Menu

📰
0

Hybrid deep-learning model eases brachytherapy planning

Physics World·@TamiFreeman·2 months ago
#3P57OV
Reading 0:00
15s threshold

***CTV segmentation test** Target contouring in two example slices of a patient’s CT scan, using BCTVNet and 12 comparison models. Red and green contours represent the ground truth and the model predictions, respectively. Each image is annotated with the corresponding Dice similarity coefficient. (Courtesy: CC BY 4.0/Mach. Learn.: Sci. Technol.* 10.1088/2632-2153/ae2233 Brachytherapy – a cancer treatment that destroys tumours using small radioactive sources implanted inside the body – plays a critical role in treating cervical cancer, offering an important option for patients with inoperable locally advanced disease. Brachytherapy can deliver high radiation doses directly to the tumour while ensuring nearby healthy tissues receive minimal dose; but its effectiveness relies on accurate delineation of the treatment target. A research team in China is using a hybrid deep-learning model to help with this task.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.

Read More