Label-free classification of hepatocellular-carcinoma grading using second harmonic generation microscopy

Area of Science:

• Biomedical Optics
• Cancer Research
• Digital Pathology

Background:

• Accurate hepatocellular carcinoma (HCC) grading is crucial for patient prognosis and treatment planning.
• Label-free and automated HCC grading remains a significant challenge in clinical pathology.

Purpose of the Study:

• To demonstrate the utility of second-harmonic generation (SHG) microscopy for label-free classification of HCC grading.
• To develop an automated algorithm for HCC grade determination using SHG imaging.

Main Methods:

• Utilized SHG microscopy on 217 paraffin-embedded HCC specimens from 113 patients.
• Analyzed SHG signals from tumor collagen using feature extraction, Mann-Whitney test, and ROC curves.
• Developed an adaptive quantification algorithm integrating image features and clinical data.

Main Results:

• SHG microscopy analysis showed good correlation with diagnoses made by experienced pathologists.
• The developed algorithm automatically determined HCC grade based on SHG image features and clinical information.
• Demonstrated the potential for automated, label-free HCC grading without extensive tissue processing.

Conclusions:

• SHG microscopy is a promising tool for the automated, label-free classification of HCC grading.
• This technique could streamline diagnostic workflows, reducing time and resources compared to traditional methods.
• The findings suggest SHG microscopy's potential for clinical adoption in HCC diagnostics.