Aprendizado Profundo para Detecção de Cálculos Renais em Imagens de Tomografia Computadorizada
Abstract
Kidney calcification is a common condition, usually detected by specialist doctors using computed tomography (CT) scans. However, analyzing this type of exam is still challenging, making it repetitive, tiring, and error-prone. In this context, we propose an automatic method for detecting calcifications in the renal region on CT images, which may facilitate the specialist’s decision-making process. For the development of this method, a private image base with 887 samples from 20 exams of different patients was used. The images were segmented using the Mask-RCNN, and for the calcification detection step, we evaluated four YOLOv5 models with different sizes of the input image. The model that stood out was YOLOv5n with an input size of 640×640, obtaining a mAP_50 of 0.89, precision of 0.87, and recall of 0.85.
References
Baccouche, A., Garcia-Zapirain, B., Zheng, Y., and Elmaghraby, A. S. (2022). Early detection and classification of abnormality in prior mammograms using image-to-image translation and yolo techniques. Computer Methods and Programs in Biomedicine, 221:106884.
Bayram, A. F., Gurkan, C., Budak, A., and KARATAŞ, H. (2022). A detection and prediction model based on deep learning assisted by explainable artificial intelligence for kidney diseases. Avrupa Bilim ve Teknoloji Dergisi, (40):67–74.
Cui, Y., Sun, Z., Ma, S., Liu, W., Wang, X., Zhang, X., and Wang, X. (2021). Automatic detection and scoring of kidney stones on noncontrast ct images using stone nephrolithometry: Combined deep learning and thresholding methods. Molecular Imaging and Biology, 23(3):436–445.
Davradou, A. (2021). Detection and segmentation of pancreas using morphological snakes and deep convolutional neural networks.
Ebrahimi, S. and Mariano, V. Y. (2015). Image quality improvement in kidney stone detection on computed tomography images. Journal of image and graphics, 3(1):40.
Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 580–587.
He, K., Gkioxari, G., Dollár, P., and Girshick, R. (2017). Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 2961–2969.
Masood, A. et al. (2018). Computer-assisted decision support system in pulmonary cancer detection and stage classification on ct images. Journal of Biomedical Informatics, 79:117 – 128.
Memarsadeghi, M., Heinz-Peer, G., Helbich, T. H., Schaefer-Prokop, C., Kramer, G., Scharitzer, M., and Prokop, M. (2005). Unenhanced multi–detector row ct in patients suspected of having urinary stone disease: effect of section width on diagnosis. Radiology, 235(2):530–536.
Montalbo, F. J. P. (2020). A computer-aided diagnosis of brain tumors using a fine-tuned yolo-based model with transfer learning. KSII Transactions on Internet and Information Systems (TIIS), 14(12):4816–4834.
Nithya, A., Appathurai, A., Venkatadri, N., Ramji, D., and Palagan, C. A. (2020). Kidney disease detection and segmentation using artificial neural network and multi-kernel k-means clustering for ultrasound images. Measurement, 149:106952.
Padilla, R., Netto, S. L., and Da Silva, E. A. (2020). A survey on performance metrics for object-detection algorithms. In 2020 international conference on systems, signals and image processing (IWSSIP), pages 237–242. IEEE.
Parvathi, S. S. and Jonnadula, H. (2022). An efficient and optimal deep learning architecture using custom u-net and mask r-cnn models for kidney tumor semantic segmentation. International Journal of Advanced Computer Science and Applications.
Pecoits-Filho, R. (2004). Diagnóstico de doença renal crônica: avaliação da função renal. J Bras Nefrol, 26(3):4–5.
Prasetyo, E., Suciati, N., and Fatichah, C. (2020). A comparison of yolo and mask r-cnn for segmenting head and tail of fish. In 2020 4th International Conference on Informatics and Computational Sciences (ICICoS), pages 1–6. IEEE.
Rangel, É. B., Gomes, S. A., and Heilberg, I. P. (2005). Litíase renal no pré e pós-transplante renal. Brazilian Journal of Transplantation, 8(4):440–445.
Soares, E. F. and Aragão, G. S. (2013). Algoritmo de apoio para tratamento da litíase renal. In Anais do Congresso de Matemática aplicada à computacional, pages 303–305.
Sozzi, M., Cantalamessa, S., Cogato, A., Kayad, A., and Marinello, F. (2022). Automatic bunch detection in white grape varieties using yolov3, yolov4, and yolov5 deep learning algorithms. Agronomy, 12(2):319.
Thein, N., Hamamoto, K., Nugroho, H. A., and Adji, T. B. (2018). A comparison of three preprocessing techniques for kidney stone segmentation in ct scan images. In 2018 11th Biomedical Engineering International Conference (BMEiCON), pages 1–5. IEEE.
Thuan, D. (2021). Evolution of yolo algorithm and yolov5: The state-of-the-art object detention algorithm.
Tiago Ferolla Nunes, Denise M. Brunetta, C. M. L. P. C. B. P. J. S. R.-F. t. . I. r. a. (2010). Biblioteca Escolar Em Revista, 43(3):272–282. DOI: https://doi.org/10.11606/issn.2176-7262.v43i3p272-282.
Viswanath, K. and Gunasundari, R. (2014). Design and analysis performance of kidney stone detection from ultrasound image by level set segmentation and ann classification. In 2014 International Conference on Advances in Computing, Communications and Informatics (ICACCI), pages 407–414. IEEE.
Xu, B., Wang, W., Falzon, G., Kwan, P., Guo, L., Chen, G., Tait, A., and Schneider, D. (2020). Automated cattle counting using mask r-cnn in quadcopter vision system. Computers and Electronics in Agriculture, 171:105300.
Yan, B., Fan, P., Lei, X., Liu, Z., and Yang, F. (2021). A real-time apple targets detection method for picking robot based on improved yolov5. Remote Sensing, 13(9):1619.
Yildirim, K., Bozdag, P. G., Talo, M., Yildirim, O., Karabatak, M., and Acharya, U. R. (2021). Deep learning model for automated kidney stone detection using coronal ct images. Computers in Biology and Medicine, page 104569.
Zhao, T., Yang, Y., Niu, H., Wang, D., and Chen, Y. (2018). Comparing u-net convolutional network with mask r-cnn in the performances of pomegranate tree canopy segmentation. In Multispectral, hyperspectral, and ultraspectral remote sensing technology, techniques and applications VII, volume 10780, pages 210–218. SPIE.
Bayram, A. F., Gurkan, C., Budak, A., and KARATAŞ, H. (2022). A detection and prediction model based on deep learning assisted by explainable artificial intelligence for kidney diseases. Avrupa Bilim ve Teknoloji Dergisi, (40):67–74.
Cui, Y., Sun, Z., Ma, S., Liu, W., Wang, X., Zhang, X., and Wang, X. (2021). Automatic detection and scoring of kidney stones on noncontrast ct images using stone nephrolithometry: Combined deep learning and thresholding methods. Molecular Imaging and Biology, 23(3):436–445.
Davradou, A. (2021). Detection and segmentation of pancreas using morphological snakes and deep convolutional neural networks.
Ebrahimi, S. and Mariano, V. Y. (2015). Image quality improvement in kidney stone detection on computed tomography images. Journal of image and graphics, 3(1):40.
Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 580–587.
He, K., Gkioxari, G., Dollár, P., and Girshick, R. (2017). Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 2961–2969.
Masood, A. et al. (2018). Computer-assisted decision support system in pulmonary cancer detection and stage classification on ct images. Journal of Biomedical Informatics, 79:117 – 128.
Memarsadeghi, M., Heinz-Peer, G., Helbich, T. H., Schaefer-Prokop, C., Kramer, G., Scharitzer, M., and Prokop, M. (2005). Unenhanced multi–detector row ct in patients suspected of having urinary stone disease: effect of section width on diagnosis. Radiology, 235(2):530–536.
Montalbo, F. J. P. (2020). A computer-aided diagnosis of brain tumors using a fine-tuned yolo-based model with transfer learning. KSII Transactions on Internet and Information Systems (TIIS), 14(12):4816–4834.
Nithya, A., Appathurai, A., Venkatadri, N., Ramji, D., and Palagan, C. A. (2020). Kidney disease detection and segmentation using artificial neural network and multi-kernel k-means clustering for ultrasound images. Measurement, 149:106952.
Padilla, R., Netto, S. L., and Da Silva, E. A. (2020). A survey on performance metrics for object-detection algorithms. In 2020 international conference on systems, signals and image processing (IWSSIP), pages 237–242. IEEE.
Parvathi, S. S. and Jonnadula, H. (2022). An efficient and optimal deep learning architecture using custom u-net and mask r-cnn models for kidney tumor semantic segmentation. International Journal of Advanced Computer Science and Applications.
Pecoits-Filho, R. (2004). Diagnóstico de doença renal crônica: avaliação da função renal. J Bras Nefrol, 26(3):4–5.
Prasetyo, E., Suciati, N., and Fatichah, C. (2020). A comparison of yolo and mask r-cnn for segmenting head and tail of fish. In 2020 4th International Conference on Informatics and Computational Sciences (ICICoS), pages 1–6. IEEE.
Rangel, É. B., Gomes, S. A., and Heilberg, I. P. (2005). Litíase renal no pré e pós-transplante renal. Brazilian Journal of Transplantation, 8(4):440–445.
Soares, E. F. and Aragão, G. S. (2013). Algoritmo de apoio para tratamento da litíase renal. In Anais do Congresso de Matemática aplicada à computacional, pages 303–305.
Sozzi, M., Cantalamessa, S., Cogato, A., Kayad, A., and Marinello, F. (2022). Automatic bunch detection in white grape varieties using yolov3, yolov4, and yolov5 deep learning algorithms. Agronomy, 12(2):319.
Thein, N., Hamamoto, K., Nugroho, H. A., and Adji, T. B. (2018). A comparison of three preprocessing techniques for kidney stone segmentation in ct scan images. In 2018 11th Biomedical Engineering International Conference (BMEiCON), pages 1–5. IEEE.
Thuan, D. (2021). Evolution of yolo algorithm and yolov5: The state-of-the-art object detention algorithm.
Tiago Ferolla Nunes, Denise M. Brunetta, C. M. L. P. C. B. P. J. S. R.-F. t. . I. r. a. (2010). Biblioteca Escolar Em Revista, 43(3):272–282. DOI: https://doi.org/10.11606/issn.2176-7262.v43i3p272-282.
Viswanath, K. and Gunasundari, R. (2014). Design and analysis performance of kidney stone detection from ultrasound image by level set segmentation and ann classification. In 2014 International Conference on Advances in Computing, Communications and Informatics (ICACCI), pages 407–414. IEEE.
Xu, B., Wang, W., Falzon, G., Kwan, P., Guo, L., Chen, G., Tait, A., and Schneider, D. (2020). Automated cattle counting using mask r-cnn in quadcopter vision system. Computers and Electronics in Agriculture, 171:105300.
Yan, B., Fan, P., Lei, X., Liu, Z., and Yang, F. (2021). A real-time apple targets detection method for picking robot based on improved yolov5. Remote Sensing, 13(9):1619.
Yildirim, K., Bozdag, P. G., Talo, M., Yildirim, O., Karabatak, M., and Acharya, U. R. (2021). Deep learning model for automated kidney stone detection using coronal ct images. Computers in Biology and Medicine, page 104569.
Zhao, T., Yang, Y., Niu, H., Wang, D., and Chen, Y. (2018). Comparing u-net convolutional network with mask r-cnn in the performances of pomegranate tree canopy segmentation. In Multispectral, hyperspectral, and ultraspectral remote sensing technology, techniques and applications VII, volume 10780, pages 210–218. SPIE.
Published
2023-06-27
How to Cite
LIMA, Thiago; CATIELY, Camila; SOUSA, Vitoria; VERAS, Rodrigo; ARAÚJO, Flávio.
Aprendizado Profundo para Detecção de Cálculos Renais em Imagens de Tomografia Computadorizada. In: BRAZILIAN SYMPOSIUM ON COMPUTING APPLIED TO HEALTH (SBCAS), 23. , 2023, São Paulo/SP.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2023
.
p. 47-58.
ISSN 2763-8952.
DOI: https://doi.org/10.5753/sbcas.2023.229430.
