Synthetic MR image generation of macrotrabecular-massive hepatocellular carcinoma using generative adversarial networks.

PURPOSE: The purpose of this study was to develop a method for generating synthetic MR images of macrotrabecular-massive hepatocellular carcinoma (MTM-HCC). MATERIALS AND METHODS: A set of abdominal MR images including fat-saturated T1-weighted images obtained during the arterial and portal venous phases of enhancement and T2-weighted images of 91 patients with MTM-HCC, and another set of MR abdominal images from 67 other patients were used. Synthetic images were obtained using a 3-step pipeline that consisted in: (i), generating a synthetic MTM-HCC tumor on a neutral background; (ii), randomly selecting a background among the 67 patients and a position inside the liver; and (iii), merging the generated tumor in the background at the specified location. Synthetic images were qualitatively evaluated by three radiologists and quantitatively assessed using a mix of 1-nearest neighbor classifier metric and Fréchet inception distance. RESULTS: A set of 1000 triplets of synthetic MTM-HCC images with consistent contrasts were successfully generated. Evaluation of selected synthetic images by three radiologists showed that the method gave realistic, consistent and diversified images. Qualitative and quantitative evaluation led to an overall score of 0.64. CONCLUSION: This study shows the feasibility of generating realistic synthetic MR images with very few training data, by leveraging the wide availability of liver backgrounds. Further studies are needed to assess the added value of those synthetic images for automatic diagnosis of MTM-HCC.

Generative adversarial networks (GAN)-based data augmentation of rare liver cancers: The SFR 2021 Artificial Intelligence Data Challenge.

PURPOSE: The 2021 edition of the Artificial Intelligence Data Challenge was organized by the French Society of Radiology together with the Centre National d'Études Spatiales and CentraleSupélec with the aim to implement generative adversarial networks (GANs) techniques to provide 1000 magnetic resonance imaging (MRI) cases of macrotrabecular-massive (MTM) hepatocellular carcinoma (HCC), a rare and aggressive subtype of HCC, generated from a limited number of real cases from multiple French centers. MATERIALS AND METHODS: A dedicated platform was used by the seven inclusion centers to securely upload their anonymized MRI examinations including all three cross-sectional images (one late arterial and one portal-venous phase T1-weighted images and one fat-saturated T2-weighted image) in compliance with general data protection regulation. The quality of the database was checked by experts and manual delineation of the lesions was performed by the expert radiologists involved in each center. Multidisciplinary teams competed between October 11th, 2021 and February 13th, 2022. RESULTS: A total of 91 MTM-HCC datasets of three images each were collected from seven French academic centers. Six teams with a total of 28 individuals participated in this challenge. Each participating team was asked to generate one thousand 3-image cases. The qualitative evaluation was performed by three radiologists using the Likert scale on ten randomly selected cases generated by each participant. A quantitative evaluation was also performed using two metrics, the Frechet inception distance and a leave-one-out accuracy of a 1-Nearest Neighbor algorithm. CONCLUSION: This data challenge demonstrates the ability of GANs techniques to generate a large number of images from a small sample of imaging examinations of a rare malignant tumor.

Hepatobiliary MR contrast agent uptake as a predictive biomarker of aggressive features on pathology and reduced recurrence-free survival in resectable hepatocellular carcinoma: comparison with dual-tracer 18F-FDG and 18F-FCH PET/CT.

OBJECTIVES: To compare the performance of the quantitative analysis of the hepatobiliary phase (HBP) tumor enhancement in gadobenate dimeglumine (Gd-BOPTA)-enhanced MRI and of dual-tracer 18F-FDG and 18F-fluorocholine (FCH) PET/CT for the prediction of tumor aggressiveness and recurrence-free survival (RFS) in resectable hepatocellular carcinoma (HCC). METHODS: This retrospective, IRB approved study included 32 patients with 35 surgically proven HCCs. All patients underwent Gd-BOPTA-enhanced MRI including delayed HBP images, 18F-FDG PET/CT, and (for 29/32 patients) 18F-FCH PET/CT during the 2 months prior to surgery. For each lesion, the lesion-to-liver contrast enhancement ratio (LLCER) on MRI HBP images and the SUVmax tumor-to-liver ratio (SUVT/L) for both tracers were calculated. Their predictive value for aggressive pathological features-including the histological grade and microvascular invasion (MVI)-and RFS were analyzed and compared using area under receiver operating characteristic (AUROC) curves and Cox regression models, respectively. RESULTS: The AUROCs for the identification of aggressive HCCs on pathology with LLCER, 18F-FDG SUVT/L, and 18F-FCH SUVT/L were 0.92 (95% CI 0.78, 0.98), 0.89 (95% CI 0.74, 0.97; p = 0.70), and 0.64 (95% CI 0.45, 0.80; p = 0.035). At multivariate Cox regression analysis, LLCER was identified as an independent predictor of RFS (HR (95% CI) = 0.91 (0.84, 0.99), p = 0.022). LLCER - 4.72% or less also accurately predicted moderate-poor differentiation grade (Se = 100%, Sp = 92.9%) and MVI (Se = 93.3%, Sp = 60%) and identified patients with poor RFS after surgical resection (p = 0.030). CONCLUSIONS: HBP tumor enhancement after Gd-BOPTA injection may help identify aggressive HCC pathological features, and patients with reduced recurrence-free survival after surgical resection. KEY POINTS: • In patients with resectable HCC, the quantitative analysis of the HBP tumor enhancement in Gd-BOPTA-enhanced MRI (LLCER) accurately identifies moderately-poorly differentiated and/or MVI-positive HCCs. • After surgical resection for HCC, patients with LLCER - 4.72% or less had significantly poorer recurrence-free survival than patients with LLCER superior to - 4.72%. • Gd-BOPTA-enhanced MRI with delayed HBP images may be suggested as part of pre-surgery workup in patients with resectable HCC.

Multiphase Liver MRI for Identifying the Macrotrabecular-Massive Subtype of Hepatocellular Carcinoma.

Background The recently described "macrotrabecular-massive" (MTM) histologic subtype of hepatocellular carcinoma (HCC) (MTM-HCC) represents an aggressive form of HCC and is associated with poor survival. Purpose To investigate whether preoperative MRI can help identify MTM-HCCs in patients with HCC. Materials and Methods This retrospective study included patients with HCC treated with surgical resection between January 2008 and February 2018 and who underwent preoperative multiphase contrast material-enhanced MRI. Least absolute shrinkage and selection operator (LASSO)-penalized and multivariable logistic regression analyses were performed to identify clinical, biologic, and imaging features associated with the MTM-HCC subtype. Early recurrence (within 2 years) and overall recurrence were evaluated by using Kaplan-Meier analysis. Multivariable Cox regression analysis was performed to determine predictors of early and overall recurrence. Results One hundred fifty-two patients (median age, 64 years; interquartile range, 56-72 years; 126 men) with 152 HCCs were evaluated. Twenty-six of the 152 HCCs (17%) were MTM-HCCs. LASSO-penalized logistic regression analysis identified substantial necrosis, high serum α-fetoprotein (AFP) level (>100 ng/mL), and Barcelona Clinic Liver Cancer (BCLC) stage B or C as independent features associated with MTM-HCCs. At multivariable analysis, substantial necrosis (odds ratio = 32; 95% confidence interval [CI] = 8.9, 114; P < .001), high serum AFP level (odds ratio = 4.4; 95% CI = 1.3, 16; P = .02), and BCLC stage B or C (odds ratio = 4.2; 95% CI = 1.2, 15; P = .03) were independent predictors of MTM-HCC subtype. Substantial necrosis helped identify 65% (17 of 26; 95% CI: 44%, 83%) of MTM-HCCs (sensitivity) with a specificity of 93% (117 of 126; 95% CI: 87%, 97%). In adjusted models, only the presence of satellite nodules was independently associated with both early (hazard ratio = 3.7; 95% CI: 1.5, 9.4; P = .006) and overall (hazard ratio = 3.0; 95% CI: 1.3, 7.2; P = .01) tumor recurrence. Conclusion At multiphase contrast-enhanced MRI, substantial necrosis helped identify macrotrabecular-massive hepatocellular carcinoma subtype with high specificity. © RSNA, 2020.

Hepatocellular carcinoma: CT texture analysis as a predictor of survival after surgical resection.

OBJECTIVES: To determine whether image texture parameters analysed on pre-operative contrast-enhanced computed tomography (CT) can predict overall survival and recurrence-free survival in patients with hepatocellular carcinoma (HCC) treated by surgical resection. METHODS: We retrospectively included all patients operated for HCC who had liver contrast-enhanced CT within 3 months prior to treatment in our centre between 2010 and 2015. The following texture parameters were evaluated on late-arterial and portal-venous phases: mean grey-level, standard deviation, kurtosis, skewness and entropy. Measurements were made before and after spatial filtration at different anatomical scales (SSF) ranging from 2 (fine texture) to 6 (coarse texture). Lasso penalised Cox regression analyses were performed to identify independent predictors of overall survival and recurrence-free survival. RESULTS: Forty-seven patients were included. Median follow-up time was 345 days (interquartile range [IQR], 176-569). Nineteen patients had a recurrence at a median time of 190 days (IQR, 141-274) and 13 died at a median time of 274 days (IQR, 96-411). At arterial CT phase, kurtosis at SSF = 4 (hazard ratio [95% confidence interval] = 3.23 [1.35-7.71] p = 0.0084) was independent predictor of overall survival. At portal-venous phase, skewness without filtration (HR [CI 95%] = 353.44 [1.31-95102.23], p = 0.039), at SSF2 scale (HR [CI 95%] = 438.73 [2.44-78968.25], p = 0.022) and SSF3 (HR [CI 95%] = 14.43 [1.38-150.51], p = 0.026) were independently associated with overall survival. No textural feature was identified as predictor of recurrence-free survival. CONCLUSIONS: In patients with resectable HCC, portal venous phase-derived CT skewness is significantly associated with overall survival and may potentially become a useful tool to select the best candidates for resection. KEY POINTS: • HCC heterogeneity as evaluated by texture analysis of contrast-enhanced CT images may predict overall survival in patients treated by surgical resection. • Among texture parameters, skewness assessed at different anatomical scales at portal-venous phase CT is an independent predictor of overall survival after resection. • In patients with HCC, CT texture analysis may have the potential to become a useful tool to select the best candidates for resection.

Can dual-energy CT replace perfusion CT for the functional evaluation of advanced hepatocellular carcinoma?

OBJECTIVES: To determine the degree of relationship between iodine concentrations derived from dual-energy CT (DECT) and perfusion CT parameters in patients with advanced HCC under treatment. METHODS: In this single-centre IRB approved study, 16 patients with advanced HCC treated with sorafenib or radioembolization who underwent concurrent dynamic perfusion CT and multiphase DECT using a single source, fast kV switching DECT scanner were included. Written informed consent was obtained for all patients. HCC late-arterial and portal iodine concentrations, blood flow (BF)-related and blood volume (BV)-related perfusion parameters maps were calculated. Mixed-effects models of the relationship between iodine concentrations and perfusion parameters were computed. An adjusted p value (Bonferroni method) < 0.05 was considered significant. RESULTS: Mean HCC late-arterial and portal iodine concentrations were 22.7±12.7 mg/mL and 18.7±8.3 mg/mL, respectively. Late-arterial iodine concentration was significantly related to BV (mixed-effects model F statistic (F)=28.52, p<0.0001), arterial BF (aBF, F=17.62, p<0.0001), hepatic perfusion index (F=28.24, p<0.0001), positive enhancement integral (PEI, F=66.75, p<0.0001) and mean slope of increase (F=32.96, p<0.0001), while portal-venous iodine concentration was mainly related to BV (F=29.68, p<0.0001) and PEI (F=66.75, p<0.0001). CONCLUSIONS: In advanced HCC lesions, DECT-derived late-arterial iodine concentration is strongly related to both aBF and BV, while portal iodine concentration mainly reflects BV, offering DECT the ability to evaluate both morphological and perfusion changes. KEY POINTS: • Late-arterial iodine concentration is highly related to arterial BF and BV. • Portal iodine concentration mainly reflects tumour blood volume. • Dual-energy CT offers significantly decreased radiation dose compared with perfusion CT.

Variable selection for generalized canonical correlation analysis.

Regularized generalized canonical correlation analysis (RGCCA) is a generalization of regularized canonical correlation analysis to 3 or more sets of variables. RGCCA is a component-based approach which aims to study the relationships between several sets of variables. The quality and interpretability of the RGCCA components are likely to be affected by the usefulness and relevance of the variables in each block. Therefore, it is an important issue to identify within each block which subsets of significant variables are active in the relationships between blocks. In this paper, RGCCA is extended to address the issue of variable selection. Specifically, sparse generalized canonical correlation analysis (SGCCA) is proposed to combine RGCCA with an [Formula: see text]-penalty in a unified framework. Within this framework, blocks are not necessarily fully connected, which makes SGCCA a flexible method for analyzing a wide variety of practical problems. Finally, the versatility and usefulness of SGCCA are illustrated on a simulated dataset and on a 3-block dataset which combine gene expression, comparative genomic hybridization, and a qualitative phenotype measured on a set of 53 children with glioma. SGCCA is available on CRAN as part of the RGCCA package.

Graph constrained discriminant analysis: a new method for the integration of a graph into a classification process.

Integrating gene regulatory networks (GRNs) into the classification process of DNA microarrays is an important issue in bioinformatics, both because this information has a true biological interest and because it helps in the interpretation of the final classifier. We present a method called graph-constrained discriminant analysis (gCDA), which aims to integrate the information contained in one or several GRNs into a classification procedure. We show that when the integrated graph includes erroneous information, gCDA's performance is only slightly worse, thus showing robustness to misspecifications in the given GRNs. The gCDA framework also allows the classification process to take into account as many a priori graphs as there are classes in the dataset. The gCDA procedure was applied to simulated data and to three publicly available microarray datasets. gCDA shows very interesting performance when compared to state-of-the-art classification methods. The software package gcda, along with the real datasets that were used in this study, are available online: http://biodev.cea.fr/gcda/.

Compressed sensing based 3D tomographic reconstruction for rotational angiography.

In this paper, we address three-dimensional tomographic reconstruction of rotational angiography acquisitions. In clinical routine, angular subsampling commonly occurs, due to the technical limitations of C-arm systems or possible improper injection. Standard methods such as filtered backprojection yield a reconstruction that is deteriorated by sampling artifacts, which potentially hampers medical interpretation. Recent developments of compressed sensing have demonstrated that it is possible to significantly improve reconstruction of subsampled datasets by generating sparse approximations through l1-penalized minimization. Based on these results, we present an extension of the iterative filtered backprojection that includes a sparsity constraint called soft background subtraction. This approach is shown to provide sampling artifact reduction when reconstructing sparse objects, and more interestingly, when reconstructing sparse objects over a non-sparse background. The relevance of our approach is evaluated in cone-beam geometry on real clinical data.

Gene association networks from microarray data using a regularized estimation of partial correlation based on PLS regression.

Reconstruction of gene-gene interactions from large-scale data such as microarrays is a first step toward better understanding the mechanisms at work in the cell. Two main issues have to be managed in such a context: 1) choosing which measures have to be used to distinguish between direct and indirect interactions from high-dimensional microarray data and 2) constructing networks with a low proportion of false-positive edges. We present an efficient methodology for the reconstruction of gene interaction networks in a small-sample-size setting. The strength of independence of any two genes is measured, in such "high-dimensional network," by a regularized estimation of partial correlation based on Partial Least Squares Regression. We finally emphasize specific properties of the proposed method. To assess the sensitivity and specificity of the method, we carried out the reconstruction of networks from simulated data. We also tested PLS-based partial correlation network on static and dynamic real microarray data. An R implementation of the proposed algorithm is available from http://biodev.extra.cea.fr/plspcnetwork/.

Detection of melanoma from dermoscopic images of naevi acquired under uncontrolled conditions.

BACKGROUND AND OBJECTIVE: Several systems for the diagnosis of melanoma from images of naevi obtained under controlled conditions have demonstrated comparable efficiency with dermatologists. However, their robustness to analyze daily routine images was sometimes questionable. The purpose of this work is to investigate to what extent the automatic melanoma diagnosis may be achieved from the analysis of uncontrolled images of pigmented skin lesions. MATERIALS AND METHODS: Images were acquired during regular practice by two dermatologists using Reflex 24 x 36 cameras combined with Heine Delta 10 dermascopes. The images were then digitalized using a scanner. In addition, five senior dermatologists were asked to give the diagnosis and therapeutic decision (exeresis) for 227 images of naevi, together with an opinion about the existence of malignancy-predictive features. Meanwhile, a learning by sample classifier for the diagnosis of melanoma was constructed, which combines image-processing with machine-learning techniques. After an automatic segmentation, geometric and colorimetric parameters were extracted from images and selected according to their efficiency in predicting malignancy features. A diagnosis was subsequently provided based on selected parameters. An extensive comparison of dermatologists' and computer results was subsequently performed. RESULTS AND CONCLUSION: The KL-PLS-based classifier shows comparable performances with respect to dermatologists (sensitivity: 95% and specificity: 60%). The algorithm provides an original insight into the clinical knowledge of pigmented skin lesions.

The intracellular localization of ID2 expression has a predictive value in non small cell lung cancer.

BACKGROUND: ID2 is a member of a subclass of transcription regulators belonging to the general bHLH (basic-helix-loop-helix) family of transcription factors. In normal cells, ID2 is responsible for regulating the balance between proliferation and differentiation. More recent studies have demonstrated that ID2 is involved in tumor progression in several cancer types such as prostate or breast. METHODOLOGY/PRINCIPAL FINDINGS: In this work, we investigated, for the first time, the relationship between the expression of ID2 in non-small cell lung cancer (NSCLC) patients and the clinicopathological features and prognosis of these patients. Immunohistochemistry was performed on tissue microarrays, which included 62 NSCLC tumors. In malignant tissues, ID2 expression has been detected in both the nuclear and cytoplasmic compartments, but we have demonstrated that only nuclear expression of ID2 is inversely correlated with the differentiation grade of the tumor (p = 0.007). Interestingly, among patients with poorly differentiated tumors, high nuclear expression of ID2 was an independent and unfavorable prognostic factor for survival (p = 0.036). CONCLUSIONS: These results suggest that ID2 could be involved in tumor dedifferentiation processes of NSCLC, and could be used as prognostic marker for patients with poorly differentiated tumors.