Abstract
Bladder cancer is a type of commonly encountered clinical malignant tumors of the urinary system with high recurrence and high mortality. Recent studies have suggested that the non-invasive and accurate classification of bladder cancer using MRI images and deep learning models is of great significance to formulating treatment plans and evaluating prognosis. However, due to various kinds of difficulties in data collection, medical imaging data often have the characteristics of small samples, incomplete sequence data, and mixed storage of all case data. To address these issues, we propose in this paper a multi-granularity intelligent diagnostic method for staging and grading bladder cancer using limited MRI data, which automatically divides the case data, and adaptively selects data augmentation methods and deep learning model according to the number of case data. For the diagnostic model of sequence image data, the autoencoder based model is used to optimize the diagnostic features of the images, and the feature correlation between data sequences is used to classify bladder cancer. For the diagnostic model of single image data, the attention mechanism is introduced to strengthen the diagnostic features of images. Experiments show that this method has an accuracy rate of 95.72% for grading of bladder cancer, and an accuracy rate of 88.57% for staging.
Similar content being viewed by others
Data availability
The data set we use is the bladder cancer data set provided by the 2019 China University Computer Design Competition.
References
Aerts H, Velazquez ER, Leijenaar R et al (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 5:1–8. https://doi.org/10.1038/ncomms5644
AJCC Cancer Staging System (2020) http://www.cancerstaging.org/references-tools/Pages/What-is-Cancer-Staging.aspx. Accessed 28 June 2020
Anthimopoulos M, Christodoulidis S, Ebner L, Christe A, Mougiakakou S (2016) Lung pattern classification for interstitial lung diseases using a deep convolutional neural network. IEEE Trans Med Imaging 35(5):1207–1216. https://doi.org/10.1109/TMI.2016.2535865
Gargeya R, Leng T (2017) Automated identification of diabetic retinopathy using deep learning. Ophthalmology 124(7):962–969. https://doi.org/10.1016/j.ophtha.2017.02.008
He KM, Zhang XY, Ren SQ, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 770–778. https://doi.org/10.1109/CVPR.2016.90
Jazvić M, Ružić B, Krušlin B et al (2019) Clinical recommendations for diagnosis, treatment and monitoring of patients with bladder cancer. Lijec̆nic̆ki Vjesnik. https://doi.org/10.26800/LV-141-11-12-42
Jiang DH, Zhang S, Dai L, Dai YM (2022) Multi-scale generative adversarial network for image super-resolution. Soft Comput 26(8):3631–3641. https://doi.org/10.1007/s00500-022-06822-5
Lenis AT, Lec PM, Chamie K, Mshs MD (2020) Bladder cancer: a review. JAMA 324(19):1980–1991. https://doi.org/10.1001/jama.2020.17598
Lin D, Yu Q, Lu Y, Cao L, Hu TH, He PL, Yang J, Wang YL, Cui S, Wu T (2020) Bayesian network analysis of open, laparoscopic, and robot-assisted radical cystectomy for bladder cancer. Medicine 99(52):e23645. https://doi.org/10.1097/MD.0000000000023645
Liu Z, Zhang GR, Zhao JY, Yu LY, Sheng JX, Zhang N, Yuan H (2020) Second-generation sequencing with deep reinforcement learning for lung infection detection. J Healthc Eng 2020:3264801. https://doi.org/10.1155/2020/3264801
Patel VG, Oh WK, Galsky MD (2020) Treatment of muscle-invasive and advanced bladder cancer in 2020. CA Cancer J Clin 70(5):404–423. https://doi.org/10.3322/caac.21631
Sarraf S, Tofighi G (2016) Classification of Alzheimer's disease structural MRI data by deep learning convolutional neural networks. ArXiv: abs/1607.06583. https://doi.org/10.48550/arXiv.1607.06583
Shi BG, Bai X, Yao C (2017) An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans Pattern Anal Mach Intell 39(11):2298–2340. https://doi.org/10.1109/TPAMI.2016.2646371
Tholomier C, Souhami L, Kassouf W (2020) Bladder-sparing protocols in the treatment of muscle-invasive bladder cancer. Transl Androl Urol 9(6):2920–2937. https://doi.org/10.21037/tau.2020.02.10
Wang Z, Chen J, Yang L et al (2020) Single-cell sequencing-enabled hexokinase 2 assay for noninvasive bladder cancer diagnosis and screening by detecting rare malignant cells in urine. Anal Chem 92(24):16284–16292. https://doi.org/10.1021/acs.analchem.0c04282
Witjes JA, Bruins HM, Cathomas R et al (2021) European Association of Urology guidelines on muscle-invasive and metastatic bladder cancer: summary of the 2020 guidelines. Eur Urol 79(1):82–104. https://doi.org/10.1016/j.eururo.2020.03.055
Woo S, Park J, Lee J, Kweon IS (2018) CBAM: convolutional block attention module. Springer, Cham, pp 3–19. https://doi.org/10.1007/978-3-030-01234-2_1
Wu XK, Lv DJ, Cai C, Zhao ZJ, Wang M, Chen WZ, Liu YD (2020) A TP53-associated immune prognostic signature for the prediction of overall survival and therapeutic responses in muscle-invasive bladder cancer. Front Immunol 11:590618. https://doi.org/10.3389/fimmu.2020.590618
Yoneda K, Kamiya N, Utsumi T, Wakai K, Oka R, Endo T, Yano M, Hiruta N, Ichikawa T, Suzuki H (2021) Impact of lymphovascular invasion on prognosis in the patients with bladder cancer-comparison of transurethral resection and radical cystectomy. Diagnostics (basel, Switzerland) 11(2):244. https://doi.org/10.3390/diagnostics11020244
Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks? Adv Neural Inf Process Syst 27:1. https://doi.org/10.48550/arXiv.1411.1792
Zamboni S, Moschini M, Gallina A et al (2019) The impact of completeness of last transurethral resection of bladder tumors on the outcomes of radical cystectomy. World J Urol 37(12):2707–2714. https://doi.org/10.1007/s00345-019-02734-6
Zhang B, Tian J, Dong D et al (2017) Radiomics features of multiparametric MRI as novel prognostic factors in advanced nasopharyngeal carcinoma. Clin Cancer Res 23(15):4259–4269. https://doi.org/10.1158/1078-0432.CCR-16-2910
Funding
This work was partially supported by Project for Research on Medical in Jiangsu Commission of Health [through grant Z2020032], by National Natural Science Foundation of China [through grant No.62102345], by The Youth Medical Science and Technology Innovation Project of Xuzhou Municipal Health Commission [through grant XWKYHT20210586], and by Special support for "Young Talents" of the Affiliated Hospital of Xuzhou Medical University [through grant 2020QQMRC08].
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Chen, X., Xu, Q., Xu, H. et al. Intelligent diagnosis of bladder cancer with limited MRI data. J Ambient Intell Human Comput 14, 13729–13740 (2023). https://doi.org/10.1007/s12652-022-04026-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-022-04026-1