Multi-phase CT Images Research Articles

Construction of a 2.5D Deep Learning Model for Predicting Early Postoperative Recurrence of Hepatocellular Carcinoma Using Multi-View and Multi-Phase CT Images

Construction of a 2.5D Deep Learning Model for Predicting Early Postoperative Recurrence of Hepatocellular Carcinoma Using Multi-View and Multi-Phase CT Images

WAW-TACE: A Hepatocellular Carcinoma Multiphase CT Dataset with Segmentations, Radiomics Features, and Clinical Data.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. The WAW-TACE dataset contains baseline multiphase abdominal CT images from 233 treatment-naive patients with hepatocellular carcinoma treated with transarterial chemoembolization and includes with 377 hand-crafted liver tumor masks, automated segmentations of multiple internal organs, extracted radiomics features, and corresponding extensive clinical data. The dataset can be accessed at: https://zenodo.org/records/12741586 (DOI:10.5281/zenodo.11063784).

Practical Step-by-step SYNAPSE VINCENT Rendering of Three-dimensional Graphics in Horseshoe Kidney with Bilateral Varicoceles.

Medical illustration serves as a cornerstone for understanding intricate anatomical anomalies, with three-dimensional (3D) rendering emerging as a pioneering tool for emphasizing basic medical concepts and clinical practices. In Japan, the SYNAPSE VINCENT software package (SVSP; Fujifilm Medical Co., Ltd., Tokyo, Japan), internationally known as "SYNAPSE 3D," is a widely embraced solution for 3D rendering. However, despite its prevalence, resources elucidating its practical usage and offering insightful tips are scarce. In this review, we focus on the use of SVSP for 3D rendering of complex anatomical anomalies, particularly in the field of urology. We demonstrate a step-by-step process of 3D rendering. 3D rendering was performed in a sample case of a patient with horseshoe kidney and coexisting bilateral varicoceles through inputting of multiphase contrast-enhanced CT images into the application, followed by segmentation of the renal parenchyma, image registration, and segmentation of the arterial and venous systems as well as the upper urinary tract. Manual adjustments were made using the "Mask edit" and "Diameter setting" tools to ensure accuracy, particularly in cases of significant anomalies. Then, color-coded structures appeared, including the renal parenchyma, arterial and venous systems, and upper urinary tract, which provided a comprehensive visualization of the anatomical anomalies. This review highlights the effectiveness of the SVSP in visualizing complex anatomical abnormalities and detailing the practical rendering process, which could promote wider adoption of the application among urologists despite the challenges associated with the software.

A flexible deep learning framework for liver tumor diagnosis using variable multi-phase contrast-enhanced CT scans

BackgroundLiver cancer is a significant cause of cancer-related mortality worldwide and requires tailored treatment strategies for different types. However, preoperative accurate diagnosis of the type presents a challenge. This study aims to develop an automatic diagnostic model based on multi-phase contrast-enhanced CT (CECT) images to distinguish between hepatocellular carcinoma (HCC), intrahepatic cholangiocarcinoma (ICC), and normal individuals.MethodsWe designed a Hierarchical Long Short-Term Memory (H-LSTM) model, whose core components consist of a shared image feature extractor across phases, an internal LSTM for each phase, and an external LSTM across phases. The internal LSTM aggregates features from different layers of 2D CECT images, while the external LSTM aggregates features across different phases. H-LSTM can handle incomplete phases and varying numbers of CECT image layers, making it suitable for real-world decision support scenarios. Additionally, we applied phase augmentation techniques to process multi-phase CECT images, improving the model’s robustness.ResultsThe H-LSTM model achieved an overall average AUROC of 0.93 (0.90, 1.00) on the test dataset, with AUROC for HCC classification reaching 0.97 (0.93, 1.00) and for ICC classification reaching 0.90 (0.78, 1.00). Comprehensive validation in scenarios with incomplete phases was performed, with the H-LSTM model consistently achieving AUROC values over 0.9.ConclusionThe proposed H-LSTM model can be employed for classification tasks involving incomplete phases of CECT images in real-world scenarios, demonstrating high performance. This highlights the potential of AI-assisted systems in achieving accurate diagnosis and treatment of liver cancer. H-LSTM offers an effective solution for processing multi-phase data and provides practical value for clinical diagnostics.

A combination model of CT-based radiomics and clinical biomarkers for staging liver fibrosis in the patients with chronic liver disease

A combined model was developed using contrast-enhanced CT-based radiomics features and clinical characteristics to predict liver fibrosis stages in patients with chronic liver disease (CLD). We retrospectively analyzed multiphase CT scans and biopsy-confirmed liver fibrosis. 160 CLD patients were randomly divided into 7:3 training/validation ratio. Clinical laboratory indicators associated with liver fibrosis were identified using Spearman's correlation and multivariate logistic regression correlation. Radiomic features were extracted after segmenting the entire liver from multiphase CT images. Feature dimensionality reduction was performed using RF-RFE, LASSO, and mRMR methods. Six radiomics-based models were developed in the training cohort of 112 patients. Internal validation was conducted on 48 randomly assigned patients. Receptor Operating Characteristic (ROC) curves and confusion matrices were constructed to evaluate model performance. The radiomics model exhibited robust performance, with AUC values of 0.810 to 1.000 for significant fibrosis, advanced fibrosis, and cirrhosis. The integrated clinical-radiomics model had superior diagnostic efficacy in the validation cohort, with AUC values of 0.836 to 0.997. Moreover, these models outperformed established biomarkers such as the aspartate aminotransferase to platelet ratio index (APRI) and the fibrosis 4 score (FIB-4), as well as the gamma glutamyl transpeptidase to platelet ratio (GPR), in predicting the fibrotic stages. The clinical-radiomics model holds considerable promise as a non-invasive diagnostic tool for the assessment and staging of liver fibrosis in the patients with CLD, potentially leading to better patient management and outcomes.

Deep learning system for malignancy risk prediction in cystic renal lesions: a multicenter study.

To develop an interactive, non-invasive artificial intelligence (AI) system for malignancy risk prediction in cystic renal lesions (CRLs). In this retrospective, multicenter diagnostic study, we evaluated 715 patients. An interactive geodesic-based 3D segmentation model was created for CRLs segmentation. A CRLs classification model was developed using spatial encoder temporal decoder (SETD) architecture. The classification model combines a 3D-ResNet50 network for extracting spatial features and a gated recurrent unit (GRU) network for decoding temporal features from multi-phase CT images. We assessed the segmentation model using sensitivity (SEN), specificity (SPE), intersection over union (IOU), and dice similarity (Dice) metrics. The classification model's performance was evaluated using the area under the receiver operator characteristic curve (AUC), accuracy score (ACC), and decision curve analysis (DCA). From 2012 to 2023, we included 477 CRLs (median age, 57 [IQR: 48-65]; 173 men) in the training cohort, 226 CRLs (median age, 60 [IQR: 52-69]; 77 men) in the validation cohort, and 239 CRLs (median age, 59 [IQR: 53-69]; 95 men) in the testing cohort (external validation cohort 1, cohort 2, and cohort 3). The segmentation model and SETD classifier exhibited excellent performance in both validation (AUC = 0.973, ACC = 0.916, Dice = 0.847, IOU = 0.743, SEN = 0.840, SPE = 1.000) and testing datasets (AUC = 0.998, ACC = 0.988, Dice = 0.861, IOU = 0.762, SEN = 0.876, SPE = 1.000). The AI system demonstrated excellent benign-malignant discriminatory ability across both validation and testing datasets and illustrated improved clinical decision-making utility. In this era when incidental CRLs are prevalent, this interactive, non-invasive AI system will facilitate accurate diagnosis of CRLs, reducing excessive follow-up and overtreatment. The rising prevalence of CRLs necessitates better malignancy prediction strategies. The AI system demonstrated excellent diagnostic performance in identifying malignant CRL. The AI system illustrated improved clinical decision-making utility.

Deep learning vs. robust federal learning for distinguishing adrenal metastases from benign lesions with multi-phase CT images

BackgroundDifferentiating adrenal adenomas from metastases poses a significant challenge, particularly in patients with a history of extra-adrenal malignancy. This study investigates the performance of three-phase computed tomography (CT) based robust federal learning algorithm and traditional deep learning for distinguishing metastases from benign adrenal lesions. Material and methodsThis retrospective analysis includes 1187 instances who underwent three-phase CT scans between January 2008 and March 2021, comprising 720 benign lesions and 467 metastases. Utilizing the three-phase CT images, both a Robust Federal Learning Signature (RFLS) and a traditional Deep Learning Signature (DLS) were constructed using the Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression. Their diagnostic capabilities were subsequently validated and compared using metrics such as the Areas Under the Receiver Operating Curve (AUCs), Net Reclassification Improvement (NRI), and Decision Curve Analysis (DCA). ResultsCompared with DLS, the RFLS showed better capability in distinguishing metastases from benign adrenal lesions (average AUC: 0.816 vs.0.798, NRI = 0.126, P < 0.072; 0.889 vs.0.838, NRI = 0.209, P < 0.001; 0.903 vs.0.825, NRI = 0.643, p < 0.001) in the four-testing cohort, respectively. DCA showed that the RFLS added more net benefit than DLS for clinical utility. Moreover, Comparison with state-of-the-art federal learning methods, the results once again confirmed that the RFLS significantly improved the diagnostic performance based on three-phase CT (AUC: AP, 0.727 vs. 0.757 vs. 0.739 vs. 0.796; PCP, 0.781 vs. 0.851 vs. 0.790 vs. 0.882; VP, 0.789 vs. 0.814 vs. 0.779 vs. 0.886). ConclusionRFLS was superior to DLS for preoperative distinguishing metastases from benign adrenal lesions with multi-phase CT Images.

MSPA-DLA++: A Multi-Scale Phase Attention Deep Layer Aggregation for Lesion Detection in Multi-Phase CT Images.

Object detection using convolutional neural networks (CNNs) has achieved high performance and achieved state-of-the-art results with natural images. Compared to natural images, medical images present several challenges for lesion detection. First, the sizes of lesions vary tremendously, from several millimeters to several centimeters. Scale variations significantly affect lesion detection accuracy, especially for the detection of small lesions. Moreover, the effective extraction of temporal and spatial features from multi-phase CT images is also an important issue. In this paper, we propose a group-based deep layer aggregation method with multiphase attention for liver lesion detection in multi-phase CT images. The method, which is called MSPA-DLA++, is a backbone feature extraction network for anchor-free liver lesion detection in multi-phase CT images that addresses scale variations and extracts hidden features from such images. The effectiveness of the proposed method is demonstrated on public datasets (LiTS2017) and our private multiphase dataset. The results of the experiments show that MSPA-DLA++ can improve upon the performance of state-of-the-art networks by approximately 3.7%.

Multi-phase CT synthesis-assisted segmentation of abdominal organs

To propose a method for abdominal multi-organ segmentation assisted by multi-phase CT synthesis. Multi-phase CT synthesis for synthesizing high-quality CT images was used to increase the information details for image segmentation. A transformer block was introduced to help to capture long-range semantic information in cooperation with perceptual loss to minimize the differences between the real image and synthesized image. The model was trained using multi-phase CT dataset of 526 total cases from Nanfang Hospital. The mean maximum absolute error (MAE) of the synthesized non-contrast CT, venous phase contrast- enhanced CT (CECT), and delay phase CECT images from arterial phase CECT was 19.192±3.381, 20.140±2.676 and 22.538±2.874, respectively, which were better than those of images synthesized using other methods. Validation of the multi-phase CT synthesis-assisted abdominal multi-organ segmentation method showed an average dice coefficient of 0.847 for the internal validation set and 0.823 for the external validation set. The propose method is capable of synthesizing high-quality multi-phase CT images to effectively reduce the errors in registration between different phase CT images and improve the performance for segmentation of 13 abdominal organs.

PA-Net: A phase attention network fusing venous and arterial phase features of CT images for liver tumor segmentation

Background and ObjectiveLiver cancer seriously threatens human health. In clinical diagnosis, contrast-enhanced computed tomography (CECT) images provide important supplementary information for accurate liver tumor segmentation. However, most of the existing methods of liver tumor automatic segmentation focus only on single-phase image features. And the existing multi-modal methods have limited segmentation effect due to the redundancy of fusion features. In addition, the spatial misalignment of multi-phase images causes feature interference. MethodsIn this paper, we propose a phase attention network (PA-Net) to adequately aggregate multi-phase information of CT images and improve segmentation performance for liver tumors. Specifically, we design a PA module to generate attention weight maps voxel by voxel to efficiently fuse multi-phase CT images features to avoid feature redundancy. In order to solve the problem of feature interference in the multi-phase image segmentation task, we design a new learning strategy and prove its effectiveness experimentally. ResultsWe conduct comparative experiments on the in-house clinical dataset and achieve the SOTA segmentation performance on multi-phase methods. In addition, our method has improved the mean dice score by 3.3% compared with the single-phase method based on nnUNet, and our learning strategy has improved the mean dice score by 1.51% compared with the ML strategy. ConclusionThe experimental results show that our method is superior to the existing multi-phase liver tumor segmentation method, and provides a scheme for dealing with missing modalities in multi-modal tasks. In addition, our proposed learning strategy makes more effective use of arterial phase image information and is proven to be the most effective in liver tumor segmentation tasks using thick-layer CT images. The source code is released on (https://github.com/Houjunfeng203934/PA-Net).

DA-Tran: Multiphase liver tumor segmentation with a domain-adaptive transformer network

Accurate liver tumor segmentation from multiphase CT images is a prerequisite for data-driven tumor analysis. This study presents a domain-adaptive transformer (DA-Tran) network to segment liver tumors from each CT phase. First, a DA module is designed to produce domain-adapted feature maps from noncontrast-enhanced (NC)-phase, arterial (ART)-phase, portal venous (PV)-phase, and delay-phase (DP) images. Then, these domain-adapted feature maps are integrated using 3D transformer blocks to catch patch-structured similarity information and global context attention. Finally, the attention fusion decoder (AFD) integrates features from different branches to generate a more refined prediction. Extensive experimental results demonstrate that DA-Tran achieves state-of-the-art tumor segmentation results, i.e., a Dice similarity coefficient (DSC) of 87.00% and a 95% Hausdorff distance (HD95) of 5.10 mm on a clinical dataset (DB1). Additionally, DA-Tran consistently outperforms other cutting-edge methods on another multiphase liver tumor dataset (DB2). The DA module and transformer blocks can boost the co-segmentation performance and make DA-Tran an ideal solution for multiphase liver tumor segmentation.

Differentiating adrenal metastases from benign lesions with multiphase CT imaging: Deep learning could play an active role in assisting radiologists

ObjectivesTo develop and externally validate multiphase CT-based deep learning (DL) models for differentiating adrenal metastases from benign lesions. Materials and methodsThis retrospective two-center study included 1146 adrenal lesions from 1059 patients who underwent multiphase CT scanning between January 2008 and March 2021. The study encompassed 564 surgically confirmed adenomas, along with 135 benign lesions and 447 metastases confirmed by observation. DL models based on multiphase CT images were developed, validated and tested. The diagnostic performance of the classification models, imaging phases and radiologists with or without DL were compared using accuracy (ACC) and receiver operating characteristic (ROC) curves. Integrated discrimination improvement (IDI) analysis and the DeLong test were used to compare the area under the curve (AUC) among models. Decision curve analysis (DCA) was used to assess the clinical usefulness of the predictive models. ResultsThe DL signature based on LASSO (DLSL) had a higher AUC than that of the other classification models (IDI > 0, P < 0.05). Furthermore, the precontrast phase (PCP)-based DLSL performed best in the independent external validation (AUC = 0.881, ACC = 82.9 %) and clinical test cohorts (AUC = 0.790, ACC = 70.4 %), outperforming DLSL based on the other single-phase or three-phase images (IDI > 0, P < 0.05). DCA demonstrated that PCP-based DLSL provided a higher net benefit (0.01–0.95). The diagnostic performance led to statistically significant improvements when radiologists incorporated the DL model, with the AUC improving by 0.056–0.159 and the ACC improving by 0.069–0.178 (P < 0.05). ConclusionThe DL model based on PCP CT images performed acceptably in differentiating adrenal metastases from benign lesions, and it may assist radiologists in accurate tumor staging for patients with a history of extra-adrenal malignancy.

Beyond radiologist-level liver lesion detection on multi-phase contrast-enhanced CT images by deep learning

Accurate detection of liver lesions from multi-phase contrast-enhanced CT (CECT) scans is a fundamental step for precise liver diagnosis and treatment. However, the analysis of multi-phase contexts is heavily challenged by the misalignment caused by respiration coupled with the movement of organs. Here, we proposed an AI system for multi-phase liver lesion segmentation (named MULLET) for precise and fully automatic segmentation of real-patient CECT images. MULLET enables effectively embedding the important ROIs of CECT images and exploring multi-phase contexts by introducing a transformer-based attention mechanism. Evaluated on 1,229 CECT scans from 1,197 patients, MULLET demonstrated significant performance gains in terms of Dice, Recall, and F2 score, which are 5.80%, 6.57%, and 5.87% higher than state of the arts, respectively. MULLET has been successfully deployed in real-world settings. The deployed AI web server provides a powerful system to boost clinical workflows of liver lesion diagnosis and could be straightforwardly extended to general CECT analyses.

Hounsfield Unit Variations-Based Liver Lesions Detection and Classification Using Deep Learning.

Deep learning-based diagnosis systems are useful to identify abnormalities in medical images with the greatly increased workload of doctors. Specifically, the rate of new cases and deaths from malignancies is rising for liver diseases. Early detection of liver lesions plays an extremely important role in effective treatment and gives a higher chance of survival for patients. Therefore, automatic detection and classification of common liver lesions are essential for doctors. In fact, radiologists mainly rely on Hounsfield Units to locate liver lesions but previous studies often pay little attention to this factor. In this paper, we propose an improved method for the automatic classification of common liver lesions based on deep learning techniques and the variation of Hounsfield Unit densities on CT images with and without contrast. Hounsfield Unit is used to locate liver lesions accurately and support data labeling for classification. We construct a multi-phase classification model developed on the deep neural networks of Faster R-CNN, R-FCN, SSD, and Mask R-CNN with the transfer learning approach. The experiments are conducted on six scenarios with multi-phase CT images of common liver lesions. Experimental results show that the proposed method improves the detection and classification of liver lesions compared with recent methods because its accuracy achieves up to 97.4%. The proposed models are very useful to assist doctors in the automatic segmentation and classification of liver lesions to solve the problem of depending on the clinician's experience in the diagnosis and treatment of liver lesions.

Small arteriole sign: an imaging feature for staging T4a colon cancer.

By analyzing the distribution of existing and newly proposed staging imaging features in pT1-3 and pT4a tumors, we searched for a salient feature and validated its diagnostic performance. Preoperative multiphase contrast-enhanced CT images of the training cohort were retrospectively collected at three centers from January 2016 to December 2017. We used the chi-square test to analyze the distribution of several stage-related imaging features in pT1-3 and pT4a tumors, including small arteriole sign (SAS), outer edge of the intestine, tumor invasion range, and peritumoral adipose tissue. Preoperative multiphase contrast-enhanced CT images of the validation cohort were retrospectively collected at Beijing Cancer Hospital from January 2018 to December 2018. The diagnostic performance of the selected imaging feature, including accuracy, sensitivity, and specificity, was validated and compared with the conventional clinical tumor stage (cT) by the McNemar test. In the training cohort, a total of 268 patients were enrolled, and only SAS was significantly different between pT1-3 and pT4a tumors. The accuracy, sensitivity, and specificity of the SAS and conventional cT in differentiating T1-3 and T4a tumors were 94.4%, 81.6%, and 97.3% and 53.7%, 32.7%, and 58.4%, respectively (all p < 0.001). In the validation cohort, a total of 135 patients were collected. The accuracy, sensitivity, and specificity of the SAS and the conventional cT were 93.3%, 76.2%, and 96.5% and 62.2%, 38.1%, and 66.7%, respectively (p < 0.001, p = 0.021, p < 0.001). Small arteriole sign positivity, an indirect imaging feature of serosa invasion, may improve the accuracy of identifying T4a colon cancer. Small arteriole sign helps to distinguish T1-3 and T4a colon cancer and further improves the accuracy of preoperative CT staging of colon cancer. • The accuracy of preoperative CT staging of colon cancer is not ideal, especially for T4a tumors. • Small arteriole sign (SAS) is a newly defined imaging feature that shows the appearance of tumor-supplying arterioles at the site where they penetrate the intestine wall. • SAS is an indirect imaging marker of tumor invasion into the serosa with a great value in distinguishing between T1-3 and T4a colon cancer.

Unsupervised Domain Adaptation Using Fourier Phase Enhanced Training Images for Liver Tumors Detection in Multi-phase CT Images.

Computer-aided diagnostic methods, such as automatic and precise liver tumor detection, have a significant impact on healthcare. In recent years, deep learning-based liver tumor detection methods in multi-phase computed tomography (CT) images have achieved noticeable performance. Deep learning frameworks require a substantial amount of annotated training data but obtaining enough training data with high quality annotations is a major issue in medical imaging. Additionally, deep learning frameworks experience domain shift problems when they are trained using one dataset (source domain) and applied to new test data (target domain). To address the lack of training data and domain shift issues in multiphase CT images, here, we present an adversarial learning-based strategy to mitigate the domain gap across different phases of multiphase CT scans. We introduce to use Fourier phase component of CT images in order to improve the semantic information and more reliably identify the tumor tissues. Our approach eliminates the requirement for distinct annotations for each phase of CT scans. The experiment results show that our proposed method performs noticeably better than conventional training and other methods.

Impact of new-onset arrhythmia on cardiac reverse remodeling following transcatheter aortic valve replacement: computed tomography-derived left ventricular and atrial strains.

Patients who undergo transcatheter aortic valve replacement (TAVR) are at risk for new-onset arrhythmia (NOA) that may require permanent pacemaker (PPM) implantation, resulting in decreased cardiac function. We aimed to investigate the factors that are associated with NOA after TAVR and to compare pre- and post-TAVR cardiac functions between patients with and without NOA using CT-derived strain analyses. We included consecutive patients who underwent pre- and post-TAVR cardiac CT scans six months after TAVR. New-onset left bundle branch block, atrioventricular block, and atrial fibrillation/flutter lasting over 30days after the procedure and/or the need for PPM diagnosed within 1year after TAVR were regarded as NOA. Implant depth and left heart function and strains were analyzed using multi-phase CT images and compared between patients with and without NOA. Of 211 patients (41.7% men; median 81years), 52 (24.6%) presented with NOA after TAVR, and 24 (11.4%) implanted PPM. Implant depth was significantly deeper in the NOA group than in the non-NOA group (- 6.7 ± 2.4 vs. - 5.6 ± 2.6mm; p = 0.009). Left ventricular global longitudinal strain (LV GLS) and left atrial (LA) reservoir strain were significantly improved only in the non-NOA group (LV GLS, - 15.5 ± 4.0 to - 17.3 ± 2.9%; p < 0.001; LA reservoir strain, 22.3 ± 8.9 to 26.5 ± 7.6%; p < 0.001). The mean percent change of the LV GLS and LA reservoir strains was evident in the non-NOA group (p = 0.019 and p = 0.035, respectively). A quarter of patients presented with NOA after TAVR. Deep implant depth on post-TAVR CT scans was associated with NOA. Patients with NOA after TAVR had impaired LV reserve remodeling assessed by CT-derived strains. New-onset arrhythmia (NOA) following transcatheter aortic valve replacement (TAVR) impairs cardiac reverse remodeling. CT-derived strain analysis reveals that patients with NOA do not show improvement in left heart function and strains, highlighting the importance of managing NOA for optimal outcomes. • New-onset arrhythmia following transcatheter aortic valve replacement (TAVR) is a concern that interferes with cardiac reverse remodeling. • Comparison of pre-and post-TAVR CT-derived left heart strain provides insight into the impaired cardiac reverse remodeling in patients with new-onset arrhythmia following TAVR. • The expected reverse remodeling was not observed in patients with new-onset arrhythmia following TAVR, given that CT-derived left heart function and strains did not improve.

Predicting Microvascular Invasion in Hepatocellular Carcinoma Using CT-based Radiomics Model.

Background Prediction of microvascular invasion (MVI) may help determine treatment strategies for hepatocellular carcinoma (HCC). Purpose To develop a radiomics approach for predicting MVI status based on preoperative multiphase CT images and to identify MVI-associated differentially expressed genes. Materials and Methods Patients with pathologically proven HCC from May 2012 to September 2020 were retrospectively included from four medical centers. Radiomics features were extracted from tumors and peritumor regions on preoperative registration or subtraction CT images. In the training set, these features were used to build five radiomics models via logistic regression after feature reduction. The models were tested using internal and external test sets against a pathologic reference standard to calculate area under the receiver operating characteristic curve (AUC). The optimal AUC radiomics model and clinical-radiologic characteristics were combined to build the hybrid model. The log-rank test was used in the outcome cohort (Kunming center) to analyze early recurrence-free survival and overall survival based on high versus low model-derived score. RNA sequencing data from The Cancer Image Archive were used for gene expression analysis. Results A total of 773 patients (median age, 59 years; IQR, 49-64 years; 633 men) were divided into the training set (n = 334), internal test set (n = 142), external test set (n = 141), outcome cohort (n = 121), and RNA sequencing analysis set (n = 35). The AUCs from the radiomics and hybrid models, respectively, were 0.76 and 0.86 for the internal test set and 0.72 and 0.84 for the external test set. Early recurrence-free survival (P < .01) and overall survival (P < .007) can be categorized using the hybrid model. Differentially expressed genes in patients with findings positive for MVI were involved in glucose metabolism. Conclusion The hybrid model showed the best performance in prediction of MVI. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Summers in this issue.

Radiogenomic Associations Clear Cell Renal Cell Carcinoma: An Exploratory Study

Introduction: This study investigates how quantitative texture analysis can be used to non-invasively identify novel radiogenomic correlations with clear cell renal cell carcinoma (ccRCC) biomarkers. Methods: The Cancer Genome Atlas-Kidney Renal Clear Cell Carcinoma open-source database was used to identify 190 sets of patient genomic data that had corresponding multiphase contrast-enhanced CT images in The Cancer Imaging Archive. 2,824 radiomic features spanning fifteen texture families were extracted from CT images using a custom-built MATLAB software package. Robust radiomic features with strong inter-scanner reproducibility were selected. Random forest, AdaBoost, and elastic net machine learning (ML) algorithms evaluated the ability of the selected radiomic features to predict the presence of 12 clinically relevant molecular biomarkers identified from the literature. ML analysis was repeated with cases stratified by stage (I/II vs. III/IV) and grade (1/2 vs. 3/4). 10-fold cross validation was used to evaluate model performance. Results: Before stratification by tumor grade and stage, radiomics predicted the presence of several biomarkers with weak discrimination (AUC 0.60–0.68). Once stratified, radiomics predicted KDM5C, SETD2, PBRM1, and mTOR mutation status with acceptable to excellent predictive discrimination (AUC ranges from 0.70 to 0.86). Conclusions: Radiomic texture analysis can potentially identify a variety of clinically relevant biomarkers in patients with ccRCC and may have a prognostic implication.

A Knowledge-Guided Framework for Fine-Grained Classification of Liver Lesions Based on Multi-Phase CT Images.

Automatic and accurate differentiation of liver lesions from multi-phase computed tomography imaging is critical for the early detection of liver cancer. Multi-phase data can provide more diagnostic information than single-phase data, and the effective use of multi-phase data can significantly improve diagnostic accuracy. Current fusion methods usually fuse multi-phase information at the image level or feature level, ignoring the specificity of each modality, therefore, the information integration capacity is always limited. In this paper, we propose a Knowledge-guided framework, named MCCNet, which adaptively integrates multi-phase liver lesion information from three different stages to fully utilize and fuse multi-phase liver information. Specifically, 1) a multi-phase self-attention module was designed to adaptively combine and integrate complementary information from three phases using multi-level phase features; 2) a cross-feature interaction module was proposed to further integrate multi-phase fine-grained features from a global perspective; 3) a cross-lesion correlation module was proposed for the first time to imitate the clinical diagnosis process by exploiting inter-lesion correlation in the same patient. By integrating the above three modules into a 3D backbone, we constructed a lesion classification network. The proposed lesion classification network was validated on an in-house dataset containing 3,683 lesions from 2,333 patients in 9 hospitals. Extensive experimental results and evaluations on real-world clinical applications demonstrate the effectiveness of the proposed modules in exploiting and fusing multi-phase information.