Affiliations 

  • 1 Department of Physics, Faculty of Science, Universiti Putra Malaysia, Serdang 43400, Selangor, Malaysia
  • 2 Department of Computer Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang 43400, Selangor, Malaysia
  • 3 Programme of Diagnostic Imaging and Radiotherapy, Universiti Kebangsaan Malaysia, Kuala Lumpur 50300, Wilayah Persekutuan, Malaysia
  • 4 Department Biochemistry & Molecular Medicine, Faculty of Medicine, Universiti Teknologi MARA, Sungai Buloh 47200, Selangor, Malaysia
Diagnostics (Basel), 2021 Aug 30;11(9).
PMID: 34573915 DOI: 10.3390/diagnostics11091573

Abstract

Hepatocellular carcinoma (HCC) is considered as a complex liver disease and ranked as the eighth-highest mortality rate with a prevalence of 2.4% in Malaysia. Magnetic resonance imaging (MRI) has been acknowledged for its advantages, a gold technique for diagnosing HCC, and yet the false-negative diagnosis from the examinations is inevitable. In this study, 30 MR images from patients diagnosed with HCC is used to evaluate the robustness of semi-automatic segmentation using the flood fill algorithm for quantitative features extraction. The relevant features were extracted from the segmented MR images of HCC. Four types of features extraction were used for this study, which are tumour intensity, shape feature, textural feature and wavelet feature. A total of 662 radiomic features were extracted from manual and semi-automatic segmentation and compared using intra-class relation coefficient (ICC). Radiomic features extracted using semi-automatic segmentation utilized flood filling algorithm from 3D-slicer had significantly higher reproducibility (average ICC = 0.952 ± 0.009, p < 0.05) compared with features extracted from manual segmentation (average ICC = 0.897 ± 0.011, p > 0.05). Moreover, features extracted from semi-automatic segmentation were more robust compared to manual segmentation. This study shows that semi-automatic segmentation from 3D-Slicer is a better alternative to the manual segmentation, as they can produce more robust and reproducible radiomic features.

* Title and MeSH Headings from MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine.