A deep learning-based approach to robotic-assisted tumor localization in minimal invasive surgeries

View at publisher Summarise with VIRAT
Authors: Hemchandra V. Nerlekar, Sagarkumar S. Badhiye, Pradnya Sulas Borkar, Shinde Patil Girisha Suresh, Mayur Nagvekar, Ujjwala Bal Aher, Santosh Kumar
Cited by: 0
References: 18

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

In cancer, minimally invasive treatments (MIS) have changed everything because they offer faster healing times, less scars, and lower risks than standard open surgery. However, pinpointing the exact location of tumours during these treatments is still a big problem. Traditional methods, like touch and images, often have trouble accurately locating tumours in real time, especially in parts of the body that are deep or complicated. This article talks about a deep learning-based method for robotic-assisted tumour localisation in MIS. The goal is to make surgery more accurate and improve patient results. Advanced convolutional neural networks (CNNs) and real-time image data are combined in the suggested framework to accurately find and locate tumours. The framework is made to guide robotic arms with great accuracy by using preoperative medical imaging, visual feedback during surgery, and robotic systems. This makes sure that the tumour is removed correctly while causing as little damage as possible to healthy tissue around it. A lot of labelled medical pictures, like CT scans, MRIs, and endoscopy images, are used to teach the deep learning model how to find different types and sizes of tumours. During surgery, a feedback loop system improves localisation even more by responding to changes that happen during the operation. Initial tests show that the deep learning model can locate tumours with a lot less mistake than traditional methods. Robotic surgery systems will likely be better with this method, giving doctors and surgeons a powerful tool in the fight against cancer. In addition, it has the potential to improve patient results by cutting down on problems and healing times.

Fields of Study & Subjects

AI in cancer detection Surgical Simulation and Training Medical Image Segmentation Techniques

Publication details

Journal / source
AIP conference proceedings
Volume
3401
Pages
020122–020122
Publication date
1 January 2026
Language
EN