1
|
Cao W, Howe BM, Wright DE, Ramanathan S, Rhodes NG, Korfiatis P, Amrami KK, Spinner RJ, Kline TL. Abnormal Brachial Plexus Differentiation from Routine Magnetic Resonance Imaging: An AI-based Approach. Neuroscience 2024; 546:178-187. [PMID: 38518925 DOI: 10.1016/j.neuroscience.2024.03.017] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2023] [Revised: 03/11/2024] [Accepted: 03/17/2024] [Indexed: 03/24/2024]
Abstract
Automatic abnormality identification of brachial plexus (BP) from normal magnetic resonance imaging to localize and identify a neurologic injury in clinical practice (MRI) is still a novel topic in brachial plexopathy. This study developed and evaluated an approach to differentiate abnormal BP with artificial intelligence (AI) over three commonly used MRI sequences, i.e. T1, FLUID sensitive and post-gadolinium sequences. A BP dataset was collected by radiological experts and a semi-supervised artificial intelligence method was used to segment the BP (based on nnU-net). Hereafter, a radiomics method was utilized to extract 107 shape and texture features from these ROIs. From various machine learning methods, we selected six widely recognized classifiers for training our Brachial plexus (BP) models and assessing their efficacy. To optimize these models, we introduced a dynamic feature selection approach aimed at discarding redundant and less informative features. Our experimental findings demonstrated that, in the context of identifying abnormal BP cases, shape features displayed heightened sensitivity compared to texture features. Notably, both the Logistic classifier and Bagging classifier outperformed other methods in our study. These evaluations illuminated the exceptional performance of our model trained on FLUID-sensitive sequences, which notably exceeded the results of both T1 and post-gadolinium sequences. Crucially, our analysis highlighted that both its classification accuracies and AUC score (area under the curve of receiver operating characteristics) over FLUID-sensitive sequence exceeded 90%. This outcome served as a robust experimental validation, affirming the substantial potential and strong feasibility of integrating AI into clinical practice.
Collapse
Affiliation(s)
- Weiguo Cao
- Department of Radiology, Mayo Clinic, 200 First Street SW, Charlton 1, Rochester, MN 55905, USA
| | - Benjamin M Howe
- Department of Radiology, Mayo Clinic, 200 First Street SW, Charlton 1, Rochester, MN 55905, USA
| | - Darryl E Wright
- Department of Radiology, Mayo Clinic, 200 First Street SW, Charlton 1, Rochester, MN 55905, USA
| | - Sumana Ramanathan
- Department of Radiology, Mayo Clinic, 200 First Street SW, Charlton 1, Rochester, MN 55905, USA
| | - Nicholas G Rhodes
- Department of Radiology, Mayo Clinic, 200 First Street SW, Charlton 1, Rochester, MN 55905, USA
| | - Panagiotis Korfiatis
- Department of Radiology, Mayo Clinic, 200 First Street SW, Charlton 1, Rochester, MN 55905, USA
| | - Kimberly K Amrami
- Department of Radiology, Mayo Clinic, 200 First Street SW, Charlton 1, Rochester, MN 55905, USA
| | - Robert J Spinner
- Department of Neurological Surgery, Mayo Clinic, 200 First Street SW, Gonda 8, Rochester, MN 55905, USA
| | - Timothy L Kline
- Department of Radiology, Mayo Clinic, 200 First Street SW, Charlton 1, Rochester, MN 55905, USA.
| |
Collapse
|
2
|
Cao W, Pomeroy MJ, Zhang S, Tan J, Liang Z, Gao Y, Abbasi AF, Pickhardt PJ. An Adaptive Learning Model for Multiscale Texture Features in Polyp Classification via Computed Tomographic Colonography. SENSORS (BASEL, SWITZERLAND) 2022; 22:907. [PMID: 35161653 PMCID: PMC8840570 DOI: 10.3390/s22030907] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/01/2021] [Revised: 01/14/2022] [Accepted: 01/20/2022] [Indexed: 12/10/2022]
Abstract
Objective: As an effective lesion heterogeneity depiction, texture information extracted from computed tomography has become increasingly important in polyp classification. However, variation and redundancy among multiple texture descriptors render a challenging task of integrating them into a general characterization. Considering these two problems, this work proposes an adaptive learning model to integrate multi-scale texture features. Methods: To mitigate feature variation, the whole feature set is geometrically split into several independent subsets that are ranked by a learning evaluation measure after preliminary classifications. To reduce feature redundancy, a bottom-up hierarchical learning framework is proposed to ensure monotonic increase of classification performance while integrating these ranked sets selectively. Two types of classifiers, traditional (random forest + support vector machine)- and convolutional neural network (CNN)-based, are employed to perform the polyp classification under the proposed framework with extended Haralick measures and gray-level co-occurrence matrix (GLCM) as inputs, respectively. Experimental results are based on a retrospective dataset of 63 polyp masses (defined as greater than 3 cm in largest diameter), including 32 adenocarcinomas and 31 benign adenomas, from adult patients undergoing first-time computed tomography colonography and who had corresponding histopathology of the detected masses. Results: We evaluate the performance of the proposed models by the area under the curve (AUC) of the receiver operating characteristic curve. The proposed models show encouraging performances of an AUC score of 0.925 with the traditional classification method and an AUC score of 0.902 with CNN. The proposed adaptive learning framework significantly outperforms nine well-established classification methods, including six traditional methods and three deep learning ones with a large margin. Conclusions: The proposed adaptive learning model can combat the challenges of feature variation through a multiscale grouping of feature inputs, and the feature redundancy through a hierarchal sorting of these feature groups. The improved classification performance against comparative models demonstrated the feasibility and utility of this adaptive learning procedure for feature integration.
Collapse
Affiliation(s)
- Weiguo Cao
- Department of Radiology, Stony Brook University, Stony Brook, NY 11794, USA; (W.C.); (M.J.P.); (S.Z.); (Y.G.); (A.F.A.)
| | - Marc J. Pomeroy
- Department of Radiology, Stony Brook University, Stony Brook, NY 11794, USA; (W.C.); (M.J.P.); (S.Z.); (Y.G.); (A.F.A.)
- Department of Biomedical Engineering, Stony Brook University, Stony Brook, NY 11794, USA
| | - Shu Zhang
- Department of Radiology, Stony Brook University, Stony Brook, NY 11794, USA; (W.C.); (M.J.P.); (S.Z.); (Y.G.); (A.F.A.)
| | - Jiaxing Tan
- Department of Computer Science, City University of New York, New York, NY 10314, USA;
| | - Zhengrong Liang
- Department of Radiology, Stony Brook University, Stony Brook, NY 11794, USA; (W.C.); (M.J.P.); (S.Z.); (Y.G.); (A.F.A.)
- Department of Biomedical Engineering, Stony Brook University, Stony Brook, NY 11794, USA
| | - Yongfeng Gao
- Department of Radiology, Stony Brook University, Stony Brook, NY 11794, USA; (W.C.); (M.J.P.); (S.Z.); (Y.G.); (A.F.A.)
| | - Almas F. Abbasi
- Department of Radiology, Stony Brook University, Stony Brook, NY 11794, USA; (W.C.); (M.J.P.); (S.Z.); (Y.G.); (A.F.A.)
| | - Perry J. Pickhardt
- Department of Radiology, School of Medicine, University of Wisconsin, Madison, WI 53792, USA;
| |
Collapse
|
3
|
Cao W, Liang Z, Gao Y, Pomeroy MJ, Han F, Abbasi A, Pickhardt PJ. A dynamic lesion model for differentiation of malignant and benign pathologies. Sci Rep 2021; 11:3485. [PMID: 33568762 PMCID: PMC7875978 DOI: 10.1038/s41598-021-83095-2] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/16/2020] [Accepted: 01/20/2021] [Indexed: 11/21/2022] Open
Abstract
Malignant lesions have a high tendency to invade their surrounding environment compared to benign ones. This paper proposes a dynamic lesion model and explores the 2nd order derivatives at each image voxel, which reflect the rate of change of image intensity, as a quantitative measure of the tendency. The 2nd order derivatives at each image voxel are usually represented by the Hessian matrix, but it is difficult to quantify a matrix field (or image) through the lesion space as a measure of the tendency. We conjecture that the three eigenvalues contain important information of the Hessian matrix and are chosen as the surrogate representation of the Hessian matrix. By treating the three eigenvalues as a vector, called Hessian vector, which is defined in a local coordinate formed by three orthogonal Hessian eigenvectors and further adapting the gray level occurrence computing method to extract the vector texture descriptors (or measures) from the Hessian vector, a quantitative presentation for the dynamic lesion model is completed. The vector texture descriptors were applied to differentiate malignant from benign lesions from two pathologically proven datasets: colon polyps and lung nodules. The classification results not only outperform four state-of-the-art methods but also three radiologist experts.
Collapse
Affiliation(s)
- Weiguo Cao
- Department of Radiology, State University of New York at Stony Brook, Stony Brook, NY, USA
| | - Zhengrong Liang
- Department of Radiology, State University of New York at Stony Brook, Stony Brook, NY, USA.
- Department of Biomedical Engineering, State University of New York at Stony Brook, Stony Brook, NY, USA.
| | - Yongfeng Gao
- Department of Radiology, State University of New York at Stony Brook, Stony Brook, NY, USA
| | - Marc J Pomeroy
- Department of Radiology, State University of New York at Stony Brook, Stony Brook, NY, USA
- Department of Biomedical Engineering, State University of New York at Stony Brook, Stony Brook, NY, USA
| | - Fangfang Han
- School of Biomedical Engineering, Southern Medical University, Guangzhou, 510515, Guangdong, People's Republic of China
| | - Almas Abbasi
- Department of Radiology, State University of New York at Stony Brook, Stony Brook, NY, USA
| | - Perry J Pickhardt
- Department of Radiology, School of Medicine, University of Wisconsin, Madison, WI, USA
| |
Collapse
|