Back

Mitigating Chemotherapy Side Effects through Targeted Gamma-Ray Delivery and Convolutional Neural Networks: A Step Toward Precision Oncology

Siddiqui, S.; ElDeen, S. E.-S. S.

2024-11-21 cancer biology
10.1101/2024.11.19.624335 bioRxiv
Show abstract

The systemic nature of chemotherapy results in widespread side effects that severely impact patients quality of life. This study presents a novel framework combining convolutional neural networks (CNNs) with precision gamma-ray delivery systems to selectively target malignant cells, minimizing collateral damage to healthy tissues. A ResNet-50-based CNN was trained on 12,000 annotated imaging datasets and integrated with a robotic radiation system for real-time targeting. Experimental validation on synthetic tissue models demonstrated a 92% reduction in healthy tissue damage and a 78% decrease in reported side effects. Statistical analyses confirmed model sensitivity (97.2%), specificity (94.8%), and improved treatment accuracy. This research provides a foundation for advancing personalized oncology and reducing the physical and emotional toll of chemotherapy.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.