1
|
Chakrabarty S, Sotiras A, Milchenko M, LaMontagne P, Hileman M, Marcus D. MRI-based Identification and Classification of Major Intracranial Tumor Types by Using a 3D Convolutional Neural Network: A Retrospective Multi-institutional Analysis. Radiol Artif Intell 2021; 3:e200301. [PMID: 34617029 DOI: 10.1148/ryai.2021200301] [Citation(s) in RCA: 25] [Impact Index Per Article: 8.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2020] [Revised: 06/23/2021] [Accepted: 07/14/2021] [Indexed: 11/11/2022]
Abstract
Purpose To develop an algorithm to classify postcontrast T1-weighted MRI scans by tumor classes (high-grade glioma, low-grade glioma [LGG], brain metastasis, meningioma, pituitary adenoma, and acoustic neuroma) and a healthy tissue (HLTH) class. Materials and Methods In this retrospective study, preoperative postcontrast T1-weighted MR scans from four publicly available datasets-the Brain Tumor Image Segmentation dataset (n = 378), the LGG-1p19q dataset (n = 145), The Cancer Genome Atlas Glioblastoma Multiforme dataset (n = 141), and The Cancer Genome Atlas Low Grade Glioma dataset (n = 68)-and an internal clinical dataset (n = 1373) were used. In all, a total of 2105 images were split into a training dataset (n = 1396), an internal test set (n = 361), and an external test dataset (n = 348). A convolutional neural network was trained to classify the tumor type and to discriminate between images depicting HLTH and images depicting tumors. The performance of the model was evaluated by using cross-validation, internal testing, and external testing. Feature maps were plotted to visualize network attention. The accuracy, positive predictive value (PPV), negative predictive value, sensitivity, specificity, F1 score, area under the receiver operating characteristic curve (AUC), and area under the precision-recall curve (AUPRC) were calculated. Results On the internal test dataset, across the seven different classes, the sensitivities, PPVs, AUCs, and AUPRCs ranged from 87% to 100%, 85% to 100%, 0.98 to 1.00, and 0.91 to 1.00, respectively. On the external data, they ranged from 91% to 97%, 73% to 99%, 0.97 to 0.98, and 0.9 to 1.0, respectively. Conclusion The developed model was capable of classifying postcontrast T1-weighted MRI scans of different intracranial tumor types and discriminating images depicting pathologic conditions from images depicting HLTH.Keywords MR-Imaging, CNS, Brain/Brain Stem, Diagnosis/Classification/Application Domain, Supervised Learning, Convolutional Neural Network, Deep Learning Algorithms, Machine Learning Algorithms Supplemental material is available for this article. © RSNA, 2021.
Collapse
Affiliation(s)
- Satrajit Chakrabarty
- Department of Electrical and Systems Engineering, Washington University in St Louis, 1 Brookings Dr, St Louis, MO 63130 (S.C.); Department of Radiology and Institute for Informatics, Washington University School of Medicine, St Louis, Mo (A.S.); and Mallinckrodt Institute of Radiology, Washington University School of Medicine, St Louis, Mo (M.M., P.L., M.H., D.M.)
| | - Aristeidis Sotiras
- Department of Electrical and Systems Engineering, Washington University in St Louis, 1 Brookings Dr, St Louis, MO 63130 (S.C.); Department of Radiology and Institute for Informatics, Washington University School of Medicine, St Louis, Mo (A.S.); and Mallinckrodt Institute of Radiology, Washington University School of Medicine, St Louis, Mo (M.M., P.L., M.H., D.M.)
| | - Mikhail Milchenko
- Department of Electrical and Systems Engineering, Washington University in St Louis, 1 Brookings Dr, St Louis, MO 63130 (S.C.); Department of Radiology and Institute for Informatics, Washington University School of Medicine, St Louis, Mo (A.S.); and Mallinckrodt Institute of Radiology, Washington University School of Medicine, St Louis, Mo (M.M., P.L., M.H., D.M.)
| | - Pamela LaMontagne
- Department of Electrical and Systems Engineering, Washington University in St Louis, 1 Brookings Dr, St Louis, MO 63130 (S.C.); Department of Radiology and Institute for Informatics, Washington University School of Medicine, St Louis, Mo (A.S.); and Mallinckrodt Institute of Radiology, Washington University School of Medicine, St Louis, Mo (M.M., P.L., M.H., D.M.)
| | - Michael Hileman
- Department of Electrical and Systems Engineering, Washington University in St Louis, 1 Brookings Dr, St Louis, MO 63130 (S.C.); Department of Radiology and Institute for Informatics, Washington University School of Medicine, St Louis, Mo (A.S.); and Mallinckrodt Institute of Radiology, Washington University School of Medicine, St Louis, Mo (M.M., P.L., M.H., D.M.)
| | - Daniel Marcus
- Department of Electrical and Systems Engineering, Washington University in St Louis, 1 Brookings Dr, St Louis, MO 63130 (S.C.); Department of Radiology and Institute for Informatics, Washington University School of Medicine, St Louis, Mo (A.S.); and Mallinckrodt Institute of Radiology, Washington University School of Medicine, St Louis, Mo (M.M., P.L., M.H., D.M.)
| |
Collapse
|
2
|
Marcus DS, Harms MP, Snyder AZ, Jenkinson M, Wilson JA, Glasser MF, Barch DM, Archie KA, Burgess GC, Ramaratnam M, Hodge M, Horton W, Herrick R, Olsen T, McKay M, House M, Hileman M, Reid E, Harwell J, Coalson T, Schindler J, Elam JS, Curtiss SW, Van Essen DC. Human Connectome Project informatics: quality control, database services, and data visualization. Neuroimage 2013; 80:202-19. [PMID: 23707591 DOI: 10.1016/j.neuroimage.2013.05.077] [Citation(s) in RCA: 258] [Impact Index Per Article: 23.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/11/2013] [Revised: 05/01/2013] [Accepted: 05/13/2013] [Indexed: 11/17/2022] Open
Abstract
The Human Connectome Project (HCP) has developed protocols, standard operating and quality control procedures, and a suite of informatics tools to enable high throughput data collection, data sharing, automated data processing and analysis, and data mining and visualization. Quality control procedures include methods to maintain data collection consistency over time, to measure head motion, and to establish quantitative modality-specific overall quality assessments. Database services developed as customizations of the XNAT imaging informatics platform support both internal daily operations and open access data sharing. The Connectome Workbench visualization environment enables user interaction with HCP data and is increasingly integrated with the HCP's database services. Here we describe the current state of these procedures and tools and their application in the ongoing HCP study.
Collapse
Affiliation(s)
- Daniel S Marcus
- Department of Radiology, Washington University School of Medicine, St. Louis, MO 63110, USA.
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
3
|
Ericson MN, Wilson M, Cote G, Britton CL, Xu W, Baba J, Bobrek M, Hileman M, Moore M, Frank S. Development of an implantable oximetry-based organ perfusion sensor. Conf Proc IEEE Eng Med Biol Soc 2007; 2004:2235-8. [PMID: 17272171 DOI: 10.1109/iembs.2004.1403651] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
A sensor system enabling real-time monitoring of organ perfusion following transplantation is presented. This system uses a three wavelength oximetry-based approach. The instrument is intended for implantation at the organ site during transplantation to provide real-time reporting of the perfusion status of the tissue for 7-10 days following the procedure. Data is transmitted from the sensor to a localized receiver using direct sequence spread spectrum techniques at 916 MHz. In this paper, the sensing method and associated electronics implementation are presented. The present status of system miniaturization is summarized along with plans for future miniaturization efforts. Preliminary sensor data is presented demonstrating the efficacy of the technique.
Collapse
Affiliation(s)
- M N Ericson
- Oak Ridge National Laboratory, Oak Ridge, TN 37831, USA
| | | | | | | | | | | | | | | | | | | |
Collapse
|