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).
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.
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%.
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.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Since the seventies, positron emission tomography (PET) has become an invaluable medical molecular imaging modality with an unprecedented sensitivity at the picomolar level, especially for cancer ...diagnosis and the monitoring of its response to therapy. More recently, its combination with x-ray computed tomography (CT) or magnetic resonance (MR) has added high precision anatomic information in fused PET/CT and PET/MR images, thus compensating for the modest intrinsic spatial resolution of PET. Nevertheless, a number of medical challenges call for further improvements in PET sensitivity. These concern in particular new treatment opportunities in the context personalized (also called precision) medicine, such as the need to dynamically track a small number of cells in cancer immunotherapy or stem cells for tissue repair procedures. A better signal-to-noise ratio (SNR) in the image would allow detecting smaller size tumours together with a better staging of the patients, thus increasing the chances of putting cancer in complete remission. Moreover, there is an increasing demand for reducing the radioactive doses injected to the patients without impairing image quality. There are three ways to improve PET scanner sensitivity: improving detector efficiency, increasing geometrical acceptance of the imaging device and pushing the timing performance of the detectors. Currently, some pre-localization of the electron-positron annihilation along a line-of-response (LOR) given by the detection of a pair of annihilation photons is provided by the detection of the time difference between the two photons, also known as the time-of-flight (TOF) difference of the photons, whose accuracy is given by the coincidence time resolution (CTR). A CTR of about 10 picoseconds FWHM will ultimately allow to obtain a direct 3D volume representation of the activity distribution of a positron emitting radiopharmaceutical, at the millimetre level, thus introducing a quantum leap in PET imaging and quantification and fostering more frequent use of 11C radiopharmaceuticals. The present roadmap article toward the advent of 10 ps TOF-PET addresses the status and current/future challenges along the development of TOF-PET with the objective to reach this mythic 10 ps frontier that will open the door to real-time volume imaging virtually without tomographic inversion. The medical impact and prospects to achieve this technological revolution from the detection and image reconstruction point-of-views, together with a few perspectives beyond the TOF-PET application are discussed.
Purpose
Hyperparathyroidism (HPT) is a common endocrine disorder caused by hyperfunctioning parathyroid glands (HP). The correct detection and localization of HP is challenging but crucial, as it may ...guide surgical treatment, particularly in patients with primary HPT. There is a growing body of data regarding the role of radiolabelled choline positron emission tomography (PET) in this setting. Therefore, we performed a systematic review and meta-analysis of the diagnostic performance of this method in detecting HP in patients with HPT.
Methods
This systematic review and meta-analysis was carried out according to PRISMA guidelines. A comprehensive computer literature search of PubMed/MEDLINE, EMBASE and Cochrane Library databases for studies published through May 2018 was performed using the following search algorithm: (a) “choline” or “fluorocholine” or “F-choline” or “C-choline” or “FCH” or “CH” or “FECH” or “FMCH” and (b) “PET” or “positron emission tomography” and (c) “parathyroid” or “hyperparathyroidism”. The diagnostic performance of radiolabelled choline PET was expressed as sensitivity and positive predictive value (PPV) on a per-patient and per-lesion basis and as detection rate (DR) on a per-patient basis, with pooled proportion and 95% confidence interval (95% CI) obtained using a random-effects model.
Results
Eighteen studies were included in the systematic review. Fourteen articles (517 patients) were selected for the meta-analysis. The meta-analysis provided the following results on a per-patient analysis analysis: sensitivity 95% (95% CI: 92–97%), PPV 97% (95% CI: 95–98%) and DR 91% (95% CI: 87–94%). On a per-lesion analysis, pooled sensitivity and PPV were 92% (95% CI: 88–96) and 92% (95% CI: 89–95%), respectively. No significant heterogeneity was found among the selected studies.
Conclusions
Radiolabelled choline PET demonstrated excellent diagnostic performance in detecting HP in patients with HPT. Large multicentre studies and cost-effectiveness analyses are needed to better define the role of this imaging method in this setting.
Bone scintigraphy with
Tc-labeled diphosphonates can identify prostate cancer bone metastases with high sensitivity, but relatively low specificity, because benign conditions such as osteoarthritis ...can also trigger osteoblastic reactions. We aimed to investigate the diagnostic performance of
Tc-2,3-dicarboxy propane-1,1-diphosphonate (
Tc-DPD) uptake quantification by single-photon emission computed tomography coupled with computed tomography (SPECT/CT) for distinguishing prostate cancer bone metastases from spinal and pelvic osteoarthritic lesions.
We retrospectively assessed 26 bone scans from 26 patients with known prostate cancer bone metastases and 13 control patients with benign spinal and pelvic osteoarthritic changes without known neoplastic disease. Quantitative SPECT/CT (xSPECT, Siemens Symbia Intevo, Erlangen, Germany) was performed and standardized uptake values (SUVs) were quantified with measurements of SUV
and SUV
(g/mL) in all bone metastases for the prostate cancer group and in spinal and pelvic osteoarthritic changes for the control group. We used receiver operating characteristics (ROC) curves to determine the optimum SUV
cutoff value to distinguish between bone metastases and benign spinal and pelvic lesions.
In total, 264 prostate cancer bone metastases were analyzed, showing a mean SUV
and SUV
of 34.6 ± 24.6 and 20.8 ± 14.7 g/mL, respectively. In 24 spinal and pelvic osteoarthritic lesions, mean SUV
and SUV
were 14.2 ± 3.8 and 8.9 ± 2.2 g/mL, respectively. SUV
and SUV
were both significantly different between the bone metastases and osteoarthritic groups (p ≤ 0.0001). Using a SUV
cutoff of 19.5 g/mL for prostate cancer bone metastases in the spine and pelvis, sensitivity, specificity, positive and negative predictive values were 87, 92, 99 and 49%, respectively.
This study showed significant differences in quantitative
Tc-DPD uptake on bone SPECT/CT between prostate cancer bone metastases and spinal and pelvic osteoarthritic changes, with higher SUV
and SUV
in metastases. Using a SUV
cutoff of 19.5 g/mL, high specificity and positive predictive value for metastases identification in the spine and pelvis were found, thus increasing accuracy of bone scintigraphy.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Purpose
Cardiac transthyretin-related amyloidosis (ATTR) is a progressive and fatal cardiomyopathy. The diagnosis of this disease is frequently delayed or missed due to the limited specificity of ...echocardiography. An increasing amount of data in the literature demonstrate the ability of bone scintigraphy with bone-seeking radiopharmaceuticals to detect myocardial amyloid deposits, in particular in patients with ATTR. Therefore we performed a systematic review and bivariate meta-analysis of the diagnostic accuracy of bone scintigraphy in patients with suspected cardiac ATTR.
Methods
A comprehensive computer literature search of studies published up to 30 November 2017 on the role of bone scintigraphy in patients with ATTR was performed using the following search algorithm: (a) “amyloid” OR “amyloidosis” AND (b) “TTR” OR “ATTR” OR “transthyretin” AND (c) “scintigraphy” OR “scan” OR “SPECT” OR “SPET” OR “bone” OR “skeletal” OR “skeleton” OR “PYP” OR “DPD” OR “HMDP” OR “MDP” OR “HDP”. Pooled sensitivity, specificity, positive and negative likelihood ratios (LR+ and LR−) and diagnostic odds ratio (DOR) of bone scintigraphy were calculated.
Results
The meta-analysis of six selected studies on bone scintigraphy in cardiac ATTR including 529 patients provided the following results: sensitivity 92.2% (95% CI 89–95%), specificity 95.4% (95% CI 77–99%), LR+ 7.02 (95% CI 3.42–14.4), LR− 0.09 (95% CI 0.06–0.14), and DOR 81.6 (95% CI 44–153). Mild heterogeneity was found among the selected studies.
Conclusion
Our evidence-based data demonstrate that bone scintigraphy using technetium-labelled radiotracers provides very high diagnostic accuracy in the non-invasive assessment of cardiac ATTR.
Abstract The aim of this prospective, observational cohort study was to investigate and assess diverse neuroimaging biomarkers to predict patients’ neurological recovery after coma. 32 patients ...(18–76 years, M = 44.8, SD = 17.7) with disorders of consciousness participated in the study. Multimodal neuroimaging data acquired during the patient’s hospitalization were used to derive cortical glucose metabolism ( 18 F-fluorodeoxyglucose positron emission tomography/computed tomography), and structural (diffusion-weighted imaging) and functional connectivity (resting-state functional MRI) indices. The recovery outcome was defined as a continuous composite score constructed from a multivariate neurobehavioral recovery assessment administered upon the discharge from the hospital. Fractional anisotropy-based white matter integrity in the anterior forebrain mesocircuit ( r = 0.72, p < .001, 95% CI: 0.87, 0.45), and the functional connectivity between the antagonistic default mode and dorsal attention resting-state networks ( r = − 0.74, p < 0.001, 95% CI: − 0.46, − 0.88) strongly correlated with the recovery outcome. The association between the posterior glucose metabolism and the recovery outcome was moderate ( r = 0.38, p = 0.040, 95% CI: 0.66, 0.02). Structural ( adjusted R 2 = 0.84, p = 0.003) or functional connectivity biomarker ( adjusted R 2 = 0.85, p = 0.001), but not their combination, significantly improved the model fit to predict the recovery compared solely to bedside neurobehavioral evaluation ( adjusted R 2 = 0.75). The present study elucidates an important role of specific MRI-derived structural and functional connectivity biomarkers in diagnosis and prognosis of recovery after coma and has implications for clinical care of patients with severe brain injury.
Background
For PET/CT, the CT transmission data are used to correct the PET emission data for attenuation. However, subject motion between the consecutive scans can cause problems for the PET ...reconstruction. A method to match the CT to the PET would reduce resulting artifacts in the reconstructed images.
Purpose
This work presents a deep learning technique for inter-modality, elastic registration of PET/CT images for improving PET attenuation correction (AC). The feasibility of the technique is demonstrated for two applications: general whole-body (WB) imaging and cardiac myocardial perfusion imaging (MPI), with a specific focus on respiratory and gross voluntary motion.
Materials and methods
A convolutional neural network (CNN) was developed and trained for the registration task, comprising two distinct modules: a feature extractor and a displacement vector field (DVF) regressor. It took as input a non-attenuation-corrected PET/CT image pair and returned the relative DVF between them—it was trained in a supervised fashion using simulated inter-image motion. The 3D motion fields produced by the network were used to resample the CT image volumes, elastically warping them to spatially match the corresponding PET distributions. Performance of the algorithm was evaluated in different independent sets of WB clinical subject data: for recovering deliberate misregistrations imposed in motion-free PET/CT pairs and for improving reconstruction artifacts in cases with actual subject motion. The efficacy of this technique is also demonstrated for improving PET AC in cardiac MPI applications.
Results
A single registration network was found to be capable of handling a variety of PET tracers. It demonstrated state-of-the-art performance in the PET/CT registration task and was able to significantly reduce the effects of simulated motion imposed in motion-free, clinical data. Registering the CT to the PET distribution was also found to reduce various types of AC artifacts in the reconstructed PET images of subjects with actual motion. In particular, liver uniformity was improved in the subjects with significant observable respiratory motion. For MPI, the proposed approach yielded advantages for correcting artifacts in myocardial activity quantification and potentially for reducing the rate of the associated diagnostic errors.
Conclusion
This study demonstrated the feasibility of using deep learning for registering the anatomical image to improve AC in clinical PET/CT reconstruction. Most notably, this improved common respiratory artifacts occurring near the lung/liver border, misalignment artifacts due to gross voluntary motion, and quantification errors in cardiac PET imaging.
Graphical Abstract
•The paper describes the first challenge on head and neck tumor segmentation in PET/CT.•Training (n=201, 4 centers) and test sets (n=53, 1 unseen center) amount to 254 cases.•All ground truth ...segmentations underwent cleaning to ensure quality and homogeneity.•The winning team obtained a DSC of 0.759, showing a larg improvement over the baseline.•Additional post-challenge analyses (e.g. false positives analysis, ranking stability).
Display omitted
This paper relates the post-analysis of the first edition of the HEad and neCK TumOR (HECKTOR) challenge. This challenge was held as a satellite event of the 23rd International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2020, and was the first of its kind focusing on lesion segmentation in combined FDG-PET and CT image modalities. The challenge’s task is the automatic segmentation of the Gross Tumor Volume (GTV) of Head and Neck (H&N) oropharyngeal primary tumors in FDG-PET/CT images. To this end, the participants were given a training set of 201 cases from four different centers and their methods were tested on a held-out set of 53 cases from a fifth center. The methods were ranked according to the Dice Score Coefficient (DSC) averaged across all test cases. An additional inter-observer agreement study was organized to assess the difficulty of the task from a human perspective. 64 teams registered to the challenge, among which 10 provided a paper detailing their approach. The best method obtained an average DSC of 0.7591, showing a large improvement over our proposed baseline method and the inter-observer agreement, associated with DSCs of 0.6610 and 0.61, respectively. The automatic methods proved to successfully leverage the wealth of metabolic and structural properties of combined PET and CT modalities, significantly outperforming human inter-observer agreement level, semi-automatic thresholding based on PET images as well as other single modality-based methods. This promising performance is one step forward towards large-scale radiomics studies in H&N cancer, obviating the need for error-prone and time-consuming manual delineation of GTVs.