Bladder Cancer Grading from H&E Stained Samples from TCGA Data

Abstract

Early diagnosis of bladder cancer (BC) is of great importance for the treatment and course of the disease. The most effective method for diagnosis is the examination of the tissue sample, on which various procedures are applied, by the pathologist under a microscope. However, this approach is subjective and may vary depending on the knowledge and experience of the pathologists. To increase objectivity and assist the pathologist, this study presents automated bladder urothelial carcinoma grading from whole slide images (WSI). Performance comparisons are made using 3 different machine learning methods such as naive Bayes, k nearest neighbor and decision tree. Experimental results show that the decision tree method achieves the highest performance with 82% and can be used to assist the pathologist during diagnosis.

Keywords

• Bladder cancer
• histopathology
• machine learning
• whole slide image (WSI)
• computer aided diagnosis (CAD)

TCGA Verilerinden H&E ile Boyanmış Örneklerden Mesane Kanseri Derecelendirmesi

Öz

Mesane kanserinin (BC) erken teşhisi, hastalığın tedavisi ve seyri için büyük önem taşımaktadır. Teşhis için en etkili yöntem, çeşitli işlemlerin uygulandığı doku örneğinin patolog tarafından mikroskop altında incelenmesidir. Ancak bu yaklaşım subjektiftir ve patologların bilgi ve tecrübesine bağlı olarak değişebilir. Objektifliği artırmak ve patoloğa yardımcı olmak için bu çalışma, tam slayt görüntülerinden (WSI) otomatik mesane ürotelyal karsinom derecelendirmesini sunar. Naive Bayes, k en yakın komşu ve karar ağacı gibi 3 farklı makine öğrenme yöntemi kullanılarak performans karşılaştırması yapılır. Deneysel sonuçlar, karar ağacı yönteminin %82 ile en yüksek performansı elde ettiğini ve tanı sırasında patoloğa yardımcı olmak için kullanılabileceğini göstermektedir.

Anahtar Kelimeler

• Mesane kanseri
• histopatoloji
• makine öğrenimi
• tam slayt görüntüsü (TSG)
• bilgisayar destekli teşhis (BDT)

Kaynakça

1. [1] Oosterlinck W, Lobel B, Jakse G, Malmström PU, Stöckle M, Sternberg C. EAU Working Group on Oncological Urology. Guidelines on bladder cancer, European urology. 2002; 41: 105-112.
2. [2] American Cancer Society. Cancer Facts & Figures. 2022.
3. [3] Degirmenci A, Karal O. Robust Incremental Outlier Detection Approach Based on a New Metric in Data Streams. IEEE Access, 2021; 9: 160347-160360.
4. [4] Degirmenci A, Karal O. Efficient density and cluster based incremental outlier detection in data streams. Information Sciences. 2022; 607: 901-920.
5. [5] Apaydin M, Yumus M, Degirmenci A, Kesikburun S, Karal O. Deep Convolutional Neural Networks Using U-Net for Automatic Intervertebral Disc Segmentation in Axial MRI. In 2022 Innovations in Intelligent Systems and Applications Conference (ASYU). 2022.
6. [6] Esen F, Degirmenci A, Karal O. Implementation of the Object Detection Algorithm (YOLOV3) on FPGA. In 2021 Innovations in Intelligent Systems and Applications Conference (ASYU). 2021.
7. [7] Karal O. Robust and optimal epsilon-insensitive Kernel-based regression for general noise models. Engineering Applications of Artificial Intelligence. 2023; 120: 105841.
8. [8] Fuster S, Khoraminia F, Kiraz U, Kanwal N, Kvikstad V, Eftestøl T. ... Engan K. Invasive cancerous area detection in Non-Muscle invasive bladder cancer whole slide images. In 2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP). 2022; 1-5.

9. [9] Khosravi P, Kazemi E, Imielinski M, Elemento O, Hajirasouliha I. Deep convolutional neural networks enable discrimination of heterogeneous digital pathology images. EBioMedicine, 2018; 27: 317-328.
10. [10] Yin PN, Kc K, Wei S, Yu Q, Li R, Haake A.R, ... Cui F. Histopathological distinction of non-invasive and invasive bladder cancers using machine learning approaches. BMC medical informatics and decision making. 2020; 20: 1-11.
11. [11] Jansen I, Lucas M, Bosschieter J, de Boer OJ, Meijer SL, van Leeuwen TG, ... Savci-Heijink CD. Automated detection and grading of non–muscle-invasive urothelial cell carcinoma of the bladder. The American journal of pathology. 2020; 190: 1483-1490.
12. [12] Woerl AC, Eckstein M, Geiger J, Wagner DC, Daher T, Stenzel P, ... Foersch S. Deep learning predicts molecular subtype of muscle-invasive bladder cancer from conventional histopathological slides. European urology. 2020; 78: 256-264.
13. [13] Chen S, Jiang L, Zheng X, Shao J, Wang T, Zhang E, ... Zheng J. Clinical use of machine learning‐based pathomics signature for diagnosis and survival prediction of bladder cancer. Cancer science. 2021; 112: 2905-2914.
14. [14] Lucas M, Jansen I, van Leeuwen TG, Oddens JR, de Bruin DM. Marquering HA. Deep learning–based recurrence prediction in patients with non–muscle-invasive bladder cancer. European Urology Focus. 2020.
15. [15] Tokuyama N, Saito A, Muraoka R, Matsubara S, Hashimoto T, Satake N, ... Ohno Y. Prediction of non-muscle invasive bladder cancer recurrence using machine learning of quantitative nuclear features. Modern Pathology. 2022; 35: 533-538.
16. [16] Bhambhvani HP, Zamora A, Shkolyar E, Prado K, Greenberg DR, Kasman AM, ... Shah JB. Development of robust artificial neural networks for prediction of 5-year survival in bladder cancer. In Urologic Oncology: Seminars and Original Investigations, 2021; 39: 193-e7.
17. [17] Song Q, Seigne JD, Schned AR, Kelsey KT, Karagas MR, Hassanpour S. A machine learning approach for long-term prognosis of bladder cancer based on clinical and molecular features. AMIA Summits on Translational Science Proceedings. 2020.
18. [18] Zheng Q, Yang R, Ni X, Yang S, Xiong L, Yan D, ... Liu X. Accurate Diagnosis and Survival Prediction of Bladder Cancer Using Deep Learning on Histological Slides. Cancers. 2022; 14: 5807.
19. [19] Zheng Q, Jiang Z, Ni X, Yang S, Jiao P, Wu J, ... Liu X. Machine Learning Quantified Tumor-Stroma Ratio Is an Independent Prognosticator in Muscle-Invasive Bladder Cancer. International Journal of Molecular Sciences. 2023; 24: 2746.
20. [20] Değirmenci A. Computer Based Grading of Bladder Carcinoma. Yüksek lisans tezi, Ankara Yıldırım Beyazıt Üniversitesi Fen Bilimleri Enstitüsü. 2017.
21. [21] Hatipoğlu Ş, Belgrat MA, Degirmenci A, Karal Ö. Prediction of Unemployment Rates in Turkey by k-Nearest Neighbor Regression Analysis. In 2021 Innovations in Intelligent Systems and Applications Conference (ASYU). 2022.
22. [22] APAYDIN M, Yumuş M, Değirmenci A, Karal Ö. Evaluation of air temperature with machine learning regression methods using Seoul City meteorological data. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi. 2022; 28: 737-747.
23. [23] Degirmenci A, Karal O. iMCOD: Incremental multi-class outlier detection model in data streams. Knowledge-Based Systems. 2022; 258: 109950.
24. [24] Ozaslan IN, Degirmenci A, Karal O. Tourism Demand Forecasting for Turkey by Using Adaboost Algorithm. In 2022 Innovations in Intelligent Systems and Applications Conference (ASYU). 2022.