Kidney Segmentation with LinkNetB7

Abstract

Cancer is a deadly disease for which early diagnosis is very important. Cancer can occur in many organs and tissues. Renal cell carcinoma (RCC) is the most common and deadly form of kidney cancer. When diagnosing the disease, segmentation of the corresponding organ on the image can help experts make decisions. With artificial intelligence supported decision support systems, experts will be able to achieve faster and more successful results in the diagnosis of kidney cancer. In this sense, segmentation of kidneys on computed tomography images (CT) will contribute to the diagnosis process. Segmentation can be done manually by experts or by methods such as artificial intelligence and image processing. The main advantages of these methods are that they do not involve human error in the diagnostic process and have almost no cost. In studies of kidney segmentation with artificial intelligence, 3d deep learning models are used in the literature. These methods require more training time than 2d models. There are also studies where 2d models are more successful than 3d models in organs that are easier to segment on the image. In this study, the LinkNetB7 model, which has not been previously used in renal segmentation studies, was modified and used. The study achieved a dice coefficient of 97.20%, precision of 97.30%, sensitivity of 97%, and recall of 97%. As a result of the study, LinknetB7 was found to be applicable in kidney segmentation. Although it is a 2d model, it is more successful than UNet3d and some other 2d models.

Keywords

• Kidney cancer
• Image processing
• Image segmentation
• LinkNet-B7
• Decision Support System

References

1. Akyel C, & Arıcı N. (2022). LinkNet-B7: Noise Removal and Lesion Segmentation in Images of Skin Cancer. Mathematics, 10(5), 736-751. DOI: https://doi.org/10.3390/math10050736
2. Budak, S., Sağlam, H. S., Köse, O., Kumsar, Ş., & Adsan, Ö. (2013). Böbrek Hücreli Karsinomada Radyolojik Tümör Boyutu ile Patolojik Boyutun İlişkisi, Sakarya Medical Journal, 3(4), 186-189, DOI: https://doi.org/10.5505/sakaryamj.2013.92485
3. Chaurasia, A., & Culurciello, E. (2017). LinkNet: Exploiting The encoder Representations for Efficient Semantic Segmentation. The IEEE Visual Communications and Image Processing (VCIP). St. Pe-tersburg, FL, USA, Retrieved from: https://arxiv.org/abs/1707.03718
4. Da Cruz, L. B., Araújo, J. D. L., Ferreira, J. L., Diniz, J. O. B., Silva, A. C., De Almeida, J. D. S., De Paiva, A. C., & Gattass, M. (2020). Kidney segmentation from computed tomography images using deep neural network, Computers in Biology and Medicine, 123, 1-12, DOI: https://doi.org/10.1016/j.compbiomed.2020.103906.
5. Demir, H., & Balçık, P. Y. (2022). Ödeyici Kurum Bakış Açısıyla İleri Evre Böbrek Kanserinde Kay-nak Kullanımı: Eğitim and Araştırma Hastanesi Örneği, Vizyoner Journal, 13(34), 1-15. DOI: https://doi.org/10.21076/vizyoner.991598
6. Devrim, T. (2019). Böbrek Tümörü Vakalarının Retrospektif Olarak Değerlendirilmesi, Kırıkkale Üni-versitesi Tıp Fakültesi Journal, 21(2), 212-217, DOI: https://doi.org/10.24938/kutfd.552211
7. Haghighi, M., Warfield, S. K., & Kurugol, S. (2018). Automatic renal segmentation in DCE-MRI using convolutional neural networks, 2018 IEEE 15th International Symposium on Biomedical Ima-ging (ISBI 2018 (pp. 1-9). Washington, USA. Retrieved from: https://ieeexplore.ieee.org/document/8363865
8. Hsiao, C., Lin, P., Chung, L., Lin, F. Y., Yang, F., Yang, S., Wu, C., Huang, Y., & Sun, T. (2022). A deep learning-based precision and automatic kidney segmentation system using efficient feature pyramid networks in computed tomography images, Computer Methods and Programs in Bio-medicine, 221, 1-17, DOI: https://doi.org/10.1016/j.cmpb.2022.106854

9. Kallam, S., Kumar, M.S., Natarajan, V.A., & Patan, R. (2020). Segmentation of Nuclei in Histopathol-ogy images using Fully Convolutional Deep Neural Architecture. The 2020 International Con-ference on Computing and Information Technology (ICCIT-1441) (pp. 319-325). Tabuk, Saudi Arabia. Retrieved from: https://ieeexplore.ieee.org/document/9213817
10. Kumar, S., Sathyadevi, G. & Sivanesh, S. (2011). ”Decision Support System for Medical Diagnosis Using Data Mining,” Retrieved from: https://www.researchgate.net/publication/267934132
11. Kölükçü, E., Deresoy, F. A., Uluocak, N., Atılgan, D., Gümüşay, Ö., Beyhan, M., & Kılıç, Ş. (2019). Sarkomatoid renal hücreli karsinom: olgu sunumu and literatürün gözden geçirilmesi, Anadolu Güncel Tıp Journal, 1(2), 42-46, DOI: https://doi.org/10.38053/agtd.512103
12. Li, D., Xiao, C., Liu, Y., Chen, Z., Hassan, H., Su, L., Li, H., Xie, W., Zhong, W., & Huanglund, B. (2022). Deep Segmentation Networks for Segmenting Kidneys and Detecting Kidney Stones in Unenhanced Abdominal CT Images, diagnostics, 12, 1-17, DOI: https://doi.org/10.3390/diagnostics12081788
13. The KiTS19 Challenge Data: 300 Kidney Tumor Cases with Clinical Context, CT Semantic Segmenta-tions, and Surgical Outcomes. Retrieved from: https://arxiv.org/abs/1904.00445
14. Üyetürk, Ü., Üyetürk, U., & Metin, A. (2014). Böbrek Hücreli Kanser, Gaziosmanpaşa Üniversitesi Tıp Fakültesi Journal, 6(1), 1-17. Retrieved from: https://dergipark.org.tr/tr/pub/gutfd/issue/34239/378385
15. Zhao, W., Jiang, D., Queralta, J. P., & Westerlund, T. (2020). MSS U-Net: 3d segmentation of kidneys and tumors from CT images with a multi-scale supervised U-Net, Informatics in Medicine Un-locked, 19, 1-11, DOI: https://doi.org/10.1016/j.imu.2020.100357
16. Zettler, N. & Mastmeyer, A. (2021). Comparison of 2d vs. 3d U-Net Organ Segmentation in ab-dominal 3d CT images. Retrieved from: arxiv.org/abs/2107.04062