1
|
Nagami N, Arimura H, Nojiri J, Yunhao C, Ninomiya K, Ogata M, Oishi M, Ohira K, Kitamura S, Irie H. Dual segmentation models for poorly and well-differentiated hepatocellular carcinoma using two-step transfer deep learning on dynamic contrast-enhanced CT images. Phys Eng Sci Med 2023; 46:83-97. [PMID: 36469246 DOI: 10.1007/s13246-022-01202-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [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: 06/12/2022] [Accepted: 11/17/2022] [Indexed: 12/12/2022]
Abstract
The aim of this study was to develop dual segmentation models for poorly and well-differentiated hepatocellular carcinoma (HCC), using two-step transfer learning (TSTL) based on dynamic contrast-enhanced (DCE) computed tomography (CT) images. From 2013 to 2019, DCE-CT images of 128 patients with 80 poorly differentiated and 48 well-differentiated HCCs were selected at our hospital. In the first transfer learning (TL) step, a pre-trained segmentation model with 192 CT images of lung cancer patients was retrained as a poorly differentiated HCC model. In the second TL step, a well-differentiated HCC model was built from a poorly differentiated HCC model. The average three-dimensional Dice's similarity coefficient (3D-DSC) and 95th-percentile of the Hausdorff distance (95% HD) were mainly employed to evaluate the segmentation accuracy, based on a nested fourfold cross-validation test. The DSC denotes the degree of regional similarity between the HCC reference regions and the regions estimated using the proposed models. The 95% HD is defined as the 95th-percentile of the maximum measures of how far two subsets of a metric space are from each other. The average 3D-DSC and 95% HD were 0.849 ± 0.078 and 1.98 ± 0.71 mm, respectively, for poorly differentiated HCC regions, and 0.811 ± 0.089 and 2.01 ± 0.84 mm, respectively, for well-differentiated HCC regions. The average 3D-DSC for both regions was 1.2 times superior to that calculated without the TSTL. The proposed model using TSTL from the lung cancer dataset showed the potential to segment poorly and well-differentiated HCC regions on DCE-CT images.
Collapse
Affiliation(s)
- Noriyuki Nagami
- Department of Health Sciences, Graduate School of Medical Sciences, Kyushu University, 3-1-1, Maidashi, Higashi-Ku, Fukuoka City, Fukuoka, 812-8582, Japan
- Department of Radiology, Saga University Hospital, 5-1-1, Nabeshima, Saga City, Saga, 849-8501, Japan
| | - Hidetaka Arimura
- Division of Medical Quantum Science, Department of Health Sciences, Faculty of Medical Sciences, Kyushu University, 3-1-1, Maidashi, Higashi-Ku, Fukuoka City, Fukuoka, 812-8582, Japan.
| | - Junichi Nojiri
- Medical Corporation Kouhoukai, Takagi Hospital, 141-11, Sakemi, Okawa City, Fukuoka, 831-0016, Japan
- Department of Radiology, Faculty of Medicine, Saga University, 5-1-1, Nabeshima, Saga City , Saga, 849-8501, Japan
| | - Cui Yunhao
- Department of Health Sciences, Graduate School of Medical Sciences, Kyushu University, 3-1-1, Maidashi, Higashi-Ku, Fukuoka City, Fukuoka, 812-8582, Japan
| | - Kenta Ninomiya
- Department of Health Sciences, Graduate School of Medical Sciences, Kyushu University, 3-1-1, Maidashi, Higashi-Ku, Fukuoka City, Fukuoka, 812-8582, Japan
| | - Manabu Ogata
- Department of Radiology, Saga University Hospital, 5-1-1, Nabeshima, Saga City, Saga, 849-8501, Japan
| | - Mitsutoshi Oishi
- Department of Radiology, Faculty of Medicine, Saga University, 5-1-1, Nabeshima, Saga City , Saga, 849-8501, Japan
| | - Keiichi Ohira
- Department of Radiology, Faculty of Medicine, Saga University, 5-1-1, Nabeshima, Saga City , Saga, 849-8501, Japan
| | - Shigetoshi Kitamura
- Department of Radiology, Saga University Hospital, 5-1-1, Nabeshima, Saga City, Saga, 849-8501, Japan
| | - Hiroyuki Irie
- Department of Radiology, Faculty of Medicine, Saga University, 5-1-1, Nabeshima, Saga City , Saga, 849-8501, Japan
| |
Collapse
|
2
|
Soufi M, Arimura H, Nagami N. Identification of optimal mother wavelets in survival prediction of lung cancer patients using wavelet decomposition-based radiomic features. Med Phys 2018; 45:5116-5128. [PMID: 30230556 DOI: 10.1002/mp.13202] [Citation(s) in RCA: 32] [Impact Index Per Article: 5.3] [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: 02/26/2018] [Revised: 08/29/2018] [Accepted: 09/10/2018] [Indexed: 12/25/2022] Open
Abstract
PURPOSE To identify the optimal mother wavelets in survival prediction of lung cancer patients using wavelet decomposition-based (WDB) radiomic features in CT images. MATERIALS AND METHODS The CT images of patients with histologically confirmed nonsmall cell lung carcinomas (NSCLCs) in training (Dataset T; n = 162) and validation (Dataset V; n = 143) datasets were analyzed for this study. The optimal mother wavelets were identified based on the impacts of the WDB radiomic features on the patient survival times. Four hundred and thirty-two three-dimensional WDB radiomic features were calculated from regions of interest (ROI) of 162 tumor contours. A Coxnet algorithm was used to select a subset of radiomic features (signature) based on the prediction of survival times with a fivefold cross validation. The impacts of the radiomic features on the patients' survival times were assessed by using a multivariate Cox proportional hazard regression (MCPHR) model. The major contribution of this study was to identify optimal mother wavelets based on a maximization of a novel ranking index (RI) incorporating the Coxnet cross-validated partial log-likelihood and the summation of the P-values of the radiomic features in the MCPHR model on Dataset T. The prognostic performance of the optimal mother wavelets was validated based on the concordance index (CI) of the MCPHR models when applied to Dataset V. The proposed approach was tested by using 31 mother wavelets from 6 wavelet families that were available in a commercially available software (Matlab® 2016b). RESULTS The optimal mother wavelets were Symlet 5 and Biorthogonal 2.6 at 128 requantization levels, which yielded RIs of 4.27 ± 0.29 (3 features) and 6.50 ± 0.50 (5 features), respectively. The CIs of the MCPHR models of Symlet 5 were 0.66 ± 0.03 (Dataset T) and 0.64 ± 0.00 (Dataset V), whereas those of Biorthogonal 2.6 were 0.68 ± 0.03 (Dataset T) and 0.62 ± 0.02 (Dataset V). The radiomic signatures included the GLRLM-based LHL gray level nonuniformity feature that demonstrated statistically significant differences in stratifying patients with better and worse prognoses in Datasets T and V. CONCLUSION This study has revealed the potential of Symlet and Biorthogonal mother wavelets in the survival prediction of lung cancer patients by using WDB radiomic features in CT images.
Collapse
Affiliation(s)
- Mazen Soufi
- Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology, 8916-5, Takayama-cho, Ikoma, Nara, 630-0192, Japan
| | - Hidetaka Arimura
- Faculty of Medical Sciences, Kyushu University, 3-1-1, Maidashi, Higashi-ku, Fukuoka, 812-8582, Japan
| | - Noriyuki Nagami
- Graduate School of Medical Sciences, Kyushu University, 3-1-1, Maidashi, Higashi-ku, Fukuoka, 812-8582, Japan
| |
Collapse
|
3
|
Kitagawa I, Simanjuntak P, Hori K, Nagami N, Mahmud T, Shibuya H, Kobayashi M. Indonesian medicinal plants. VII. Seven new clerodane-type diterpenoids, peronemins A2, A3, B1, B2, B3, C1, and D1, from the leaves of Peronema canescens (Verbenaceae). Chem Pharm Bull (Tokyo) 1994; 42:1050-5. [PMID: 8069955 DOI: 10.1248/cpb.42.1050] [Citation(s) in RCA: 10] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/28/2023]
Abstract
Seven new clerodane-type diterpenoids, named peronemins B2 (1), A2 (2), B1 (3), C1 (4), B3 (5), A3 (6), and D1 (7), were isolated from the leaves of Peronema canescens (Verbenaceae), an Indonesian medicinal plant collected in Bengkulu, Sumatera Island, Indonesia. The chemical structures of 1-7 have been elucidated on the basis of their chemical and physicochemical properties.
Collapse
Affiliation(s)
- I Kitagawa
- Faculty of Pharmaceutical Sciences, Osaka University, Japan
| | | | | | | | | | | | | |
Collapse
|