Skip to main content

Advertisement

SpringerLink
Log in

Deep learning algorithm (YOLOv7) for automated renal mass detection on contrast-enhanced MRI: a 2D and 2.5D evaluation of results

  • Kidneys, Ureters, Bladder, Retroperitoneum
  • Published:
Abdominal Radiology Aims and scope Submit manuscript

Abstract

Introduction

Accurate diagnosis and treatment of kidney tumors greatly benefit from automated solutions for detection and classification on MRI. In this study, we explore the application of a deep learning algorithm, YOLOv7, for detecting kidney tumors on contrast-enhanced MRI.

Material and methods

We assessed the performance of YOLOv7 tumor detection on excretory phase MRIs in a large institutional cohort of patients with RCC. Tumors were segmented on MRI using ITK-SNAP and converted to bounding boxes. The cohort was randomly divided into ten benchmarks for training and testing the YOLOv7 algorithm. The model was evaluated using both 2-dimensional and a novel in-house developed 2.5-dimensional approach. Performance measures included F1, Positive Predictive Value (PPV), Sensitivity, F1 curve, PPV-Sensitivity curve, Intersection over Union (IoU), and mean average PPV (mAP).

Results

A total of 326 patients with 1034 tumors with 7 different pathologies were analyzed across ten benchmarks. The average 2D evaluation results were as follows: Positive Predictive Value (PPV) of 0.69 ± 0.05, sensitivity of 0.39 ± 0.02, and F1 score of 0.43 ± 0.03. For the 2.5D evaluation, the average results included a PPV of 0.72 ± 0.06, sensitivity of 0.61 ± 0.06, and F1 score of 0.66 ± 0.04. The best model performance demonstrated a 2.5D PPV of 0.75, sensitivity of 0.69, and F1 score of 0.72.

Conclusion

Using computer vision for tumor identification is a cutting-edge and rapidly expanding subject. In this work, we showed that YOLOv7 can be utilized in the detection of kidney cancers.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Abbreviations

YOLO:

You only look ones

PPV:

Positive predictive value

ccRCC:

Clear cell renal cell carcinoma

AML:

Angiomyolipoma

HLRCC:

Hereditary leiomyomatosis and renal cell cancer

RCC:

Renal cell carcinoma

mAP:

Mean average PPV

References

  1. Padala SA, Barsouk A, Thandra KC, Saginala K, Mohammed A, Vakiti A, et al. Epidemiology of Renal Cell Carcinoma. World J Oncol. 2020;11(3):79-87.

    Article  PubMed  PubMed Central  Google Scholar 

  2. Escudier B, Porta C, Schmidinger M, Rioux-Leclercq N, Bex A, Khoo V, et al. Renal cell carcinoma: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up. Annals of Oncology. 2019;30(5):706-20.

    Article  CAS  PubMed  Google Scholar 

  3. Cooper S, Flood TA, Khodary ME, Shabana WM, Papadatos D, Lavallee LT, et al. Diagnostic Yield and Complication Rate in Percutaneous Needle Biopsy of Renal Hilar Masses With Comparison With Renal Cortical Mass Biopsies in a Cohort of 195 Patients. American Journal of Roentgenology. 2019;212(3):570-5.

    Article  PubMed  Google Scholar 

  4. Cotta BH, Meagher MF, Bradshaw A, Ryan ST, Rivera-Sanfeliz G, Derweesh IH. Percutaneous renal mass biopsy: historical perspective, current status, and future considerations. Expert Review of Anticancer Therapy. 2019;19(4):301-8.

    Article  CAS  PubMed  Google Scholar 

  5. Sahni VA, Silverman SG. Biopsy of renal masses: when and why. Cancer imaging : the official publication of the International Cancer Imaging Society. 2009;9(1):44-55.

    Article  PubMed  Google Scholar 

  6. Rybicki FJ, Shu KM, Cibas ES, Fielding JR, VanSonnenberg E, Silverman SG. Percutaneous biopsy of renal masses: sensitivity and negative predictive value stratified by clinical setting and size of masses. American Journal of Roentgenology. 2003;180(5):1281-7.

    Article  PubMed  Google Scholar 

  7. Fonseca RB, Straub Hogan MM, Kapp ME, Cate F, Coogan A, Arora S, et al. Diagnostic renal mass biopsy is associated with individual categories of PADUA and RENAL nephrometry scores: Analysis of diagnostic and concordance rates with surgical resection. Urol Oncol. 2021;39(6):371.e7-.e15.

  8. Kim JH, Sun HY, Hwang J, Hong SS, Cho YJ, Doo SW, et al. Diagnostic accuracy of contrast-enhanced computed tomography and contrast-enhanced magnetic resonance imaging of small renal masses in real practice: sensitivity and specificity according to subjective radiologic interpretation. World Journal of Surgical Oncology. 2016;14(1):260.

    Article  PubMed  PubMed Central  Google Scholar 

  9. Elkassem AMA, Lo SS, Gunn AJ, Shuch BM, Dewitt-Foy ME, Abouassaly R, et al. Role of Imaging in Renal Cell Carcinoma: A Multidisciplinary Perspective. RadioGraphics. 2021;41(5):1387-407.

    Article  PubMed  Google Scholar 

  10. Pierorazio PM, Johnson MH, Ball MW, Gorin MA, Trock BJ, Chang P, et al. Five-year analysis of a multi-institutional prospective clinical trial of delayed intervention and surveillance for small renal masses: the DISSRM registry. Eur Urol. 2015;68(3):408-15.

    Article  PubMed  Google Scholar 

  11. Wang W, Cao K, Jin S, Zhu X, Ding J, Peng W. Differentiation of renal cell carcinoma subtypes through MRI-based radiomics analysis. European radiology. 2020;30(10):5738-47.

    Article  PubMed  Google Scholar 

  12. Oren O, Gersh BJ, Bhatt DL. Artificial intelligence in medical imaging: switching from radiographic pathological data to clinically meaningful endpoints. The Lancet Digital Health. 2020;2(9):e486-e8.

    Article  PubMed  Google Scholar 

  13. Erickson BJ, Korfiatis P, Akkus Z, Kline TL. Machine Learning for Medical Imaging. Radiographics. 2017;37(2):505-15.

    Article  PubMed  Google Scholar 

  14. Fu X, Liu H, Bi X, Gong X. Deep-Learning-Based CT Imaging in the Quantitative Evaluation of Chronic Kidney Diseases. Journal of Healthcare Engineering. 2021;2021:3774423.

    Article  PubMed  PubMed Central  Google Scholar 

  15. Lay N, Anari PY, Chaurasia A, Firouzabadi FD, Harmon S, Turkbey E, et al. Deep learning-based decision forest for hereditary clear cell renal cell carcinoma segmentation on MRI. Medical physics. 2023.

  16. Anari PY, Lay N, Chaurasia A, Gopal N, Samimi S, Harmon S, et al. Automatic segmentation of clear cell renal cell tumors, kidney, and cysts in patients with von Hippel-Lindau syndrome using U-net architecture on magnetic resonance images. ArXiv. 2023.

  17. Gudbjartsson H, Patz S. The rician distribution of noisy mri data. Magn Reson Med. 1995;34(6):910-4.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  18. Wang C-Y, Bochkovskiy A, Liao H-YM. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv preprint arXiv:220702696. 2022.

  19. Nikpanah M, Xu Z, Jin D, Farhadi F, Saboury B, Ball MW, et al. A deep-learning based artificial intelligence (AI) approach for differentiation of clear cell renal cell carcinoma from oncocytoma on multi-phasic MRI. Clinical imaging. 2021;77:291-8.

    Article  PubMed  PubMed Central  Google Scholar 

  20. Xi IL, Zhao Y, Wang R, Chang M, Purkayastha S, Chang K, et al. Deep Learning to Distinguish Benign from Malignant Renal Lesions Based on Routine MR Imaging. Clinical Cancer Research. 2020;26(8):1944-52.

    Article  PubMed  Google Scholar 

  21. Lopes Vendrami C, McCarthy RJ, Villavicencio CP, Miller FH. Predicting common solid renal tumors using machine learning models of classification of radiologist-assessed magnetic resonance characteristics. Abdominal Radiology. 2020;45(9):2797-809.

    Article  PubMed  Google Scholar 

  22. Uhm K-H, Jung S-W, Choi MH, Shin H-K, Yoo J-I, Oh SW, et al. Deep learning for end-to-end kidney cancer diagnosis on multi-phase abdominal computed tomography. npj Precision Oncology. 2021;5(1):54.

  23. Lin Z, Cui Y, Liu J, Sun Z, Ma S, Zhang X, et al. Automated segmentation of kidney and renal mass and automated detection of renal mass in CT urography using 2.5D U-Net-based deep convolutional neural network. European radiology. 2021;31(7):5021-31.

    Article  PubMed  Google Scholar 

  24. Bruno F, Arrigoni F, Mariani S, Splendiani A, Di Cesare E, Masciocchi C, et al. Advanced magnetic resonance imaging (MRI) of soft tissue tumors: techniques and applications. La Radiologia medica. 2019;124(4):243-52.

    Article  PubMed  Google Scholar 

Download references

Funding

Foundation for the National Institutes of Health

Author information

Authors and Affiliations

  1. Radiology and Imaging Sciences, Clinical Center,, National Institutes of Health, 10 Center Drive, 1C352, Bethesda, MD, 20892, USA

    Pouria Yazdian Anari, Aryan Zahergivar, Fatemeh Dehghani Firouzabadi, Mahshid Golagha, Shiva Singh, Fiona Obiezu, Evrim Turkbey, Elizabeth C. Jones & Ashkan A. Malayeri

  2. Artificial Intelligence Resource, National Institutes of Health, Bethesda, USA

    Nathan Lay, Stephanie Harmon & Baris Turkbey

  3. Urology Oncology Branch, National Cancer Institutes, National Institutes of Health, Bethesda, USA

    Aditi Chaurasia, Mark W. Ball & W. Marston Linehan

  4. Pathology Department, National Cancer Institutes, National Institutes of Health, Bethesda, USA

    Maria Merino

Authors
  1. Pouria Yazdian Anari
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nathan Lay
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Aryan Zahergivar
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Fatemeh Dehghani Firouzabadi
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Aditi Chaurasia
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Mahshid Golagha
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Shiva Singh
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Fatemeh Homayounieh
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Fiona Obiezu
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Stephanie Harmon
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Evrim Turkbey
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Maria Merino
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Elizabeth C. Jones
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Mark W. Ball
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. W. Marston Linehan
    View author publications

    You can also search for this author in PubMed Google Scholar

  16. Baris Turkbey
    View author publications

    You can also search for this author in PubMed Google Scholar

  17. Ashkan A. Malayeri
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ashkan A. Malayeri.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 15 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Anari, P.Y., Lay, N., Zahergivar, A. et al. Deep learning algorithm (YOLOv7) for automated renal mass detection on contrast-enhanced MRI: a 2D and 2.5D evaluation of results. Abdom Radiol 49, 1194–1201 (2024). https://doi.org/10.1007/s00261-023-04172-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00261-023-04172-w

Keywords

Search

Navigation