Öz
When metallic implants are present within the human body, they frequently introduce metallic artifacts into X-ray CT images. These artifacts can lead to significant distortions, obscuring critical information and potentially degrading the quality of the CT images, thereby impacting diagnostic accuracy for clinicians. In recent years, there has been extensive research aimed at mitigating the challenges posed by metallic artifacts, resulting in the development of multiple solutions to address this issue. In this study, we present an efficient approach for artifact removal. Our method involves utilizing the image reconstructed from a sinogram affected by artifacts to generate a synthesized sinogram, deviating from the conventional acquisition of sinogram data. The key stages of our approach encompass segmentation, sinogram gap-filling, and subsequent image enhancement. To achieve rapid segmentation, we employed a K-means classification method. For the retrieval of missing data, we utilized an interpolation algorithm based on a penalized least squares method. In the final phase of image reconstruction enhancement, we implemented an advanced contrast equalization technique to restore image intensities to their inherent dynamic range. Through rigorous verification using both simulated and clinical data, our method consistently demonstrates a remarkable improvement in image quality.
Anahtar Kelimeler
Computed tomography Image reconstruction Metal artifact Segmentation Inpainting sinogram Contrast enhancement
Kaynakça
- Al-Ameen, Z., (2018). An improved contrast equalization technique for contrast enhancement in scanning electron microscopy images, Wiley Periodicals, Inc. Microsc Res Tech.1–11.
- Amorim, R.C., & Makarenkov, V., (2016). Applying subclustering and Lp distance in weighted K-means with distributed centroids, Neurocomputing, (173), 700–707.
- Arabi H. & Zaidi H., (2021). Deep learning–based metal artefact reduction in PET/CT imaging, European Radiology, https://doi.org/10.1007/s00330-021-07709-z.
- Bamberg, F., Dierks, A., Nikolaou, K., Reiser, M.F., Becker, C.R., Johnson T.R., (2011). Metal artefact reduction by dual energy computed tomography using monoenergetic extrapolation, Eur Radiol, 7, 1424-1429.
Öz
Kaynakça
- Al-Ameen, Z., (2018). An improved contrast equalization technique for contrast enhancement in scanning electron microscopy images, Wiley Periodicals, Inc. Microsc Res Tech.1–11.
- Amorim, R.C., & Makarenkov, V., (2016). Applying subclustering and Lp distance in weighted K-means with distributed centroids, Neurocomputing, (173), 700–707.
- Arabi H. & Zaidi H., (2021). Deep learning–based metal artefact reduction in PET/CT imaging, European Radiology, https://doi.org/10.1007/s00330-021-07709-z.
- Bamberg, F., Dierks, A., Nikolaou, K., Reiser, M.F., Becker, C.R., Johnson T.R., (2011). Metal artefact reduction by dual energy computed tomography using monoenergetic extrapolation, Eur Radiol, 7, 1424-1429.
Ayrıntılar
| Birincil Dil | İngilizce |
|---|---|
| Konular | Çevresel ve Sürdürülebilir Süreçler |
| Bölüm | Makaleler |
| Yazarlar | |
| Erken Görünüm Tarihi | 31 Aralık 2023 |
| Yayımlanma Tarihi | 30 Aralık 2023 |
| Yayımlandığı Sayı | Yıl 2023Cilt: 26 |
