Magnetic induction of hyperthermia by a modified self-learning fuzzy temperature controller

Area of Science:

• Biomedical Engineering
• Control Systems
• Oncology

Background:

• Magnetic induction hyperthermia (MIH) offers a promising, minimally invasive approach for cancer treatment.
• Precise temperature control is critical for hyperthermia efficacy and minimizing side effects.
• Control performance in MIH systems is often challenged by perturbations and parameter variations.

Purpose of the Study:

• To develop an advanced temperature controller for MIH systems.
• To enhance control performance and robustness under varying treatment conditions.
• To investigate a modified self-learning fuzzy logic controller (SLFLC) for MIH temperature regulation.

Main Methods:

• Implementation of a closed-loop controller with a reference model for temperature tracking.
• Development of a modified self-learning fuzzy logic controller (SLFLC) with a gain tuning mechanism.
• Validation through in vitro experiments using porcine liver tissue.

Main Results:

• The proposed SLFLC demonstrated superior robustness and adaptability compared to classical self-tuning fuzzy logic controllers and fuzzy model reference learning control.
• The controller effectively managed temperature control despite perturbations and parameter variations.
• In vitro experiments confirmed the SLFLC's excellent performance in MIH temperature regulation.

Conclusions:

• The modified SLFLC offers a highly effective solution for precise temperature control in MIH cancer therapy.
• The controller's adaptability and robustness make it suitable for diverse clinical scenarios.
• This advancement holds potential for improving the outcomes of hyperthermia treatments.