Role of Contrast-Enhanced Ultrasonography in Hepatocellular Carcinoma by Using LI-RADS and Ancillary Features: A Single Tertiary Centre Experience

Impact of the COVID-19 Pandemic on Gut Cancer Admissions and Management: A Comparative Study of Two Pandemic Years to a Similar Pre-Pandemic Period

Background/Objective: Gastrointestinal tract cancers may have been severely affected by the COVID-19 pandemic. The limitations of digestive endoscopy, the fear effect, and restrictions on hospital admissions during the pandemic may have delayed the presentation of patients to hospitals and surgical procedures and may have impacted overall survival. Methods: We conducted an observational, cross-sectional study of esophageal, gastric, small bowel, and colorectal cancer patients admitted to our hospital between 1 January 2018 and 31 December 2021. We analyzed the hospitalization rates, pathological type, the onset by complications, staging, and surgery during the pandemic compared to a pre-pandemic period (January 2018-December 2019). Results: During 2018-2021, 1613 patients with malignant gut tumors were admitted to our hospital (112 esophageal and eso-cardial tumors, 419 gastric tumors, 34 small bowel tumors, and 1058 colorectal tumors). Admission was reduced by 30.3% for esophageal and eso-cardial malignant tumors, 27.6% for gastric tumors, and 17.3% for malignant colorectal tumors. For esophageal and eso-cardial tumors, a higher frequency of stenosing tumors and palliative gastrostomies was noted. More stage III gastric cancers and a lower rate of vascular invasion were recorded during the pandemic. No differences regarding small bowel tumors were noted. In colorectal tumors, slightly more stage II cancers and more stenosing tumors were recorded, but occlusive, bleeding, and perforated tumors were similar; also, surgical rates were similar, with a two-fold higher perioperative mortality. The overall survival of gastric and colorectal carcinoma was higher during the pandemic (but with no statistical significance), although a clear explanation has not emerged. Conclusions: The impact of the COVID-19 pandemic on gut cancer included a significantly lower rate of newly diagnosed admissions, more stage II colorectal and stage III gastric carcinomas, a two-fold higher perioperative mortality for colorectal carcinoma, and a trend for a surprisingly higher overall survival for gastric and colorectal tumors (but without statistical significance). Future research is necessary for assessing long-term impact.

Challenges in Diagnosing Focal Liver Lesions Using Contrast-Enhanced Ultrasound

Background: Contrast-enhanced ultrasound (CEUS) has become the preferred method for many clinicians in evaluating focal liver lesions (FLLs) initially identified through standard ultrasound. However, in clinical practice, certain lesions may deviate from the typical enhancement patterns outlined in EFSUMB guidelines. Methods: This study aims to assess FLLs that remained inconclusive or misdiagnosed after CEUS evaluation, spanning eight years of single-center experience. Following CEUS, all FLLs underwent secondary imaging (CT, MRI) or histopathological analysis for diagnostic confirmation. Results: From the initial 979 FLLs, 350 lesions (35.7%) were either inconclusive or misdiagnosed by CEUS, with hepatocellular carcinoma (HCC) and liver metastases constituting the majority of these cases. The most frequent enhancement pattern in inconclusive lesions at CEUS was hyper-iso-iso. Factors such as advanced liver fibrosis, adenomas, and cholangiocarcinoma were significantly associated with higher rates of diagnostic inaccuracies. Conclusions: Advanced liver fibrosis, adenomas, and cholangiocarcinoma were significantly associated with increased diagnostic challenges, emphasizing the need for supplementary imaging techniques.

Diagnostic Performance of an Artificial Intelligence Model Based on Contrast-Enhanced Ultrasound in Patients with Liver Lesions: A Comparative Study with Clinicians

Contrast-enhanced ultrasound (CEUS) is widely used in the characterization of liver tumors; however, the evaluation of perfusion patterns using CEUS has a subjective character. This study aims to evaluate the accuracy of an automated method based on CEUS for classifying liver lesions and to compare its performance with that of two experienced clinicians. The system used for automatic classification is based on artificial intelligence (AI) algorithms. For an interpretation close to the clinical setting, both clinicians knew which patients were at high risk for hepatocellular carcinoma (HCC), but only one was aware of all the clinical data. In total, 49 patients with 59 liver tumors were included. For the benign and malignant classification, the AI model outperformed both clinicians in terms of specificity (100% vs. 93.33%); still, the sensitivity was lower (74% vs. 93.18% vs. 90.91%). In the second stage of multiclass diagnosis, the automatic model achieved a diagnostic accuracy of 69.93% for HCC and 89.15% for liver metastases. Readers demonstrated greater diagnostic accuracy for HCC (83.05% and 79.66%) and liver metastases (94.92% and 96.61%) compared to the AI system; however, both were experienced sonographers. The AI model could potentially assist and guide less-experienced clinicians to discriminate malignant from benign liver tumors with high accuracy and specificity.

LI-RADS: Looking Back, Looking Forward

Since its initial release in 2011, the Liver Imaging Reporting and Data System (LI-RADS) has evolved and expanded in scope. It started as a single algorithm for hepatocellular carcinoma (HCC) diagnosis with CT or MRI with extracellular contrast agents and has grown into a multialgorithm network covering all major liver imaging modalities and contexts of use. Furthermore, it has developed its own lexicon, report templates, and supplementary materials. This article highlights the major achievements of LI-RADS in the past 11 years, including adoption in clinical care and research across the globe, and complete unification of HCC diagnostic systems in the United States. Additionally, the authors discuss current gaps in knowledge, which include challenges in surveillance, diagnostic population definition, perceived complexity, limited sensitivity of LR-5 (definite HCC) category, management implications of indeterminate observations, challenges in reporting, and treatment response assessment following radiation-based therapies and systemic treatments. Finally, the authors discuss future directions, which will focus on mitigating the current challenges and incorporating advanced technologies. Tha authors envision that LI-RADS will ultimately transform into a probability-based system for diagnosis and prognostication of liver cancers that will integrate patient characteristics and quantitative imaging features, while accounting for imaging modality and contrast agent.

An Automated Method for Classifying Liver Lesions in Contrast-Enhanced Ultrasound Imaging Based on Deep Learning Algorithms

Background: Contrast-enhanced ultrasound (CEUS) is an important imaging modality in the diagnosis of liver tumors. By using contrast agent, a more detailed image is obtained. Time-intensity curves (TIC) can be extracted using a specialized software, and then the signal can be analyzed for further investigations. Methods: The purpose of the study was to build an automated method for extracting TICs and classifying liver lesions in CEUS liver investigations. The cohort contained 50 anonymized video investigations from 49 patients. Besides the CEUS investigations, clinical data from the patients were provided. A method comprising three modules was proposed. The first module, a lesion segmentation deep learning (DL) model, handled the prediction of masks frame-by-frame (region of interest). The second module performed dilation on the mask, and after applying colormap to the image, it extracted the TIC and the parameters from the TIC (area under the curve, time to peak, mean transit time, and maximum intensity). The third module, a feed-forward neural network, predicted the final diagnosis. It was trained on the TIC parameters extracted by the second model, together with other data: gender, age, hepatitis history, and cirrhosis history. Results: For the feed-forward classifier, five classes were chosen: hepatocarcinoma, metastasis, other malignant lesions, hemangioma, and other benign lesions. Being a multiclass classifier, appropriate performance metrics were observed: categorical accuracy, F1 micro, F1 macro, and Matthews correlation coefficient. The results showed that due to class imbalance, in some cases, the classifier was not able to predict with high accuracy a specific lesion from the minority classes. However, on the majority classes, the classifier can predict the lesion type with high accuracy. Conclusions: The main goal of the study was to develop an automated method of classifying liver lesions in CEUS video investigations. Being modular, the system can be a useful tool for gastroenterologists or medical students: either as a second opinion system or a tool to automatically extract TICs.

LI-RADS LR-5 on contrast-enhanced ultrasonography has satisfactory diagnostic specificity for hepatocellular carcinoma: a systematic review and meta-analysis

Background

The Liver Imaging Reporting and Data System (LI-RADS) for contrast-enhanced ultrasonography (CEUS) was invented to define suspected liver nodules based on their imaging characteristics. Among the categories of nodules of LI-RADS for CEUS, LR-5 is generally considered to be definitely malignant; however, the exact diagnostic performance of this liver nodule category has varied between different studies. Therefore, we performed this systematic review and meta-analysis to calculate the pooled diagnostic sensitivity, specificity based on important data extracted from some influential clinical studies.

Methods

A preliminary search of national and international databases, including PubMed/Ovid Medline, Embase, Cochrane Library, Web of Science, and Wan Fang Data, for relevant studies on CEUS LI-RADS LR-5 published between January 2017 and June 2021 was conducted. A literature screening and selection process was undertaken to evaluate the relevance of the articles, and studies deemed eligible for inclusion in the review were subsequently identified. The updated Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool was applied as the main method to assess the risk of bias and applicability of the studies. A meta-analysis of the diagnostic sensitivity and specificity of CEUS LI-RADS LR-5 was performed using the free software, Meta-DiSc 1.4 (Ramóny Cajal Hospital, Madrid, Spain). The area under curve (AUC) was calculated to help determine the diagnostic efficiency. A meta-regression analysis was also performed to identify factors that could have contributed to heterogeneity between the studies.

Results

Twelve studies with 20 observations focused on investigating the relative diagnostic performance of the CEUS LI-RADS LR-5 category for hepatocellular carcinoma (HCC) detection were finally recruited into the systematic review and meta-analysis. The pooled diagnostic sensitivity was 0.71 [95% confidence interval (CI): 0.69-0.72], with heterogeneity (I²) of 88.4%, and the pooled specificity was 0.93 (95% CI: 0.92-0.95), with an I² of 71.2%. Study heterogeneity was observed and statistically correlated with the number of centers and the reference standard.

Conclusions

The CEUS LI-RADS LR-5 category has satisfactory diagnostic efficacy for HCC, as evidenced by an acceptable diagnostic sensitivity of 0.71 and a good diagnostic specificity of 0.93.

Deep Learning Algorithms in the Automatic Segmentation of Liver Lesions in Ultrasound Investigations

BACKGROUND

The ultrasound is one of the most used medical imaging investigations worldwide. It is non-invasive and effective in assessing liver tumors or other types of parenchymal changes.

METHODS

The aim of the study was to build a deep learning model for image segmentation in ultrasound video investigations. The dataset used in the study was provided by the University of Medicine and Pharmacy Craiova, Romania and contained 50 video examinations from 49 patients. The mean age of the patients in the cohort was 69.57. Regarding presence of a subjacent liver disease, 36.73% had liver cirrhosis and 16.32% had chronic viral hepatitis (5 patients: chronic hepatitis C and 3 patients: chronic hepatitis B). Frames were extracted and cropped from each examination and an expert gastroenterologist labelled the lesions in each frame. After labelling, the labels were exported as binary images. A deep learning segmentation model (U-Net) was trained with focal Tversky loss as a loss function. Two models were obtained with two different sets of parameters for the loss function. The performance metrics observed were intersection over union and recall and precision.

RESULTS

Analyzing the intersection over union metric, the first segmentation model obtained performed better compared to the second model: 0.8392 (model 1) vs. 0.7990 (model 2). The inference time for both models was between 32.15 milliseconds and 77.59 milliseconds.

CONCLUSIONS

Two segmentation models were obtained in the study. The models performed similarly during training and validation. However, one model was trained to focus on hard-to-predict labels. The proposed segmentation models can represent a first step in automatically extracting time-intensity curves from CEUS examinations.

Risk Stratification and Distribution of Hepatocellular Carcinomas in CEUS and CT/MRI LI-RADS: A Meta-Analysis

Background

CEUS LI-RADS and CT/MRI LI-RADS have been used in clinical practice for several years. However, there is a lack of evidence-based study to compare the proportion of hepatocellular carcinomas (HCCs) in each category and the distribution of HCCs of these two categorization systems.

Purpose

The purpose of this study was to compare the proportion of HCCs between corresponding CEUS LI-RADS and CT/MRI LI-RADS categories and the distribution of HCCs and non-HCC malignancies in each category.

Methods

We searched PubMed, Embase, and Cochrane Central databases from January 2014 to December 2021. The proportion of HCCs and non-HCC malignancies and the corresponding sensitivity, specificity, accuracy, diagnostic odds ratio (DOR), and area under the curve (AUC) of the LR-5 and LR-M categories were determined using a random-effect model.

Results

A total of 43 studies were included. The proportion of HCCs in CEUS LR-5 was 96%, and that in CECT/MRI LR-5 was 95% (p > 0.05). The proportion of non-HCC malignancy in CEUS LR-M was lower than that of CT/MRI LR-M (35% vs. 58%, p = 0.01). The sensitivity, specificity, and accuracy of CEUS LR-5 for HCCs were 73%, 92%, and 78%, respectively, and of CT/MRI LR-5 for HCCs, 69%, 92%, and 76%, respectively.

Conclusion

With the upshift of the LI-RADS category, the proportion of HCCs increased. CEUS LR-3 has a lower risk of HCCs than CT/MRI LR-3. CEUS LR-5 and CT/MRI LR-5 have a similar diagnostic performance for HCCs. CEUS LR-M has a higher proportion of HCCs and a lower proportion of non-HCC malignancies compared with CT/MRI LR-M.