Abstract:Purpose To assess the performance of the ITK-SNAP software for fluorodeoxyglucose (FDG) positron emission tomography (PET) segmentation of complex-shaped lung tumors compared with an optimized, expert-based manual reference standard. Materials and Methods Seventy-six FDG PET images of thoracic lesions were retrospectively segmented by using ITK-SNAP software. Each tumor was manually segmented by six raters to generate an optimized reference standard by using the simultaneous truth and performance level estimat… Show more
“…Among the 110 stage III–IV LSCC patients enrolled in this retrospective study, seven patients with unqualified segmentation results and four patients with segmentation data unable to recognize were required to re-segment after the blind review, until qualified. Figure 2 describes the manual segmentation by using ITK-SNAP [ 32 ]. Fig.…”
Objectives
To establish a pre-therapy prognostic index model (PIM) of the first-line chemotherapy aiming to achieve accurate prediction of time to progression (TTP) and overall survival among the patients diagnosed with locally advanced (stage III) or distant metastasis (stage IV) lung squamous cell carcinoma (LSCC).
Methods
Ninety-six LSCC patients treated with first-line chemotherapy were retrospectively enrolled to build the model. Fourteen epidermal growth factor receptor (
EGFR
)-mutant LSCC patients treated with first-line EGFR-tyrosine kinase inhibitor (TKI) therapy were enrolled for validation dataset. From CT images, 56,000 phenotype features were initially computed. PIM was constructed by integrating a CT phenotype signature selected by the least absolute shrinkage and selection operator and the significant blood-based biomarkers selected by multivariate Cox regression. PIM was then compared with other four prognostic models constructed by the CT phenotype signature, clinical factors, post-therapy tumor response, and Glasgow Prognostic Score.
Results
The signature includes eight optimal features extracted from co-occurrence, run length, and Gabor features. By using PIM, chemotherapy efficacy of patients categorized in the low-risk, intermediate-risk, and high-risk progression subgroups (median TTP = 7.2 months, 3.4 months, and 1.8 months, respectively) was significantly different (
p
< 0.0001, log-rank test). Chemotherapy efficacy of the low-risk progression subgroup was comparable with EGFR-TKI therapy (
p
= 0.835, log-rank test). Prognostic prediction of chemotherapy efficacy by PIM was significantly higher than other models (
p
< 0.05,
z
test).
Conclusion
The study demonstrated that the PIM yielded significantly higher performance to identify individual stage III–IV LSCC patients who can potentially benefit most from first-line chemotherapy, and predict the risk of failure from chemotherapy for individual patients.
Key Points
• TTP and OS of first-line chemotherapy in individual stage III–IV LSCC patients could be predicted by pre-therapy blood-based biomarkers and image-based signatures.
• Risk status of pre-therapy indicators affected the efficacy of first-line chemotherapy in stage III–IV LSCC patients.
• Those stage III–IV LSCC patients who were able to achieve similar efficacy to EGFR-TKI therapy through chemotherapy were identified.
Electronic supplementary material
The online version of this article (10.1007/s00330-018-5912-2) contains supplementary material, which is available to authorized users.
“…Among the 110 stage III–IV LSCC patients enrolled in this retrospective study, seven patients with unqualified segmentation results and four patients with segmentation data unable to recognize were required to re-segment after the blind review, until qualified. Figure 2 describes the manual segmentation by using ITK-SNAP [ 32 ]. Fig.…”
Objectives
To establish a pre-therapy prognostic index model (PIM) of the first-line chemotherapy aiming to achieve accurate prediction of time to progression (TTP) and overall survival among the patients diagnosed with locally advanced (stage III) or distant metastasis (stage IV) lung squamous cell carcinoma (LSCC).
Methods
Ninety-six LSCC patients treated with first-line chemotherapy were retrospectively enrolled to build the model. Fourteen epidermal growth factor receptor (
EGFR
)-mutant LSCC patients treated with first-line EGFR-tyrosine kinase inhibitor (TKI) therapy were enrolled for validation dataset. From CT images, 56,000 phenotype features were initially computed. PIM was constructed by integrating a CT phenotype signature selected by the least absolute shrinkage and selection operator and the significant blood-based biomarkers selected by multivariate Cox regression. PIM was then compared with other four prognostic models constructed by the CT phenotype signature, clinical factors, post-therapy tumor response, and Glasgow Prognostic Score.
Results
The signature includes eight optimal features extracted from co-occurrence, run length, and Gabor features. By using PIM, chemotherapy efficacy of patients categorized in the low-risk, intermediate-risk, and high-risk progression subgroups (median TTP = 7.2 months, 3.4 months, and 1.8 months, respectively) was significantly different (
p
< 0.0001, log-rank test). Chemotherapy efficacy of the low-risk progression subgroup was comparable with EGFR-TKI therapy (
p
= 0.835, log-rank test). Prognostic prediction of chemotherapy efficacy by PIM was significantly higher than other models (
p
< 0.05,
z
test).
Conclusion
The study demonstrated that the PIM yielded significantly higher performance to identify individual stage III–IV LSCC patients who can potentially benefit most from first-line chemotherapy, and predict the risk of failure from chemotherapy for individual patients.
Key Points
• TTP and OS of first-line chemotherapy in individual stage III–IV LSCC patients could be predicted by pre-therapy blood-based biomarkers and image-based signatures.
• Risk status of pre-therapy indicators affected the efficacy of first-line chemotherapy in stage III–IV LSCC patients.
• Those stage III–IV LSCC patients who were able to achieve similar efficacy to EGFR-TKI therapy through chemotherapy were identified.
Electronic supplementary material
The online version of this article (10.1007/s00330-018-5912-2) contains supplementary material, which is available to authorized users.
“…For this purpose, the dynamic PET data and the MR pre-contrast T 1 -mapping data were resampled to the 3D-T 1 space (libraries nilearn and nibabel), whereas the DCE data were motion-compensated (warping to the 3D-T 1 space) using the SyNQuicK procedure (library nipype, defaut parameters) implemented in Advanced Normalization Tools (ANTs) [ 38 , 39 ]. Tumor mask: the last frame of [18F]FDG-PET and DCE data, the pre-contrast T 1 -mapping data, and the post-contrast 3D-T 1 data were masked semi-automatically with ITK-SNAP ( http://www.itksnap.org ), which implements an active contour-based algorithm [ 40 , 41 ], as follows: an intensity-grading feature image was first computed to define the lesion boundaries by thresholding the intensities of the input image into the background and foreground (region competition approach, in which the intensity values ranged from − 1 to 1 for background and foreground respectively); one or more spherical seeds were then placed on the feature image to initialize the segmentation task; and the iterative algorithm was launched to propagate the seeds, driven by regularity constraints and the image intensity properties. The resulting PET, DCE, T 1 -mapping, and 3D-T 1 tumor masks were combined into a single multimodal tumor mask (library nilearn) using a basic intersection operation.…”
Objectives: To decipher the correlations between PET and DCE kinetic parameters in non-small-cell lung cancer (NSCLC), by using voxel-wise analysis of dynamic simultaneous [18F]FDG PET-MRI. Material and methods: Fourteen treatment-naïve patients with biopsy-proven NSCLC prospectively underwent a 1-h dynamic [18F]FDG thoracic PET-MRI scan including DCE. The PET and DCE data were normalized to their corresponding T 1-weighted MR morphological space, and tumors were masked semi-automatically. Voxel-wise parametric maps of PET and DCE kinetic parameters were computed by fitting the dynamic PET and DCE tumor data to the Sokoloff and Extended Tofts models respectively, by using in-house developed procedures. Curve-fitting errors were assessed by computing the relative root mean square error (rRMSE) of the estimated PET and DCE signals at the voxel level. For each tumor, Spearman correlation coefficients (r s) between all the pairs of PET and DCE kinetic parameters were estimated on a voxel-wise basis, along with their respective bootstrapped 95% confidence intervals (n = 1000 iterations). Results: Curve-fitting metrics provided fit errors under 20% for almost 90% of the PET voxels (median rRMSE = 10.3, interquartile ranges IQR = 8.1; 14.3), whereas 73.3% of the DCE voxels showed fit errors under 45% (median rRMSE = 31.8%, IQR = 22.4; 46.6). The PET-PET, DCE-DCE, and PET-DCE voxel-wise correlations varied according to individual tumor behaviors. Beyond this wide variability, the PET-PET and DCE-DCE correlations were mainly high (absolute r s values > 0.7), whereas the PET-DCE correlations were mainly low to moderate (absolute r s values < 0.7). Half the tumors showed a hypometabolism with low perfused/vascularized profile, a hallmark of hypoxia, and tumor aggressiveness.
“…Detailed mathematical insight into algorithms implemented in this software lies beyond the scope of current study and may be found in the paper by Yushkevich et al [15]. Although initially designed and tested for anatomical segmentation of brain structures, this segmentation technique has been validated both for other anatomical segmentation applications, e.g., for airway volume measurement on cone beam CT images by Almuzian et al [16] and for lung cancer metabolic volume segmentation on 18 F-FDG-PET imaging by Besson et al [17].…”
Background18F-FDG positron emission tomography/computed tomography (PET/CT) is a successfully used imaging modality in oncology. The aim of the study was to investigate a connection of epithelial tumour differentiation grade with both semiquantitative and quantitative metabolic PET data focusing on creation of multiparametric model of tumour grade prediction utilising both standardised uptake value-based and texture-based 18F-FDG PET parameters and to investigate an influence of different image segmentation techniques on these parameters and modelling.Methods18F-FDG PET/CT data from 84 patients with epithelial malignant tumours was retrospectively analysed to create sets of both conventional semiquantitative (based on standardised uptake values), volumetric, and quantitative texture metabolic parameters of primary tumours with four different segmentation techniques.ResultsMost of the calculated volumetric and texture parameters showed to be influenced by segmentation technique. There was no significant difference in values of only three parameters, in all four segmentation methods: homogeneity, energy, and sphericity. Almost every extracted parameter in all segmentation technique subsets showed significant ability to discriminate individual tumour grade versus the subset of remaining two tumour grades. No parameters were able to discriminate all three tumour grades separately simultaneously or without the overlapping of threshold values. Group method of data handling (GMDH) modelling included all the above-mentioned extracted parameters. The highest value to discriminate tumour grade was achieved using ITK-SNAP segmentation, with an accuracy ranging from 91 to 100%.ConclusionsMultiparametric modelling with GMDH utilising both semiquantitative and quantitative texture metabolic PET parameters seems to be an interesting tool for non-invasive malignant epithelial tumours grade differentiation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
