MAKİNE ÖĞRENMESİ İLE MESANE KANSERİ TESPİTİ

Öz

Mesane kanseri, özellikle ileri evrede ölümcül seyreden ve erken teşhisi zor olan bir kanser türüdür. Bu çalışmada, metin tabanlı hasta şikâyet verileri ile görüntü verilerinin bir arada değerlendirildiği hibrit bir yapay zekâ yaklaşımı sunulmuştur. Amaç, Türkiye'de geliştirilen yerli karar destek sistemi aracılığıyla mesane kanseri tanısında hekimlere yardımcı olacak bir araç ortaya koymak ve geliştirilen yazılımın sağlık ekonomisine katkı potansiyelini değerlendirmektir. Çalışmada, doğal dil işleme (NLP) ve görüntü işleme tekniklerinin entegrasyonu ile oluşturulan hibrit yapının doğruluk, hassasiyet, özgüllük, F1 skoru ve dice kaybı gibi metriklerle performansı ölçülmüş ve sonuçlar literatürle karşılaştırılarak klinik anlamlılık düzeyi tartışılmıştır.

Anahtar Kelimeler

• makine öğrenmesi
• mesane kanseri
• sağlık teknolojileri
• derin öğrenme
• Karar destek sistemi
• Hibrit model

Detection of Bladder Cancer Using Machine Learning

Öz

Bladder cancer is a type of cancer that is fatal, especially in advanced stages, and is difficult to diagnose early. In this study, a hybrid artificial intelligence approach is presented in which text-based patient complaint data and image data are evaluated together. The aim is to develop a tool that will assist physicians in the diagnosis of bladder cancer through a local decision support system developed in Türkiye and to evaluate the potential contribution of the developed software to health economics. In the study, the performance of the hybrid structure created by the integration of natural language processing (NLP) and image processing techniques was measured with metrics such as accuracy, sensitivity, specificity, F1 score and dice loss, and the clinical significance level was discussed by comparing the results with the literature.

Anahtar Kelimeler

• baldder cancer
• deep learning
• machine learning
• Decision support system
• Hybrid model
• Health technologies

Kaynakça

1. Sung H, Ferlay J, Siegel RL, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries, CA Cancer J Clin. 2021; 71: 209–249. https://doi.org/10.3322/caac.21660
2. Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017; 42: 60–88. https://doi.org/10.1016/j.media.2017.07.005
3. Baressi Šegota S, Lorencin I, Smolić K, Andelić N, Markić D, Mrzljak V, Štifanić D, Musulin J, Španjol J, Car Z. Semantic segmentation of urinary bladder cancer masses from CT images: A transfer learning approach. Biology. 2021; 10:1134. https://doi.org/10.3390/biology10111134
4. Patel NR, Sharma S, Gupta M. Multi-layered decision support systems for medical image diagnostics. Journal of Biomedical Informatics. 2019; 95:103195. https://doi.org/10.1016/j.jbi.2019.103195
5. Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. Med Image Comput Comput Assist Interv (MICCAI). 2015;234–241. https://doi.org/10.1007/978-3-319- 24574-4_28
6. Howard AG, Zhu M, Chen B, et al. MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint. 2017. https://doi.org/10.48550/arXiv.1704.04861
7. Chollet F. Xception: Deep learning with depthwise separable convolutions. Proc IEEE Conf Comput Vis Pattern Recognit (CVPR). 2017;1251–1258. https://doi.org/10.48550/arXiv.1610.02357
8. Xu Y, Hosny A, Zeleznik R, et al. Deep learning predicts lung cancer treatment response from serial medical imaging. Clin Cancer Res. 2019;25(11):3266–3275. https://doi.org/10.1158/1078-0432.CCR-18- 2495

9. Wang S, Yang DM, Rong R, et al. Pathology image analysis using segmentation deep learning algorithms. Am J Pathol. 2019;189(9):1686–1698. https://doi.org/10.1016/j.ajpath.2019.05.007