Machine Learning Models for Prediction of Posttreatment Recurrence in Early-Stage Hepatocellular Carcinoma Using Pretreatment Clinical and MRI Features: A Proof-of-Concept Study.

BACKGROUND. Posttreatment recurrence is an unpredictable complication after liver transplant for hepatocellular carcinoma (HCC) that is associated with poor survival. Biomarkers are needed to estimate recurrence risk before organ allocation. OBJECTIVE. This proof-of-concept study evaluated the use of machine learning (ML) to predict recurrence from pretreatment laboratory, clinical, and MRI data in patients with early-stage HCC initially eligible for liver transplant. METHODS. This retrospective study included 120 patients (88 men, 32 women; median age, 60.0 years) with early-stage HCC diagnosed who were initially eligible for liver transplant and underwent treatment by transplant, resection, or thermal ablation between June 2005 and March 2018. Patients underwent pretreatment MRI and posttreatment imaging surveillance. Imaging features were extracted from postcontrast phases of pretreatment MRI examinations using a pretrained convolutional neural network. Pretreatment clinical characteristics (including laboratory data) and extracted imaging features were integrated to develop three ML models (clinical model, imaging model, combined model) for predicting recurrence within six time frames ranging from 1 through 6 years after treatment. Kaplan-Meier analysis with time to recurrence as the endpoint was used to assess the clinical relevance of model predictions. RESULTS. Tumor recurred in 44 of 120 (36.7%) patients during follow-up. The three models predicted recurrence with AUCs across the six time frames of 0.60-0.78 (clinical model), 0.71-0.85 (imaging model), and 0.62-0.86 (combined model). The mean AUC was higher for the imaging model than the clinical model (0.76 vs 0.68, respectively; p = .03), but the mean AUC was not significantly different between the clinical and combined models or between the imaging and combined models (p > .05). Kaplan-Meier curves were significantly different between patients predicted to be at low risk and those predicted to be at high risk by all three models for the 2-, 3-, 4-, 5-, and 6-year time frames (p < .05). CONCLUSION. The findings suggest that ML-based models can predict recurrence before therapy allocation in patients with early-stage HCC initially eligible for liver transplant. Adding MRI data as model input improved predictive performance over clinical parameters alone. The combined model did not surpass the imaging model's performance. CLINICAL IMPACT. ML-based models applied to currently underutilized imaging features may help design more reliable criteria for organ allocation and liver transplant eligibility.

An Interpretable Multitask Framework BiLAT Enables Accurate Prediction of Cyclin-Dependent Protein Kinase Inhibitors.

The cyclin-dependent protein kinases (CDKs) are protein-serine/threonine kinases with crucial effects on the regulation of cell cycle and transcription. CDKs can be a hallmark of cancer since their excessive expression could lead to impaired cell proliferation. However, the selectivity profile of most developed CDK inhibitors is not enough, which have hindered the therapeutic use of CDK inhibitors. In this study, we propose a multitask deep learning framework called BiLAT based on SMILES representation for the prediction of the inhibitory activity of molecules on eight CDK subtypes (CDK1, 2, 4-9). The framework is mainly composed of an improved bidirectional long short-term memory module BiLSTM and the encode layer of the Transformer framework. Additionally, the data enhancement method of SMILES enumeration is applied to improve the performance of the model. Compared with baseline predictive models based on three conventional machine learning methods and two multitask deep learning algorithms, BiLAT achieves the best performance with the highest average AUC, ACC, F1-score, and MCC values of 0.938, 0.894, 0.911, and 0.715 for the test set. Moreover, we constructed a targeted external data set CDK-Dec for the CDK family, which mainly contains bait values screened by 3D similarity with active compounds. This dataset was utilized in the subsequent evaluation of our model. It is worth mentioning that the BiLAT model is interpretable and can be used by chemists to design and synthesize compounds with improved activity. To further verify the generalization ability of the multitask BiLAT model, we also conducted another evaluation on three public datasets (Tox21, ClinTox, and SIDER). Compared with several currently popular models, BiLAT shows the best performance on two datasets. These results indicate that BiLAT is an effective tool for accelerating drug discovery.

Optimization of the BCLC Staging System for Locoregional Therapy for Hepatocellular Carcinoma by Using Quantitative Tumor Burden Imaging Biomarkers at MRI.

Background Patients with intermediate- and advanced-stage hepatocellular carcinoma (HCC) represent a highly heterogeneous patient collective with substantial differences in overall survival. Purpose To evaluate enhancing tumor volume (ETV) and enhancing tumor burden (ETB) as new criteria within the Barcelona Clinic Liver Cancer (BCLC) staging system for optimized allocation of patients with intermediate- and advanced-stage HCC to undergo transarterial chemoembolization (TACE). Materials and Methods In this retrospective study, 682 patients with HCC who underwent conventional TACE or TACE with drug-eluting beads from January 2000 to December 2014 were evaluated. Quantitative three-dimensional analysis of contrast-enhanced MRI was performed to determine thresholds of ETV and ETB (ratio of ETV to normal liver volume). Patients with ETV below 65 cm3 or ETB below 4% were reassigned to BCLC Bn, whereas patients with ETV or ETB above the determined cutoffs were restratified or remained in BCLC Cn by means of stepwise verification of the median overall survival (mOS). Results This study included 494 patients (median age, 62 years [IQR, 56-71 years]; 401 men). Originally, 123 patients were classified as BCLC B with mOS of 24.3 months (95% CI: 21.4, 32.9) and 371 patients as BCLC C with mOS of 11.9 months (95% CI: 10.5, 14.8). The mOS of all included patients (including the BCLC B and C groups) was 15 months (95% CI: 12.3, 17.2). A total of 152 patients with BCLC C tumors were restratified into a new BCLC Bn class, in which the mOS was then 25.1 months (95% CI: 21.8, 29.7; P < .001). The mOS of the remaining patients (ie, BCLC Cn group) (n = 222; ETV ≥65 cm3 or ETB ≥4%) was 8.4 months (95% CI: 6.1, 11.2). Conclusion Substratification of patients with intermediate- and advanced-stage hepatocellular carcinoma according to three-dimensional quantitative tumor burden identified patients with a survival benefit from transarterial chemoembolization before therapy. © RSNA, 2022 Online supplemental material is available for this article.

Direct and indirect strategies of deep-learning-based attenuation correction for general purpose and dedicated cardiac SPECT.

PURPOSE: Deep-learning-based attenuation correction (AC) for SPECT includes both indirect and direct approaches. Indirect approaches generate attenuation maps (µ-maps) from emission images, while direct approaches predict AC images directly from non-attenuation-corrected (NAC) images without µ-maps. For dedicated cardiac SPECT scanners with CZT detectors, indirect approaches are challenging due to the limited field-of-view (FOV). In this work, we aim to 1) first develop novel indirect approaches to improve the AC performance for dedicated SPECT; and 2) compare the AC performance between direct and indirect approaches for both general purpose and dedicated SPECT. METHODS: For dedicated SPECT, we developed strategies to predict truncated µ-maps from NAC images reconstructed with a small matrix, or full µ-maps from NAC images reconstructed with a large matrix using 270 anonymized clinical studies scanned on a GE Discovery NM/CT 570c SPECT/CT. For general purpose SPECT, we implemented direct and indirect approaches using 400 anonymized clinical studies scanned on a GE NM/CT 850c SPECT/CT. NAC images in both photopeak and scatter windows were input to predict µ-maps or AC images. RESULTS: For dedicated SPECT, the averaged normalized mean square error (NMSE) using our proposed strategies with full µ-maps was 1.20 ± 0.72% as compared to 2.21 ± 1.17% using the previous direct approaches. The polar map absolute percent error (APE) using our approaches was 3.24 ± 2.79% (R2 = 0.9499) as compared to 4.77 ± 3.96% (R2 = 0.9213) using direct approaches. For general purpose SPECT, the averaged NMSE of the predicted AC images using the direct approaches was 2.57 ± 1.06% as compared to 1.37 ± 1.16% using the indirect approaches. CONCLUSIONS: We developed strategies of generating µ-maps for dedicated cardiac SPECT with small FOV. For both general purpose and dedicated SPECT, indirect approaches showed superior performance of AC than direct approaches.

Comparison of metabolic and immunologic responses to transarterial chemoembolization with different chemoembolic regimens in a rabbit VX2 liver tumor model.

OBJECTIVES: The goal of this study was to investigate the effects of TACE using Lipiodol, Oncozene™ drug-eluting embolics (DEEs), or LUMI™-DEEs alone, or combined with bicarbonate on the metabolic and immunological tumor microenvironment in a rabbit VX2 tumor model. METHODS: VX2 liver tumor-bearing rabbits were assigned to five groups. MRI and extracellular pH (pHe) mapping using Biosensor Imaging of Redundant Deviation in Shifts (BIRDS) were performed before and after intra-arterial therapy with conventional TACE (cTACE), DEE-TACE with Idarubicin-eluting Oncozene™-DEEs, or Doxorubicin-eluting LUMI™-DEEs, each with or without prior bicarbonate infusion, and in untreated rabbits or treated with intra-arterial bicarbonate only. Imaging results were validated with immunohistochemistry (IHC) staining of cell viability (PCNA, TUNEL) and immune response (HLA-DR, CD3). Statistical analysis was performed using Mann-Whitney U test. RESULTS: pHe mapping revealed that combining cTACE with prior bicarbonate infusion significantly increased tumor pHe compared to control (p = 0.0175) and cTACE alone (p = 0.0025). IHC staining revealed peritumoral accumulation of HLA-DR+ antigen-presenting cells and CD3 + T-lymphocytes in controls. cTACE-treated tumors showed reduced immune infiltration, which was restored through combination with bicarbonate. DEE-TACE with Oncozene™-DEEs induced moderate intratumoral and marked peritumoral infiltration, which was slightly reduced with bicarbonate. Addition of bicarbonate prior to LUMI™-beads enhanced peritumoral immune cell infiltration compared to LUMI™-beads alone and resulted in the strongest intratumoral immune cell infiltration across all treated groups. CONCLUSIONS: The choice of chemoembolic regimen for TACE strongly affects post-treatment TME pHe and the ability of immune cells to accumulate and infiltrate the tumor tissue. KEY POINTS: • Combining conventional transarterial chemotherapy with prior bicarbonate infusion increases the pHe towards a more physiological value (p = 0.0025). • Peritumoral infiltration and intratumoral accumulation patterns of antigen-presenting cells and T-lymphocytes after transarterial chemotherapy were dependent on the choice of the chemoembolic regimen. • Combination of intra-arterial treatment with Doxorubicin-eluting LUMI™-beads and bicarbonate infusion resulted in the strongest intratumoral presence of immune cells (positivity index of 0.47 for HLADR+-cells and 0.62 for CD3+-cells).

Quantitative Automated Segmentation of Lipiodol Deposits on Cone-Beam CT Imaging Acquired during Transarterial Chemoembolization for Liver Tumors: A Deep Learning Approach.

PURPOSE: To show that a deep learning (DL)-based, automated model for Lipiodol (Guerbet Pharmaceuticals, Paris, France) segmentation on cone-beam computed tomography (CT) after conventional transarterial chemoembolization performs closer to the "ground truth segmentation" than a conventional thresholding-based model. MATERIALS AND METHODS: This post hoc analysis included 36 patients with a diagnosis of hepatocellular carcinoma or other solid liver tumors who underwent conventional transarterial chemoembolization with an intraprocedural cone-beam CT. Semiautomatic segmentation of Lipiodol was obtained. Subsequently, a convolutional U-net model was used to output a binary mask that predicted Lipiodol deposition. A threshold value of signal intensity on cone-beam CT was used to obtain a Lipiodol mask for comparison. The dice similarity coefficient (DSC), mean squared error (MSE), center of mass (CM), and fractional volume ratios for both masks were obtained by comparing them to the ground truth (radiologist-segmented Lipiodol deposits) to obtain accuracy metrics for the 2 masks. These results were used to compare the model versus the threshold technique. RESULTS: For all metrics, the U-net outperformed the threshold technique: DSC (0.65 ± 0.17 vs 0.45 ± 0.22, P < .001) and MSE (125.53 ± 107.36 vs 185.98 ± 93.82, P = .005). The difference between the CM predicted and the actual CM was 15.31 mm ± 14.63 versus 31.34 mm ± 30.24 (P < .001), with lesser distance indicating higher accuracy. The fraction of volume present ([predicted Lipiodol volume]/[ground truth Lipiodol volume]) was 1.22 ± 0.84 versus 2.58 ± 3.52 (P = .048) for the current model's prediction and threshold technique, respectively. CONCLUSIONS: This study showed that a DL framework could detect Lipiodol in cone-beam CT imaging and was capable of outperforming the conventionally used thresholding technique over several metrics. Further optimization will allow for more accurate, quantitative predictions of Lipiodol depositions intraprocedurally.

MR Imaging Biomarkers for the Prediction of Outcome after Radiofrequency Ablation of Hepatocellular Carcinoma: Qualitative and Quantitative Assessments of the Liver Imaging Reporting and Data System and Radiomic Features.

PURPOSE: To assess the Liver Imaging Reporting and Data System (LI-RADS) and radiomic features in pretreatment magnetic resonance (MR) imaging for predicting progression-free survival (PFS) in patients with nodular hepatocellular carcinoma (HCC) treated with radiofrequency (RF) ablation. MATERIAL AND METHODS: Sixty-five therapy-naïve patients with 85 nodular HCC tumors <5 cm in size were included in this Health Insurance Portability and Accountability Act-compliant, institutional review board-approved, retrospective study. All patients underwent RF ablation as first-line treatment and demonstrated complete response on the first follow-up imaging. Gadolinium-enhanced MR imaging biomarkers were analyzed for LI-RADS features by 2 board-certified radiologists or by analysis of nodular and perinodular radiomic features from 3-dimensional segmentations. A radiomic signature was calculated with the most informative features of a least absolute shrinkage and selection operator Cox regression model using leave-one-out cross-validation. The association between both LI-RADS features and radiomic signatures with PFS was assessed via the Kaplan-Meier analysis and a weighted log-rank test. RESULTS: The median PFS was 19 months (95% confidence interval, 16.1-19.4) for a follow-up period of 24 months. Multifocality (P = .033); the appearance of capsular continuity, compared with an absent or discontinuous capsule (P = .012); and a higher radiomic signature based on nodular and perinodular features (P = .030) were associated with poorer PFS in early-stage HCC. The observation size, presence of arterial hyperenhancement, nonperipheral washout, and appearance of an enhancing "capsule" were not associated with PFS (P > .05). CONCLUSIONS: Although multifocal HCC clearly indicates a more aggressive phenotype even in early-stage disease, the continuity of an enhancing capsule and a higher radiomic signature may add value as MR imaging biomarkers for poor PFS in HCC treated with RF ablation.

Impact of Chemoembolic Regimen on Immune Cell Recruitment and Immune Checkpoint Marker Expression following Transcatheter Arterial Chemoembolization in a VX2 Rabbit Liver Tumor Model.

PURPOSE: To characterize the effects of commonly used transcatheter arterial chemoembolization (TACE) regimens on the immune response and immune checkpoint marker expression using a VX2 rabbit liver tumor model. MATERIALS AND METHODS: Twenty-four VX2 liver tumor-bearing New Zealand white rabbits were assigned to 7 groups (n = 3 per group) undergoing locoregional therapy as follows: (a) bicarbonate infusion without embolization, (b) conventional TACE (cTACE) using a water-in-oil emulsion containing doxorubicin mixed 1:2 with Lipiodol, drug-eluting embolic-TACE with either (c) idarubicin-eluting Oncozene microspheres (40 µm) or (d) doxorubicin-eluting Lumi beads (40-90 µm). For each therapy arm (b-d), a tandem set of 3 animals with additional bicarbonate infusion before TACE was added, to evaluate the effect of pH modification on the immune response. Three untreated rabbits served as controls. Tissue was harvested 24 hours after treatment, followed by digital immunohistochemistry quantification (counts/µm2 ± SEM) of tumor-infiltrating cluster of differentiation 3+ T-lymphocytes, human leukocyte antigen DR type antigen-presenting cells (APCs), cytotoxic T-lymphocyte-associated protein-4 (CTLA-4), and programmed cell death protein-1 (PD-1)/PD-1 ligand (PD-L1) pathway axis expression. RESULTS: Lumi-bead TACE induced significantly more intratumoral T-cell and APC infiltration than cTACE and Oncozene-microsphere TACE. Additionally, tumors treated with Lumi-bead TACE expressed significantly higher intratumoral immune checkpoint markers compared with cTACE and Oncozene-microsphere TACE. Neoadjuvant bicarbonate demonstrated the most pronounced effect on cTACE and resulted in a significant increase in intratumoral cluster of differentiation 3+ T-cell infiltration compared with cTACE alone. CONCLUSIONS: This preclinical study revealed significant differences in evoked tumor immunogenicity depending on the choice of chemoembolic regimen for TACE.

KID: A Kinase-Focused Interaction Database and Its Application in the Construction of Kinase-Focused Molecule Databases.

Protein kinases are important drug targets for the treatment of several diseases. The interaction between kinases and ligands is vital in the process of small-molecule kinase inhibitor (SMKI) design. In this study, we propose a method to extract fragments and amino acid residues from crystal structures for kinase-ligand interactions. In addition, core fragments that interact with the important hinge region of kinases were extracted along with their decorations. Based on the superimposed structural data of kinases from the kinase-ligand interaction fingerprint and structure database, we obtained two libraries, namely, a hinge-unfocused fragment-amino acid pair library (FAP Lib) that contains 6672 pairs of fragments and corresponding amino-acids, and a hinge-focused hinge binder library (HB Lib) of 3560 pairs of hinge-binding scaffolds with their corresponding decorations. These two libraries constitute a kinase-focused interaction database (KID). In depth analysis was conducted on KID to explore important characteristics of fragments in the design of SMKIs. With KID, we built two kinase-focused molecule databases, one called Recomb_DB, which contains 1,72,346 molecules generated through fragment recombination based on the FAP Lib, and another called RsdHB_DB, which contains 93,030 molecules generated based on our HB Lib using molecular generation methods. Compared with five databases both commercial and non-commercial, these two databases both ranked top 3 in scaffold diversity, top 4 in molecule fingerprint diversity, and are more focused on the chemical space of kinase inhibitors. Hence, KID presents a useful addition to existing databases for the exploration of novel SMKIs.

Deep learning-assisted differentiation of pathologically proven atypical and typical hepatocellular carcinoma (HCC) versus non-HCC on contrast-enhanced MRI of the liver.

OBJECTIVES: To train a deep learning model to differentiate between pathologically proven hepatocellular carcinoma (HCC) and non-HCC lesions including lesions with atypical imaging features on MRI. METHODS: This IRB-approved retrospective study included 118 patients with 150 lesions (93 (62%) HCC and 57 (38%) non-HCC) pathologically confirmed through biopsies (n = 72), resections (n = 29), liver transplants (n = 46), and autopsies (n = 3). Forty-seven percent of HCC lesions showed atypical imaging features (not meeting Liver Imaging Reporting and Data System [LI-RADS] criteria for definitive HCC/LR5). A 3D convolutional neural network (CNN) was trained on 140 lesions and tested for its ability to classify the 10 remaining lesions (5 HCC/5 non-HCC). Performance of the model was averaged over 150 runs with random sub-sampling to provide class-balanced test sets. A lesion grading system was developed to demonstrate the similarity between atypical HCC and non-HCC lesions prone to misclassification by the CNN. RESULTS: The CNN demonstrated an overall accuracy of 87.3%. Sensitivities/specificities for HCC and non-HCC lesions were 92.7%/82.0% and 82.0%/92.7%, respectively. The area under the receiver operating curve was 0.912. CNN's performance was correlated with the lesion grading system, becoming less accurate the more atypical imaging features the lesions showed. CONCLUSION: This study provides proof-of-concept for CNN-based classification of both typical- and atypical-appearing HCC lesions on multi-phasic MRI, utilizing pathologically confirmed lesions as "ground truth." KEY POINTS: • A CNN trained on atypical appearing pathologically proven HCC lesions not meeting LI-RADS criteria for definitive HCC (LR5) can correctly differentiate HCC lesions from other liver malignancies, potentially expanding the role of image-based diagnosis in primary liver cancer with atypical features. • The trained CNN demonstrated an overall accuracy of 87.3% and a computational time of < 3 ms which paves the way for clinical application as a decision support instrument.

Identifying enhancement-based staging markers on baseline MRI in patients with colorectal cancer liver metastases undergoing intra-arterial tumor therapy.

OBJECTIVES: To determine if three-dimensional whole liver and baseline tumor enhancement features on MRI can serve as staging biomarkers and help predict survival of patients with colorectal cancer liver metastases (CRCLM) more accurately than one-dimensional and non-enhancement-based features. METHODS: This retrospective study included 88 patients with CRCLM, treated with transarterial chemoembolization or Y90 transarterial radioembolization between 2001 and 2014. Semi-automated segmentations of up to three dominant lesions were performed on pre-treatment MRI to calculate total tumor volume (TTV) and total liver volumes (TLV). Quantitative 3D analysis was performed to calculate enhancing tumor volume (ETV), enhancing tumor burden (ETB, calculated as ETV/TLV), enhancing liver volume (ELV), and enhancing liver burden (ELB, calculated as ELV/TLV). Overall and enhancing tumor diameters were also measured. A modified Kaplan-Meier method was used to determine appropriate cutoff values for each metric. The predictive value of each parameter was assessed by Kaplan-Meier survival curves and univariable and multivariable cox proportional hazard models. RESULTS: All methods except whole liver (ELB, ELV) and one-dimensional/non-enhancement-based methods were independent predictors of survival. Multivariable analysis showed a HR of 2.1 (95% CI 1.3-3.4, p = 0.004) for enhancing tumor diameter, HR 1.7 (95% CI 1.1-2.8, p = 0.04) for TTV, HR 2.3 (95% CI 1.4-3.9, p < 0.001) for ETV, and HR 2.4 (95% CI 1.4-4.0, p = 0.001) for ETB. CONCLUSIONS: Tumor enhancement of CRCLM on baseline MRI is strongly associated with patient survival after intra-arterial therapy, suggesting that enhancing tumor volume and enhancing tumor burden are better prognostic indicators than non-enhancement-based and one-dimensional-based markers. KEY POINTS: • Tumor enhancement of colorectal cancer liver metastases on MRI prior to treatment with intra-arterial therapies is strongly associated with patient survival. • Three-dimensional, enhancement-based imaging biomarkers such as enhancing tumor volume and enhancing tumor burden may serve as the basis of a novel prognostic staging system for patients with liver-dominant colorectal cancer metastases.

Reliable prediction of survival in advanced-stage hepatocellular carcinoma treated with sorafenib: comparing 1D and 3D quantitative tumor response criteria on MRI.

OBJECTIVES: To compare 1D and 3D quantitative tumor response criteria applied to DCE-MRI in patients with advanced-stage HCC undergoing sorafenib therapy to predict overall survival (OS) early during treatment. METHODS: This retrospective analysis included 29 patients with advanced-stage HCC who received sorafenib for at least 60 days. All patients underwent baseline and follow-up DCE-MRI at 81.5 ± 29.3 days (range 35-140 days). Response to sorafenib was assessed in 46 target lesions using 1D criteria RECIST1.1 and mRECIST. In addition, a segmentation-based 3D quantification of absolute enhancing lesion volume (vqEASL) was performed on the arterial phase MRI, and the enhancement fraction of total tumor volume (%qEASL) was calculated. Accordingly, patients were stratified into groups of disease control (DC) and disease progression (DP). OS was evaluated using Kaplan-Meier curves with log-rank test and Cox proportional hazards regression model. RESULTS: The Kaplan-Meier analysis revealed that stratification of patients in DC vs. DP according to mRECIST (p = 0.0371) and vqEASL (p = 0.0118) successfully captured response and stratified OS, while stratification according to RECIST and %qEASL did not correlate with OS (p = 0.6273 and p = 0.7474, respectively). Multivariable Cox regression identified tumor progression according to mRECIST and qEASL as independent risk factors of decreased OS (p = 0.039 and p = 0.006, respectively). CONCLUSIONS: The study identified enhancement-based vqEASL and mRECIST as reliable predictors of patient survival early after initiation of treatment with sorafenib. This data provides evidence for potential advantages 3D quantitative, enhancement-based tumor response analysis over conventional techniques regarding early identification of treatment success or failure. KEY POINTS: • Tumor response criteria on MRI can be used to predict survival benefit of sorafenib therapy in patients with advanced HCC. • Stratification into DC and DP using mRECIST and vqEASL significantly correlates with OS (p = 0.0371 and p = 0.0118, respectively) early after initiation of sorafenib, while stratification according to RECIST and %qEASL did not correlate with OS (p = 0.6273 and p = 0.7474, respectively). • mRECIST (HR = 0.325, p = 0.039. 95%CI 0.112-0.946) and qEASL (HR = 0.183, p = 0.006, 95%CI 0.055-0.613) are independent prognostic factors of survival in HCC patients undergoing sorafenib therapy.

Molecular MRI of the Immuno-Metabolic Interplay in a Rabbit Liver Tumor Model: A Biomarker for Resistance Mechanisms in Tumor-targeted Therapy?

Background The immuno-metabolic interplay has gained interest for determining and targeting immunosuppressive tumor micro-environments that remain a barrier to current immuno-oncologic therapies in hepatocellular carcinoma. Purpose To develop molecular MRI tools to reveal resistance mechanisms to immuno-oncologic therapies caused by the immuno-metabolic interplay in a translational liver cancer model. Materials and Methods A total of 21 VX2 liver tumor-bearing New Zealand white rabbits were used between October 2018 and February 2020. Rabbits were divided into three groups. Group A (n = 3) underwent intra-arterial infusion of gadolinium 160 (160Gd)-labeled anti-human leukocyte antigen-DR isotope (HLA-DR) antibodies to detect antigen-presenting immune cells. Group B (n = 3) received rhodamine-conjugated superparamagnetic iron oxide nanoparticles (SPIONs) intravenously to detect macrophages. These six rabbits underwent 3-T MRI, including T1- and T2-weighted imaging, before and 24 hours after contrast material administration. Group C (n = 15) underwent extracellular pH mapping with use of MR spectroscopy. Of those 15 rabbits, six underwent conventional transarterial chemoembolization (TACE), four underwent conventional TACE with extracellular pH-buffering bicarbonate, and five served as untreated controls. MRI signal intensity distribution was validated by using immunohistochemistry staining of HLA-DR and CD11b, Prussian blue iron staining, fluorescence microscopy of rhodamine, and imaging mass cytometry (IMC) of gadolinium. Statistical analysis included Mann-Whitney U and Kruskal-Wallis tests. Results T1-weighted MRI with 160Gd-labeled antibodies revealed localized peritumoral ring enhancement, which corresponded to gadolinium distribution detected with IMC. T2-weighted MRI with SPIONs showed curvilinear signal intensity representing selective peritumoral deposition in macrophages. Extracellular pH-specific MR spectroscopy of untreated liver tumors showed acidosis (mean extracellular pH, 6.78 ± 0.09) compared with liver parenchyma (mean extracellular pH, 7.18 ± 0.03) (P = .008) and peritumoral immune cell exclusion. Normalization of tumor extracellular pH (mean, 6.96 ± 0.05; P = .02) using bicarbonate during TACE increased peri- and intratumoral immune cell infiltration (P = .002). Conclusion MRI in a rabbit liver tumor model was used to visualize resistance mechanisms mediated by the immuno-metabolic interplay that inform susceptibility and response to immuno-oncologic therapies, providing a therapeutic strategy to restore immune permissiveness in liver cancer. © RSNA, 2020 Online supplemental material is available for this article.

Extracellular pH mapping of liver cancer on a clinical 3T MRI scanner.

PURPOSE: To demonstrate feasibility of developing a noninvasive extracellular pH (pHe ) mapping method on a clinical MRI scanner for molecular imaging of liver cancer. METHODS: In vivo pHe mapping has been demonstrated on preclinical scanners (e.g., 9.4T, 11.7T) with Biosensor Imaging of Redundant Deviation in Shifts (BIRDS), where the pHe readout by 3D chemical shift imaging (CSI) depends on hyperfine shifts emanating from paramagnetic macrocyclic chelates like TmDOTP5- which upon extravasation from blood resides in the extracellular space. We implemented BIRDS-based pHe mapping on a clinical 3T Siemens scanner, where typically diamagnetic 1 H signals are detected using millisecond-long radiofrequency (RF) pulses, and 1 H shifts span over ±10 ppm with long transverse (T2 , 102 ms) and longitudinal (T1 , 103 ms) relaxation times. We modified this 3D-CSI method for ultra-fast acquisition with microsecond-long RF pulses, because even at 3T the paramagnetic 1 H shifts of TmDOTP5- have millisecond-long T2 and T1 and ultra-wide chemical shifts (±200 ppm) as previously observed in ultra-high magnetic fields. RESULTS: We validated BIRDS-based pH in vitro with a pH electrode. We measured pHe in a rabbit model for liver cancer using VX2 tumors, which are highly vascularized and hyperglycolytic. Compared to intratumoral pHe (6.8 ± 0.1; P < 10-9 ) and tumor's edge pHe (6.9 ± 0.1; P < 10-7 ), liver parenchyma pHe was significantly higher (7.2 ± 0.1). Tumor localization was confirmed with histopathological markers of necrosis (hematoxylin and eosin), glucose uptake (glucose transporter 1), and tissue acidosis (lysosome-associated membrane protein 2). CONCLUSION: This work demonstrates feasibility and potential clinical translatability of high-resolution pHe mapping to monitor tumor aggressiveness and therapeutic outcome, all to improve personalized cancer treatment planning.

Neutrophil-to-lymphocyte and platelet-to-lymphocyte ratios as predictors of tumor response in hepatocellular carcinoma after DEB-TACE.

OBJECTIVES: To investigate the predictive value of quantifiable imaging and inflammatory biomarkers in patients with hepatocellular carcinoma (HCC) for the clinical outcome after drug-eluting bead transarterial chemoembolization (DEB-TACE) measured as volumetric tumor response and progression-free survival (PFS). METHODS: This retrospective study included 46 patients with treatment-naïve HCC who received DEB-TACE. Laboratory work-up prior to treatment included complete and differential blood count, liver function, and alpha-fetoprotein levels. Neutrophil-to-lymphocyte ratio (NLR) and platelet-to-lymphocyte ratio (PLR) were correlated with radiomic features extracted from pretreatment contrast-enhanced magnetic resonance imaging (MRI) and with tumor response according to quantitative European Association for the Study of the Liver (qEASL) criteria and progression-free survival (PFS) after DEB-TACE. Radiomic features included single nodular tumor growth measured as sphericity, dynamic contrast uptake behavior, arterial hyperenhancement, and homogeneity of contrast uptake. Statistics included univariate and multivariate linear regression, Cox regression, and Kaplan-Meier analysis. RESULTS: Accounting for laboratory and clinical parameters, high baseline NLR and PLR were predictive of poorer tumor response (p = 0.014 and p = 0.004) and shorter PFS (p = 0.002 and p < 0.001). When compared to baseline imaging, high NLR and PLR correlated with non-spherical tumor growth (p = 0.001 and p < 0.001). CONCLUSIONS: This study establishes the prognostic value of quantitative inflammatory biomarkers associated with aggressive non-spherical tumor growth and predictive of poorer tumor response and shorter PFS after DEB-TACE. KEY POINTS: • In treatment-naïve hepatocellular carcinoma (HCC), high baseline platelet-to-lymphocyte ratio (PLR) and neutrophil-to-lymphocyte ratio (NLR) are associated with non-nodular tumor growth measured as low tumor sphericity. • High PLR and NLR are predictive of poorer volumetric enhancement-based tumor response and PFS after DEB-TACE in HCC. • This set of readily available, quantitative immunologic biomarkers can easily be implemented in clinical guidelines providing a paradigm to guide and monitor the personalized application of loco-regional therapies in HCC.

Quantification of contrast-uptake as imaging biomarker for disease progression of renal cell carcinoma after tumor ablation.

BACKGROUND: The prognosis of patients with renal cell carcinoma (RCC) depends greatly on the presence of extra-renal metastases. PURPOSE: To investigate the value of total tumor volume (TTV) and enhancing tumor volume (ETV) as three-dimensional (3D) quantitative imaging biomarkers for disease aggressiveness in patients with RCC. MATERIAL AND METHODS: Retrospective, HIPAA-compliant, IRB-approved study including 37 patients with RCC treated with image-guided thermal ablation during 2007-2015. TNM stage, RENAL Nephrometry Score, largest tumor diameter, TTV, and ETV were assessed on cross-sectional imaging at baseline and correlated with outcome measurements. The primary outcome was time-to-occurrence of extra-renal metastases and the secondary outcome was progression-free survival (PFS). Correlation was assessed using a Cox regression model and differences in outcomes were shown by Kaplan-Meier plots with significance and odds ratios (OR) calculated by Log-rank test/generalized Wilcoxon and continuity-corrected Woolf logit method. RESULTS: Patients with a TTV or ETV > 5 cm3 were more likely to develop distant metastases compared to patients with TTV (OR 6.69, 95% confidence interval [CI] 0.33-134.4, P=0.022) or ETV (OR 8.48, 95% CI 0.42-170.1, P=0.016) < 5 cm3. Additionally, PFS was significantly worse in patients with larger ETV (P = 0.039; median PFS 51.87 months vs. 69.97 months). In contrast, stratification by median value of the established, caliper-based measurements showed no significant correlation with outcome parameters. CONCLUSION: ETV, as surrogate of lesion vascularity, is a sensitive imaging biomarker for occurrence of extra-renal metastatic disease and PFS in patients with RCC.

Deep learning for liver tumor diagnosis part II: convolutional neural network interpretation using radiologic imaging features.

OBJECTIVES: To develop a proof-of-concept "interpretable" deep learning prototype that justifies aspects of its predictions from a pre-trained hepatic lesion classifier. METHODS: A convolutional neural network (CNN) was engineered and trained to classify six hepatic tumor entities using 494 lesions on multi-phasic MRI, described in Part 1. A subset of each lesion class was labeled with up to four key imaging features per lesion. A post hoc algorithm inferred the presence of these features in a test set of 60 lesions by analyzing activation patterns of the pre-trained CNN model. Feature maps were generated that highlight regions in the original image that correspond to particular features. Additionally, relevance scores were assigned to each identified feature, denoting the relative contribution of a feature to the predicted lesion classification. RESULTS: The interpretable deep learning system achieved 76.5% positive predictive value and 82.9% sensitivity in identifying the correct radiological features present in each test lesion. The model misclassified 12% of lesions. Incorrect features were found more often in misclassified lesions than correctly identified lesions (60.4% vs. 85.6%). Feature maps were consistent with original image voxels contributing to each imaging feature. Feature relevance scores tended to reflect the most prominent imaging criteria for each class. CONCLUSIONS: This interpretable deep learning system demonstrates proof of principle for illuminating portions of a pre-trained deep neural network's decision-making, by analyzing inner layers and automatically describing features contributing to predictions. KEY POINTS: • An interpretable deep learning system prototype can explain aspects of its decision-making by identifying relevant imaging features and showing where these features are found on an image, facilitating clinical translation. • By providing feedback on the importance of various radiological features in performing differential diagnosis, interpretable deep learning systems have the potential to interface with standardized reporting systems such as LI-RADS, validating ancillary features and improving clinical practicality. • An interpretable deep learning system could potentially add quantitative data to radiologic reports and serve radiologists with evidence-based decision support.

Deep learning for liver tumor diagnosis part I: development of a convolutional neural network classifier for multi-phasic MRI.

OBJECTIVES: To develop and validate a proof-of-concept convolutional neural network (CNN)-based deep learning system (DLS) that classifies common hepatic lesions on multi-phasic MRI. METHODS: A custom CNN was engineered by iteratively optimizing the network architecture and training cases, finally consisting of three convolutional layers with associated rectified linear units, two maximum pooling layers, and two fully connected layers. Four hundred ninety-four hepatic lesions with typical imaging features from six categories were utilized, divided into training (n = 434) and test (n = 60) sets. Established augmentation techniques were used to generate 43,400 training samples. An Adam optimizer was used for training. Monte Carlo cross-validation was performed. After model engineering was finalized, classification accuracy for the final CNN was compared with two board-certified radiologists on an identical unseen test set. RESULTS: The DLS demonstrated a 92% accuracy, a 92% sensitivity (Sn), and a 98% specificity (Sp). Test set performance in a single run of random unseen cases showed an average 90% Sn and 98% Sp. The average Sn/Sp on these same cases for radiologists was 82.5%/96.5%. Results showed a 90% Sn for classifying hepatocellular carcinoma (HCC) compared to 60%/70% for radiologists. For HCC classification, the true positive and false positive rates were 93.5% and 1.6%, respectively, with a receiver operating characteristic area under the curve of 0.992. Computation time per lesion was 5.6 ms. CONCLUSION: This preliminary deep learning study demonstrated feasibility for classifying lesions with typical imaging features from six common hepatic lesion types, motivating future studies with larger multi-institutional datasets and more complex imaging appearances. KEY POINTS: • Deep learning demonstrates high performance in the classification of liver lesions on volumetric multi-phasic MRI, showing potential as an eventual decision-support tool for radiologists. • Demonstrating a classification runtime of a few milliseconds per lesion, a deep learning system could be incorporated into the clinical workflow in a time-efficient manner.

Predicting Treatment Response to Intra-arterial Therapies for Hepatocellular Carcinoma with the Use of Supervised Machine Learning-An Artificial Intelligence Concept.

PURPOSE: To use magnetic resonance (MR) imaging and clinical patient data to create an artificial intelligence (AI) framework for the prediction of therapeutic outcomes of transarterial chemoembolization by applying machine learning (ML) techniques. MATERIALS AND METHODS: This study included 36 patients with hepatocellular carcinoma (HCC) treated with transarterial chemoembolization. The cohort (age 62 ± 8.9 years; 31 men; 13 white; 24 Eastern Cooperative Oncology Group performance status 0, 10 status 1, 2 status 2; 31 Child-Pugh stage A, 4 stage B, 1 stage C; 1 Barcelona Clinic Liver Cancer stage 0, 12 stage A, 10 stage B, 13 stage C; tumor size 5.2 ± 3.0 cm; number of tumors 2.6 ± 1.1; and 30 conventional transarterial chemoembolization, 6 with drug-eluting embolic agents). MR imaging was obtained before and 1 month after transarterial chemoembolization. Image-based tumor response to transarterial chemoembolization was assessed with the use of the 3D quantitative European Association for the Study of the Liver (qEASL) criterion. Clinical information, baseline imaging, and therapeutic features were used to train logistic regression (LR) and random forest (RF) models to predict patients as treatment responders or nonresponders under the qEASL response criterion. The performance of each model was validated using leave-one-out cross-validation. RESULTS: Both LR and RF models predicted transarterial chemoembolization treatment response with an overall accuracy of 78% (sensitivity 62.5%, specificity 82.1%, positive predictive value 50.0%, negative predictive value 88.5%). The strongest predictors of treatment response included a clinical variable (presence of cirrhosis) and an imaging variable (relative tumor signal intensity >27.0). CONCLUSIONS: Transarterial chemoembolization outcomes in patients with HCC may be predicted before procedures by combining clinical patient data and baseline MR imaging with the use of AI and ML techniques.

Validation of the Hong Kong Liver Cancer Staging System in Determining Prognosis of the North American Patients Following Intra-arterial Therapy.

BACKGROUND & AIMS: There is debate over the best way to stage hepatocellular carcinoma (HCC). We attempted to validate the prognostic and clinical utility of the recently developed Hong Kong Liver Cancer (HKLC) staging system, a hepatitis B-based model, and compared data with that from the Barcelona Clinic Liver Cancer (BCLC) staging system in a North American population that underwent intra-arterial therapy (IAT). METHODS: We performed a retrospective analysis of data from 1009 patients with HCC who underwent IAT from 2000 through 2014. Most patients had hepatitis C or unresectable tumors; all patients underwent IAT, with or without resection, transplantation, and/or systemic chemotherapy. We calculated HCC stage for each patient using 5-stage HKLC (HKLC-5) and 9-stage HKLC (HKLC-9) system classifications, and the BCLC system. Survival information was collected up until the end of 2014 at which point living or unconfirmed patients were censored. We compared performance of the BCLC, HKLC-5, and HKLC-9 systems in predicting patient outcomes using Kaplan-Meier estimates, calibration plots, C statistic, Akaike information criterion, and the likelihood ratio test. RESULTS: Median overall survival time, calculated from first IAT until date of death or censorship, for the entire cohort (all stages) was 9.8 months. The BCLC and HKLC staging systems predicted patient survival times with significance (P < .001). HKLC-5 and HKLC-9 each demonstrated good calibration. The HKLC-5 system outperformed the BCLC system in predicting patient survival times (HKLC C = 0.71, Akaike information criterion = 6242; BCLC C = 0.64, Akaike information criterion = 6320), reducing error in predicting survival time (HKLC reduced error by 14%, BCLC reduced error by 12%), and homogeneity (HKLC chi-square = 201, P < .001; BCLC chi-square = 119, P < .001) and monotonicity (HKLC linear trend chi-square = 193, P < .001; BCLC linear trend chi-square = 111, P < .001). Small proportions of patients with HCC of stages IV or V, according to the HKLC system, survived for 6 months and 4 months, respectively. CONCLUSIONS: In a retrospective analysis of patients who underwent IAT for unresectable HCC, we found the HKLC-5 staging system to have the best combination of performances in survival separation, calibration, and discrimination; it consistently outperformed the BCLC system in predicting survival times of patients. The HKLC system identified patients with HCC of stages IV and V who are unlikely to benefit from IAT.