1
|
Baidya Kayal E, Kandasamy D, Sharma R, Sharma MC, Bakhshi S, Mehndiratta A. SLIC-supervoxels-based response evaluation of osteosarcoma treated with neoadjuvant chemotherapy using multi-parametric MR imaging. Eur Radiol 2020; 30:3125-3136. [PMID: 32086578 DOI: 10.1007/s00330-019-06647-1] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2019] [Revised: 12/01/2019] [Accepted: 12/18/2019] [Indexed: 01/24/2023]
Abstract
OBJECTIVE Histopathological examination (HPE) is the current gold standard for assessing chemotherapy response to tumor, but it is possible only after surgery. The purpose of the study was to develop a noninvasive, imaging-based robust method to delineate, visualize, and quantify the proportions of necrosis and viable tissue present within the tumor along with peritumoral edema before and after neoadjuvant chemotherapy (NACT) and to evaluate treatment response with correlation to HPE necrosis after surgery. METHODS The MRI dataset of 30 patients (N = 30; male:female = 24:6; age = 17.6 ± 2.7 years) with osteosarcoma was acquired using 1.5 T Philips Achieva MRI scanner before (baseline) and after 3 cycles of NACT (follow-up). After NACT, all patients underwent surgical resection followed by HPE. Simple linear iterative clustering supervoxels and Otsu multithresholding were combined to develop the proposed method-SLICs+MTh-to subsegment and quantify viable and nonviable regions within tumor using multiparametric MRI. Manually drawn ground-truth ROIs and SLICs+MTh-based segmentation of tumor, edema, and necrosis were compared using Jacquard index (JI), Dice coefficient (DC), precision (P), and recall (R). Postcontrast T1W images (PC-T1W) were used to validate the SLICs+MTh-based necrosis. SLICs+MTh-based necrosis volume at follow-up was compared with HPE necrosis using paired t test (p ≤ 0.05). RESULTS Active tumor, necrosis, and edema were segmented with moderate to satisfactory accuracy (JI = 62-78%; DC = 72-87%; P = 67-87%; R = 63-88%). Qualitatively and quantitatively (DC = 74 ± 9%), the SLICs+MTh-based necrosis area correlated well with the hypointense necrosis areas in PC-T1W. No significant difference (paired t test, p = 0.26; Bland-Altman plot, bias = 2.47) between SLICs+MTh-based necrosis at follow-up and HPE necrosis was observed. CONCLUSION The proposed multiparametric MRI-based SLICs+MTh method performs noninvasive assessment of NACT response in osteosarcoma that may improve cancer treatment monitoring, planning, and overall prognosis. KEY POINTS • The simple linear iterative clustering supervoxels and Otsu multithresholding-based technique (SLICs+MTh) successfully estimates the proportion of necrosis, viable tumor, and edema in osteosarcoma in the course of chemotherapy. • The proposed technique is noninvasive and uses multiparametric MRI to measure necrosis as an indication of anticancer treatment response. • SLICs+MTh-based necrosis was in satisfactory agreement with histological necrosis after surgery.
Collapse
Affiliation(s)
- Esha Baidya Kayal
- Centre for Biomedical Engineering, Indian Institute of Technology Delhi, Hauz Khas, New Delhi, 110016, India
| | | | - Raju Sharma
- Department of Radiology, All India Institute of Medical Sciences, New Delhi, India
| | - Mehar C Sharma
- Department of Pathology, All India Institute of Medical Sciences, New Delhi, India
| | - Sameer Bakhshi
- Department of Medical Oncology, Dr. B.R. Ambedkar Institute-Rotary Cancer Hospital (IRCH), All India Institute of Medical Sciences, New Delhi, India
| | - Amit Mehndiratta
- Centre for Biomedical Engineering, Indian Institute of Technology Delhi, Hauz Khas, New Delhi, 110016, India. .,Department of Biomedical Engineering, All India Institute of Medical Sciences, New Delhi, India.
| |
Collapse
|
2
|
Koyasu S, Nishio M, Isoda H, Nakamoto Y, Togashi K. Usefulness of gradient tree boosting for predicting histological subtype and EGFR mutation status of non-small cell lung cancer on 18F FDG-PET/CT. Ann Nucl Med 2019; 34:49-57. [PMID: 31659591 DOI: 10.1007/s12149-019-01414-0] [Citation(s) in RCA: 53] [Impact Index Per Article: 10.6] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/30/2019] [Accepted: 10/11/2019] [Indexed: 01/19/2023]
Abstract
OBJECTIVE To develop and evaluate a radiomics approach for classifying histological subtypes and epidermal growth factor receptor (EGFR) mutation status in lung cancer on PET/CT images. METHODS PET/CT images of lung cancer patients were obtained from public databases and used to establish two datasets, respectively to classify histological subtypes (156 adenocarcinomas and 32 squamous cell carcinomas) and EGFR mutation status (38 mutant and 100 wild-type samples). Seven types of imaging features were obtained from PET/CT images of lung cancer. Two types of machine learning algorithms were used to predict histological subtypes and EGFR mutation status: random forest (RF) and gradient tree boosting (XGB). The classifiers used either a single type or multiple types of imaging features. In the latter case, the optimal combination of the seven types of imaging features was selected by Bayesian optimization. Receiver operating characteristic analysis, area under the curve (AUC), and tenfold cross validation were used to assess the performance of the approach. RESULTS In the classification of histological subtypes, the AUC values of the various classifiers were as follows: RF, single type: 0.759; XGB, single type: 0.760; RF, multiple types: 0.720; XGB, multiple types: 0.843. In the classification of EGFR mutation status, the AUC values were: RF, single type: 0.625; XGB, single type: 0.617; RF, multiple types: 0.577; XGB, multiple types: 0.659. CONCLUSIONS The radiomics approach to PET/CT images, together with XGB and Bayesian optimization, is useful for classifying histological subtypes and EGFR mutation status in lung cancer.
Collapse
Affiliation(s)
- Sho Koyasu
- Department of Diagnostic Imaging and Nuclear Medicine, Graduate School of Medicine, Kyoto University, 54 Kawahara-cho, Shogoin, Sakyo-ku, Kyoto, Kyoto, 606-8507, Japan.,Research Center for Advanced Science and Technology, The University of Tokyo, 4-6-1 Komaba, Meguro-ku, Tokyo, 153-8904, Japan
| | - Mizuho Nishio
- Department of Diagnostic Imaging and Nuclear Medicine, Graduate School of Medicine, Kyoto University, 54 Kawahara-cho, Shogoin, Sakyo-ku, Kyoto, Kyoto, 606-8507, Japan. .,Preemptive Medicine and Lifestyle-related Disease Research Center, Kyoto University Hospital, 53 Kawahara-cho, Shogoin, Sakyo-ku, Kyoto, Kyoto, 606-8507, Japan.
| | - Hiroyoshi Isoda
- Department of Diagnostic Imaging and Nuclear Medicine, Graduate School of Medicine, Kyoto University, 54 Kawahara-cho, Shogoin, Sakyo-ku, Kyoto, Kyoto, 606-8507, Japan.,Preemptive Medicine and Lifestyle-related Disease Research Center, Kyoto University Hospital, 53 Kawahara-cho, Shogoin, Sakyo-ku, Kyoto, Kyoto, 606-8507, Japan
| | - Yuji Nakamoto
- Department of Diagnostic Imaging and Nuclear Medicine, Graduate School of Medicine, Kyoto University, 54 Kawahara-cho, Shogoin, Sakyo-ku, Kyoto, Kyoto, 606-8507, Japan
| | - Kaori Togashi
- Department of Diagnostic Imaging and Nuclear Medicine, Graduate School of Medicine, Kyoto University, 54 Kawahara-cho, Shogoin, Sakyo-ku, Kyoto, Kyoto, 606-8507, Japan
| |
Collapse
|
3
|
Fast PET Scan Tumor Segmentation Using Superpixels, Principal Component Analysis and K-Means Clustering. Methods Protoc 2018. [PMCID: PMC6526433 DOI: 10.3390/mps1010007] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/06/2023] Open
Abstract
Positron Emission Tomography scan images are extensively used in radiotherapy planning, clinical diagnosis, assessment of growth and treatment of a tumor. These all rely on fidelity and speed of detection and delineation algorithm. Despite intensive research, segmentation has remained a challenging problem due to the diverse image content, resolution, shape, and noise. This paper presents a fast positron emission tomography tumor segmentation method using superpixels. Principal component analysis is applied on the superpixels and their average value. The distance vector of each superpixel from the average is computed in the principal components coordinate system. Finally, k-means clustering is applied on the distance vector to recognize tumor and non-tumor superpixels. The proposed approach is implemented in MATLAB 2016A, and promising accuracy with execution time of 2.35 ± 0.26 s is achieved. Fast execution time is achieved since the number of superpixels, and the size of distance vector on which clustering was done are low compared to the number of pixels in the image.
Collapse
|