholangiopancreatography (MRCP) at 3T MRI. METHODS: Two 3D-MRCP data sets were acquired subsequently within one imaging session with traditional respiratory belt- (BRT) or camera- (CRT) based triggering in 28 patients. Overall image quality, blurring, motion artifacts and discernibility of the pancreaticobiliary tree (PBT) structures were scored on a 4-point scale retrospectively by 2 radiologists. The contrast ratio between the common bile duct and its adjacent tissue was measured by region-of-interest (ROI) analysis. The signal intensity increase at the duct boundaries was quantified by line profiles to objectify blurring and motion artifacts. The extracted respiratory signal curves were analyzed for signal quality and trigger timing. RESULTS: Total scan time was 72 s for both acquisitions. CRT yielded significantly better ratings in image quality, background suppression, blurring and discernibility of PBT structures compared to BRT. Contrast ratios were significantly higher in CRT (0.94 ±â€¯0.03) than in BRT (0.93 ±â€¯0.03) exams; paired t test P = 0.0017. Line profile slopes through the common bile duct revealed significantly higher values in CRT (42.23 ±â€¯8.74% of maximum intensity/mm) compared to BRT (36.06 ±â€¯8.96% of maximum intensity/mm; paired t test P < 0.0001). Camera-derived respiratory signal curves showed a higher SNR, lower standard deviation of the signal amplitude and less incorrect triggering than the respiratory belt-derived respiratory signal curves. CONCLUSION: Camera-based respiratory triggering significantly improves image quality of 3D-MRCP compared to conventional respiratory belt triggering.

Magnetic resonance cholangiopancreatography at 3 Tesla: Image quality comparison between 3D compressed sensing and 2D single-shot acquisitions.

OBJECTIVES: To compare the image quality between compressed sensing (CS) 3D-magnetic resonance cholangiopancreatography (MRCP) using respiratory-triggered (RT) and breath-hold (BH) acquisitions and 2D single-shot breath-hold (SSBH) MRCP at 3 T MRI. METHODS: 53 datasets were retrospectively assessed. 3D-MRCP with CS (RT-CS10, BH-CS24) and 2D-SSBH MRCP were acquired. Overall image quality, blurring/motion artifacts and discernibility of the pancreaticobiliary tree (PBT) structures were scored on a 4-point scale by 2 radiologists. The contrast ratio between the common bile duct and its adjacent tissue was measured by region-of-interest (ROI) analysis. Signal intensity increase at the boundaries of the ducts was quantified by line profiles to objectively characterize blurring and motion artifacts. RESULTS: Total scan duration was 17 s for BH-CS24, 1m12 s for 2D-SSBH and 3m48 s for RT-CS10. Images acquired with CS were consistently rated superior in terms of image quality, background suppression, blurring and discernibility of PBT structures compared to 2D-SSBH images. RT-CS10 was superior to BH-CS24 for all ratings except for blurring. Objective analysis yielded the highest contrast ratio for RT-CS10 (0.91 ± 0.04) followed by BH-C24 (0.88 ± 0.05) and 2D-SSBH (0.85 ± 0.06); one-way ANOVA P < 0.0001. The line-profile slope through the CBD was significantly higher in BH-CS24 (37.91 ± 6.38% of maximum intensity/mm) compared to RT-CS10 (29.46 ± 8.17% of maximum intensity/mm) and on par with 2D-SSBH (35.8 ± 12.30% of maximum intensity/mm); one-way-ANOVA P = 0.017. CONCLUSION: CS allows acquisition of volumetric image data with improved image quality compared to SSBH. CS24 yields substantial gains in acquisition speed while robust towards artifacts, enabling diagnostic image quality with a single breath-hold acquisition.

Borderline-resectable pancreatic adenocarcinoma: Contour irregularity of the venous confluence in pre-operative computed tomography predicts histopathological infiltration.

PURPOSE: The purpose of the current study was to compare CT-signs of portal venous confluence infiltration for actual histopathological infiltration of the vein or the tumor/vein interface (TVI) in borderline resectable pancreatic ductal adenocarcinoma (PDAC). METHODS AND MATERIALS: 101 patients with therapy-naïve, primarily resected PDAC of the pancreatic head without arterial involvement were evaluated. The portal venous confluence was assessed for contour irregularity (defined as infiltration) and degree of contact. The sensitivity and specificity of contour irregularity versus tumor to vein contact >180° as well as the combination of the signs for tumor cell infiltration of the vessel wall or TVI was calculated. Overall survival (OS) was compared between groups. RESULTS: Sensitivity and specificity of contour irregularity for identification of tumor infiltration of the portal venous confluence or the TVI was higher compared to tumor to vessel contact >180° for tumor cell infiltration (96%/79% vs. 91%/38% respectively, p<0.001). The combination of the signs increased specificity to 92% (sensitivity 88%). Patients with contour irregularity/ tumor to vein contact >180°/ both signs had significantly worse overall survival (16.2 vs. 26.5 months/ 17.9 vs. 37.4 months/ 18.5 vs. 26.5 months respectively, all p<0.05). CONCLUSION: Portal venous confluence contour irregularity is a strong predictor of actual tumor cell infiltration of the vessel wall or the TVI and should be noted as such in radiological reports.