Computed x-ray tomography is one of the most common medical imaging modalities andas such ways of improving the images are of high relevance. Applying deep learningmethods to denoise CT images has been of particular interest in recent years. In thisstudy, rather than using traditional denoising metrics such as MSE or PSNR for evaluation, we use a radiomic approach combined with 3D printed phantoms as a "groundtruth" to compare with. Our approach of having a ground truth ensures that we withabsolute certainty can say what a scanned tumor is supposed to look like and compareour results to a true value. This performance metric is better suited for evaluation thanMSE since we want to maintain structures and edges in tumors and MSE-evaluationrewards over-smoothing. Here we apply U-Net networks to images of 3D printed tumors. The 4 tumors and alung phantom were printed with PLA filament and 80% fill rate with a gyroidal patternto mimic soft tissue in a CT-scan while maintaining isotropicity. CT images of the 3Dprinted phantom and tumors were taken with a GE revolution DE scanner at KarolinskaUniversity Hospital. The networks were trained on the 2016 NIH-AAPM-Mayo ClinicLow Dose CT Grand Challenge dataset, mapping Low Dose CT images to Normal DoseCT images using three different loss functions, l1, vgg16, and vgg16_l1. Evaluating the networks on RadiomicsShape features from SlicerRadiomics® we findcompetitive performance with TrueFidelityTM Deep Learning Image Reconstruction (DLIR)by GE HealthCareTM. With one of our networks (UNet_alt, vgg16_l1 loss function with32 features, and batch size 16 in training.) outperforming TrueFidelity in 63% of caseswhen evaluated by counting if a radiomic feature has a lower relative error comparedto ground truth after our own denoising for four different kind of tumors. The samenetwork outperformed FBP in 84% of cases which in combination with the majority ofour networks performing substantially better against FBP than TrueFidelity shows theviability of DLIR compared to older methods such as FBP.
Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:kth-331466 |
Date | January 2023 |
Creators | Back, Alex, Pandurevic, Pontus |
Publisher | KTH, Skolan för teknikvetenskap (SCI) |
Source Sets | DiVA Archive at Upsalla University |
Language | English |
Detected Language | English |
Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
Format | application/pdf |
Rights | info:eu-repo/semantics/openAccess |
Relation | TRITA-SCI-GRU ; 2023:192 |
Page generated in 0.0016 seconds