Cancer Cell Removing Using a Reinforcement Learning Agent
Mousavi Fard, S. A.
Show abstract
Cancer cell is a deadly problem which is the main cause of global death. Unfortunately, the conventional therapies like chemo/radio therapy are not viable ways to remove all of the cancer cells. Although Robotic achievements have been increased in cancer therapy, these devices do not have the decision-making ability to grasp their environment like biologists. In this paper, a cancer cell removing method based on Artificial Intelligence techniques is introduced. The proposed idea adopts a combination of object detection and reinforcement model in order to detect the cancer cells and take some actions to remove them. To implement this idea, YOLOv9 is trained on a cancer cell image dataset to detect and segment the cancer cell and create a set point for RL model then in the next step, Soft Actor Critic (SAC) is considered as a RL model to grasp the desired environment and take some appropriate actions to reach the target. The experimental result of this model shows that the proposed model can be adopted in different cancer therapy robots like micro/wireless soft robots to boost their performance in terms of their decision-making ability.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Prediction and control of COVID-19 infection based on a hybrid intelligent model 96%
- Delivering biochemicals with precision using bioelectronic devices enhanced with feedback control 95%
- Artificial intelligence tool for the study of COVID-19 microdroplet spread across the human diameter and airborne space 95%
Similar papers in this journal
Similar papers in this journal
- Fertility-LightGBM: A fertility-related protein prediction model by multi-information fusion and light gradient boosting machine 91%
- Hilbert-Envelope Features for Cardiac Disease Classification from Noisy Phonocardiograms 90%
- Evaluating three different adaptive decomposition methods for EEG signal seizure detection and classification 89%
Similar papers in this journal
"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.