Radiation Damage can now be minimized significantly with the new Deep- learning method that Spots Organs on CT Scans

In order to attack the tumors present in a body, the conventionally accepted procedure is that of Radiotherapy. Administering radiation to a lesion can be done through a variety of techniques; however none of them comes without the risk of harming the tissues and organs that are present nearby the lesion being tackled. A grave issue that arises while using gamma beams and any other devices that depend on high energy is that all the tissues that are on the way and even those on the other side of the target are directly exposed to the beams.

One approach that can help clinicians ensure relatively lesser collateral damage could be if the clinicians are well aware of the positioning of the significant organs in individual patients that are being treated at the time; helping them prepare radiation therapy in accordance to that. The one preferred technique used to map the internal anatomy is CT scanning which is done by radiation oncologists. However; tracing the relevant organs in order to plan a treatment path that guarantees minimal damage is still a difficult task.

Through the collaborative efforts of a team of researchers from University of California Irvine, Shanghai Jiao Tong University School of Medicine in China, and DeepVoxel, a company based in Costa Mesa, California, this issue has found a solution. A system has been developed and now unveiled by the team, which functions by taking input of a CT scan and through it provides an outline of all the important organs within it.

While if attempted manually, the process of scanning takes up to half an hour, however; through this system the scans are processed within a few seconds as it depends on deep- learning methods. According to one of the co- authors of the study that has been published in ‘Nature Machine Intelligence’, Xiaohui Xie, an average similarity coefficient of more than 78 percent was achieved by their deep-learning method on a data set of 100 CT scans. This is impressive by the current standards.

Chris Sokol

Consultant respiratory physician at DescriptionThe Perelman School of Medicine, commonly known as Penn Med, is the medical school of the University of Pennsylvania, Philadelphia, PA 19104, United States. Mail Me : Chrissokol@timestechpharma.com

Leave a Reply

Your email address will not be published. Required fields are marked *