Kidney Tumour Detection Using Deep Neural Network

Tawseeful Haziq; Ashish Obroi; Yogesh

doi:10.55524/

Authors

Tawseeful Haziq M. Tech Scholar, Department of Computer Science & Engineering, RIMT University, Mandi Gobindgarh, Punjab, India Author
Ashish Obroi Head, Department of Computer Science & Engineering, RIMT University, Mandi Gobindgarh, Punjab, India Author
Yogesh Associate Professor, Department of Computer Science & Engineering, RIMT University, Mandi Gobindgarh, Punjab, India Author

DOI:

https://doi.org/10.55524/

Keywords:

Deep neural, Renal tumour, CT-Scan, Benign, Malignant

Abstract

Classifying the malignancy of a renal tumour is one of the most important urological duties because it plays a key role in determining whether or not to undergo kidney removal surgery (nephrectomy). Currently, the radiological diagnostic made us89++ing computed tomography (CT) scans determines the likelihood of a tumour being malignant. However, it's believed that up to 16 percent of nephrectomies may have been avoided since a postoperative histological study revealed that a tumour that had been first identified as malignant was actually benign. Numerous false-positive diagnoses lead to unnecessary nephrectomies, which increase the chance of post-procedural problems. In this article, we offer a computer-aided diagnostic method that analyses a CT scan to determine the tumour’s malignancy. The prediction, which is used to identify false-positive diagnoses, is carried out following radiological diagnosis. Our solution can complete this challenge with an F1 score of 0.84. Additionally, we suggest a cutting-edge method for knowledge transmission in the medical field using colorization-based pre-processing, which can raise the F1- score by as much as to 1.8.

Downloads

Download data is not yet available.

References

. Aboutalib, S. S.; Mohamed, A. A.; Berg, W. A.; Zuley, M. L.; Sumkin, J. H.; and Wu, S. 2018. Deep learning to distinguish

recalled but benign mammography images in breast cancer screening. Clinical Cancer Research 24(23):5902– 5909. [2]. Attique, M.; Gilanie, G.; Mehmood, M. S.; Naweed, M. S.; Ikram, M.; Kamran, J. A.; Vitkin, A.; et al. 2012. Colorization and automated segmentation of human t2 mr brain images for characterization of soft tissues. PloS one 7(3):e33616. [3]. Baghdadi, A.; Aldhaam, N. A.; Elsayed, A. S.; Hussein, A. A.; Cavuoto, L. A.; Kauffman, E.; and Guru, K. A. 2020. Automated differentiation of benign renal oncocytoma and chromophobe renal cell carcinoma on computed tomography using deep learning. BJU Int 125(4):553–60.

. Chollet, F. 2017. Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, 1251– 1258.

. Cokkinides, V., A. J. S. A. e. a. 2020. American cancer society: Cancer facts and figures.

. Deng, J.; Dong, W.; Socher, R.; Li, L.-J.; Li, K.; and FeiFei, L. 2009. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, 248–255. Ieee.

. Erdim, C.; Yardimci, A. H.; Bektas, C. T.; Kocak, B.; Koca, S. B.; Demir, H.; and Kilickesmez, O. 2020. Prediction of benign and malignant solid renal masses: machine learningbased ct texture analysis. Academic radiology 27(10):1422– 1429.

. Han, S.; Hwang, S. I.; and Lee, H. J. 2019. The classification of renal cancer in 3-phase ct images using a deep learning method. Journal of digital imaging 32(4):638–643.

. He, K.; Zhang, X.; Ren, S.; and Sun, J. 2015. Deep residual learning for image recognition.

. Heller, N.; Sathianathen, N.; Kalapara, A.; Walczak, E.; Moore, K.; Kaluzniak, H.; Rosenberg, J.; Blake, P.; Rengel, Z.; Oestreich, M.; et al. 2019. The kits19 challenge data: 300 kidney tumor cases with clinical context, ct semantic segmentations, and surgical outcomes. arXiv preprint arXiv:1904.00445.

. Iandola, F.; Moskewicz, M.; Karayev, S.; Girshick, R.; Darrell, T.; and Keutzer, K. 2014. Densenet: Implementing efficient convnet descriptor pyramids. arXiv preprint arXiv:1404.1869.