Multi-Center Follow-up Study to Develop a Classification System Which Differentiates Mucinous Cystic Neoplasm of the Liver and Benign Hepatic Cyst Using Machine Learning

Benign biliary conditions with increased risk of malignant lesions

Numerous conditions and pathologies affect the biliary system, many of which have underlying benign courses. However, these overall benign conditions can predispose the patient to malignant pathologies, often due to malignancy arising from abnormal biliary ducts (such as with cholangiocarcinoma) or due to malignancy arising from end-stage liver disease caused by the biliary condition (such as with hepatocellular carcinoma). While these malignancies can at times be obvious, some pathologies can be very difficult to detect and distinguish from the underlying benign biliary etiology. This paper discusses various benign biliary pathologies, with discussion of epidemiology, imaging features, malignant potential, and treatment considerations, with the goal of educating radiologists and referring clinicians to the risk and appearance of hepatobiliary malignancies associated with benign biliary conditions.

Artificial intelligence for detection and characterization of focal hepatic lesions: a review

Focal liver lesions (FLL) are common incidental findings in abdominal imaging. While the majority of FLLs are benign and asymptomatic, some can be malignant or pre-malignant, and need accurate detection and classification. Current imaging techniques, such as computed tomography (CT) and magnetic resonance imaging (MRI), play a crucial role in assessing these lesions. Artificial intelligence (AI), particularly deep learning (DL), offers potential solutions by analyzing large data to identify patterns and extract clinical features that aid in the early detection and classification of FLLs. This manuscript reviews the diagnostic capacity of AI-based algorithms in processing CT and MRIs to detect benign and malignant FLLs, with an emphasis in the characterization and classification of these lesions and focusing on differentiating benign from pre-malignant and potentially malignant lesions. A comprehensive literature search from January 2010 to April 2024 identified 45 relevant studies. The majority of AI systems employed convolutional neural networks (CNNs), with expert radiologists providing reference standards through manual lesion delineation, and histology as the gold standard. The studies reviewed indicate that AI-based algorithms demonstrate high accuracy, sensitivity, specificity, and AUCs in detecting and characterizing FLLs. These algorithms excel in differentiating between benign and malignant lesions, optimizing diagnostic protocols, and reducing the needs of invasive procedures. Future research should concentrate on the expansion of data sets, the improvement of model explainability, and the validation of AI tools across a range of clinical setting to ensure the applicability and reliability of such tools.

Differentiation between mucinous cystic neoplasms and simple cysts of the liver: a systematic review and meta-analysis

PURPOSE

Radiologic examinations frequently identify cystic liver lesions, which encompass various entities from simple benign cysts to malignant neoplasms. This work analyses the available data to compare diagnostic features of biliary cystic neoplasms and hepatic simple cysts.

METHODS

A systematic search of PubMed, Scopus, Embase, and Web of Science up to October 2024 was conducted. The characteristics were categorized into hepatic simple cysts (HSC) and mucinous cystic neoplasms (MCN), including biliary cystadenoma (BCA) and cystadenocarcinoma (BCAC) detected by imaging modalities including ultrasound, CT scans with IV contrast, or MRI. We analyzed biliary cystic neoplasms and hepatic simple cysts across multiple studies using Review Manager Ver. 5, calculating summary measures for each feature.

RESULTS

The study analyzed 577 lesions in 577 patients and 49 studies. Hepatic simple cysts were the most common finding, with 349 identified, mainly in the right hepatic lobe, presented with abdominal pain or incidentally. Intracystic septation was found in 50.1% of HSC lesions, with thick septation in 10.52% of lesions. 228 (49.9%) patients were diagnosed with MCN, with abdominal swelling and pain as the most common presentation. Septation was the most common radiological feature of MCNs, with thick septa in 50.61%. MCNs had internal septa, solid mural nodule, upstream bile duct dilation, presence in the left hepatic lobe, septal thickening, cystic wall enhancement, calcifications, and internal debris. The presence of a cyst in the left lobe was more related to MCNs.

CONCLUSION

Characterizing cystic liver lesions necessitates a comprehensive evaluation of the lesions' location, size, and complexity. Imaging and clinical findings are essential for a final diagnosis.

Refining imaging criteria for mucinous cystic neoplasm of the liver: simplified diagnostic approach

OBJECTIVES

To propose a simplified diagnostic approach for mucinous cystic neoplasm (MCN) of the liver and compare its diagnostic performance with the European Association for the Study of the Liver (EASL) criteria.

METHODS

We conducted a retrospective cohort study of 124 patients with pathologically confirmed lesions (13 MCNs, 111 hepatic cysts) who underwent CT/MRI between January 2016 and January 2023. Two major features (thick septation, nodularity) and five minor features (upstream biliary dilatation, thin septations, internal hemorrhage, perfusion change, < 3 coexistent hepatic cysts) of the EASL criteria were evaluated. For a septa-wall relationship, the angle of indentation was measured, and the optimal angle predicting MCN was determined by receiver operating characteristic curve analysis. Logistic regression identified features predicting MCN, and a modified criteria was developed. The sensitivity, specificity, and accuracy of both criteria were compared using McNemar's test.

RESULTS

The optimal indentation angle was 111°. Absence of indentation or indentation at an angle > 111° (odds ratio (OR), 100.4; 95% confidence interval (CI), 4.9-2076.0) and < 3 coexistent hepatic cysts (OR, 47.8; 95% CI, 1.5-1489.1) were independent features predicting MCN. Our modified criteria used a combination of them and demonstrated greater accuracy (98.4% vs. 92.7%; p = 0.035) than the EASL criteria (a combination of ≥ 1 major and ≥ 1 minor feature[s]), with comparable sensitivity (92.3% vs. 76.9%; p = 0.317) and specificity (99.1% vs. 94.6%; p = 0.059).

CONCLUSION

Our modified criteria using two imaging features may be a promising alternative to current EASL criteria to improve accuracy in diagnosing MCN.

KEY POINTS

Question Radiological diagnosis of mucinous cystic neoplasm of the liver remains challenging due to the lack of specific imaging features, leading to suboptimal treatment decisions. Findings No external indentation or an indentation angle > 111° and fewer than 3 coexistent hepatic cysts are independent factors predicting mucinous cystic neoplasm of the liver. Clinical relevance The simplified approach using these two imaging features for diagnosing mucinous cystic neoplasm of the liver offers improved accuracy and reliability over the 2022 EASL criteria, potentially reducing misdiagnosis and unnecessary surgeries.

To develop a classification system which helps differentiate cystic intraductal papillary neoplasm of the bile duct from mucinous cystic neoplasm of the liver

OBJECTIVE

To establish a classification system which differentiates cystic intraductal papillary neoplasm of the bile duct (cystic IPNB) from hepatic mucinous cystic tumors (MCN) based on their radiological difference.

METHODS

A total of 75 patients pathologically diagnosed as MCN and IPNB in two major hospitals from 2015 to 2024 were enrolled. Radiological features were recorded and compared between these two tumors. Variables with significant differences were included in multivariate logistic regression (LR) analysis. A decision model was built and simplified based on importance ranking of variables. K-nearest-neighbor (KNN) model was introduced to learn distribution of individuals in main dimensions based on multiple correspondence analysis (MCA) and predicted diagnosis. The diagnostic efficacy of the classification system and the KNN model was compared.

RESULTS

Significant differences existed in Dmax-IVC angle, septation, mural nodule, upstream and downstream biliary dilatation, communication with bile duct between MCN and cystic IPNB. Downstream biliary dilatation and communication with bile duct were highly specific for IPNB (specificity, 97.9 % and 100 %, respectively), which could independently diagnose IPNB. Among four significant indicators in LR analysis, upstream biliary dilatation and Dmax-IVC angle were used for a simplified decision model to attain good applicability. The KNN model based on MCA data achieved highest accuracy (0.910) when K = 11. Overall, the classification system achieved an AUC of 0.882 (0.95CI: 0.797-0.966), compared with 0.911 (0.95CI: 0.818-1.000) in the KNN model, which demonstrated no significant difference (p = 0.655) in differential performance.

CONCLUSION

The classification system combining four important indicators had equivalent performance to KNN model in discrimination, which was simple and applicable for clinical practice, and also accessible on unenhanced examinations.

WFUMB Review Paper. Incidental Findings in Otherwise Healthy Subjects, How to Manage: Liver

An incidental focal liver lesion (IFLL) is defined as a hepatic lesion identified in a patient imaged for an unrelated reason. They are frequently encountered in daily practice, sometimes leading to unnecessary, invasive and potentially harmful follow-up investigations. The clinical presentation and the imaging aspects play an important role in deciding if, and what further evaluation, is needed. In low-risk patients (i.e., without a history of malignant or chronic liver disease or related symptoms), especially in those younger than 40 years old, more than 95% of IFLLs are likely benign. Shear Wave liver Elastography (SWE) of the surrounding liver parenchyma should be considered to exclude liver cirrhosis and for further risk stratification. If an IFLL in a low-risk patient has a typical appearance on B-mode ultrasound of a benign lesion (e.g., simple cyst, calcification, focal fatty change, typical hemangioma), no further imaging is needed. Contrast-Enhanced Ultrasound (CEUS) should be considered as the first-line contrast imaging modality to differentiate benign from malignant IFLLs, since it has a similar accuracy to contrast-enhanced (CE)-MRI. On CEUS, hypoenhancement of a lesion in the late vascular phase is characteristic for malignancy. CE-CT should be avoided for characterizing probable benign FLL and reserved for staging once a lesion is proven malignant. In high-risk patients (i.e., with chronic liver disease or an oncological history), each IFLL should initially be considered as potentially malignant, and every effort should be made to confirm or exclude malignancy. US-guided biopsy should be considered in those with unresectable malignant lesions, particularly if the diagnosis remains unclear, or when a specific tissue diagnosis is needed.

To identify important MRI features to differentiate hepatic mucinous cystic neoplasms from septated hepatic cysts based on random forest

OBJECTIVE

To identify important MRI features to differentiate hepatic mucinous cystic neoplasms (MCN) from septated hepatic cysts (HC) using random forest and compared with logistic regression algorithm.

METHODS

Pathologically diagnosed hepatic cysts and hepatic MCNs with pre-operative contrast-enhanced MRI in our hospital from 2010 to 2023 were collected and only septated lesions on enhanced MRI were enrolled. A total of 21 septated HC and 18 MCNs were included in this study. Eighteen MRI features were analyzed and top important features were identified based on random forest (RF) algorithm. The results were evaluated by the prediction performance of a RF model combining the important features and compared with the performance of the logistic regression (LR) algorithm. Finally, for each identified feature, diagnostic probability, sensitivity, and specificity were calculated and compared.

RESULTS

Four variables, i.e., the septation arising from wall without indentation, multiseptate, intracapsular cyst sign, and solitary lesion were extracted as top important features with significance for MCNs by the random forest algorithm. The RF model using these variables had an AUC of 0.982 (0.95CI, 0.950-1.000), compared with the LR model based on two identified features with AUC of 0.931 (0.95CI, 0.846-1.000), p = 0.202. Among the four important features, multiseptate had the highest specificity (95.2%) and good sensitivity (72.2%, lower than the septation from wall without indentation, 94.4%) to diagnose MCNs.

CONCLUSION

Four out of 18 MRI features were extracted as reliably important factors to differ hepatic MCNs from septated HC. The combination of these four features in a RF model could achieve satisfactory diagnostic efficacy.

Artificial Intelligence in Radiology: Opportunities and Challenges

Artificial intelligence's (AI) emergence in radiology elicits both excitement and uncertainty. AI holds promise for improving radiology with regards to clinical practice, education, and research opportunities. Yet, AI systems are trained on select datasets that can contain bias and inaccuracies. Radiologists must understand these limitations and engage with AI developers at every step of the process - from algorithm initiation and design to development and implementation - to maximize benefit and minimize harm that can be enabled by this technology.

The Use of Artificial Intelligence in the Liver Histopathology Field: A Systematic Review

Digital pathology (DP) has begun to play a key role in the evaluation of liver specimens. Recent studies have shown that a workflow that combines DP and artificial intelligence (AI) applied to histopathology has potential value in supporting the diagnosis, treatment evaluation, and prognosis prediction of liver diseases. Here, we provide a systematic review of the use of this workflow in the field of hepatology. Based on the PRISMA 2020 criteria, a search of the PubMed, SCOPUS, and Embase electronic databases was conducted, applying inclusion/exclusion filters. The articles were evaluated by two independent reviewers, who extracted the specifications and objectives of each study, the AI tools used, and the results obtained. From the 266 initial records identified, 25 eligible studies were selected, mainly conducted on human liver tissues. Most of the studies were performed using whole-slide imaging systems for imaging acquisition and applying different machine learning and deep learning methods for image pre-processing, segmentation, feature extractions, and classification. Of note, most of the studies selected demonstrated good performance as classifiers of liver histological images compared to pathologist annotations. Promising results to date bode well for the not-too-distant inclusion of these techniques in clinical practice.

External validation of a machine learning based algorithm to differentiate hepatic mucinous cystic neoplasms from benign hepatic cysts

PURPOSE

To externally validate an algorithm for non-invasive differentiation of hepatic mucinous cystic neoplasms (MCN) from benign hepatic cysts (BHC), which differ in management.

METHODS

Patients with cystic liver lesions pathologically confirmed as MCN or BHC between January 2005 and March 2022 from multiple institutions were retrospectively included. Five readers (2 radiologists, 3 non-radiologist physicians) independently reviewed contrast-enhanced CT or MRI examinations before tissue sampling and applied the 3-feature classification algorithm described by Hardie et al. to differentiate between MCN and BHC, which had a reported accuracy of 93.5%. The classification was then compared to the pathology results. Interreader agreement between readers across different levels of experience was evaluated with Fleiss' Kappa.

RESULTS

The final cohort included 159 patients, median age of 62 years (IQR [52.0, 70.0]), 66.7% female (106). Of all patients, 89.3% (142) had BHC, and the remaining 10.7% (17) had MCN on pathology. Agreement for class designation between the radiologists was almost perfect (Fleiss' Kappa 0.840, p < 0.001). The algorithm had an accuracy of 98.1% (95% CI [94.6%, 99.6%]), a positive predictive value of 100.0% (95% CI [76.8%, 100.0%]), a negative predictive value of 97.9% (95% CI [94.1%, 99.6%]), and an area under the receiver operator characteristic curve (AUC) of 0.911 (95% CI [0.818, 1.000]).

CONCLUSION

The evaluated algorithm showed similarly high diagnostic accuracy in our external, multi-institutional validation cohort. This 3-feature algorithm is easily and rapidly applied and its features are reproducible among radiologists, showing promise as a clinical decision support tool.

Mucinous Cystic Neoplasms of the Liver: Epidemiology, Diagnosis, and Management

Mucinous cystic neoplasms (MCNs) are rare tumors of the liver, occasionally seen in the biliary tree. Epidemiologic data are limited by their indolence and recent changes to diagnostic criteria. They are considered premalignant lesions capable of invasive behavior. While their etiology remains unknown, their female predominance, age of onset, and hormonally responsive ovarian-type stroma suggest ectopic organogenesis during embryologic development. MCNs can typically be recognized on imaging; yet, invasiveness is often indeterminate, and percutaneous tissue biopsy has shown limited value. Therefore, complete excision is recommended for all lesions as focal malignant transformation and metastatic disease has been reported.

A Machine Learning Applied Diagnosis Method for Subcutaneous Cyst by Ultrasonography

For decades, ultrasound images have been widely used in the detection of various diseases due to their high security and efficiency. However, reading ultrasound images requires years of experience and training. In order to support the diagnosis of clinicians and reduce the workload of doctors, many ultrasonic computer aided diagnostic systems have been proposed. In recent years, the success of deep learning in image classification and segmentation has made more and more scholars realize the potential performance improvement brought by the application of deep learning in ultrasonic computer-aided diagnosis systems. This study is aimed at applying several machine learning algorithms and develop a machine learning method to diagnose subcutaneous cyst. Clinical features are extracted from datasets and images of ultrasonography of 132 patients from Hunan Provincial People's Hospital in China. All datasets are separated into 70% training and 30% testing. Four kinds of machine learning algorithms including decision tree (DT), support vector machine (SVM), K-nearest neighbors (KNN), and neural networks (NN) had been approached to determine the best performance. Compared with all the results from each feature, SVM achieved the best performance from 91.7% to 100%. Results show that SVM performed the highest accuracy in the diagnosis of subcutaneous cyst by ultrasonography, which provide a good reference in further application to clinical practice of ultrasonography of subcutaneous cyst.