1
|
Klontzas ME, Kalarakis G, Koltsakis E, Papathomas T, Karantanas AH, Tzortzakakis A. Convolutional neural networks for the differentiation between benign and malignant renal tumors with a multicenter international computed tomography dataset. Insights Imaging 2024; 15:26. [PMID: 38270726 PMCID: PMC10811309 DOI: 10.1186/s13244-023-01601-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/22/2023] [Accepted: 12/17/2023] [Indexed: 01/26/2024] Open
Abstract
OBJECTIVES To use convolutional neural networks (CNNs) for the differentiation between benign and malignant renal tumors using contrast-enhanced CT images of a multi-institutional, multi-vendor, and multicenter CT dataset. METHODS A total of 264 histologically confirmed renal tumors were included, from US and Swedish centers. Images were augmented and divided randomly 70%:30% for algorithm training and testing. Three CNNs (InceptionV3, Inception-ResNetV2, VGG-16) were pretrained with transfer learning and fine-tuned with our dataset to distinguish between malignant and benign tumors. The ensemble consensus decision of the three networks was also recorded. Performance of each network was assessed with receiver operating characteristics (ROC) curves and their area under the curve (AUC-ROC). Saliency maps were created to demonstrate the attention of the highest performing CNN. RESULTS Inception-ResNetV2 achieved the highest AUC of 0.918 (95% CI 0.873-0.963), whereas VGG-16 achieved an AUC of 0.813 (95% CI 0.752-0.874). InceptionV3 and ensemble achieved the same performance with an AUC of 0.894 (95% CI 0.844-0.943). Saliency maps indicated that Inception-ResNetV2 decisions are based on the characteristics of the tumor while in most tumors considering the characteristics of the interface between the tumor and the surrounding renal parenchyma. CONCLUSION Deep learning based on a diverse multicenter international dataset can enable accurate differentiation between benign and malignant renal tumors. CRITICAL RELEVANCE STATEMENT Convolutional neural networks trained on a diverse CT dataset can accurately differentiate between benign and malignant renal tumors. KEY POINTS • Differentiation between benign and malignant tumors based on CT is extremely challenging. • Inception-ResNetV2 trained on a diverse dataset achieved excellent differentiation between tumor types. • Deep learning can be used to distinguish between benign and malignant renal tumors.
Collapse
Affiliation(s)
- Michail E Klontzas
- Department of Medical Imaging, University Hospital of Heraklion, Heraklion, Crete, Greece
- Computational BioMedicine Laboratory, Institute of Computer Science, Foundation for Research and Technology (FORTH), Heraklion, Crete, Greece
- Department of Radiology, School of Medicine, University of Crete, Voutes Campus, Heraklion, Greece
| | - Georgios Kalarakis
- Department of Diagnostic Radiology, Karolinska University Hospital, Stockholm, Sweden
- Division of Radiology, Department for Clinical Science, Intervention and Technology (CLINTEC), Karolinska Institutet, Stockholm, Sweden
| | - Emmanouil Koltsakis
- Department of Diagnostic Radiology, Karolinska University Hospital, Stockholm, Sweden
| | - Thomas Papathomas
- Institute of Metabolism and Systems Research, University of Birmingham, Birmingham, UK
- Department of Clinical Pathology, Vestre Viken Hospital Trust, Drammen, Norway
| | - Apostolos H Karantanas
- Department of Medical Imaging, University Hospital of Heraklion, Heraklion, Crete, Greece
- Computational BioMedicine Laboratory, Institute of Computer Science, Foundation for Research and Technology (FORTH), Heraklion, Crete, Greece
- Department of Radiology, School of Medicine, University of Crete, Voutes Campus, Heraklion, Greece
| | - Antonios Tzortzakakis
- Division of Radiology, Department for Clinical Science, Intervention and Technology (CLINTEC), Karolinska Institutet, Stockholm, Sweden.
- Medical Radiation Physics and Nuclear Medicine, Section for Nuclear Medicine, Karolinska University Hospital, 14 186, Huddinge, Stockholm, Sweden.
| |
Collapse
|
2
|
Causey J, Stubblefield J, Qualls J, Fowler J, Cai L, Walker K, Guan Y, Huang X. An Ensemble of U-Net Models for Kidney Tumor Segmentation With CT Images. IEEE/ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2022; 19:1387-1392. [PMID: 34061750 PMCID: PMC9210325 DOI: 10.1109/tcbb.2021.3085608] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/26/2023]
Abstract
We present here the Arkansas AI-Campus solution method for the 2019 Kidney Tumor Segmentation Challenge (KiTS19). Our Arkansas AI-Campus team participated the KiTS19 Challenge for four months, from March to July of 2019. This paper provides a summary of our methods, training, testing and validation results for this grand challenge in biomedical imaging analysis. Our deep learning model is an ensemble of U-Net models developed after testing many model variations. Our model has consistent performance on the local test dataset and the final competition independent test dataset. The model achieved local test Dice scores of 0.949 for kidney and tumor segmentation, and 0.601 for tumor segmentation, and the final competition test earned Dice scores 0.9470 and 0.6099 respectively. The Arkansas AI-Campus team solution with a composite DICE score of 0.7784 has achieved a final ranking of top fifty worldwide, and top five among the United States teams in the KiTS19 Competition.
Collapse
|
3
|
Crispin-Ortuzar M, Gehrung M, Ursprung S, Gill AB, Warren AY, Beer L, Gallagher FA, Mitchell TJ, Mendichovszky IA, Priest AN, Stewart GD, Sala E, Markowetz F. Three-Dimensional Printed Molds for Image-Guided Surgical Biopsies: An Open Source Computational Platform. JCO Clin Cancer Inform 2020; 4:736-748. [PMID: 32804543 PMCID: PMC7469624 DOI: 10.1200/cci.20.00026] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 06/22/2020] [Indexed: 12/14/2022] Open
Abstract
PURPOSE Spatial heterogeneity of tumors is a major challenge in precision oncology. The relationship between molecular and imaging heterogeneity is still poorly understood because it relies on the accurate coregistration of medical images and tissue biopsies. Tumor molds can guide the localization of biopsies, but their creation is time consuming, technologically challenging, and difficult to interface with routine clinical practice. These hurdles have so far hindered the progress in the area of multiscale integration of tumor heterogeneity data. METHODS We have developed an open-source computational framework to automatically produce patient-specific 3-dimensional-printed molds that can be used in the clinical setting. Our approach achieves accurate coregistration of sampling location between tissue and imaging, and integrates seamlessly with clinical, imaging, and pathology workflows. RESULTS We applied our framework to patients with renal cancer undergoing radical nephrectomy. We created personalized molds for 6 patients, obtaining Dice similarity coefficients between imaging and tissue sections ranging from 0.86 to 0.96 for tumor regions and between 0.70 and 0.76 for healthy kidneys. The framework required minimal manual intervention, producing the final mold design in just minutes, while automatically taking into account clinical considerations such as a preference for specific cutting planes. CONCLUSION Our work provides a robust and automated interface between imaging and tissue samples, enabling the development of clinical studies to probe tumor heterogeneity on multiple spatial scales.
Collapse
Affiliation(s)
- Mireia Crispin-Ortuzar
- Cancer Research UK, Cambridge Institute, University of Cambridge, Cambridge, United Kingdom
| | - Marcel Gehrung
- Cancer Research UK, Cambridge Institute, University of Cambridge, Cambridge, United Kingdom
| | - Stephan Ursprung
- Cancer Research UK, Cambridge Institute, University of Cambridge, Cambridge, United Kingdom
- Department of Radiology, University of Cambridge, Cambridge, United Kingdom
| | - Andrew B. Gill
- Department of Radiology, University of Cambridge, Cambridge, United Kingdom
| | - Anne Y. Warren
- Department of Histopathology, Cambridge University Hospitals National Health Service (NHS) Foundation Trust, Cambridge, United Kingdom
| | - Lucian Beer
- Department of Radiology, University of Cambridge, Cambridge, United Kingdom
- Department of Biomedical Imaging and Image-Guided Therapy, Medical University Vienna, Vienna, Austria
| | | | - Thomas J. Mitchell
- Department of Surgery, University of Cambridge, Cambridge, United Kingdom
- Wellcome Trust Sanger Institute, Hinxton, United Kingdom
| | - Iosif A. Mendichovszky
- Department of Radiology, University of Cambridge, Cambridge, United Kingdom
- Department of Radiology, Cambridge University Hospitals NHS Foundation Trust, Cambridge, United Kingdom
| | - Andrew N. Priest
- Department of Radiology, University of Cambridge, Cambridge, United Kingdom
- Department of Radiology, Cambridge University Hospitals NHS Foundation Trust, Cambridge, United Kingdom
| | - Grant D. Stewart
- Department of Surgery, University of Cambridge, Cambridge, United Kingdom
| | - Evis Sala
- Cancer Research UK, Cambridge Institute, University of Cambridge, Cambridge, United Kingdom
- Department of Radiology, University of Cambridge, Cambridge, United Kingdom
| | - Florian Markowetz
- Cancer Research UK, Cambridge Institute, University of Cambridge, Cambridge, United Kingdom
| |
Collapse
|
4
|
Gupta GN, Boris RS, Campbell SC, Zhang Z. Tumor Enucleation for Sporadic Localized Kidney Cancer: Pro and Con. J Urol 2015; 194:623-5. [DOI: 10.1016/j.juro.2015.06.033] [Citation(s) in RCA: 22] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/08/2015] [Indexed: 10/23/2022]
Affiliation(s)
- Gopal N. Gupta
- Departments of Urology, Surgery and Radiology, Loyola University Chicago, Chicago, Illinois
| | - Ronald S. Boris
- Department of Urology, Indiana University, Indianapolis, Indiana
| | | | - Zhiling Zhang
- Department of Urology, Sun Yat-Sen University Cancer Center, Guangzhou, China
- Glickman Urological and Kidney Institute, Cleveland Clinic, Cleveland, Ohio
| |
Collapse
|