CPP-UNet: Combined Pyramid Pooling Modules in the U-Net Network for Kidney, Tumor and Cyst Segmentation

Authors

Keywords:

Pyramid Pooling Module, Segmentation Renal Diseases, Kidney Cancer, U-Net

Abstract

Renal carcinoma stands prominently as a significant contributor to global cancer-related mortality rates, highlighting the critical importance of early detection and diagnosis in the management of this ailment. Moreover, the rising incidence of kidney tumors poses a challenge in differentiating between malignant and benign lesions using radiographic methods. Therefore, we present CPP-UNet, an innovative convolutional neural network-based architecture designed for the segmentation of renal structures, including the kidneys themselves and renal masses (cysts and tumors), in a computed tomography (CT) scan. Particularly, we investigate the fusion of the Pyramid Pooling Module (PPM) and Atrous Spatial Pyramid Pooling (ASPP) for improving the UNet network by integrating contextual information across multiple scales. Our proposed method yielded promising outcomes in the Kidney and Kidney Tumor Segmentation challenge (KiTS21 and KiTS23) datasets, exhibiting Dice indices of 93.51% and 92.84% for Kidneys and Masses, 90.33% and 92.08% for Renal Masses, and 85.69% and 88.17% for Tumors, respectively.

Downloads

Download data is not yet available.

Author Biographies

Caio Eduardo Falcão Matos, Federal University of Maranhão (UFMA)

Caio Falcao is a PhD student at Federal University of Maranhao (UFMA) since 2020. He received his Master's Degree in Computer Science from Federal University of Maranhao (UFMA). He is currently a Professor of Basic, Technical, and Technological Education at the Federal Institute of Education, Science and Technology of Maranhao (IFMA), Barreirinhas Campus. He served as a Substitute Professor at the Federal University of Maranhao (UFMA) and as a researcher at the Applied Computing Center (NCA/UFMA), developing mainly research/extension projects focused on the following topics: image processing, pattern recognition, machine learning, and medical images.

Geraldo Braz Junior, Federal University of Maranhão (UFMA)

Geraldo Braz Junior receive PhD in Electrical Engineering from Federal University of Maranhao. He is currently Associate Professor I at the Federal University of Maranhao a permanent member of the Postgraduate Programs of the Master's in Computer Science (PPGCC/UFMA) and the Doctorate in Computer Science Association UFMA-UFPI (DCCMAPI). Has experience in computer vision, machine learning, deep learning, and medical image processing.

João Dallyson Sousa de Almeida, Federal University of Maranhão (UFMA)

Joao Almeida received a DSc. Degree in Electric Engineering from the Federal University of Maranhao (UFMA), Brazil, in 2013. He is currently Associate Professor I at the Federal University of Maranhao. He coordinates the VipLab-UFMA Vision and Image Processing Laboratory. He has experience in Computer Science, working mainly on the following topics: image processing, pattern recognition, machine learning, and ophthalmological medical images.

Anselmo Cardoso de Paiva, Federal University of Maranhão (UFMA)

Anselmo Paiva received a DSc. Degree in Computing from Pontifical Catholic University of Rio de Janeiro. He is currently a Full Professor at the Federal University of Maranhao. Coordinator of the NCA-UFMA Applied Computing Center. He has experience in Computer Science, with an emphasis on Graphics Processing, working mainly on the following topics: Virtual and Augmented Reality, Computer Graphics, GIS, Medical Image Processing, and Volumetric Visualization.

References

A. L. Ammirati, “Chronic kidney disease,” Revista da Associação

Médica Brasileira, vol. 66, pp. s03–s09, 2020. DOI:https://doi.org/10.

/1806-9282.66.S1.3.

A. Chang, A. Finelli, J. S. Berns, and M. Rosner, “Chronic kidney

disease in patients with renal cell carcinoma,” Advances in chronic

kidney disease, vol. 21, no. 1, pp. 91–95, 2014. DOI:https://doi.org/

1053/j.ackd.2013.09.003.

T. Gansler, S. Fedewa, M. B. Amin, C. C. Lin, and A. Jemal, “Trends

in reporting histological subtyping of renal cell carcinoma: association

with cancer center type,” Human pathology, vol. 74, pp. 99–108, 2018.

DOI:https://doi.org/10.1016/j.humpath.2018.01.010.

R. Siegel, J. Ma, Z. Zou, and A. Jemal, “Cancer statistics, 2014.,” CA: a

cancer journal for clinicians, vol. 64, no. 1, pp. 9–29, 2014. DOI:https:

//doi.org/10.3322/caac.21208.

Q. Cai, Y. Chen, X. Qi, D. Zhang, J. Pan, Z. Xie, C. Xu, S. Li, X. Zhang,

Y. Gao, et al., “Temporal trends of kidney cancer incidence and mortality

from 1990 to 2016 and projections to 2030,” Translational Andrology

and Urology, vol. 9, no. 2, p. 166, 2020. DOI:https://doi.org/10.21037/

tau.2020.02.23.

X. Bai, M. Yi, B. Dong, X. Zheng, and K. Wu, “The global, regional,

and national burden of kidney cancer and attributable risk factor analysis

from 1990 to 2017,” Experimental Hematology & Oncology, vol. 9,

pp. 1–15, 2020. DOI:https://doi.org/10.1186/s40164-020-00181-3.

R. L. Siegel, A. N. Giaquinto, and A. Jemal, “Cancer statistics, 2024,”

CA: A Cancer Journal for Clinicians, 2024. DOI:https://doi.org/10.3322/

caac.21820.

American Cancer Society, “Kidney cancer early detection, diagnosis,

and staging.” Available online: https://www.cancer.org/content/dam/

CRC/PDF/Public/8661.00.pdf (accessed on 06 February 2024), February

E. Bercovich and M. C. Javitt, “Medical imaging: from roentgen to the

digital revolution, and beyond,” Rambam Maimonides medical journal,

vol. 9, no. 4, 2018. DOI:https://doi.org/10.5041/RMMJ.10355.

Z. Zhao, H. Chen, and L. Wang, “A coarse-to-fine framework for the

kidney and kidney tumor segmentation challenge,” in Kidney and

Kidney Tumor Segmentation: MICCAI 2021 Challenge, KiTS 2021, Held

in Conjunction with MICCAI 2021, Strasbourg, France, September 27,

, Proceedings, pp. 53–58, Springer, 2022. DOI:https://doi.org/10.

/978-3-030-98385-7_8.

A. Golts, D. Khapun, D. Shats, Y. Shoshan, and F. Gilboa-Solomon,

“An ensemble of 3d u-net based models for segmentation of kidney

and masses in ct scans,” in Kidney and Kidney Tumor Segmentation:

MICCAI 2021 Challenge, KiTS 2021, Held in Conjunction with MICCAI

, Strasbourg, France, September 27, 2021, Proceedings, pp. 103–

, Springer, 2022. DOI:https://doi.org/10.1007/978-3-030-98385-7_

Y. George, “A coarse-to-fine 3d u-net network for semantic segmentation

of kidney ct scans,” in Kidney and Kidney Tumor Segmentation: MICCAI

Challenge, KiTS 2021, Held in Conjunction with MICCAI 2021,

Strasbourg, France, September 27, 2021, Proceedings, pp. 137–142,

Springer, 2022. DOI:https://doi.org/10.1007/978-3-030-98385-7_18.

X. Yang, J. Zhang, J. Zhang, and Y. Xia, “Transfer learning for

kits21 challenge,” in Kidney and Kidney Tumor Segmentation: MICCAI

Challenge, KiTS 2021, Held in Conjunction with MICCAI 2021,

Strasbourg, France, September 27, 2021, Proceedings, pp. 158–163,

Springer, 2022. DOI:https://doi.org/10.1007/978-3-030-98385-7_21.

P. Sun, Z. Mo, F. Hu, X. Song, T. Mo, B. Yu, Y. Zhang, and

Z. Chen, “Segmentation of kidney mass using agdenseu-net 2.5 d

model,” Computers in Biology and Medicine, vol. 150, p. 106223, 2022.

DOI:https://doi.org/10.1016/j.compbiomed.2022.106223.

M. Wu and Z. Liu, “Less is more: Contrast attention assisted unet

for kidney, tumor and cyst segmentations,” in Kidney and Kidney

Tumor Segmentation: MICCAI 2021 Challenge, KiTS 2021, Held in

Conjunction with MICCAI 2021, Strasbourg, France, September 27,

, Proceedings, pp. 46–52, Springer, 2022. DOI:https://doi.org/10.

/978-3-030-98385-7_7.

K.-H. Uhm, H. Cho, Z. Xu, S. Lim, S.-W. Jung, S.-H. Hong, and S.-

J. Ko, “Exploring 3d u-net training configurations and post-processing

strategies for the miccai 2023 kidney and tumor segmentation challenge,”

arXiv preprint arXiv:2312.05528, 2023. DOI:https://doi.org/10.48550/

arXiv.2312.05528.

A. Myronenko, D. Yang, Y. He, and D. Xu, “Automated 3d segmentation

of kidneys and tumors in miccai kits 2023 challenge,” arXiv

preprint arXiv:2310.04110, 2023. DOI:https://doi.org/10.48550/arXiv.

04110.

G. Stoica, M. Breaban, and V. Barbu, “Analyzing domain shift

when using additional data for the miccai kits23 challenge,” arXiv

preprint arXiv:2309.02001, 2023. DOI:https://doi.org/10.48550/arXiv.

02001.

S. Zheng, Q. Sun, X. Ye, W. Li, L. Yu, and C. Yang, “Multi-scale

adversarial learning with difficult region supervision learning models for

primary tumor segmentation,” Physics in Medicine & Biology, vol. 69,

no. 8, p. 085009, 2024. DOI:https://doi.org/10.1088/1361-6560/ad3321.

N. Heller, N. Sathianathen, A. Kalapara, E. Walczak, K. Moore,

H. Kaluzniak, J. Rosenberg, P. Blake, Z. Rengel, M. Oestreich, et al.,

“The 2021 kidney and kidney tumor segmentation challenge.” Available

online: https://kits21.kits-challenge.org/ (accessed on 06 January 2024),

S. Samuel, M. Moore, B. Patterson, H. Sheridan, and C. Sorensen,

“Neuroimaging data primer: A resource for curating digital imaging

and communications in medicine (dicom) and neuroimaging informatics

technology initiative (nifti) files,” 2020. DOI:https://doi.org/10.7302/

S. M. Pizer, E. P. Amburn, J. D. Austin, R. Cromartie, A. Geselowitz,

T. Greer, B. ter Haar Romeny, J. B. Zimmerman, and K. Zuiderveld,

“Adaptive histogram equalization and its variations,” Computer vision,

graphics, and image processing, vol. 39, no. 3, pp. 355–368, 1987.

DOI:https://doi.org/10.1016/S0734-189X(87)80186-X.

L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, “Encoderdecoder

with atrous separable convolution for semantic image segmentation,”

in Proceedings of the European conference on computer vision

(ECCV), pp. 801–818, 2018. DOI:https://doi.org/10.48550/arXiv.1802.

M. Bland, An Introduction to Medical Statistics. OUP Oxford, 2015.

ISBN: 9780191002991.

A. A. Taha and A. Hanbury, “Metrics for evaluating 3d medical

image segmentation: analysis, selection, and tool,” BMC medical imaging,

vol. 15, no. 1, pp. 1–28, 2015. DOI:https://doi.org/10.1186/

s12880-015-0068-x.

T. Eelbode, J. Bertels, M. Berman, D. Vandermeulen, F. Maes, R. Bisschops,

and M. B. Blaschko, “Optimization for medical image segmentation:

theory and practice when evaluating with dice score or

jaccard index,” IEEE Transactions on Medical Imaging, vol. 39, no. 11,

pp. 3679–3690, 2020. DOI:https://doi.org/10.1109/TMI.2020.3002417.

C. E. F. Matos, M. V. S. L. Oliveira, J. O. B. Diniz, A. G. S. Fernandes,

G. B. Junior, and A. C. de Paiva, “Ppm-deeplab: Módulo de pirâmide

de pooling como codificador da rede deeplabv3+ para segmentaçao de

rins, cistos e tumores renais,” in Anais do XXIII Simpósio Brasileiro de

Computação Aplicada à Saúde, pp. 210–221, SBC, 2023. DOI:https:

//doi.org/10.5753/sbcas.2023.229611.

Downloads

Published

2024-07-31

How to Cite

Matos, C. E. F., Junior, G. B., Almeida, J. D. S. de ., & Paiva, . A. C. de . (2024). CPP-UNet: Combined Pyramid Pooling Modules in the U-Net Network for Kidney, Tumor and Cyst Segmentation. IEEE Latin America Transactions, 22(8), 642–650. Retrieved from https://latamt.ieeer9.org/index.php/transactions/article/view/8866

Issue

Vol. 22 No. 8 (2024): Ordinary Issue

Section

Computing

Most read articles by the same author(s)