AI-Assisted Fusion of Scanning Electrochemical Microscopy Images Using Novel Soft Probe

Area of Science:

• Analytical Chemistry
• Biomedical Engineering
• Materials Science

Background:

• Scanning Electrochemical Microscopy (SECM) offers insights into surface morphology and electrochemical reactivity.
• Current SECM techniques face limitations due to electrode size, uncontrollable factors, fragile probes, and image blurring.
• Investigating protein biomarker distribution in oral cancer requires high-resolution imaging.

Purpose of the Study:

• To overcome limitations in traditional SECM by developing novel soft gold probes.
• To establish an AI-assisted image fusion methodology to enhance SECM image quality.
• To improve the detection and analysis of EGFR distribution in oral cancer.

Main Methods:

• Development of novel, highly soft gold microelectrode probes for scanning fragile samples.
• Fusion of optical microscopy and SECM images using Matlab software to improve image quality.
• Implementation of a deep learning model to automatically select optimal fused images based on contrast and clarity.

Main Results:

• Novel soft gold probes enabled the investigation of EGFR distribution in oral cancer samples.
• Image fusion techniques significantly enhanced the quality of SECM images.
• The deep learning model effectively identified the best-fused images, reducing manual selection burden.

Conclusions:

• The combination of soft probes and AI-assisted image fusion substantially improves SECM image quality.
• This advanced SECM approach holds promise for precise interpretation and early cancer detection.
• Future developments may lead to even more accurate AI-assisted SECM image processing for clinical applications.