Computer‐aided diagnosis program for classifying the risk of hepatocellular carcinoma on MR images following liver imaging reporting and data system (LI‐RADS)

Kim, Youngwoo; Furlan, Alessandro; Borhani, Amir A.; Bae, Kyongtae T.

doi:10.1002/jmri.25772

Cited by 16 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In liver cancer, this has been mostly based on computed tomography to make predictions such as survival, prognosis, and recurrence (12)(13)(14). For MRI in liver cancer, radiomics has been used to classify focal liver lesions (15)(16)(17)(18), and as LI-RADS (19) surrogate (20). Radiomics thus shows potential for usage in liver lesion characterization.…”

Section: Introductionmentioning

confidence: 99%

Automated differentiation of malignant and benign primary solid liver lesions on MRI: an externally validated radiomics model

Starmans

Miclea

Vilgrain

et al. 2021

Preprint

View full text Add to dashboard Cite

Background & Aims: Distinguishing malignant from benign primary solid liver lesions is highly important for treatment planning. However, diagnosis on radiological imaging is challenging. In this study, we developed a radiomics model based on magnetic resonance imaging (MRI) to distinguish the most common malignant and benign primary solid liver lesions, and externally validated the model in two centers. Approach & Results: Datasets were retrospectively collected from three tertiary referral centers (A, B and C) including data from affiliated hospitals sent for revision. Patients with malignant (hepatocellular carcinoma and intrahepatic cholangiocarcinoma) and benign (hepatocellular adenoma and focal nodular hyperplasia) lesions were included. For each patient, only a T2-weighted MRI was included. A radiomics model was developed on dataset A using a combination of machine learning approaches, and internally evaluated on dataset A through cross-validation. Next, the model was externally validated on datasets B and C, and compared to scoring by two experienced abdominal radiologists on dataset C. In the resulting dataset, in total, 486 patients were included (A: 187, B: 98 and C: 201). Despite substantial MRI acquisition heterogeneity, the radiomics model developed on dataset A had a mean area under the receiver operating characteristic curve (AUC) of 0.78 in the internal validation on dataset A, and a similar AUC in the external validations (B: 0.74, C: 0.76). In dataset C, the two radiologists showed moderate agreement (Cohens κ: 0.61) and achieved AUCs of 0.86 and 0.82, respectively. Conclusions: Our radiomics model using T2-weighted MRI only can non-invasively distinguish malignant from benign primary solid liver lesions. External validation indicated that our model is generalizable despite substantial differences in the acquisition protocols.

show abstract

Section: Introductionmentioning

confidence: 99%

Automated differentiation of malignant and benign primary solid liver lesions on MRI: an externally validated radiomics model

Starmans

Miclea

Vilgrain

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Radiomics, the automated high-throughput extraction and analysis of quantitative and phenotypic features from radiographic images [107] , has emerged as a non-invasive tool for diagnosis and prognostication in several cancers, including HCC [108] . Qualitative and quantitative radiomics features may predict HCC recurrence and treatment response [109] , and are promising as novel biomarkers that may be complementary to existing serum biomarkers for HCC surveillance and treatment response assessment.…”

Section: Future Directions For Imaging In Hccmentioning

confidence: 99%

Role of imaging in management of hepatocellular carcinoma: surveillance, diagnosis, and treatment response

Osho¹,

Rich²,

Singal³

2020

View full text Add to dashboard Cite

Imaging plays a notable role in hepatocellular carcinoma (HCC) surveillance, diagnosis, and treatment response assessment. Whereas HCC surveillance among at-risk patients, including those with cirrhosis, has traditionally been ultrasound-based, there are increasing data showing that this strategy is operator-dependent and has insufficient sensitivity when used alone. Several novel blood-based and imaging modalities are currently being evaluated to increase sensitivity for early HCC detection. Multi-phase computed tomography (CT) or contrastenhanced magnetic resonance imaging (MRI) should be performed in patients with positive surveillance tests to confirm a diagnosis of HCC and perform cancer staging, as needed. HCC is a unique cancer in that most cases can be diagnosed radiographically without histological confirmation when demonstrating characteristic features such as arterial phase hyperenhancement and delayed phase washout. The Liver Imaging Reporting and Data System offers a standardized nomenclature for reporting CT or MRI liver findings among at-risk patients. Finally, crosssectional imaging plays a critical role for assessing response to any HCC therapy as well as monitoring for HCC recurrence in those who achieve complete response.

show abstract

“…Kim et al [47] developed and evaluated a CAD program for hepatic lesions on MRI for the classification of HCC risk according to the LI-RADS criteria. MRI images of the livers of 41 patients with hyperenhancing liver lesions classified as LR 3, 4 and 5 were evaluated by two radiologists.…”

Section: In the Futurementioning

confidence: 99%

Diagnostic imaging for hepatocellular carcinoma

Santis¹,

Gallusi²

2019

View full text Add to dashboard Cite

Hepatocellular carcinoma (HCC) occurs mostly in individuals with cirrhosis, which is why the guidelines of the most important scientific societies indicate that these patients are included in surveillance programs through the repetition of an ultrasound examination every 6 months. The aim is to achieve early identification of the neoplasia in order to increase the possibility of curative therapies (liver transplantation, surgery or local ablative therapies) and to increase patient survival. HCC nodules arising in cirrhotic livers show characteristic angiographic behavior that can be evaluated with dynamic multidetector computed tomography and dynamic magnetic resonance imaging (MRI). However, the use of these techniques in real life is often hindered by the lack of uniform terminology in reporting and in the interpretation of the exams reflected in the impossibility of comparing examinations performed in different centers and/or at different times. Liver Imaging Reporting and Data System® was created to standardize reporting and data collection of computed tomography and MRI for HCC. In some cases HCC arises in patients with healthy livers and, although there is evidence that angiographic behavior is not different from cirrhotic patients in this clinical situation, the guidelines still indicate the execution of a biopsy. Frequent use of palliative therapeutic techniques such as transarterial chemoembolization, transarterial radioembolization or administration of antiangiogenic drugs (sorafenib) poses problems of interpretation of the therapeutic response with repercussions on the subsequent choices that have been attempted to resolve with the use of stringent criteria such as Modified Response Evaluation Criteria In Solid Tumors.

show abstract

Computer‐aided diagnosis program for classifying the risk of hepatocellular carcinoma on MR images following liver imaging reporting and data system (LI‐RADS)

Abstract: 1 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2018;47:710-722.

Cited by 16 publications

References 31 publications

Automated differentiation of malignant and benign primary solid liver lesions on MRI: an externally validated radiomics model

Automated differentiation of malignant and benign primary solid liver lesions on MRI: an externally validated radiomics model

Role of imaging in management of hepatocellular carcinoma: surveillance, diagnosis, and treatment response

Diagnostic imaging for hepatocellular carcinoma

Contact Info

Product

Resources

About