TED: Two-stage expert-guided interpretable diagnosis framework for microvascular invasion in hepatocellular carcinoma

Pathological Priors Inspired Network for Vertebral Osteophytes Recognition

Automatic vertebral osteophyte recognition in Digital Radiography is of great importance for the early prediction of degenerative disease but is still a challenge because of the tiny size and high inter-class similarity between normal and osteophyte vertebrae. Meanwhile, common sampling strategies applied in Convolution Neural Network could cause detailed context loss. All of these could lead to an incorrect positioning predicament. In this paper, based on important pathological priors, we define a set of potential lesions of each vertebra and propose a novel Pathological Priors Inspired Network (PPIN) to achieve accurate osteophyte recognition. PPIN comprises a backbone feature extractor integrating with a Wavelet Transform Sampling module for high-frequency detailed context extraction, a detection branch for locating all potential lesions and a classification branch for producing final osteophyte recognition. The Anatomical Map-guided Filter between two branches helps the network focus on the specific anatomical regions via the generated heatmaps of potential lesions in the detection branch to address the incorrect positioning problem. To reduce the inter-class similarity, a Bilateral Augmentation Module based on the graph relationship is proposed to imitate the clinical diagnosis process and to extract discriminative contextual information between adjacent vertebrae in the classification branch. Experiments on the two osteophytes-specific datasets collected from the public VinDr-Spine database show that the proposed PPIN achieves the best recognition performance among multitask frameworks and shows strong generalization. The results on a private dataset demonstrate the potential in clinical application. The Class Activation Maps also show the powerful localization capability of PPIN. The source codes are available in https://github.com/Phalo/PPIN.

Multitask deep learning for prediction of microvascular invasion and recurrence-free survival in hepatocellular carcinoma based on MRI images

BACKGROUND AND AIMS

Accurate preoperative prediction of microvascular invasion (MVI) and recurrence-free survival (RFS) is vital for personalised hepatocellular carcinoma (HCC) management. We developed a multitask deep learning model to predict MVI and RFS using preoperative MRI scans.

METHODS

Utilising a retrospective dataset of 725 HCC patients from seven institutions, we developed and validated a multitask deep learning model focused on predicting MVI and RFS. The model employs a transformer architecture to extract critical features from preoperative MRI scans. It was trained on a set of 234 patients and internally validated on a set of 58 patients. External validation was performed using three independent sets (n = 212, 111, 110).

RESULTS

The multitask deep learning model yielded high MVI prediction accuracy, with AUC values of 0.918 for the training set and 0.800 for the internal test set. In external test sets, AUC values were 0.837, 0.815 and 0.800. Radiologists' sensitivity and inter-rater agreement for MVI prediction improved significantly when integrated with the model. For RFS, the model achieved C-index values of 0.763 in the training set and ranged between 0.628 and 0.728 in external test sets. Notably, PA-TACE improved RFS only in patients predicted to have high MVI risk and low survival scores (p < .001).

CONCLUSIONS

Our deep learning model allows accurate MVI and survival prediction in HCC patients. Prospective studies are warranted to assess the clinical utility of this model in guiding personalised treatment in conjunction with clinical criteria.

Vascularized organoid-on-a-chip: design, imaging, and analysis

Vascularized organoid-on-a-chip (VOoC) models achieve substance exchange in deep layers of organoids and provide a more physiologically relevant system in vitro. Common designs for VOoC primarily involve two categories: self-assembly of endothelial cells (ECs) to form microvessels and pre-patterned vessel lumens, both of which include the hydrogel region for EC growth and allow for controlled fluid perfusion on the chip. Characterizing the vasculature of VOoC often relies on high-resolution microscopic imaging. However, the high scattering of turbid tissues can limit optical imaging depth. To overcome this limitation, tissue optical clearing (TOC) techniques have emerged, allowing for 3D visualization of VOoC in conjunction with optical imaging techniques. The acquisition of large-scale imaging data, coupled with high-resolution imaging in whole-mount preparations, necessitates the development of highly efficient analysis methods. In this review, we provide an overview of the chip designs and culturing strategies employed for VOoC, as well as the applicable optical imaging and TOC methods. Furthermore, we summarize the vascular analysis techniques employed in VOoC, including deep learning. Finally, we discuss the existing challenges in VOoC and vascular analysis methods and provide an outlook for future development.

MRI-Based Radiomics and Deep Learning in Biological Characteristics and Prognosis of Hepatocellular Carcinoma: Opportunities and Challenges

Hepatocellular carcinoma (HCC) is the fifth most common malignancy and the third leading cause of cancer-related death worldwide. HCC exhibits strong inter-tumor heterogeneity, with different biological characteristics closely associated with prognosis. In addition, patients with HCC often distribute at different stages and require diverse treatment options at each stage. Due to the variability in tumor sensitivity to different therapies, determining the optimal treatment approach can be challenging for clinicians prior to treatment. Artificial intelligence (AI) technology, including radiomics and deep learning approaches, has emerged as a unique opportunity to improve the spectrum of HCC clinical care by predicting biological characteristics and prognosis in the medical imaging field. The radiomics approach utilizes handcrafted features derived from specific mathematical formulas to construct various machine-learning models for medical applications. In terms of the deep learning approach, convolutional neural network models are developed to achieve high classification performance based on automatic feature extraction from images. Magnetic resonance imaging offers the advantage of superior tissue resolution and functional information. This comprehensive evaluation plays a vital role in the accurate assessment and effective treatment planning for HCC patients. Recent studies have applied radiomics and deep learning approaches to develop AI-enabled models to improve accuracy in predicting biological characteristics and prognosis, such as microvascular invasion and tumor recurrence. Although AI-enabled models have demonstrated promising potential in HCC with biological characteristics and prognosis prediction with high performance, one of the biggest challenges, interpretability, has hindered their implementation in clinical practice. In the future, continued research is needed to improve the interpretability of AI-enabled models, including aspects such as domain knowledge, novel algorithms, and multi-dimension data sources. Overcoming these challenges would allow AI-enabled models to significantly impact the care provided to HCC patients, ultimately leading to their deployment for clinical use. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 2.

Vision-Guided Attention-Enhanced Network for Predicting Microvascular Invasion in Hepatocellular Carcinoma

As the most common malignant tumor worldwide, hepatocellular carcinoma (HCC) has a high rate of death and recurrence, and microvascular invasion (MVI) is considered to be an independent risk factor affecting its early recurrence and poor survival rate. Accurate preoperative prediction of MVI is of great significance for the formulation of individualized treatment plans and long-term prognosis assessment for HCC patients. However, as the mechanism of MVI is still unclear, existing studies use deep learning methods to directly train CT or MR images, with limited predictive performance and lack of explanation. We map the pathological "7-point" baseline sampling method used to confirm the diagnosis of MVI onto MR images, propose a vision-guided attention-enhanced network to improve the prediction performance of MVI, and validate the prediction on the corresponding pathological images reliability of the results. Specifically, we design a learnable online class activation map (CAM) to guide the network to focus on high-incidence regions of MVI guided by an extended tumor mask. Further, an attention-enhanced module is proposed to force the network to learn image regions that can explain the MVI results. The generated attention maps capture long-distance dependencies and can be used as spatial priors for MVI to promote the learning of vision-guided module. The experimental results on the constructed multi-center dataset show that the proposed algorithm achieves the state-of-the-art compared to other models.

Ultrasound radiomics in the prediction of microvascular invasion in hepatocellular carcinoma: A systematic review and meta-analysis

Purpose

To systematically assess the clinical value of ultrasound radiomics in the prediction of microvascular invasion in hepatocellular carcinoma (HCC).

Methods

Relevant articles were searched in PubMed, Web of Science, Cochrane Library, Embase and Medline and screened according to the eligibility criteria. The quality of the included articles was assessed based on the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool. After article assessment and data extraction, the diagnostic performance of ultrasound radiomics was evaluated based on pooled sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR) and diagnostic odds ratio (DOR), and the area under the curve (AUC) was calculated by generating the ROC curve. Meta-analysis was performed using Stata 15.1, and subgroup analysis was conducted to identify the sources of heterogeneity. A Fagan nomogram was generated to assess the clinical utility of ultrasound radiomics.

Results

Five studies involving 1260 patients were included. Meta-analysis showed that ultrasound radiomics had a pooled sensitivity of 79% (95% CI: 75-83%), specificity of 70% (95% CI: 59-79%), PLR of 2.6 (95% CI: 1.9-3.7), NLR of 0.30 (95% CI: 0.23-0.39), DOR of 9 (95% CI: 5-16), and AUC of 0.81 (95% CI: 0.78-0.85). Sensitivity analysis indicated that the results were statistically reliable and stable, and no significant difference was identified during subgroup analysis.

Conclusion

Ultrasound radiomics has favorable predictive performance in the microvascular invasion of HCC and may serve as an auxiliary tool for guiding clinical decision-making.

Local-to-global spatial learning for whole-slide image representation and classification

Whole-slide image (WSI) provides an important reference for clinical diagnosis. Classification with only WSI-level labels can be recognized for multi-instance learning (MIL) tasks. However, most existing MIL-based WSI classification methods have moderate performance on correlation mining between instances limited by their instance- level classification strategy. Herein, we propose a novel local-to-global spatial learning method to mine global position and local morphological information by redefining the MIL-based WSI classification strategy, better at learning WSI-level representation, called Global-Local Attentional Multi-Instance Learning (GLAMIL). GLAMIL can focus on regional relationships rather than single instances. It first learns relationships between patches in the local pool to aggregate region correlation (tissue types of a WSI). These correlations then can be further mined to fulfill WSI-level representation, where position correlation between different regions can be modeled. Furthermore, Transformer layers are employed to model global and local spatial information rather than being simply used as feature extractors, and the corresponding structure improvements are present. In addition, we evaluate GIAMIL on three benchmarks considering various challenging factors and achieve satisfactory results. GLAMIL outperforms state-of-the-art methods and baselines by about 1 % and 10 %, respectively.

MVI-TR: A Transformer-Based Deep Learning Model with Contrast-Enhanced CT for Preoperative Prediction of Microvascular Invasion in Hepatocellular Carcinoma

In this study, we considered preoperative prediction of microvascular invasion (MVI) status with deep learning (DL) models for patients with early-stage hepatocellular carcinoma (HCC) (tumor size ≤ 5 cm). Two types of DL models based only on venous phase (VP) of contrast-enhanced computed tomography (CECT) were constructed and validated. From our hospital (First Affiliated Hospital of Zhejiang University, Zhejiang, P.R. China), 559 patients, who had histopathological confirmed MVI status, participated in this study. All preoperative CECT were collected, and the patients were randomly divided into training and validation cohorts at a ratio of 4:1. We proposed a novel transformer-based end-to-end DL model, named MVI-TR, which is a supervised learning method. MVI-TR can capture features automatically from radiomics and perform MVI preoperative assessments. In addition, a popular self-supervised learning method, the contrastive learning model, and the widely used residual networks (ResNets family) were constructed for fair comparisons. With an accuracy of 99.1%, a precision of 99.3%, an area under the curve (AUC) of 0.98, a recalling rate of 98.8%, and an F1-score of 99.1% in the training cohort, MVI-TR achieved superior outcomes. Additionally, the validation cohort's MVI status prediction had the best accuracy (97.2%), precision (97.3%), AUC (0.935), recalling rate (93.1%), and F1-score (95.2%). MVI-TR outperformed other models for predicting MVI status, and showed great preoperative predictive value for early-stage HCC patients.

VICT2 Trait: Prognostic Alternative to Peritumoral Hepatobiliary Phase Hypointensity in HCC

Background Peritumoral hepatobiliary phase (HBP) hypointensity is an established prognostic imaging feature in hepatocellular carcinoma (HCC), often associated with microvascular invasion (MVI). Similar prognostic features are needed for non-HBP MRI. Purpose To propose a non-hepatobiliary-specific MRI tool with similar prognostic value to peritumoral HBP hypointensity. Materials and Methods From December 2011 to November 2021, consecutive patients with HCC who underwent preoperative contrast-enhanced MRI were retrospectively enrolled and followed up until recurrence. All MRI scans were reviewed by two blinded radiologists with 7 and 10 years of experiences with liver MRI. A scoring system based on non-hepatobiliary-specific features that highly correlated with peritumoral HBP hypointensity was identified in a stratified sampling-derived training set of the gadoxetate disodium (EOB) group by means of multivariable logistic regression, and its values to predict MVI and recurrence-free survival (RFS) were assessed. Results There were 660 patients (551 men; median age, 53 years; IQR, 45-61 years) enrolled. Peritumoral portal venous phase hypoenhancement (odds ratio [OR] = 8.8), incomplete "capsule" (OR = 3.3), corona enhancement (OR, 2.6), and peritumoral mild-moderate T2 hyperintensity (OR, 2.2) (all P < .001) were associated with peritumoral HBP hypointensity and constituted the "VICT2 trait" (test set area under the receiver operating characteristic curve = 0.84; 95% CI: 0.78, 0.90). For the EOB group, both peritumoral HBP hypointensity (OR for MVI = 2.5, P = .02; hazard ratio for RFS = 2.5, P < .001) and the VICT2 trait (OR for MVI = 5.1, P < .001; hazard ratio for RFS = 2.3, P < .001) were associated with MVI and RFS, despite a higher specificity of the VICT2 trait for MVI (89% vs 80%, P = .01). These values of the VICT2 trait were confirmed in the extracellular contrast agent group (OR for MVI = 4.0; hazard ratio for RFS = 1.7; both P < .001). Conclusion Based on four non-hepatobiliary-specific MRI features, the VICT2 trait was comparable to peritumoral hepatobiliary phase hypointensity in predicting microvascular invasion and postoperative recurrence of hepatocellular carcinoma. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Harmath in this issue.

Preoperative and Prognostic Prediction of Microvascular Invasion in Hepatocellular Carcinoma: A Review Based on Artificial Intelligence

Microvascular invasion of hepatocellular carcinoma is an important factor affecting tumor recurrence after liver resection and liver transplantation. There are many ways to classify microvascular invasion, however, an international consensus is urgently needed. Recently, artificial intelligence has emerged as an important tool for improving the clinical management of hepatocellular carcinoma. Many studies about microvascular invasion currently focus on preoperative and prognosis prediction of microvascular invasion using artificial intelligence. In this paper, we review the definition and staging of microvascular invasion, especially the diagnosis of it by using artificial intelligence. In preoperative prediction, deep learning based on multimodal data modeling of radiomics-screened features, clinical features, and medical images is currently the most effective means. In prognostic prediction, pathology is the gold standard, and the techniques used should more effectively utilize the global features of the pathology images.

Role of radiomics in the diagnosis and treatment of gastrointestinal cancer

Gastrointestinal cancer (GIC) has high morbidity and mortality as one of the main causes of cancer death. Preoperative risk stratification is critical to guide patient management, but traditional imaging studies have difficulty predicting its biological behavior. The emerging field of radiomics allows the conversion of potential pathophysiological information in existing medical images that cannot be visually recognized into high-dimensional quantitative image features. Tumor lesion characterization, therapeutic response evaluation, and survival prediction can be achieved by analyzing the relationships between these features and clinical and genetic data. In recent years, the clinical application of radiomics to GIC has increased dramatically. In this editorial, we describe the latest progress in the application of radiomics to GIC and discuss the value of its potential clinical applications, as well as its limitations and future directions.