The researches find that the External-beam radiotherapy followed by High Dose Rate (HDR) brachytherapy is the standard-of-care for treating gynecologic cancers. Therefore The enhanced soft-tissue contrast provided by Magnetic Resonance Imaging (MRI) makes it a valuable imaging modality for diagnosing and treating these cancers. But However; in contrast to Compute Tomography (CT) imaging, the appearance of the brachytherapy catheters; through which radiation sources are insert to reach the cancerous tissue later on; is often variable across images.
Magnetic Resonance Imaging (MRI)
This paper reports; for the first time, a new deep-learning-based method for fully automatic segmentation of multiple closely spaced brachytherapy catheters in intraoperative MRI. Represent in the data are 50 gynecologic cancer patients treat by MRI-guided HDR brachytherapy. For each patient; a single intraoperative MRI is use. 826 catheters in the images were manually segment by an expert radiation physicist who is also a trained radiation oncologist.
The number of catheters in a patient ranged between 10 and 35. A deep 3-dimensional Convolutional Neural Network (CNN) model is develop and train. In order to make the learning process more robust, the network is train 5 times, each time using a different combination of shows patients. Finally; each test case is process by the 5 networks and the final segmentation was generated by voting on the obtained 5 candidate segmentations.
Platform 3D Slicer
4-fold validation was executed and all the patients were segmented. An average distance error of 2.0±3.4 mm was achieved. False positive and false negative catheters were 6.7% and 1.5% respectively. Therefore Average Dice score was equal to 0.60±0.17. The algorithm is available for use in the open source software c allowing for wide scale testing and research discussion. In conclusion, to the best of our knowledge, fully automatic segmentation of multiple closely space catheters from intraoperative MR images is achieve for the first time in gynecological brachytherapy.
Gynecologic (GYN) malignancies, which include cervical, endometrial, ovarian, vaginal and vulvar cancers, cause significant mortality in women worldwide. According to an estimation, in the U.S., approximately 110,070 women developed gynecologic cancer in 2018, and over 30% died from the disease (American Cancer Society 2018). The standard-of-care treatment for many primary and recurrent gynecologic cancers consists of external-beam radiation followed by High Dose Rate (HDR) brachytherapy (Viswanathan et al 2012).
Vaginal and vulvar cancers
In contrast to external-beam radiation treatment; in which a linear accelerator aims radiation beams at the pelvis from outside the body, in HDR brachytherapy, radioactive sources; that deliver very high doses of radiation (typically in the range of 80-90 Gray for cervical cancer), are place directly inside the cancerous tissue using intracavitary or interstitial catheters.