A Detection and Prediction Model Based on Deep Learning Assisted by Explainable Artificial Intelligence for Kidney Diseases

Yıl 2022, Sayı: 40, 67 - 74, 30.09.2022

Ahmet Furkan Bayram , Caglar Gurkan , Abdulkadir Budak , Hakan Karataş

https://doi.org/10.31590/ejosat.1171777

Cited By: 5

Öz

Kidney diseases are one of the most common diseases worldwide and cause unbearable pain in most people. In this study aims to detecting the cyst and stone in the kidney. For the this purpose, YOLO architecture designs were used for detection of kidney, kidney cyst and kidney stone. The YOLO architecture designs were supported by the explainable artificial intelligence (xAI) feature. CT images in three classes, namely 72 kidney cysts, 394 kidney stones and 192 healthy kidneys were used in the performance analysis part of the YOLO architecture designs. As a result, YOLOv7 architecture design outperformed the YOLOv7 Tiny architecture design. YOLOv7 architecture design achieved the mAP50 of 0.85, precision of 0.882, sensitivity of 0.829 and F1 score of 0.854. Consequently, deep learning based xAI assisted computer aided diagnosis (CAD) system was developed for diagnosis of kidney diseases.

Anahtar Kelimeler

Kidney stone, Kidney cyst, Deep learning, YOLOv7, Explainable artificial intelligence

Teşekkür

This paper has been prepared by AKGUN Computer Incorporated Company. We would like to thank AKGUN Computer Inc. for providing all kinds of opportunities and funds for the execution of this project.

Böbrek Hastalıkları için Açıklanabilir Yapay Zeka Destekli Derin Öğrenmeye Dayalı Bir Tespit ve Tahmin Modeli

Öz

Böbrek hastalıkları dünya çapında en yaygın hastalıklardan biridir ve çoğu insanda dayanılmaz ağrılara neden olur. Bu çalışmada böbrekteki kist ve taşın tespiti amaçlanmıştır. Bu amaçla böbrek, böbrek kisti ve böbrek taşı tespiti için YOLO mimari tasarımları kullanılmıştır. YOLO mimari tasarımları açıklanabilir yapay zeka (AYZ) özelliği ile desteklenmiştir. YOLO mimari tasarımlarının performans analizi kısmında 72 böbrek kisti, 394 böbrek taşı ve 192 sağlıklı böbrek olmak üzere üç sınıftaki BT görüntüleri kullanılmıştır. Sonuç olarak, YOLOv7 mimari tasarımı, YOLOv7 Tiny mimari tasarımından daha iyi performans gösterdi. YOLOv7 mimari tasarımı 0.85 mAP50 değerini, 0.882 kesinliği, 0.829 duyarlılığı ve 0.854 F1 skorunu elde etmiştir. Sonuç olarak, böbrek hastalıklarının teşhisi için derin öğrenme tabanlı AYZ destekli bilgisayar destekli tanı (BDT) sistemi geliştirilmiştir.

Anahtar Kelimeler

Böbrek taşı, Böbrek kisti, Derin öğrenme, YOLOv7, Açıklanabilir yapay zeka

Kaynakça

• Türk, C., Petřík, A., Sarica, K., Seitz, C., Skolarikos, A., Straub, M., & Knoll, T. (2016). EAU Guidelines on Diagnosis and Conservative Management of Urolithiasis. European Urology, 69(3), 468–474. https://doi.org/10.1016/J.EURURO.2015.07.040
• Stamatelou, K. K., Francis, M. E., Jones, C. A., Nyberg, L. M., & Curhan, G. C. (2003). Time trends in reported prevalence of kidney stones in the United States: 1976–1994. Kidney International, 63(5), 1817–1823. https://doi.org/10.1046/J.1523-1755.2003.00917.X
• Scales, C. D., Smith, A. C., Hanley, J. M., & Saigal, C. S. (2012). Prevalence of Kidney Stones in the United States. European Urology, 62(1), 160–165. https://doi.org/10.1016/J.EURURO.2012.03.052
• Fwu, C. W., Eggers, P. W., Kimmel, P. L., Kusek, J. W., & Kirkali, Z. (2013). Emergency department visits, use of imaging, and drugs for urolithiasis have increased in the United States. Kidney International, 83(3), 479–486. https://doi.org/10.1038/KI.2012.419
• Chewcharat, A., & Curhan, G. (2021). Trends in the prevalence of kidney stones in the United States from 2007 to 2016. Urolithiasis, 49(1), 27–39. https://doi.org/10.1007/S00240-020-01210-W/TABLES/7
• Weston, A. D., Korfiatis, P., Kline, T. L., Philbrick, K. A., Kostandy, P., Sakinis, T., Sugimoto, M., Takahashi, N., & Erickson, B. J. (2019). Automated Abdominal Segmentation of CT Scans for Body Composition Analysis Using Deep Learning. Radiology, 290(3), 669–679. https://doi.org/10.1148/RADIOL.2018181432/ASSET/IMAGES/LARGE/RADIOL.2018181432.FIG5.JPEG
• Ozturk, T., Talo, M., Yildirim, E. A., Baloglu, U. B., Yildirim, O., & Rajendra Acharya, U. (2020). Automated detection of COVID-19 cases using deep neural networks with X-ray images. Computers in Biology and Medicine, 121, 103792. https://doi.org/10.1016/J.COMPBIOMED.2020.103792
• Yan, K., Wang, X., Lu, L., & Summers, R. M. (2018). DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning. Https://Doi.Org/10.1117/1.JMI.5.3.036501, 5(3), 036501. https://doi.org/10.1117/1.JMI.5.3.036501
• Lin, Z., Cui, Y., Liu, J., Sun, Z., Ma, S., Zhang, X., & Wang, X. (2021). Automated segmentation of kidney and renal mass and automated detection of renal mass in CT urography using 3D U-Net-based deep convolutional neural network. European Radiology, 31(7), 5021–5031. https://doi.org/10.1007/S00330-020-07608-9/FIGURES/6
• Lin, D. T., Lei, C. C., & Hung, S. W. (2006). Computer-aided kidney segmentation on abdominal CT images. IEEE Transactions on Information Technology in Biomedicine, 10(1), 59–65. https://doi.org/10.1109/TITB.2005.855561
• Lin, Z., Cui, Y., Liu, J., Sun, Z., Ma, S., Zhang, X., & Wang, X. (2021). Automated segmentation of kidney and renal mass and automated detection of renal mass in CT urography using 3D U-Net-based deep convolutional neural network. European Radiology, 31(7), 5021–5031. https://doi.org/10.1007/S00330-020-07608-9/FIGURES/6
• Baygin, M., Yaman, O., Barua, P. D., Dogan, S., Tuncer, T., & Acharya, U. R. (2022). Exemplar Darknet19 feature generation technique for automated kidney stone detection with coronal CT images. Artificial Intelligence in Medicine, 127, 102274. https://doi.org/10.1016/J.ARTMED.2022.102274
• Ruberto, C. Di, Loddo, A., Putzu, L., Stefano, A., Comelli, A., Li, D., Xiao, C., Liu, Y., Chen, Z., Hassan, H., Su, L., Liu, J., Li, H., Xie, W., Zhong, W., & Huang, B. (2022). Deep Segmentation Networks for Segmenting Kidneys and Detecting Kidney Stones in Unenhanced Abdominal CT Images. Diagnostics 2022, Vol. 12, Page 1788, 12(8), 1788. https://doi.org/10.3390/DIAGNOSTICS12081788
• Yildirim, K., Bozdag, P. G., Talo, M., Yildirim, O., Karabatak, M., & Acharya, U. R. (2021). Deep learning model for automated kidney stone detection using coronal CT images. Computers in Biology and Medicine, 135, 104569. https://doi.org/10.1016/J.COMPBIOMED.2021.104569
• Cui, Y., Sun, Z., Ma, S., Liu, W., Wang, X., Zhang, X., & Wang, X. (2021). Automatic Detection and Scoring of Kidney Stones on Noncontrast CT Images Using S.T.O.N.E. Nephrolithometry: Combined Deep Learning and Thresholding Methods. Molecular Imaging and Biology, 23(3), 436–445. https://doi.org/10.1007/S11307-020-01554-0/FIGURES/6
• Fu, X., Liu, H., Bi, X., & Gong, X. (2021). Deep-Learning-Based CT Imaging in the Quantitative Evaluation of Chronic Kidney Diseases. Journal of Healthcare Engineering, 2021. https://doi.org/10.1155/2021/3774423
• Islam, N., Hasan, M., Hossain, K., & Alam, G. R. (2022). Vision transformer and explainable transfer learning models for auto detection of kidney cyst , stone and tumor from CT radiography. Scientific Reports, 1–14. https://doi.org/10.1038/s41598-022-15634-4
• Make Sense. (n.d.). Retrieved August 28, 2022, from https://www.makesense.ai/
• Gothane, S. (n.d.). A Practice for Object Detection Using YOLO Algorithm Cite this paper A Practice for Object Detection Using YOLO Algorithm. https://doi.org/10.32628/CSEIT217249
• Dosilovic, F. K., Brcic, M., & Hlupic, N. (2018). Explainable artificial intelligence: A survey. 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics, MIPRO 2018 - Proceedings, 210–215. https://doi.org/10.23919/MIPRO.2018.8400040
• Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization (pp. 618–626). http://gradcam.cloudcv.org
• Selvaraju, R. R., Das, A., Vedantam, R., Cogswell, M., Parikh, D., Batra, D., & Tech, V. (2016). Grad-CAM: Why did you say that? https://doi.org/10.48550/arxiv.1611.07450