18F-FDG PET/CT radiomic analysis for classifying and predicting microvascular invasion in hepatocellular carcinoma and intrahepatic cholangiocarcinoma

Immunotherapy and targeted therapy for cholangiocarcinoma: Artificial intelligence research in imaging

Cholangiocarcinoma (CCA) is a highly aggressive hepatobiliary malignancy, second only to hepatocellular carcinoma in prevalence. Despite surgical treatment being the recommended method to achieve a cure, it is not viable for patients with advanced CCA. Gene sequencing and artificial intelligence (AI) have recently opened up new possibilities in CCA diagnosis, treatment, and prognosis assessment. Basic research has furthered our understanding of the tumor-immunity microenvironment and revealed targeted molecular mechanisms, resulting in immunotherapy and targeted therapy being increasingly employed in the clinic. Yet, the application of these remedies in CCA is a challenging endeavor due to the varying pathological mechanisms of different CCA types and the lack of expressed immune proteins and molecular targets in some patients. AI in medical imaging has emerged as a powerful tool in this situation, as machine learning and deep learning are able to extract intricate data from CCA lesion images while assisting clinical decision making, and ultimately improving patient prognosis. This review summarized and discussed the current immunotherapy and targeted therapy related to CCA, and the research progress of AI in this field.

Prediction of preoperative microvascular invasion by dynamic radiomic analysis based on contrast-enhanced computed tomography

PURPOSE

Microvascular invasion (MVI) is a common complication of hepatocellular carcinoma (HCC) surgery, which is an important predictor of reduced surgical prognosis. This study aimed to develop a fully automated diagnostic model to predict pre-surgical MVI based on four-phase dynamic CT images.

METHODS

A total of 140 patients with HCC from two centers were retrospectively included (training set, n = 98; testing set, n = 42). All CT phases were aligned to the portal venous phase, and were then used to train a deep-learning model for liver tumor segmentation. Radiomics features were extracted from the tumor areas of original CT phases and pairwise subtraction images, as well as peritumoral features. Lastly, linear discriminant analysis (LDA) models were trained based on clinical features, radiomics features, and hybrid features, respectively. Models were evaluated by area under curve (AUC), accuracy, sensitivity, specificity, positive and negative predictive values (PPV and NPV).

RESULTS

Overall, 86 and 54 patients with MVI- (age, 55.92 ± 9.62 years; 68 men) and MVI+ (age, 53.59 ± 11.47 years; 43 men) were included. Average dice coefficients of liver tumor segmentation were 0.89 and 0.82 in training and testing sets, respectively. The model based on radiomics (AUC = 0.865, 95% CI: 0.725-0.951) showed slightly better performance than that based on clinical features (AUC = 0.841, 95% CI: 0.696-0.936). The classification model based on hybrid features achieved better performance in both training (AUC = 0.955, 95% CI: 0.893-0.987) and testing sets (AUC = 0.913, 95% CI: 0.785-0.978), compared with models based on clinical and radiomics features (p-value < 0.05). Moreover, the hybrid model also provided the best accuracy (0.857), sensitivity (0.875), and NPV (0.917).

CONCLUSION

The classification model based on multimodal intra- and peri-tumoral radiomics features can well predict HCC patients with MVI.

Clinical application of 18F-fluorodeoxyglucose positron emission tomography/computed tomography radiomics-based machine learning analyses in the field of oncology

Machine learning (ML) analyses using 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT) radiomics features have been applied in the field of oncology. The current review aimed to summarize the current clinical articles about 18F-FDG PET/CT radiomics-based ML analyses to solve issues in classifying or constructing prediction models for several types of tumors. In these studies, lung and mediastinal tumors were the most commonly evaluated lesions, followed by lymphatic, abdominal, head and neck, breast, gynecological, and other types of tumors. Previous studies have commonly shown that 18F-FDG PET radiomics-based ML analysis has good performance in differentiating benign from malignant tumors, predicting tumor characteristics and stage, therapeutic response, and prognosis by examining significant differences in the area under the receiver operating characteristic curves, accuracies, or concordance indices (> 0.70). However, these studies have reported several ML algorithms. Moreover, different ML models have been applied for the same purpose. Thus, various procedures were used in 18F-FDG PET/CT radiomics-based ML analysis in oncology, and 18F-FDG PET/CT radiomics-based ML models, which are easy and universally applied in clinical practice, would be expected to be established.

Perineural invasion confers poorer clinical outcomes in patients with T1/T2 intrahepatic cholangiocarcinoma: a single center, retrospective cohort study

Background

Intrahepatic cholangiocarcinoma (ICC) poses a significant clinical challenge, demanding a thorough understanding of prognostic indicators for effective patient management. Despite reports suggesting the impact of perineural invasion (PNI) on the prognosis of early-stage ICC patients, there has been a dearth of comprehensive research specifically targeting this subgroup. This study seeks to investigate the influence of PNI on survival outcomes in early-stage ICC patients and aims to enhance the prognostic value of the American Joint Committee on Cancer (AJCC) T category.

Methods

A cohort of 268 early-stage (T1-T2N0M0) ICC patients, who underwent curative-intent resection (R0) between 2011 and 2015 at the Eastern Hepatobiliary Surgery Hospital, were enrolled in this study. Lasso and Cox regression analyses were employed to explore differences in clinical and prognostic data. Kaplan-Meier curves were generated to illustrate the clinical significance of the combination of PNI and T category.

Results

Among the 268 patients, 24.6% exhibited PNI. Patients with PNI demonstrated shorter recurrence-free survival (RFS) [median RFS: 16 months (interquartile range, 9.5-19 months)] and overall survival (OS) [median OS: 16.53 months (interquartile range, 10-25 months)]. PNI emerged as an independent risk factor for both RFS and OS in T1- and T2-stage patients (all P<0.05), whereas tumor size was only an independent risk factor for OS (P=0.004). PNI was associated with all prognostic markers for ICC patients, including gender, jaundice, cholangitis, hepatitis B virus (HBV) infection, cancer antigen 199 (CA199), preoperative serum albumin, and preoperative platelet count (all P<0.05). However, there was no significant difference in RFS (P=0.270) and OS (P=0.360) between T2 patients without PNI and T1 patients with PNI.

Conclusions

This study underscores PNI as a robust prognostic factor in early-stage ICC, emphasizing the necessity of incorporating PNI into the AJCC T category for precise risk stratification. Clinically, understanding the impact of PNI on survival outcomes can guide tailored treatment strategies for early ICC patients.

Nuclear medicine radiomics in digestive system tumors: Concept, applications, challenges, and future perspectives

Radiomics aims to develop novel biomarkers and provide relevant deeper subvisual information about pathology, immunophenotype, and tumor microenvironment. It uses automated or semiautomated quantitative analysis of high-dimensional images to improve characterization, diagnosis, and prognosis. Recent years have seen a rapid increase in radiomics applications in nuclear medicine, leading to some promising research results in digestive system oncology, which have been driven by big data analysis and the development of artificial intelligence. Although radiomics advances one step further toward the non-invasive precision medical analysis, it is still a step away from clinical application and faces many challenges. This review article summarizes the available literature on digestive system tumors regarding radiomics in nuclear medicine. First, we describe the workflow and steps involved in radiomics analysis. Subsequently, we discuss the progress in clinical application regarding the utilization of radiomics for distinguishing between various diseases and evaluating their prognosis, and demonstrate how radiomics advances this field. Finally, we offer our viewpoint on how the field can progress by addressing the challenges facing clinical implementation.

Predicting the microvascular invasion and tumor grading of intrahepatic mass-forming cholangiocarcinoma based on magnetic resonance imaging radiomics and morphological features

Background

Preoperative diagnosis of microvascular invasion (MVI) and tumor grading of intrahepatic mass-forming cholangiocarcinoma (IMCC) using imaging findings can facilitate patient treatment decision-making. This study was conducted to establish and validate nomograms based on magnetic resonance imaging (MRI) radiomics and morphological features for predicting the MVI and tumor grading of IMCC before radical hepatectomy.

Methods

A total of 235 patients with resected IMCC at the Chinese Academy of Medical Sciences and Peking Union Medical College were divided into a training set (n=167) and a validation set (n=68), retrospectively. Clinical data and MRI morphological features were recorded. Univariate and multivariate analyses were conducted to identify the significant features for the prediction of MVI and tumor grading. Radiomics features were extracted from T2-weighted imaging fat-suppressed and diffusion-weighted imaging (DWI). Radiomics signatures (rad_scores) were built based on the least absolute shrinkage and selection operator (LASSO) method. Then, the nomograms were constructed by combining the rad_scores and the significant clinical or MRI morphologic features. The predictive performances for MVI and tumor grading were evaluated by the area under the receiver operating characteristic curve (AUC), calibration, and clinical utility.

Results

Totals of 16 and 9 radiomics features were selected to build the rad_scores for the prediction of MVI and tumor grading for the training and validation set, respectively. The nomogram for the prediction of MVI comprised the morphologic features including number of tumors, tumor margin, and rad_score. For the prediction of tumor grading, the nomogram comprised the number of tumors, tumor necrosis, and rad_score. The best discriminations were observed in the training and validation sets for the MVI nomogram [AUCs of 0.874, 95% confidence interval (CI): (0.822-0.926) and 0.869 (0.783-0955)] and tumor grading nomogram [AUCs of 0.827 (0.763-0.891) and 0.848 (0.759-0.937)]. Decision curve analysis (DCA) further confirmed the clinical utilities of the nomograms.

Conclusions

Nomograms based on MRI radiomics and morphological features can effectively predict the individualized risks of MVI and tumor grading for IMCC.

Differentiation of Hepatocellular Carcinoma from Intrahepatic Cholangiocarcinoma through MRI Radiomics

The purpose of this study was to investigate the efficacy of magnetic resonance imaging (MRI) radiomics in differentiating hepatocellular carcinoma (HCC) from intrahepatic cholangiocarcinoma (ICC). The clinical and MRI data of 129 pathologically confirmed HCC patients and 48 ICC patients treated at the Affiliated Hospital of North Sichuan Medical College between April 2016 and December 2021 were retrospectively analyzed. The patients were randomly divided at a ratio of 7:3 into a training group of 124 patients (90 with HCC and 34 with ICC) and a validation group of 53 patients (39 with HCC and 14 with ICC). Radiomic features were extracted from axial fat suppression T2-weighted imaging (FS-T2WI) and axial arterial-phase (AP) and portal-venous-phase (PVP) dynamic-contrast-enhanced MRI (DCE-MRI) sequences, and the corresponding datasets were generated. The least absolute shrinkage and selection operator (LASSO) method was used to select the best radiomic features. Logistic regression was used to establish radiomic models for each sequence (FS-T2WI, AP and PVP models), a clinical model for optimal clinical variables (C model) and a joint radiomics model (JR model) integrating the radiomics features of all the sequences as well as a radiomics-clinical model combining optimal radiomic features and clinical risk factors (RC model). The performance of each model was evaluated using the area under the receiver operating characteristic curve (AUC). The AUCs of the FS-T2WI, AP, PVP, JR, C and RC models for distinguishing HCC from ICC were 0.693, 0.863, 0.818, 0.914, 0.936 and 0.977 in the training group and 0.690, 0.784, 0.727, 0.802, 0.860 and 0.877 in the validation group, respectively. The results of this study suggest that MRI-based radiomics may help noninvasively differentiate HCC from ICC. The model integrating the radiomics features and clinical risk factors showed a further improvement in performance.

Effect of multiple peritumoral regions of interest ranges based on computed tomography radiomics for the prediction of early recurrence of hepatocellular carcinoma after resection

Background

Early recurrence (ER) of hepatocellular carcinoma (HCC) is defined as recurrence that occurs within two years after resection. Our study aimed to determine the optimal peritumoral regions of interest (ROI) range by comparing the effect of multiple peritumoral radiomics ROIs on predicting ER of HCC, and to develop and validate a combined clinical-radiomics prediction model.

Methods

A total of 160 HCC patients were randomly divided into a training cohort (n=112) and a validation cohort (n=48). The intratumoral original ROI was outlined based on enhanced computed tomography images and then used as the base to sequentially extend outward 1-5 mm to form peritumoral ROI. We developed a logistic regression model to predict ER of HCC. The efficacy of different ROI prediction models was compared to determine the optimal ROI. The combined model divided the patients into a high-risk group and low-risk group.

Results

Ninety-seven (60.6%) of the patients were ER; the remaining 63 (39.4%) were not ER. The area under the curve values and 95% confidence intervals for ROI 3 were 0.867 (0.802-0.933) and 0.807 (0.682-0.931) in the training and validation cohorts, respectively, and ROI 3 was identified as the optimal ROI. Multivariate logistic regression analysis determined microvascular invasion (MVI) (P=0.037) and alpha-fetoprotein (AFP) (P=0.013) to be independent risk factors for ER. The combined clinical-radiomic model containing the radiomics score, MVI, and AFP had the optimal predictive efficacy, with area under the curve values and 95% confidence intervals of 0.903 (0.848-0.957) and 0.830 (0.709-0.952) in the training and validation cohort, respectively. Subgroup analysis showed significantly ER predicted in the high-risk group than the low-risk group (P<0.001).

Conclusions

Peritumoral radiomics 3 mm range was determined as the optimal ROI in this study. The clinical-radiomics combined models can effectively stratify high- and low-risk patients for timely clinical treatment and decision making.

Revolutionising hepatocellular carcinoma surveillance: Harnessing contrast-enhanced ultrasound and serological indicators for postoperative early recurrence prediction

This study aimed to develop a noninvasive predictive model for identifying early postoperative recurrence of hepatocellular carcinoma (within 2 years after surgery) based on contrast-enhanced ultrasound and serum biomarkers. Additionally, the model's validity was assessedthrough internal and external validation. Clinical data were collected from patients who underwent liver resection at the First Hospital of Quanzhou and Mengchao Hepatobiliary Hospital. The data included general information, contrast-enhanced ultrasound parameters, Liver Imaging Reporting and Data System (LI-RADS) classification, and serum biomarkers. The data from Mengchao Hospital were divided into 2 groups, with a ratio of 6:4, to form the modeling and internal validation sets, respectively. On the other hand, the data from the First Hospital of Quanzhou served as the external validation group. The developed model was named the Hepatocellular Carcinoma Early Recurrence (HCC-ER) prediction model. The predictive efficiency of the HCC-ER model was compared with other established models. The baseline characteristics were found to be well-balanced across the modeling, internal validation, and external validation groups. Among the independent risk factors identified for early recurrence, LI-RADS classification, alpha-fetoprotein, and tumor maximum diameter exhibited hazard ratios of 1.352, 1.337, and 1.135 respectively. Regarding predictive accuracy, the HCC-ER, Tumour-Node-Metastasis, Barcelona Clinic Liver Cancer, and China Liver Cancer models demonstrated prediction errors of 0.196, 0.204, 0.201, and 0.200 in the modeling group; 0.215, 0.215, 0.218, and 0.212 in the internal validation group; 0.210, 0.215, 0.216, and 0.221 in the external validation group. Using the HCC-ER model, risk scores were calculated for all patients, and a cutoff value of 50 was selected. This cutoff effectively distinguished the high-risk recurrence group from the low-risk recurrence group in the modeling, internal validation, and external validation groups. However, the calibration curve of the predictive model slightly overestimated the risk of recurrence. The HCC-ER model developed in this study demonstrated high accuracy in predicting early recurrence within 2 years after hepatectomy. It provides valuable information for developing precise treatment strategies in clinical practice and holds considerable promise for further clinical implementation.

Precise localization of microvascular invasion in hepatocellular carcinoma based on three-dimensional histology-MR image fusion: an ex vivo experimental study

Background

Microvascular invasion (MVI) is an independent risk factor for postoperative recurrence of hepatocellular carcinoma (HCC). However, MVI cannot be detected by conventional imaging. To localize MVI precisely on magnetic resonance (MR) images, we evaluated the feasibility and accuracy of 3-dimensional (3D) histology-MR image fusion of the liver.

Methods

Animal models of VX2 liver tumors were established in 10 New Zealand white rabbits under ultrasonographic guidance. The whole liver lobe containing the VX2 tumor was extracted and divided into 4 specimens, for a total of 40 specimens. MR images were obtained with a T2-weighted sequence for each specimen, and then histological images were obtained by intermittent, serial pathological sections. 3D histology-MR image fusion was performed via landmark registration in 3D Slicer software. We calculated the success rate and registration errors of image fusion, and then we located the MVI on MR images. Regarding influencing factors, we evaluated the uniformity of tissue thickness after sampling and the uniformity of tissue shrinkage after dehydration.

Results

The VX2 liver tumor model was successfully established in the 10 rabbits. The incidence of MVI was 80% (8/10). 3D histology-MR image fusion was successfully performed in the 39 specimens, and the success rate was 97.5% (39/40). The average registration error was 0.44±0.15 mm. MVI was detected in 20 of the 39 successfully registered specimens, resulting in a total of 166 MVI lesions. The specific location of all MVI lesions was accurately identified on MR images using 3D histology-MR image fusion. All MVI lesions showed as slightly hyperintense on the high-resolution MR T2-weighted images. The results of the influencing factor assessment showed that the tissue thickness was uniform after sampling (P=0.38), but the rates of the tissue shrinkage was inconsistent after dehydration (P<0.001).

Conclusions

3D histology-MR image fusion of the isolated liver tumor model is feasible and accurate and allows for the successful identification of the specific location of MVI on MR images.

Development of a novel tumor microenvironment-related radiogenomics model for prognosis prediction in hepatocellular carcinoma

Background

The tumour microenvironment (TME) has occupied a potent position in the tumorigenesis and tumor progression of hepatocellular carcinoma (HCC). Radiogenomics is an emerging field that integrates imaging and genetic information, thus offering a novel class of non-invasive biomarkers with diagnostic, prognostic, and treatment response. However, optimal evaluation methodologies for radiogenomics in patients with HCC have not been well established. Therefore, this study aims to develop a radiogenomics models, associating contrast-enhanced computed tomography (CECT) based radiomics features and transcriptomics data with TME, to increase predictive precision for overall survival (OS) in patients with HCC.

Methods

Transcriptome profiles of 365 patients with HCC from The Cancer Genome Atlas (TCGA)-HCC cohort were used to obtain TME-related genes by differential expression analysis. TME-related radiomics features of 53 patients with HCC from The Cancer Imaging Archive (TCIA)-HCC cohort matched with the TCGA-HCC cohort were screened via correlation analysis. Furthermore, a radiogenomics score-based prognostic model was constructed using the least absolute shrinkage and selection operator (LASSO) Cox regression analysis in the TCIA-HCC cohort. Finally, the ability to predict prognosis and the value of the model in identifying the abundance of immune cell infiltration were investigated.

Results

A radiogenomics prognostic model was developed, which incorporated 1 radiomics feature [original_gray-level co-occurrence matrix (glcm)_inverse difference normalized (Idn)] and 3 genes [spen paralogue and orthologue C‑terminal domain containing 1 (SPOCD1); killer cell lectin like receptor B1 (KLRB1); G protein-coupled receptor 182 (GPR182)]. The model performed satisfactorily in the training and test sets [1-year, 2-year, 3-year area under the curve (AUC) of 0.81, 0.85 and 0.87 in the training set, respectively; and 0.73, 0.83, and 0.84 in the test set, respectively]. Moreover, the model showed that higher radiogenomics scores were associated with worse OS and lower levels of immune infiltration.

Conclusions

The novel CECT-based radiogenomics model may provide valuable insights for prognostic stratification and TME assessment of patients with HCC.

Differential diagnosis of hepatocellular carcinoma and intrahepatic cholangiocarcinoma based on spatial and channel attention mechanisms

BACKGROUND

The pre-operative non-invasive differential diagnosis of hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC) mainly depends on imaging. However, the accuracy of conventional imaging and radiomics methods in differentiating between the two carcinomas is unsatisfactory. In this study, we aimed to establish a novel deep learning model based on computed tomography (CT) images to provide an effective and non-invasive pre-operative differential diagnosis method for HCC and ICC.

MATERIALS AND METHODS

We retrospectively investigated the CT images of 395 HCC patients and 99 ICC patients who were diagnosed based on pathological analysis. To differentiate between HCC and ICC we developed a deep learning model called CSAM-Net based on channel and spatial attention mechanisms. We compared the proposed CSAM-Net with conventional radiomic models such as conventional logistic regression, least absolute shrinkage and selection operator regression, support vector machine, and random forest models.

RESULTS

With respect to differentiating between HCC and ICC, the CSAM-Net model showed area under the receiver operating characteristic curve (AUC) values of 0.987 (accuracy = 0.939), 0.969 (accuracy = 0.914), and 0.959 (accuracy = 0.912) for the training, validation, and test sets, respectively, which were significantly higher than those of the conventional radiomics models (0.736-0.913 [accuracy = 0.735-0.912], 0.602-0.828 [accuracy = 0.647-0.818], and 0.638-0.845 [accuracy = 0.618-0.849], respectively. The decision curve analysis showed a high net benefit of the CSAM-Net model, which suggests potential efficacy in differentiating between HCC and ICC in the diagnosis of liver cancers.

CONCLUSIONS

The proposed CSAM-Net model based on channel and spatial attention mechanisms provides an effective and non-invasive tool for the differential diagnosis of HCC and ICC on CT images, and has potential applications in diagnosis of liver cancers.

The application of 18F-FDG PET/CT imaging for human hepatocellular carcinoma: a narrative review

Background and Objective

Primary hepatocellular carcinoma (HCC) poses a significant threat to human health. The mean overall survival (OS) of HCC is approximately 15.8 months whereas the 6-month and 1-year OS rates are only 71.6% and 49.7%, respectively. 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) has been widely used for the management of several solid cancers; however, HCC frequently displays low 18F-FDG uptake; approximately 50% of HCC cases do not take up 18F-FDG. Therefore, 18F-FDG PET is not considered very useful for the visualization of HCC and is not currently a recommended standard imaging modality for HCC. Conversely, 18F-FDG PET/CT has been reported to be clinically important in the management, staging, and prognosis of HCC patients. Currently, reports relating to 18F-FDG uptake in HCC are unclear and controversial. There is an urgent need to clarify the efficacy of 18F-FDG PET for the management of HCC.

Methods

The PubMed database was searched for all articles on the application of 18F-FDG PET/CT imaging for human HCC up to December 2021. The following search terms were used: 'Hepatocellular carcinoma', '[18F]FDG PET/CT', 'Hypoxia', '[11C]Choline'.

Key Content and Findings

In this review, we re-evaluate the potential hypoxia-dependent uptake mechanism of 18F-FDG in HCC and review the usefulness of 18F-FDG PET/CT for identifying, managing, and investigating the biological properties of HCC.

Conclusions

18F-FDG PET/CT is very useful for HCC visualization, management, and the evaluation of biological properties. A negative test for 18F-FDG uptake is not meaningless and may reflect a relatively better outcome. 18F-FDG-positive lesions indicate a significantly less favorable prognosis.

Contrast-Enhanced Imaging in the Management of Intrahepatic Cholangiocarcinoma: State of Art and Future Perspectives

Intrahepatic cholangiocarcinoma (iCCA) represents the second most common liver cancer after hepatocellular carcinoma, accounting for 15% of primary liver neoplasms. Its incidence and mortality rate have been rising during the last years, and total new cases are expected to increase up to 10-fold during the next two or three decades. Considering iCCA's poor prognosis and rapid spread, early diagnosis is still a crucial issue and can be very challenging due to the heterogeneity of tumor presentation at imaging exams and the need to assess a correct differential diagnosis with other liver lesions. Abdominal contrast-enhanced computed tomography (CT) and magnetic resonance imaging (MRI) plays an irreplaceable role in the evaluation of liver masses. iCCA's most typical imaging patterns are well-described, but atypical features are not uncommon at both CT and MRI; on the other hand, contrast-enhanced ultrasound (CEUS) has shown a great diagnostic value, with the interesting advantage of lower costs and no renal toxicity, but there is still no agreement regarding the most accurate contrastographic patterns for iCCA detection. Besides diagnostic accuracy, all these imaging techniques play a pivotal role in the choice of the therapeutic approach and eligibility for surgery, and there is an increasing interest in the specific imaging features which can predict tumor behavior or histologic subtypes. Further prognostic information may also be provided by the extraction of quantitative data through radiomic analysis, creating prognostic multi-parametric models, including clinical and serological parameters. In this review, we aim to summarize the role of contrast-enhanced imaging in the diagnosis and management of iCCA, from the actual issues in the differential diagnosis of liver masses to the newest prognostic implications.

Modality-based attention and dual-stream multiple instance convolutional neural network for predicting microvascular invasion of hepatocellular carcinoma

Background and purpose

The presence of microvascular invasion (MVI) is a crucial indicator of postoperative recurrence in patients with hepatocellular carcinoma (HCC). Detecting MVI before surgery can improve personalized surgical planning and enhance patient survival. However, existing automatic diagnosis methods for MVI have certain limitations. Some methods only analyze information from a single slice and overlook the context of the entire lesion, while others require high computational resources to process the entire tumor with a three-dimension (3D) convolutional neural network (CNN), which could be challenging to train. To address these limitations, this paper proposes a modality-based attention and dual-stream multiple instance learning(MIL) CNN.

Materials and methods

In this retrospective study, 283 patients with histologically confirmed HCC who underwent surgical resection between April 2017 and September 2019 were included. Five magnetic resonance (MR) modalities including T2-weighted, arterial phase, venous phase, delay phase and apparent diffusion coefficient images were used in image acquisition of each patient. Firstly, Each two-dimension (2D) slice of HCC magnetic resonance image (MRI) was converted into an instance embedding. Secondly, modality attention module was designed to emulates the decision-making process of doctors and helped the model to focus on the important MRI sequences. Thirdly, instance embeddings of 3D scans were aggregated into a bag embedding by a dual-stream MIL aggregator, in which the critical slices were given greater consideration. The dataset was split into a training set and a testing set in a 4:1 ratio, and model performance was evaluated using five-fold cross-validation.

Results

Using the proposed method, the prediction of MVI achieved an accuracy of 76.43% and an AUC of 74.22%, significantly surpassing the performance of the baseline methods.

Conclusion

Our modality-based attention and dual-stream MIL CNN can achieve outstanding results for MVI prediction.

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.

Personalized intrahepatic cholangiocarcinoma prognosis prediction using radiomics: Application and development trend

Radiomics was proposed by Lambin et al. in 2012 and since then there has been an explosion of related research. There has been significant interest in developing high-throughput methods that can automatically extract a large number of quantitative image features from medical images for better diagnostic or predictive performance. There have also been numerous radiomics investigations on intrahepatic cholangiocarcinoma in recent years, but no pertinent review materials are readily available. This work discusses the modeling analysis of radiomics for the prediction of lymph node metastasis, microvascular invasion, and early recurrence of intrahepatic cholangiocarcinoma, as well as the use of deep learning. This paper briefly reviews the current status of radiomics research to provide a reference for future studies.

18F-FDG PET/CT imaging of pediatric peripheral neuroblastic tumor: a combined model to predict the International Neuroblastoma Pathology Classification

Background

The aim of this study was to evaluate the effect of a model combining a 18F-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT)-based radiomics signature with clinical factors in the preoperative prediction of the International Neuroblastoma Pathology Classification (INPC) type of pediatric peripheral neuroblastic tumor (pNT).

Methods

A total of 106 consecutive pediatric pNT patients confirmed by pathology were retrospectively analyzed. Significant features determined by multivariate logistic regression were retained to establish a clinical model (C-model), which included clinical parameters and PET/CT radiographic features. A radiomics model (R-model) was constructed on the basis of PET and CT images. A semiautomatic method was used for segmenting regions of interest. A total of 1,016 radiomics features were extracted. Univariate analysis and the least absolute shrinkage selection operator were then used to select significant features. The C-model was combined with the R-model to establish a combination model (RC-model). The predictive performance was validated by receiver operating characteristic (ROC) curve analysis, calibration curves, and decision curve analysis (DCA) in both the training cohort and validation cohort.

Results

The radiomics signature was constructed using 5 selected radiomics features. The RC-model, which was based on the 5 radiomics features and 3 clinical factors, showed better predictive performance compared with the C-model alone [area under the curve in the validation cohort: 0.908 vs. 0.803; accuracy: 0.903 vs. 0.710; sensitivity: 0.895 vs. 0.789; specificity: 0.917 vs. 0.583; net reclassification improvement (NRI) 0.439, 95% confidence interval (CI): 0.1047-0.773; P=0.01]. The calibration curve showed that the RC-model had goodness of fit, and DCA confirmed its clinical utility.

Conclusions

In this preliminary single-center retrospective study, an R-model based on ¹⁸F-FDG PET/CT was shown to be promising in predicting INPC type in pediatric pNT, allowing for the noninvasive prediction of INPC and assisting in therapeutic strategies.