1
|
Nakagawa M, Nakaura T, Yoshida N, Azuma M, Uetani H, Nagayama Y, Kidoh M, Miyamoto T, Yamashita Y, Hirai T. Performance of Machine Learning Methods Based on Multi-Sequence Textural Parameters Using Magnetic Resonance Imaging and Clinical Information to Differentiate Malignant and Benign Soft Tissue Tumors. Acad Radiol 2023; 30:83-92. [PMID: 35725692 DOI: 10.1016/j.acra.2022.04.007] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2021] [Revised: 04/01/2022] [Accepted: 04/09/2022] [Indexed: 11/18/2022]
Abstract
RATIONALE AND OBJECTIVES To evaluate the performance of a machine learning method to differentiate malignant from benign soft tissue tumors based on textural features on multiparametric magnetic resonance imaging (mpMRI). MATERIALS AND METHODS We enrolled 163 patients with soft tissue tumors whose diagnosis was pathologically proven (71 malignant, 92 benign). All patients underwent mpMRI. Twelve histographic and textural parameters were assessed on T1-weighted imaging (T1WI), T2-weighted imaging, diffusion-weighted imaging, apparent diffusion coefficient maps, and contrast-enhanced T1WI imaging. We compared mean signals of all sequences from the malignant and benign tumors using Welch's t-test. Prediction models were developed via a machine learning technique (support vector machine) using textural features of each sequence, clinical information (sex + age + tumor size), and the combined model incorporating all features. Areas under the receiver operating characteristic curves (AUCs) of these models were calculated using fivefold cross validation. RESULTS The diagnostic ability of clinical information model (AUC 0.85) was not inferior to the model with textural features of each sequence (AUC 0.79-0.84). The combined model showed the highest diagnostic ability (AUC 0.89). The AUC of the combined model (0.89) was comparable to those of two board-certified radiologists (0.89 and 0.87). CONCLUSIONS Machine learning methods based on textural features on mpMRI and clinical information offer adequate diagnostic performance to differentiate between malignant and benign soft tissue tumors.
Collapse
Affiliation(s)
- Masataka Nakagawa
- Department of Diagnostic Radiology, Graduate School of Life Sciences, Kumamoto University, 1-1-1, Honjo, Chuoku, Kumamoto, Japan
| | - Takeshi Nakaura
- Department of Diagnostic Radiology, Graduate School of Life Sciences, Kumamoto University, 1-1-1, Honjo, Chuoku, Kumamoto, Japan.
| | - Naofumi Yoshida
- Department of Diagnostic Radiology, Graduate School of Life Sciences, Kumamoto University, 1-1-1, Honjo, Chuoku, Kumamoto, Japan
| | - Minako Azuma
- Department of Radiology, Faculty of Medicine, University of Miyazaki, Kiyotake, Miyazaki, Japan
| | - Hiroyuki Uetani
- Department of Diagnostic Radiology, Graduate School of Life Sciences, Kumamoto University, 1-1-1, Honjo, Chuoku, Kumamoto, Japan
| | - Yasunori Nagayama
- Department of Diagnostic Radiology, Graduate School of Life Sciences, Kumamoto University, 1-1-1, Honjo, Chuoku, Kumamoto, Japan
| | - Masafumi Kidoh
- Department of Diagnostic Radiology, Graduate School of Life Sciences, Kumamoto University, 1-1-1, Honjo, Chuoku, Kumamoto, Japan
| | - Takeshi Miyamoto
- Department of Orthopedic Surgery, Graduate School of Life Sciences, Kumamoto University, 1-1-1, Honjo, Chuoku, Kumamoto, Japan
| | - Yasuyuki Yamashita
- Department of Diagnostic Radiology, Graduate School of Life Sciences, Kumamoto University, 1-1-1, Honjo, Chuoku, Kumamoto, Japan
| | - Toshinori Hirai
- Department of Diagnostic Radiology, Graduate School of Life Sciences, Kumamoto University, 1-1-1, Honjo, Chuoku, Kumamoto, Japan
| |
Collapse
|