Dataset Information

Automatic lesion detection and segmentation of 18F-FET PET in gliomas: A full 3D U-Net convolutional neural network study.

ABSTRACT:

Introduction

Amino-acids positron emission tomography (PET) is increasingly used in the diagnostic workup of patients with gliomas, including differential diagnosis, evaluation of tumor extension, treatment planning and follow-up. Recently, progresses of computer vision and machine learning have been translated for medical imaging. Aim was to demonstrate the feasibility of an automated 18F-fluoro-ethyl-tyrosine (18F-FET) PET lesion detection and segmentation relying on a full 3D U-Net Convolutional Neural Network (CNN).

Methods

All dynamic 18F-FET PET brain image volumes were temporally realigned to the first dynamic acquisition, coregistered and spatially normalized onto the Montreal Neurological Institute template. Ground truth segmentations were obtained using manual delineation and thresholding (1.3 x background). The volumetric CNN was implemented based on a modified Keras implementation of a U-Net library with 3 layers for the encoding and decoding paths. Dice similarity coefficient (DSC) was used as an accuracy measure of segmentation.

Results

Thirty-seven patients were included (26 [70%] in the training set and 11 [30%] in the validation set). All 11 lesions were accurately detected with no false positive, resulting in a sensitivity and a specificity for the detection at the tumor level of 100%. After 150 epochs, DSC reached 0.7924 in the training set and 0.7911 in the validation set. After morphological dilatation and fixed thresholding of the predicted U-Net mask a substantial improvement of the DSC to 0.8231 (+ 4.1%) was noted. At the voxel level, this segmentation led to a 0.88 sensitivity [95% CI, 87.1 to, 88.2%] a 0.99 specificity [99.9 to 99.9%], a 0.78 positive predictive value: [76.9 to 78.3%], and a 0.99 negative predictive value [99.9 to 99.9%].

Conclusions

With relatively high performance, it was proposed the first full 3D automated procedure for segmentation of 18F-FET PET brain images of patients with different gliomas using a U-Net CNN architecture.

SUBMITTER: Blanc-Durand P

PROVIDER: S-EPMC5898737 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automatic lesion detection and segmentation of 18F-FET PET in gliomas: A full 3D U-Net convolutional neural network study.

Blanc-Durand Paul P Van Der Gucht Axel A Schaefer Niklaus N Itti Emmanuel E Prior John O JO

PloS one 20180413 4

<h4>Introduction</h4>Amino-acids positron emission tomography (PET) is increasingly used in the diagnostic workup of patients with gliomas, including differential diagnosis, evaluation of tumor extension, treatment planning and follow-up. Recently, progresses of computer vision and machine learning have been translated for medical imaging. Aim was to demonstrate the feasibility of an automated 18F-fluoro-ethyl-tyrosine (18F-FET) PET lesion detection and segmentation relying on a full 3D U-Net Co ...[more]

PMID: 29652908

Similar Datasets

Project description:IntroductionAim was to develop a full automatic clustering approach of the time-activity curves (TAC) from dynamic 18F-FET PET and evaluate its association with IDH1 mutation status and survival in patients with gliomas.MethodsThirty-seven patients (mean age: 45±13 y) with newly diagnosed gliomas and dynamic 18F-FET PET before any histopathologic investigation or treatment were retrospectively included. Each dynamic 18F-FET PET was realigned to the first image and spatially normalized in the Montreal Neurological Institute template. A tumor mask was semi-automatically generated from Z-score maps. Each brain tumor voxel was clustered in one of the 3 following centroids using dynamic time warping and k-means clustering (centroid #1: slowly increasing slope; centroid #2: rapidly increasing followed by slowly decreasing slope; and centroid #3: rapidly increasing followed by rapidly decreasing slope). The percentage of each dynamic 18F-FET TAC within tumors and other conventional 18F-FET PET parameters (maximum and mean tumor-to-brain ratios [TBRmax and TBRmean], time-to-peak [TTP] and slope) was compared between wild-type and IDH1 mutant tumors. Their prognostic value was assessed in terms of progression free-survival (PFS) and overall survival (OS) by Kaplan-Meier estimates.ResultsTwenty patients were IDH1 wild-type and 17 IDH1 mutant. Higher percentage of centroid #1 and centroid #3 within tumors were positively (P = 0.016) and negatively (P = 0.01) correlated with IDH1 mutated status. Also, TBRmax, TBRmean, TTP, and slope discriminated significantly between tumors with and without IDH1 mutation (P range 0.01 to 0.04). Progression occurred in 22 patients (59%) at a median of 13.1 months (7.6-37.6 months) and 13 patients (35%) died from tumor progression. Patients with a percentage of centroid #1 > 90% had a longer survival compared with those with a percentage of centroid #1 < 90% (P = 0.003 for PFS and P = 0.028 for OS). This remained significant after stratification on IDH1 mutation status (P = 0.029 for PFS and P = 0.034 for OS). Compared to other conventional 18F-FET PET parameters, TTP and slope were associated with PFS and OS (P range 0.009 to 0.04).ConclusionsBased on dynamic 18F-FET PET acquisition, we developed a full automatic clustering approach of TAC which appears to be a valuable noninvasive diagnostic and prognostic marker in patients with gliomas.

Project description:Purpose: Gliomas are the most common primary brain malignancies, with varying degrees of aggressiveness and prognosis. Understanding of tumor biology and intra-tumor heterogeneity is necessary for planning personalized therapy and predicting response to therapy. Accurate tumoral and intra-tumoral segmentation on MRI is the first step toward understanding the tumor biology through computational methods. The purpose of this study was to design a segmentation algorithm and evaluate its performance on pre-treatment brain MRIs obtained from patients with gliomas. Materials and Methods: In this study, we have designed a novel 3D U-Net architecture that segments various radiologically identifiable sub-regions like edema, enhancing tumor, and necrosis. Weighted patch extraction scheme from the tumor border regions is proposed to address the problem of class imbalance between tumor and non-tumorous patches. The architecture consists of a contracting path to capture context and the symmetric expanding path that enables precise localization. The Deep Convolutional Neural Network (DCNN) based architecture is trained on 285 patients, validated on 66 patients and tested on 191 patients with Glioma from Brain Tumor Segmentation (BraTS) 2018 challenge dataset. Three dimensional patches are extracted from multi-channel BraTS training dataset to train 3D U-Net architecture. The efficacy of the proposed approach is also tested on an independent dataset of 40 patients with High Grade Glioma from our tertiary cancer center. Segmentation results are assessed in terms of Dice Score, Sensitivity, Specificity, and Hausdorff 95 distance (ITCN intra-tumoral classification network). Result: Our proposed architecture achieved Dice scores of 0.88, 0.83, and 0.75 for the whole tumor, tumor core and enhancing tumor, respectively, on BraTS validation dataset and 0.85, 0.77, 0.67 on test dataset. The results were similar on the independent patients' dataset from our hospital, achieving Dice scores of 0.92, 0.90, and 0.81 for the whole tumor, tumor core and enhancing tumor, respectively. Conclusion: The results of this study show the potential of patch-based 3D U-Net for the accurate intra-tumor segmentation. From experiments, it is observed that the weighted patch-based segmentation approach gives comparable performance with the pixel-based approach when there is a thin boundary between tumor subparts.

Project description:BACKGROUND:O-(2-[18F]-fluoroethyl)-L-tyrosine (18F-FET) is a highly sensitive PET tracer for glioma imaging, and its uptake is suggested to be driven by an overexpression of the L-type amino-acid transporter 1 (LAT1). However, 30% of low- and 5% of high-grade gliomas do not present enhanced 18F-FET uptake at primary diagnosis ("18F-FET-negative gliomas") and the pathophysiologic basis for this phenomenon remains unclear. The aim of this study was to determine the expression of LAT1 in a homogeneous group of newly diagnosed 18F-FET-negative gliomas and to compare them to a matched group of 18F-FET-positive gliomas. Forty newly diagnosed IDH-mutant astrocytomas without 1p/19q codeletion were evaluated (n = 20 18F-FET-negative (tumour-to-background ratio (TBR) < 1.6), n = 20 18F-FET-positive gliomas (TBR > 1.6)). LAT1 immunohistochemistry (IHC) was performed using SLC7A5/LAT1 antibody. The percentage of LAT1-positive tumour cells (%) and the staining intensity (range 0-2) were multiplied to an overall score (H-score; range 0-200) and correlated to PET findings as well as progression-free survival (PFS). RESULTS:IHC staining of LAT1 expression was positive in both, 18F-FET-positive as well as 18F-FET-negative gliomas. No differences were found between the 18F-FET-negative and 18F-FET-positive group with regard to percentage of LAT1-positive tumour cells, staining intensity or H-score. Interestingly, the LAT1 expression showed a significant negative correlation with the PFS (p = 0.031), whereas no significant correlation was found for TBRmax, neither in the overall group nor in the 18F-FET-positive group only (p = 0.651 and p = 0.140). CONCLUSION:Although LAT1 is reported to mediate the uptake of 18F-FET into tumour cells, the levels of LAT1 expression do not correlate with the levels of 18F-FET uptake in IDH-mutant astrocytomas. In particular, the lack of tracer uptake in 18F-FET-negative gliomas cannot be explained by a reduced LAT1 expression. A higher LAT1 expression in IDH-mutant astrocytomas seems to be associated with a short PFS. Further studies regarding mechanisms influencing the uptake of 18F-FET are necessary.

Dataset Information

Automatic lesion detection and segmentation of 18F-FET PET in gliomas: A full 3D U-Net convolutional neural network study.

Introduction

Methods

Results

Conclusions

Publications

Automatic lesion detection and segmentation of 18F-FET PET in gliomas: A full 3D U-Net convolutional neural network study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets