Breaking boundaries in radiology: redefining AI diagnostics via raw data ahead of reconstruction.

Objective.In the realm of utilizing artificial intelligence (AI) for medical image analysis, the paradigm of 'signal-image-knowledge' has remained unchanged. However, the process of 'signal to image' inevitably introduces information distortion, ultimately leading to irrecoverable biases in the 'image to knowledge' process. Our goal is to skip reconstruction and build a diagnostic model directly from the raw data (signal).Approach. This study focuses on computed tomography (CT) and its raw data (sinogram) as the research subjects. We simulate the real-world process of 'human-signal-image' using the workflow 'CT-simulated data- reconstructed CT,' and we develop a novel AI predictive model directly targeting raw data (RCTM). This model comprises orientation, spatial, and global analysis modules, embodying the fusion of local to global information extraction from raw data. We selected 1994 patients with retrospective cases of solid lung nodules and modeled different types of data.Main results. We employed predefined radiomic features to assess the diagnostic feature differences caused by reconstruction. The results indicated that approximately 14% of the features had Spearman correlation coefficients below 0.8. These findings suggest that despite the increasing maturity of CT reconstruction algorithms, they still introduce perturbations to diagnostic features. Moreover, our proposed RCTM achieved an area under the curve (AUC) of 0.863 in the diagnosis task, showcasing a comprehensive superiority over models constructed from secondary reconstructed CTs (0.840, 0.822, and 0.825). Additionally, the performance of RCTM closely resembled that of models constructed from original CT scans (0.868, 0.878, and 0.866).Significance. The diagnostic and therapeutic approach directly based on CT raw data can enhance the precision of AI models and the concept of 'signal-to-image' can be extended to other types of imaging. AI diagnostic models tailored to raw data offer the potential to disrupt the traditional paradigm of 'signal-image-knowledge', opening up new avenues for more accurate medical diagnostics.

Production of light-coloured, low heat-absorbing Holstein Friesian cattle by precise embryo-mediated genome editing.

CONTEXT: Genome editing enables the introduction of beneficial sequence variants into the genomes of animals with high genetic merit in a single generation. This can be achieved by introducing variants into primary cells followed by producing a live animal from these cells by somatic cell nuclear transfer cloning. The latter step is associated with low efficiencies and developmental problems due to incorrect reprogramming of the donor cells, causing animal welfare concerns. Direct editing of fertilised one-cell embryos could circumvent this issue and might better integrate with genetic improvement strategies implemented by the industry. METHODS: In vitro fertilised zygotes were injected with TALEN editors and repair template to introduce a known coat colour dilution mutation in the PMEL gene. Embryo biopsies of injected embryos were screened by polymerase chain reaction and sequencing for intended biallelic edits before transferring verified embryos into recipients for development to term. Calves were genotyped and their coats scanned with visible and hyperspectral cameras to assess thermal energy absorption. KEY RESULTS: Multiple non-mosaic calves with precision edited genotypes were produced, including calves from high genetic merit parents. Compared to controls, the edited calves showed a strong coat colour dilution which was associated with lower thermal energy absorbance. CONCLUSIONS: Although biopsy screening was not absolutely accurate, non-mosaic, precisely edited calves can be readily produced by embryo-mediated editing. The lighter coat colouring caused by the PMEL mutation can lower radiative heat gain which might help to reduce heat stress. IMPLICATIONS: The study validates putative causative sequence variants to rapidly adapt grazing cattle to changing environmental conditions.

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.

A multi-scale, multi-region and attention mechanism-based deep learning framework for prediction of grading in hepatocellular carcinoma.

BACKGROUND: Histopathological grading is a significant risk factor for postsurgical recurrence in hepatocellular carcinoma (HCC). Preoperative knowledge of histopathological grading could provide instructive guidance for individualized treatment decision-making in HCC management. PURPOSE: This study aims to develop and validate a newly proposed deep learning model to predict histopathological grading in HCC with improved accuracy. METHODS: In this dual-centre study, we retrospectively enrolled 384 HCC patients with complete clinical, pathological and radiological data. Aiming to synthesize radiological information derived from both tumour parenchyma and peritumoral microenvironment regions, a modelling strategy based on a multi-scale and multi-region dense connected convolutional neural network (MSMR-DenseCNNs) was proposed to predict histopathological grading using preoperative contrast enhanced computed tomography (CT) images. Multi-scale inputs were defined as three-scale enlargement of an original minimum bounding box in width and height by given pixels, which correspondingly contained more peritumoral analysis areas with the enlargement. Multi-region inputs were defined as three regions of interest (ROIs) including a squared ROI, a precisely delineated tumour ROI, and a peritumoral tissue ROI. The DenseCNN structure was designed to consist of a shallow feature extraction layer, dense block module, and transition and attention module. The proposed MSMR-DenseCNN was pretrained by the ImageNet dataset to capture basic graphic characteristics from the images and was retrained by the collected retrospective CT images. The predictive ability of the MSMR-DenseCNN models on triphasic images was compared with a conventional radiomics model, radiological model and clinical model. RESULTS: MSMR-DenseCNN applied to the delayed phase (DP) achieved the highest area under the curve (AUC) of 0.867 in the validation cohort for grading prediction, outperforming those on the arterial phase (AP) and portal venous phase (PVP). Fusion of the results on triphasic images did not increase the predictive ability, which underscored the role of DP for grading prediction. Compared with a single-scale and single-region network, the DP-phase based MSMR-DenseCNN model remarkably raised sensitivity from 67.4% to 75.5% with comparable specificity of 78.6%. MSMR-DenseCNN on DP defeated conventional radiomics, radiological and clinical models, where the AUCs were correspondingly 0.765, 0.695 and 0.612 in the validation cohort. CONCLUSIONS: The MSMR-DenseCNN modelling strategy increased the accuracy for preoperative prediction of grading in HCC, and enlightens similar radiological analysis pipelines in a variety of clinical scenarios in HCC management.

The Applications of Artificial Intelligence in Digestive System Neoplasms: A Review.

Importance: Digestive system neoplasms (DSNs) are the leading cause of cancer-related mortality with a 5-year survival rate of less than 20%. Subjective evaluation of medical images including endoscopic images, whole slide images, computed tomography images, and magnetic resonance images plays a vital role in the clinical practice of DSNs, but with limited performance and increased workload of radiologists or pathologists. The application of artificial intelligence (AI) in medical image analysis holds promise to augment the visual interpretation of medical images, which could not only automate the complicated evaluation process but also convert medical images into quantitative imaging features that associated with tumor heterogeneity. Highlights: We briefly introduce the methodology of AI for medical image analysis and then review its clinical applications including clinical auxiliary diagnosis, assessment of treatment response, and prognosis prediction on 4 typical DSNs including esophageal cancer, gastric cancer, colorectal cancer, and hepatocellular carcinoma. Conclusion: AI technology has great potential in supporting the clinical diagnosis and treatment decision-making of DSNs. Several technical issues should be overcome before its application into clinical practice of DSNs.

Cytoplasmic Injection of Zygotes to Genome Edit Naturally Occurring Sequence Variants Into Bovine Embryos.

Genome editing provides opportunities to improve current cattle breeding strategies through targeted introduction of natural sequence variants, accelerating genetic gain. This can be achieved by harnessing homology-directed repair mechanisms following editor-induced cleavage of the genome in the presence of a repair template. Introducing the genome editors into zygotes and editing in embryos has the advantage of uncompromised development into live animals and alignment with contemporary embryo-based improvement practices. In our study, we investigated the potential to introduce sequence variants, known from the pre-melanosomal protein 17 (PMEL) and prolactin receptor (PRLR) genes, and produce non-mosaic, edited embryos, completely converted into the precision genotype. Injection of gRNA/Cas9 editors into bovine zygotes to introduce a 3 bp deletion variant into the PMEL gene produced up to 11% fully converted embryos. The conversion rate was increased to up to 48% with the use of TALEN but only when delivered by plasmid. Testing three gRNA/Cas9 editors in the context of several known PRLR sequence variants, different repair template designs and delivery as DNA, RNA or ribonucleoprotein achieved full conversion rates up to 8%. Furthermore, we developed a biopsy-based screening strategy for non-mosaic embryos which has the potential for exclusively producing non-mosaic animals with intended precision edits.

Radiomics-Based Preoperative Prediction of Lymph Node Metastasis in Intrahepatic Cholangiocarcinoma Using Contrast-Enhanced Computed Tomography.

BACKGROUND: Lymph node (LN) metastasis is significantly associated with worse prognosis for patients with intrahepatic cholangiocarcinoma (ICC). Improvement in preoperative assessment on LN metastasis helps in treatment decision-making. We aimed to investigate the role of radiomics-based method in predicting LN metastasis for patients with ICC. METHODS: A total of 296 patients with ICC who underwent curative-intent hepatectomy and lymphadenectomy at two centers in China were analyzed. Radiomic features, including histogram- and wavelet-based features, shape and size features, and texture features were extracted from four-phase computerized tomography (CT) images. The clinical and conventional radiological variables which were independently associated with LN metastasis were also identified. A combined nomogram predicting LN metastasis was developed, and its performance was determined by discrimination, calibration, and stratification of long-term prognosis. The results were validated by the internal and external validation cohorts. RESULTS: Twenty-four radiomic features were selected into the nomogram. The established nomogram demonstrated good discrimination and calibration, with areas under the curve (AUCs) of 0.98 [95% confidence interval (CI) 0.96-0.99], 0.93 (0.88-0.98), and 0.89 (0.81-0.96) in the training and two validation cohorts, respectively. The 5-year overall survival (OS) and recurrence-free survival (RFS) rates of patients with high risk of LN metastasis as grouped by nomogram were poorer than those of patients with low risk in the training cohort (OS 28.8% versus 53.9%, p < 0.001; RFS 26.3% versus 44.2%, p = 0.001). Similar results were observed in the two validation cohorts. CONCLUSIONS: Radiomics-based method provided accurate prediction of LN metastasis and prognostic assessment for ICC patients, and might aid the preoperative surgical decision.

Predicting microvascular invasion in hepatocellular carcinoma: A dual-institution study on gadoxetate disodium-enhanced MRI.

BACKGROUND & AIMS: Microvascular invasion (MVI) is an important risk factor in hepatocellular carcinoma (HCC), but its diagnosis mandates postoperative histopathologic analysis. We aimed to develop and externally validate a predictive scoring system for MVI. METHODS: From July 2015 to November 2020, consecutive patients underwent surgery for HCC with preoperative gadoxetate disodium (EOB)-enhanced MRI was retrospectively enrolled. All MR images were reviewed independently by two radiologists who were blinded to the outcomes. In the training centre, a radio-clinical MVI score was developed via logistic regression analysis against pathology. In the testing centre, areas under the receiver operating curve (AUCs) of the MVI score and other previous MVI schemes were compared. Overall survival (OS) and recurrence-free survival (RFS) were analysed by the Kaplan-Meier method with the log-rank test. RESULTS: A total of 417 patients were included, 195 (47%) with pathologically-confirmed MVI. The MVI score included: non-smooth tumour margin (odds ratio [OR] = 4.4), marked diffusion restriction (OR = 3.0), internal artery (OR = 3.0), hepatobiliary phase peritumoral hypointensity (OR = 2.5), tumour multifocality (OR = 1.6), and serum alpha-fetoprotein >400 ng/mL (OR = 2.5). AUCs for the MVI score were 0.879 (training) and 0.800 (testing), significantly higher than those for other MVI schemes (testing AUCs: 0.648-0.684). Patients with model-predicted MVI had significantly shorter OS (median 61.0 months vs not reached, P < .001) and RFS (median 13.0 months vs. 42.0 months, P < .001) than those without. CONCLUSIONS: A preoperative MVI score integrating five EOB-MRI features and serum alpha-fetoprotein level could accurately predict MVI and postoperative survival in HCC. Therefore, this score may aid in individualized treatment decision making.

CT-based radiomics to predict development of macrovascular invasion in hepatocellular carcinoma: A multicenter study.

BACKGROUND: Macrovascular invasion (MaVI) occurs in nearly half of hepatocellular carcinoma (HCC) patients at diagnosis or during follow-up, which causes severe disease deterioration, and limits the possibility of surgical approaches. This study aimed to investigate whether computed tomography (CT)-based radiomics analysis could help predict development of MaVI in HCC. METHODS: A cohort of 226 patients diagnosed with HCC was enrolled from 5 hospitals with complete MaVI and prognosis follow-ups. CT-based radiomics signature was built via multi-strategy machine learning methods. Afterwards, MaVI-related clinical factors and radiomics signature were integrated to construct the final prediction model (CRIM, clinical-radiomics integrated model) via random forest modeling. Cox-regression analysis was used to select independent risk factors to predict the time of MaVI development. Kaplan-Meier analysis was conducted to stratify patients according to the time of MaVI development, progression-free survival (PFS), and overall survival (OS) based on the selected risk factors. RESULTS: The radiomics signature showed significant improvement for MaVI prediction compared with conventional clinical/radiological predictors (P < 0.001). CRIM could predict MaVI with satisfactory areas under the curve (AUC) of 0.986 and 0.979 in the training (n = 154) and external validation (n = 72) datasets, respectively. CRIM presented with excellent generalization with AUC of 0.956, 1.000, and 1.000 in each external cohort that accepted disparate CT scanning protocol/manufactory. Peel9_fos_InterquartileRange [hazard ratio (HR) = 1.98; P < 0.001] was selected as the independent risk factor. The cox-regression model successfully stratified patients into the high-risk and low-risk groups regarding the time of MaVI development (P < 0.001), PFS (P < 0.001) and OS (P = 0.002). CONCLUSIONS: The CT-based quantitative radiomics analysis could enable high accuracy prediction of subsequent MaVI development in HCC with prognostic implications.

Multi-scale patches convolutional neural network predicting the histological grade of hepatocellular carcinoma.

Preoperative predicting histological grade of hepatocellular carcinoma (HCC) is a crucial issue for the evaluation of patient prognosis and determining clinical treatment strategies. Previous studies have shown the potential of preoperative medical imaging in HCC grading diagnosis, however, there still remain challenges. In this work, we proposed a multi-scale 2D dense connected convolutional neural network (MS-DenseNet) for the classification of grade. This architecture consisted of three CNN branches to extract features of CT image patches in different scale. Then the outputs for each CNN branch were concatenated to the final fully connected layer. Our network was developed and evaluated on 455 HCC patients from two different centers. For data augmentation, more than 2000 patches for each scale were cropped from transverse section 2D region of interest on these patients. Besides, three-channel inputs including original CT image, tumor region and peritumoral component provided complementary knowledge. Experimental results demonstrated that the proposed method achieved encouraging prediction performance with AUC of 0.798 in testing dataset.Clinical Relevance-The proposed MS-DenseNet yielded an encouraging prediction performance for HCC histological grade and might assist the clinical diagnosis and decision making of HCC patients.

A Radiomics-based Approach for Predicting Early Recurrence in Intrahepatic Cholangiocarcinoma after Surgical Resection: A Multicenter Study.

This work aimed to develop a noninvasive and reliable computed tomography (CT)-based imaging biomarker to predict early recurrence (ER) of intrahepatic cholangiocarcinoma (ICC) via radiomics analysis. In this retrospective study, a total of 177 ICC patients were enrolled from three independent hospitals. Radiomic features were extracted on CT images, then 11 feature selection algorithms and 4 classifiers were to conduct a multi-strategy radiomics modeling. Six established radiomics models were selected as stable ones by robustness-based rule. Among those models, Max-Relevance Min-Redundancy (MRMR) combined with Gradient Boosting Machine (GBM) yielded the highest areas under the receiver operating characteristics curve (AUCs) of 0.802 (95% confidence interval [CI]: 0.727-0.876) and 0.781 (95% CI: 0.655-0.907) in the training and test cohorts, respectively. To evaluate the generalization of the developed radiomics model, stratification analysis was performed regarding different centers. The MRMR-GBM-based model manifested good generalization with comparable AUCs in each hospital (p > 0.05 for paired comparison). Thus, the MRMR-GBM-based model could offer a potential imaging biomarker to assist the prediction of ER in ICC in a noninvasive manner.Clinical Relevance-The proposed radiomics model achieved satisfactory accuracy and good generalization ability in predicting ER in ICC, which might assist personalized surveillance and clinical treatment strategy making.

Multi-Omics and Its Clinical Application in Hepatocellular Carcinoma: Current Progress and Future Opportunities.

Hepatocellular carcinoma (HCC) is the sixth most common malignancy and the fourth leading cause of cancer related death worldwide. China covers over half of cases, leading HCC to be a vital threaten to public health. Despite advances in diagnosis and treatments, high recurrence rate remains a major obstacle in HCC management. Multi-omics currently facilitates surveillance, precise diagnosis, and personalized treatment decision making in clinical setting. Non-invasive radiomics utilizes preoperative radiological imaging to reflect subtle pixel-level pattern changes that correlate to specific clinical outcomes. Radiomics has been widely used in histopathological diagnosis prediction, treatment response evaluation, and prognosis prediction. High-throughput sequencing and gene expression profiling enabled genomics and proteomics to identify distinct transcriptomic subclasses and recurrent genetic alterations in HCC, which would reveal the complex multistep process of the pathophysiology. The accumulation of big medical data and the development of artificial intelligence techniques are providing new insights for our better understanding of the mechanism of HCC via multi-omics, and show potential to convert surgical/intervention treatment into an antitumorigenic one, which would greatly advance precision medicine in HCC management.

Radiomics diagnosed histopathological growth pattern in prediction of response and 1-year progression free survival for colorectal liver metastases patients treated with bevacizumab containing chemotherapy.

OBJECTIVE: To investigate the capability of a radiomics model, which was designed to identify histopathologic growth pattern (HGP) of colorectal liver metastases (CRLMs) based on contrast-enhanced multidetector computed tomography (ceMDCT), to predict early response and 1-year progression free survival (PFS) in patients treated with bevacizumab-containing chemotherapy. METHODS: Patients with unresectable CRLMs who were treated with bevacizumab-containing chemotherapy were included in this multicenter retrospective study. For each target lesion, the radiomics-diagnosed HGP (RAD_HGP) of desmoplastic (D) pattern or replacement (R) pattern was determined. Logistic regression and receiver operating characteristic (ROC) curves were used to assess lesion- and patient-based responses according to morphologic response criteria. One-year PFS was calculated using Kaplan-Meier curves. Hazard ratios for 1-year PFS were obtained through Cox proportional hazard regression analysis. RESULTS: Among 119 study patients, 206 D pattern and 140 R pattern lesions were identified. In patients with multiple lesions, 52 had D pattern, 31 had R pattern, and 36 had mixed (D + R) pattern. The area under the curve value for RAD_HGP in predicting early response was 0.707 for lesion-based analysis and 0.720 for patient-based analysis. Patients with D pattern had a significantly longer PFS than patients with R pattern or mixed pattern (P < 0.001). RAD_HGP was the only independent predictor of 1-year PFS. CONCLUSIONS: HGP diagnosed using a radiomics model could be used as an effective predictor of PFS for patients with CRLMs treated with bevacizumab-containing chemotherapy.

Prediction of Microvascular Invasion in Hepatocellular Carcinoma via Deep Learning: A Multi-Center and Prospective Validation Study.

Microvascular invasion (MVI) is a critical risk factor for postoperative recurrence of hepatocellular carcinoma (HCC). Preknowledge of MVI would assist tailored surgery planning in HCC management. In this multicenter study, we aimed to explore the validity of deep learning (DL) in MVI prediction using two imaging modalities-contrast-enhanced computed tomography (CE-CT) and gadoxetic acid-enhanced magnetic resonance imaging (EOB-MRI). A total of 750 HCCs were enrolled from five Chinese tertiary hospitals. Retrospective CE-CT (n = 306, collected between March, 2013 and July, 2019) and EOB-MRI (n = 329, collected between March, 2012 and March, 2019) data were used to train two DL models, respectively. Prospective external validation (n = 115, collected between July, 2015 and February, 2018) was performed to assess the developed models. Furthermore, DL-based attention maps were utilized to visualize high-risk MVI regions. Our findings revealed that the EOB-MRI-based DL model achieved superior prediction outcome to the CE-CT-based DL model (area under receiver operating characteristics curve (AUC): 0.812 vs. 0.736, p = 0.038; sensitivity: 70.4% vs. 57.4%, p = 0.015; specificity: 80.3% vs. 86.9%, p = 0.052). DL attention maps could visualize peritumoral high-risk areas with genuine histopathologic confirmation. Both DL models could stratify high and low-risk groups regarding progression free survival and overall survival (p < 0.05). Thus, DL can be an efficient tool for MVI prediction, and EOB-MRI was proven to be the modality with advantage for MVI assessment than CE-CT.

Deep learning-based radiomics predicts response to chemotherapy in colorectal liver metastases.

PURPOSE: The purpose of this study was to develop and validate a deep learning (DL)-based radiomics model to predict the response to chemotherapy in colorectal liver metastases (CRLM). METHODS: In this retrospective study, we enrolled 192 patients diagnosed with CRLM who received first-line chemotherapy and were followed by response assessment. Tumor response was identified according to the Response Evaluation Criteria in Solid Tumors (RECIST). Contrast-enhanced multidetector computed tomography (MDCT) images were fed as inputs of the ResNet10-based DL radiomics model, and the possibility of response was predicted as the output. The final combined DL radiomics model was constructed by integrating the response-related clinical factors and the developed DL radiomics signature. A time-independent validation cohort (n = 48) was extracted from the 192 patients to evaluate the DL model with area under the receiver operating characteristic curve (AUC), specificity, and sensitivity. Meanwhile, a traditional radiomics model was constructed using least absolute shrinkage and selection operator (lasso) as comparisons with the DL-based model. RESULTS: According to RECIST criteria, 131 patients were identified as responders with complete response, partial response, and stable disease, while 61 patients were nonresponders with progression disease. The selected predictive clinical factor turned out to be the carcinoembryonic antigen (CEA) level with AUC of 0.489 (95% confidence interval [CI], 0.380-0.599) and 0.558 (95% CI, 0.374-0.741) in the training and validation cohorts, respectively. The DL-based model provided better performance than the traditional classifier-based radiomics model with significantly higher AUC (training: 0.903 [95% CI, 0.851-0.955] vs 0.745 [95% CI, 0.659-0.831]; validation: 0.820 [95% CI, 0.681-0.959] vs 0.598 [95% CI, 0.422-0.774]). The combination of DL-based model with the CEA level provided slightly increased performance with AUC of 0.935 [95% CI, 0.897-0.973] in the training cohort and 0.830 [95% CI, 0.688-0.973] in the validation cohort. CONCLUSIONS: The developed DL-based radiomics model could improve the efficiency to predict the response to chemotherapy in CRLM, which may assist in subsequent personalized treatment decision-making in CRLM management.

Identification of Predominant Histopathological Growth Patterns of Colorectal Liver Metastasis by Multi-Habitat and Multi-Sequence Based Radiomics Analysis.

Purpose: Developing an MRI-based radiomics model to effectively and accurately predict the predominant histopathologic growth patterns (HGPs) of colorectal liver metastases (CRLMs). Materials and Methods: In this study, 182 resected and histopathological proven CRLMs of chemotherapy-naive patients from two institutions, including 123 replacement CRLMs and 59 desmoplastic CRLMs, were retrospectively analyzed. Radiomics analysis was performed on two regions of interest (ROI), the tumor zone and the tumor-liver interface (TLI) zone. Decision tree (DT) algorithm was used for radiomics modeling on each MR sequence, and fused radiomics model was constructed by combining the radiomics signature of each sequence. The clinical and combination models were developed through multivariate logistic regression method. The performance of the developed models was assessed by receiver operating characteristic (ROC) curves with indicators of area under curve (AUC), accuracy, sensitivity, and specificity. A nomogram was constructed to evaluate the discrimination, calibration, and usefulness. Results: The fused radiomicstumor and radiomicsTLI models showed better performance than any single sequence and clinical model. In addition, the radiomicsTLI model exhibited better performance than radiomicstumor model (AUC of 0.912 vs. 0.879) in internal validation cohort. The combination model showed good discrimination, and the AUC of nomogram was 0.971, 0.909, and 0.905 in the training, internal validation, and external validation cohorts, respectively. Conclusion: MRI-based radiomics method has high potential in predicting the predominant HGPs of CRLM. Preoperative non-invasive identification of predominant HGPs could further explore the ability of HGPs as a potential biomarker for clinical treatment strategy, reflecting different biological pathways.

MRI-Based Radiomics Signature: A Potential Biomarker for Identifying Glypican 3-Positive Hepatocellular Carcinoma.

BACKGROUND: Glypican 3 (GPC3) expression has proved to be a critical risk factor related to prognosis in hepatocellular carcinoma (HCC) patients. PURPOSE: To investigate the performance of MRI-based radiomics signature in identifying GPC3-positive HCC. STUDY TYPE: Retrospective. POPULATION: An initial cohort of 293 patients with pathologically confirmed HCC was involved in this study, and patients were randomly divided into training (195) and validation (98) cohorts. FIELD STRENGTH/SEQUENCES: Contrast-enhanced T1 -weight MRI was performed with a 1.5T scanner. ASSESSMENT: A total of 853 radiomic features were extracted from the volume imaging. Univariate analysis and Fisher scoring were utilized for feature reduction. Subsequently, forward stepwise feature selection and radiomics signature building were performed based on a support vector machine (SVM). Incorporating independent risk factors, a combined nomogram was developed by multivariable logistic regression modeling. STATISTICAL TESTS: The predictive performance of the nomogram was calculated using the area under the receive operating characteristic curve (AUC). Decision curve analysis (DCA) was applied to estimate the clinical usefulness. RESULTS: The radiomics signature consisting of 10 selected features achieved good prediction efficacy (training cohort: AUC = 0.879, validation cohort: AUC = 0.871). Additionally, the combined nomogram integrating independent clinical risk factor α-fetoprotein (AFP) and radiomics signature showed improved calibration and prominent predictive performance with AUCs of 0.926 and 0.914 in the training and validation cohorts, respectively. DATA CONCLUSION: The proposed MR-based radiomics signature is strongly related to GPC3-positive. The combined nomogram incorporating AFP and radiomics signature may provide an effective tool for noninvasive and individualized prediction of GPC3-positive in patients with HCC. J. MAGN. RESON. IMAGING 2020;52:1679-1687.

Accurate Preoperative Distinction of Intracranial Hemangiopericytoma From Meningioma Using a Multihabitat and Multisequence-Based Radiomics Diagnostic Technique.

Background: Intracranial hemangiopericytoma (IHPC) and meningioma are both meningeal neoplasms, but they have extremely different malignancy and outcomes. Because of their similar radiological characteristics, they are difficult to distinguish prior to surgery, leading to a high rate of misdiagnosis. Methods: We enrolled 292 patients (IHPC, 155; meningiomas, 137) with complete clinic-radiological and histopathological data, from a 10-year database established at Tiantan hospital. Radiomics analysis of tumor and peritumoral edema was performed on multisequence magnetic resonance images, and a fusion radiomics signature was generated using a machine-learning strategy. By combining clinic-radiological data with the fusion radiomics signature, we developed an integrated diagnostic approach that we named the IHPC and Meningioma Diagnostic Tool (HMDT). Results: The HMDT displayed remarkable diagnostic ability, with areas under the curve (AUCs) of 0.985 and 0.917 in the training and validation cohorts, respectively. The calibration curve showed excellent agreement between the diagnosis predicted by HMDT and the histological outcome, with p-values of 0.801 and 0.622 for the training and the validation cohorts, respectively. Cross-validation showed no statistical difference across three divisions of the cohort, with average AUCs of 0.980 and 0.941 for the training and validation cohorts, respectively. Stratification analysis showed consistent performance of the HMDT in distinguishing IHPC from highly misdiagnosed subgroups of grade I meningioma and angiomatous meningioma (AM) with AUCs of 0.913 and 0.914 in the validation cohorts for the two subgroups. Conclusions: By integrating clinic-radiological information with radiomics signature, the proposed HMDT could assist in preoperative diagnosis to distinguish IHPC from meningioma, providing the basis for strategic decisions regarding surgery.

Radiomics in liver diseases: Current progress and future opportunities.

Liver diseases, a wide spectrum of pathologies from inflammation to neoplasm, have become an increasingly significant health problem worldwide. Noninvasive imaging plays a critical role in the clinical workflow of liver diseases, but conventional imaging assessment may provide limited information. Accurate detection, characterization and monitoring remain challenging. With progress in quantitative imaging analysis techniques, radiomics emerged as an efficient tool that shows promise to aid in personalized diagnosis and treatment decision-making. Radiomics could reflect the heterogeneity of liver lesions via extracting high-throughput and high-dimensional features from multi-modality imaging. Machine learning algorithms are then used to construct clinical target-oriented imaging biomarkers to assist disease management. Here, we review the methodological process in liver disease radiomics studies in a stepwise fashion from data acquisition and curation, region of interest segmentation, liver-specific feature extraction, to task-oriented modelling. Furthermore, the applications of radiomics in liver diseases are outlined in aspects of diagnosis and staging, evaluation of liver tumour biological behaviours, and prognosis according to different disease type. Finally, we discuss the current limitations of radiomics in liver disease studies and explore its future opportunities.