Abstract #1942

Radiomics assessment of liver fibrosis in patients with chronic liver disease using MRI: a machine learning approach

Farzin Mobayyyen^1,2, Behrooz Taghvainia³, Hassan Homayoun², Ali Abbasian Ardakani⁴, Anahita Fathi Kazerooni², Hanieh Mobarak Salari², Nasser Rakhshani⁵, Hamidreza Salighehrad^1,2, and Hamid Reza haghighatkhah⁶

¹Department of Medical Physics and Biomedical Engineering, School of Medicine, Tehran University of Medical Sciences, Tehran, Iran (Islamic Republic of), Tehran, Iran (Islamic Republic of), ²Quantitative MR Imaging and Spectroscopy Group, Research Center for Molecular and Cellular Imaging, Tehran University of Medical Sciences, Tehran, Iran (Islamic Republic of), ³Shahid Beheshti University of Medical Science, Tehran, Iran (Islamic Republic of), ⁴Department of Radiology Technology, School of Allied Medical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran (Islamic Republic of), ⁵Gastrointestinal and Liver Disease Research Center, Firoozgar Hospital, Iran University of Medical Sciences, Tehran, Iran (Islamic Republic of), ⁶Department of Diagnostic Imaging, Shohada-e-Tajrish Hospital, Shahid Beheshti University of Medical Science, Tehran, Iran (Islamic Republic of)

Synopsis

Neither biochemical markers nor a qualitative assessment of medical images are reliable to differentiate mild from moderate stages of liver fibrosis. The main purpose of this study is to develop a machine learning model to classify mild and moderate liver fibrosis based on radiomic features extracted from MRI images (T₁-w, T₂^*-map & ADC-map). Nu-SVC classifier was employed as the classification technique, trained by the extracted data from image series of 29 patients with histopathology-confirmed mild and moderate liver fibrosis. Results demonstrate that radiomic analysis of T₂^*-map and ADC-map has high potential in classifying different stages of liver fibrosis.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.