Scots pine blister rust (SPBR) is a forest pathogen that infects pine trees, primarily in northern Sweden. The tree’s defense mechanism is to use resin for compartmentalise wounds, namely resin wood, which gives it undesirable properties in use as sawmill timber. Since the rate of infection is increasing, significantly more timber damaged by SPBR is expected to reach Swedish sawmills in the future. We have previous developed classic image segmentation pipeline for detecting resin wood. However, the method is less ideal when the IOU metrics have been evaluated. Expert advisory team in the Department of computer science Uppsala University recommended to use Deep Learning approach to potentially achieve better performance. I begun my PhD at Luleå Tekniska Universitets and then transferred to KTH, had earlier project shown that damage from SPBR in tree logs is possible to detect via CT-scanning (3D X-ray). In this project, the goal is to automate the detection method in images from laboratory-environment CT-scanners. The biggest challenge is to distinguish between resin wood and normal heart wood, since these have similar intensity values in the CT image. Both classical and more machine learning methods will be tested. Another challenge is to handle the large image datasets from the CT scanned logs. Ultimately, when algorithm run-time will be tested in real-time, ideally through GPU, then resin wood feature detection can be realistically pilot test in digital sawmill environment.