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

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.

Clinical application of dual-layer spectral CT multi-parameter feature to predict microvascular invasion in hepatocellular carcinoma

OBJECTIVE

This study aimed to investigate the feasibility of using dual-layer spectral CT multi-parameter feature to predict microvascular invasion of hepatocellular carcinoma.

METHODS

This retrospective study enrolled 50 HCC patients who underwent multiphase contrast-enhanced spectral CT studies preoperatively. Combined clinical data, radiological features with spectral CT quantitative parameter were constructed to predict MVI. ROC was applied to identify potential predictors of MVI. The CT values obtained by simulating the conventional CT scans with 70 keV images were compared with those obtained with 40 keV images.

RESULTS

50 hepatocellular carcinomas were detected with 30 lesions (Group A) with microvascular invasion and 20 (Group B) without. There were significant differences in AFP,tumer size, IC, NIC,slope and effective atomic number in AP and ICrr in VP between Group A ((1000(10.875,1000),4.360±0.3105, 1.7750 (1.5350,1.8825) mg/ml, 0.1785 (0.1621,0.2124), 2.0362±0.2108,8.0960±0.1043,0.2830±0.0777) and Group B (4.750(3.325,20.425),3.190±0.2979,1.4700 (1.4500,1.5775) mg/ml, 0.1441 (0.1373,0.1490),1.8601±0.1595, 7.8105±0.7830 and 0.2228±0.0612) (all p < 0.05). Using 0.1586 as the threshold for NIC, one could obtain an area-under-curve (AUC) of 0.875 in ROC to differentiate between tumours with and without microvascular invasion. AUC was 0.625 with CT value at 70 keV and improved to 0.843 at 40 keV.

CONCLUSION

Dual-layer spectral CT provides additional quantitative parameters than conventional CT to enhance the differentiation between hepatocellular carcinoma with and without microvascular invasion. Especially, the normalized iodine concentration (NIC) in arterial phase has the greatest potential application value in determining whether microvascular invasion exists, and can offer an important reference for clinical treatment plan and prognosis assessment.

Leveraging radiomics and AI for precision diagnosis and prognostication of liver malignancies

Liver tumors, whether primary or metastatic, have emerged as a growing concern with substantial global health implications. Timely identification and characterization of liver tumors are pivotal factors in order to provide optimum treatment. Imaging is a crucial part of the detection of liver tumors; however, conventional imaging has shortcomings in the proper characterization of these tumors which leads to the need for tissue biopsy. Artificial intelligence (AI) and radiomics have recently emerged as investigational opportunities with the potential to enhance the detection and characterization of liver lesions. These advancements offer opportunities for better diagnostic accuracy, prognostication, and thereby improving patient care. In particular, these techniques have the potential to predict the histopathology, genotype, and immunophenotype of tumors based on imaging data, hence providing guidance for personalized treatment of such tumors. In this review, we outline the progression and potential of AI in the field of liver oncology imaging, specifically emphasizing manual radiomic techniques and deep learning-based representations. We discuss how these tools can aid in clinical decision-making challenges. These challenges encompass a broad range of tasks, from prognosticating patient outcomes, differentiating benign treatment-related factors and actual disease progression, recognizing uncommon response patterns, and even predicting the genetic and molecular characteristics of the tumors. Lastly, we discuss the pitfalls, technical limitations and future direction of these AI-based techniques.

Enhancing preoperative diagnosis of microvascular invasion in hepatocellular carcinoma: domain-adaptation fusion of multi-phase CT images

Objectives

In patients with hepatocellular carcinoma (HCC), accurately predicting the preoperative microvascular invasion (MVI) status is crucial for improving survival rates. This study proposes a multi-modal domain-adaptive fusion model based on deep learning methods to predict the preoperative MVI status in HCC.

Materials and methods

From January 2008 to May 2022, we collected 163 cases of HCC from our institution and 42 cases from another medical facility, with each case including Computed Tomography (CT) images from the pre-contrast phase (PCP), arterial phase (AP), and portal venous phase (PVP). We divided our institution's dataset (n=163) into training (n=119) and test sets (n=44) in an approximate 7:3 ratio. Additionally, we included cases from another institution (n=42) as an external validation set (test1 set). We constructed three single-modality models, a simple concatenated multi-modal model, two current state-of-the-art image fusion model and a multi-modal domain-adaptive fusion model (M-DAFM) based on deep learning methods. We evaluated and analyzed the performance of these constructed models in predicting preoperative MVI using the area under the receiver operating characteristic curve (AUC), decision curve analysis (DCA), and net reclassification improvement (NRI) methods.

Results

In comparison with all models, M-DAFM achieved the highest AUC values across the three datasets (0.8013 for the training set, 0.7839 for the test set, and 0.7454 for the test1 set). Notably, in the test set, M-DAFM's Decision Curve Analysis (DCA) curves consistently demonstrated favorable or optimal net benefits within the 0-0.65 threshold probability range. Additionally, the Net Reclassification Improvement (NRI) values between M-DAFM and the three single-modal models, as well as the simple concatenation model, were all greater than 0 (all p < 0.05). Similarly, the NRI values between M-DAFM and the two current state-of-the-art image fusion models were also greater than 0. These findings collectively indicate that M-DAFM effectively integrates valuable information from multi-phase CT images, thereby enhancing the model's preoperative predictive performance for MVI.

Conclusion

The M-DAFM proposed in this study presents an innovative approach to improve the preoperative predictive performance of MVI.

Intra-patient variability of iodine quantification across different dual-energy CT platforms: assessment of normalization techniques

OBJECTIVES

To investigate intra-patient variability of iodine concentration (IC) between three different dual-energy CT (DECT) platforms and to test different normalization approaches.

METHODS

Forty-four patients who underwent portal venous phase abdominal DECT on a dual-source (dsDECT), a rapid kVp switching (rsDECT), and a dual-layer detector platform (dlDECT) during cancer follow-up were retrospectively included. IC in the liver, pancreas, and kidneys and different normalized ICs (NICPV:portal vein; NICAA:abdominal aorta; NICALL:overall iodine load) were compared between the three DECT scanners for each patient. A longitudinal mixed effects analysis was conducted to elucidate the effect of the scanner type, scan order, inter-scan time, and contrast media amount on normalized iodine concentration.

RESULTS

Variability of IC was highest in the liver (dsDECT vs. dlDECT 28.96 (14.28-46.87) %, dsDECT vs. rsDECT 29.08 (16.59-62.55) %, rsDECT vs. dlDECT 22.85 (7.52-33.49) %), and lowest in the kidneys (dsDECT vs. dlDECT 15.76 (7.03-26.1) %, dsDECT vs. rsDECT 15.67 (8.86-25.56) %, rsDECT vs. dlDECT 10.92 (4.92-22.79) %). NICALL yielded the best reduction of IC variability throughout all tissues and inter-scanner comparisons, yet did not reduce the variability between dsDECT vs. dlDECT and rsDECT, respectively, in the liver. The scanner type remained a significant determinant for NICALL in the pancreas and the liver (F-values, 12.26 and 23.78; both, p < 0.0001).

CONCLUSIONS

We found tissue-specific intra-patient variability of IC across different DECT scanner types. Normalization mitigated variability by reducing physiological fluctuations in iodine distribution. After normalization, the scanner type still had a significant effect on iodine variability in the pancreas and liver.

CLINICAL RELEVANCE STATEMENT

Differences in iodine quantification between dual-energy CT scanners can partly be mitigated by normalization, yet remain relevant for specific tissues and inter-scanner comparisons, which should be taken into account at clinical routine imaging.

KEY POINTS

• Iodine concentration showed the least variability between scanner types in the kidneys (range 10.92-15.76%) and highest variability in the liver (range 22.85-29.08%). • Normalizing tissue-specific iodine concentrations against the overall iodine load yielded the greatest reduction of variability between scanner types for 2/3 inter-scanner comparisons in the liver and for all (3/3) inter-scanner comparisons in the kidneys and pancreas, respectively. • However, even after normalization, the dual-energy CT scanner type was found to be the factor significantly influencing variability of iodine concentration in the liver and pancreas.

Dynamic contrast-enhanced ultrasonography with sonazoid predicts microvascular invasion in early-stage hepatocellular carcinoma

OBJECTIVE

Microvascular invasion (MVI) is an independent risk factor for the early recurrence and poor survival of hepatocellular carcinoma (HCC). This study aims to investigate the potential clinical value of dynamic contrast-enhanced ultrasound (DCE-ultrasound)-Sonazoid in pre-operatively assessing MVI in HCC.

METHODS AND MATERIALS

This single centre prospective study included 140 patients with histopathologically confirmed single HCC lesions. Patients were classified according to the post-operative pathological information presence of MVI: MVI+ group (n = 32) and MVI- group (n = 108). All patients underwent DCE-ultrasound within 1 week before surgery. The quantitative perfusion parameters of HCC lesions, margins of HCC lesions, and distal liver parenchyma were obtained and analyzed.

RESULTS

Clinicopathological (serum alpha-fetoprotein, Des-gamma-carboxyprothrombin, and pathological grade) and grayscale imaging features (tumor size) were significantly different between the MVI+ and MVI- groups (p < 0.05). Further quantitative analysis showed that when comparing the MVI+ and MVI- groups, half-decrease time and wash-out rate of HCC lesions and peak enhancement in the arterial phase of difference between the margin area of HCC and distal liver parenchyma were significantly different (p = 0.045, p = 0.035, and p = 0.023, respectively). Combining the above three quantitative parameters, the accuracy, sensitivity, specificity, positive-predictive value, and negative-predictive value were 69.3% (97/140), 37.8% (17/45), 84.3% (80/95), 53.1% (17/32), 74.1% (80/108), respectively.

CONCLUSION

DCE-ultrasound with quantitative perfusion analysis has the potential to predict MVI in HCC lesions.

ADVANCES IN KNOWLEDGE

DCE-ultrasound with quantitative perfusion analysis has the potential to predict MVI in HCC lesions.

Preoperative prediction and risk assessment of microvascular invasion in hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is one of the most common and highly lethal tumors worldwide. Microvascular invasion (MVI) is a significant risk factor for recurrence and poor prognosis after surgical resection for HCC patients. Accurately predicting the status of MVI preoperatively is critical for clinicians to select treatment modalities and improve overall survival. However, MVI can only be diagnosed by pathological analysis of postoperative specimens. Currently, numerous indicators in serology (including liquid biopsies) and imaging have been identified to effective in predicting the occurrence of MVI, and the multi-indicator model based on deep learning greatly improves accuracy of prediction. Moreover, several genes and proteins have been identified as risk factors that are strictly associated with the occurrence of MVI. Therefore, this review evaluates various predictors and risk factors, and provides guidance for subsequent efforts to explore more accurate predictive methods and to facilitate the conversion of risk factors into reliable predictors.

Prediction of Microvascular Invasion in Solitary AFP-Negative Hepatocellular Carcinoma ≤ 5 cm Using a Combination of Imaging Features and Quantitative Dual-Layer Spectral-Detector CT Parameters

RATIONALE AND OBJECTIVES

AFP-negative hepatocellular carcinoma (AFPN-HCC) within 5 cm is a special subgroup of HCC. This study aimed to investigate the value of dual-layer spectral-detector CT (DLCT) and construct a scoring model based on imaging features as well as DLCT for predicting microvascular invasion (MVI) in AFPN-HCC within 5 cm.

METHODS

This retrospective study enrolled 104 HCC patients who underwent multiphase contrast-enhanced DLCT studies preoperatively. Combined radiological features (CR) and combined DLCT quantitative parameter (CDLCT) were constructed to predict MVI. Multivariable logistic regression was applied to identify potential predictors of MVI. Based on the coefficient of the regression model, a scoring model was developed. The predictive efficacy was assessed through ROC analysis.

RESULTS

Microvascular invasion (MVI) was found in 28 (26.9%) AFPN-HCC patients. Among single parameters, the effective atomic number in arterial phase demonstrated the best predictive efficiency for MVI with an area under the curve (AUC) of 0.792. CR and CDLCT showed predictive performance with AUCs of 0.848 and 0.849, respectively. A risk score (RS) was calculated using the independent predictors of MVI as follows: RS = 2 × (mosaic architecture) + 2 × (corona enhancement) + 2 × (incomplete tumor capsule) + 2 × (2-trait predictor of venous invasion [TTPVI]) + 3 × (CDLCT > -1.229). Delong's test demonstrated this scoring system could significantly improve the AUC to 0.929 compared with CR (p = 0.016) and CDLCT (p = 0.034).

CONCLUSION

The scoring model combining radiological features with DLCT provides a promising tool for predicting MVI in solitary AFPN-HCC within 5 cm preoperatively.

Dual-Energy CT Deep Learning Radiomics to Predict Macrotrabecular-Massive Hepatocellular Carcinoma

Background It is unknown whether the additional information provided by multiparametric dual-energy CT (DECT) could improve the noninvasive diagnosis of the aggressive macrotrabecular-massive (MTM) subtype of hepatocellular carcinoma (HCC). Purpose To evaluate the diagnostic performance of dual-phase contrast-enhanced multiparametric DECT for predicting MTM HCC. Materials and Methods Patients with histopathologic examination-confirmed HCC who underwent contrast-enhanced DECT between June 2019 and June 2022 were retrospectively recruited from three independent centers (center 1, training and internal test data set; centers 2 and 3, external test data set). Radiologic features were visually analyzed and combined with clinical information to establish a clinical-radiologic model. Deep learning (DL) radiomics models were based on DL features and handcrafted features extracted from virtual monoenergetic images and material composition images on dual phase using binary least absolute shrinkage and selection operators. A DL radiomics nomogram was developed using multivariable logistic regression analysis. Model performance was evaluated with the area under the receiver operating characteristic curve (AUC), and the log-rank test was used to analyze recurrence-free survival. Results A total of 262 patients were included (mean age, 54 years ± 12 [SD]; 225 men [86%]; training data set, n = 146 [56%]; internal test data set, n = 35 [13%]; external test data set, n = 81 [31%]). The DL radiomics nomogram better predicted MTM than the clinical-radiologic model (AUC = 0.91 vs 0.77, respectively, for the training set [P < .001], 0.87 vs 0.72 for the internal test data set [P = .04], and 0.89 vs 0.79 for the external test data set [P = .02]), with similar sensitivity (80% vs 87%, respectively; P = .63) and higher specificity (90% vs 63%; P < .001) in the external test data set. The predicted positive MTM groups based on the DL radiomics nomogram had shorter recurrence-free survival than predicted negative MTM groups in all three data sets (training data set, P = .04; internal test data set, P = .01; and external test data set, P = .03). Conclusion A DL radiomics nomogram derived from multiparametric DECT accurately predicted the MTM subtype in patients with HCC. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Chu and Fishman in this issue.

Spectral CT: Current Liver Applications

Using two different energy levels, dual-energy computed tomography (DECT) allows for material differentiation, improves image quality and iodine conspicuity, and allows researchers the opportunity to determine iodine contrast and radiation dose reduction. Several commercialized platforms with different acquisition techniques are constantly being improved. Furthermore, DECT clinical applications and advantages are continually being reported in a wide range of diseases. We aimed to review the current applications of and challenges in using DECT in the treatment of liver diseases. The greater contrast provided by low-energy reconstructed images and the capability of iodine quantification have been mostly valuable for lesion detection and characterization, accurate staging, treatment response assessment, and thrombi characterization. Material decomposition techniques allow for the non-invasive quantification of fat/iron deposition and fibrosis. Reduced image quality with larger body sizes, cross-vendor and scanner variability, and long reconstruction time are among the limitations of DECT. Promising techniques for improving image quality with lower radiation dose include the deep learning imaging reconstruction method and novel spectral photon-counting computed tomography.

Radiomics: A radiological evidence-based artificial intelligence technique to facilitate personalized precision medicine in hepatocellular carcinoma

The high postoperative recurrence rates in hepatocellular carcinoma (HCC) remain a major hurdle in its management. Appropriate staging and treatment selection may alleviate the extent of fatal recurrence. However, effective methods to preoperatively evaluate pathophysiologic and molecular characteristics of HCC are lacking. Imaging plays a central role in HCC diagnosis and stratification due to the non-invasive diagnostic criteria. Vast and crucial information is hidden within image data. Other than providing a morphological sketch for lesion diagnosis, imaging could provide new insights to describe the pathophysiological and genetic landscape of HCC. Radiomics aims to facilitate diagnosis and prognosis of HCC using artificial intelligence techniques to harness the immense information contained in medical images. Radiomics produces a set of archetypal and robust imaging features that are correlated to key pathological or molecular biomarkers to preoperatively risk-stratify HCC patients. Inferred with outcome data, comprehensive combination of radiomic, clinical and/or multi-omics data could also improve direct prediction of response to treatment and prognosis. The evolution of radiomics is changing our understanding of personalized precision medicine in HCC management. Herein, we review the key techniques and clinical applications in HCC radiomics and discuss current limitations and future opportunities to improve clinical decision making.

Association between extramural vascular invasion and iodine quantification using dual-energy computed tomography of rectal cancer: a preliminary study

OBJECTIVE

This study aimed to investigate whether histopathological confirmed extramural vascular invasion (EMVI) is associated with quantitative parameters derived from dual-energy computed tomography (DECT) of rectal cancer.

METHODS

This retrospective study included patients with rectal cancer who underwent rectal cancer surgery and DECT (including arterial-, venous-, and delay-phase scanning) between November 2019 and November 2020. The EMVI of rectal cancer was confirmed via postoperative pathological results. Iodine concentration (IC), IC normalized to the aorta (NIC), and CT attenuation values of the three phases were measured and compared between patients with and without EMVI. Receiver operating characteristic (ROC) curves were generated to determine the diagnostic performance of these DECT quantitative parameters.

RESULTS

Herein, 36 patients (22 men and 14 women) with a mean age of 62 [range, 43-77] years) with (n = 13) and without (n = 23) EMVI were included. Patients with EMVI exhibited significantly higher IC in the venous and delay phases (venous-phase: 2.92 ± 0.6 vs 2.34 ± 0.48; delay-phase: 2.46 ± 0.47 vs 1.88 ± 0.35) and NIC in all the three phases (arterial-phase: 0.31 ± 0.12 vs 0.24 ± 0.06; venous-phase: 0.58 ± 0.11 vs 0.41 ± 0.07; delay-phase: 0.68 ± 0.10 vs 0.46 ± 0.08) than patients without EMVI. Among them, the highest area under the ROC curve (AUC) was obtained in the delay-phase NIC (AUC = 0.983). IC in the arterial-phase and CT attenuation in all the three phases did not significantly differ between patients with and without EMVI (p = 0.205-0.869).

CONCLUSION

Iodine quantification using dual-energy CT, especially the NIC of the tumor, differs between the EMVI-positive and EMVI-negative groups and seems to help predict the EMVI of rectal cancer in this preliminary study; however, a larger sample size study is warranted in the future.