Comparison of region-of-interest analysis and human observers in the diagnosis of Parkinson's disease using [99mTc]TRODAT-1 and SPECT

Faster Region-Based Convolutional Neural Network in the Classification of Different Parkinsonism Patterns of the Striatum on Maximum Intensity Projection Images of [18F]FP-CIT Positron Emission Tomography

The aim of this study was to compare the performance of a deep-learning convolutional neural network (Faster R-CNN) model to detect imaging findings suggestive of idiopathic Parkinson's disease (PD) based on [¹⁸F]FP-CIT PET maximum intensity projection (MIP) images versus that of nuclear medicine (NM) physicians. The anteroposterior MIP images of the [¹⁸F]FP-CIT PET scan of 527 patients were classified as having PD (139 images) or non-PD (388 images) patterns according to the final diagnosis. Non-PD patterns were classified as overall-normal (ONL, 365 images) and vascular parkinsonism with definite defects or prominently decreased dopamine transporter binding (dVP, 23 images) patterns. Faster R-CNN was trained on 120 PD, 320 ONL, and 16 dVP pattern images and tested on the 19 PD, 45 ONL, and seven dVP patterns images. The performance of the Faster R-CNN and three NM physicians was assessed using receiver operating characteristics curve analysis. The difference in performance was assessed using Cochran's Q test, and the inter-rater reliability was calculated. Faster R-CNN showed high accuracy in differentiating PD from non-PD patterns and also from dVP patterns, with results comparable to those of NM physicians. There were no significant differences in the area under the curve and performance. The inter-rater reliability among Faster R-CNN and NM physicians showed substantial to almost perfect agreement. The deep-learning model accurately differentiated PD from non-PD patterns on MIP images of [¹⁸F]FP-CIT PET, and its performance was comparable to that of NM physicians.

High-accuracy Automated Diagnosis of Parkinson's Disease

PURPOSE

Parkinson's disease (PD), which is the second most common neurodegenerative disease following Alzheimer's disease, can be diagnosed clinically when about 70% of the dopaminergic neurons are lost and symptoms are noticed. Neuroimaging methods such as single photon emission computed tomography have become useful tools in vivo to assess dopamine transporters (DATs) in the striatal region. However, inter- and intra-reader variability of construing the images might result in misdiagnosis. To overcome the challenges posed by classification of the disease, image preparation techniques and a back propagation neural network (BPNN) have been proposed. The aim of this study is to show that the proposed method can be used for the classification of PD with high accuracy.

METHODS

In this study, we used basic image preparation techniques and a BPNN on DAT imaging datasets from the Parkinson's Progression Markers Initiative. 1,334 PD and 212 normal control (NC) subjects were included. In the image preparation phase, adaptive histogram equalization was applied to the cropped images, followed by image binarization. Then, the mass-difference method was applied to separate the regions of interest with similar values. Finally, the binarized images were subtracted from the original images, and the average pixel per node approach was applied to the images to minimize the inputs. In the BPNN phase, 400 input neurons and 2 output neurons were used. The dataset was divided into three sets: training, validation, and test. The BPNN was trained several times in order to obtain the optimum values.

RESULTS

The use of 40 hidden neurons, a learning rate of 0.00079, and a momentum factor of 0.90 produced superior results and were applied in the final BPNN architecture. The tolerance value used was 0.80. Uniquely, we found the sensitivity, specificity, and accuracy for PD vs. NC classification to be 99.7%, 99.2%, 99.6%, respectively. To the best of our knowledge, this is the highest accuracy value achieved in the existing literature. Our method increases computational speed together with improved performance.

CONCLUSION

We have shown that effective image processing methods and the use of BPNN can successfully be applied to PD datasets to accurately determine any abnormalities in DATs. Using the shallow neural network, this procedure requires less processing time compared to other methods, and its accuracy, sensitivity, and specificity are reliable. However, further studies are needed to establish a prediction method for the preclinical and prodromal stages of the disease.

N-Acetyl Cysteine Is Associated With Dopaminergic Improvement in Parkinson's Disease

This study assessed the biological and clinical effects in patients with Parkinson's disease (PD) of N-acetyl-cysteine (NAC), the prodrug to l-cysteine, a precursor to the natural biological antioxidant glutathione. Forty-two patients with PD were randomized to either weekly intravenous infusions of NAC (50 mg/kg) plus oral doses (500 mg twice per day) for 3 months or standard of care only. Participants received prebrain and postbrain imaging with ioflupane (DaTscan) to measure dopamine transporter (DAT) binding. In the NAC group, significantly increased DAT binding was found in the caudate and putamen (mean increase from 3.4% to 8.3%) compared with controls (P < 0.05), along with significantly improved PD symptoms (P < 0.0001). The results suggest NAC may positively affect the dopaminergic system in patients with PD, with corresponding positive clinical effects. Larger scale studies are warranted.

Analysis of the Effect of Dopamine Transporter Scan on the Diagnosis and Management in a Tertiary Neurology Center

Background and Purpose

The dopamine transporter scan or DaT scan is abnormal in presynaptic parkinsonism but normal in nondegenerative or postsynaptic parkinsonism. In this study, we tried to ascertain the impact of DaT scan on the diagnosis and clinical management and if the semiquantitative analysis of the DaT scans has any correlation with the clinical symptoms.

Methods

The electronic and nonelectronic records of patients of Plymouth Hospital NHS Trust, United Kingdom, from 2011 to 2015 were studied to find the indication, outcome, and the impact of the scan on the management of patients. The DaT scan results were assessed visually and semiquantitatively by the Department of Nuclear Medicine. The available data were statistically analyzed with the help of Microsoft XL2010 and GraphPad software.

Results

A total of 258 people had DaT scan. The scan results suggested an alternate diagnosis in 50.5% of clinically diagnosed patients with Parkinson disease. Similarly, DaT scan changed the diagnosis of 40% of patients with clinical diagnosis of vascular parkinsonism, 25% of clinically diagnosed drug-induced parkinsonism, and 54% of patients with possible Lewy body dementia. Visual assessment of the DaT scan revealed that more than 60% had grade 2 abnormalities. The distribution volume ratio, a semiquantitative tool for tracer uptake, was significantly less in the patients with akinetic-rigid subtype of Parkinson disease in comparison to a tremor predominant subtype.

Conclusions

Dopamine transporter scan had a significant impact in diagnosis and management.

Visual and Semiquantitative Accuracy in Clinical Baseline 123I-Ioflupane SPECT/CT Imaging

PURPOSE

We aimed to (a) elucidate the concordance of visual assessment of an initial I-ioflupane scan by a human interpreter with comparison to results using a fully automatic semiquantitative method and (b) to assess the accuracy compared to follow-up (f/u) diagnosis established by movement disorder specialists.

METHODS

An initial I-ioflupane scan was performed in 382 patients with clinically uncertain Parkinsonian syndrome. An experienced reader performed a visual evaluation of all scans independently. The findings of the visual read were compared with semiquantitative evaluation. In addition, available f/u clinical diagnosis (serving as a reference standard) was compared with results of the human read and the software.

RESULTS

When comparing the semiquantitative method with the visual assessment, discordance could be found in 25 (6.5%) of 382 of the cases for the experienced reader (ĸ = 0.868). The human observer indicated region of interest misalignment as the main reason for discordance. With neurology f/u serving as reference, the results of the reader revealed a slightly higher accuracy rate (87.7%, ĸ = 0.75) compared to semiquantification (86.2%, ĸ = 0.719, P < 0.001, respectively). No significant difference in the diagnostic performance of the visual read versus software-based assessment was found.

CONCLUSIONS

In comparison with a fully automatic semiquantitative method in I-ioflupane interpretation, human assessment obtained an almost perfect agreement rate. However, compared to clinical established diagnosis serving as a reference, visual read seemed to be slightly more accurate as a solely software-based quantitative assessment.

Fully Automated Quantification of the Striatal Uptake Ratio of [(99m)Tc]-TRODAT with SPECT Imaging: Evaluation of the Diagnostic Performance in Parkinson's Disease and the Temporal Regression of Striatal Tracer Uptake

Purpose. We aimed at improving the existing methods for the fully automatic quantification of striatal uptake of [^99mTc]-TRODAT with SPECT imaging. Procedures. A normal [^99mTc]-TRODAT template was first formed based on 28 healthy controls. Images from PD patients (n = 365) and nPD subjects (28 healthy controls and 33 essential tremor patients) were spatially normalized to the normal template. We performed an inverse transform on the predefined striatal and reference volumes of interest (VOIs) and applied the transformed VOIs to the original image data to calculate the striatal-to-reference ratio (SRR). The diagnostic performance of the SRR was determined through receiver operating characteristic (ROC) analysis. Results. The SRR measured with our new and automatic method demonstrated excellent diagnostic performance with 92% sensitivity, 90% specificity, 92% accuracy, and an area under the curve (AUC) of 0.94. For the evaluation of the mean SRR and the clinical duration, a quadratic function fit the data with R² = 0.84. Conclusions. We developed and validated a fully automatic method for the quantification of the SRR in a large study sample. This method has an excellent diagnostic performance and exhibits a strong correlation between the mean SRR and the clinical duration in PD patients.

Optimization of imaging parameters for SPECT scans of [99mTc]TRODAT-1 using Taguchi analysis

Parkinson's disease (PD) is a neurodegenerative disease characterized by progressive loss of dopaminergic neurons in the basal ganglia. Single photon emission computed tomography (SPECT) scans using [99mTc]TRODAT-1 can image dopamine transporters and provide valuable diagnostic information of PD. In this study, we optimized the scanning parameters for [99mTc]TRODAT-1/SPECT using the Taguchi analysis to improve image quality. SPECT scans were performed on forty-five healthy volunteers according to an L9 orthogonal array. Three parameters were considered, including the injection activity, uptake duration, and acquisition time per projection. The signal-to-noise ratio (SNR) was calculated from the striatum/occipital activity ratio as an image quality index. Ten healthy subjects and fifteen PD patients were used to verify the optimal parameters. The estimated optimal parameters were 962 MBq for [99mTc]TRODAT-1 injection, 260 min for uptake duration, and 60 s/projection for data acquisition. The uptake duration and time per projection were the two dominant factors which had an F-value of 18.638 (38%) and 25.933 (53%), respectively. Strong cross interactions existed between the injection activity/uptake duration and injection activity/time per projection. Therefore, under the consideration of as low as reasonably achievable (ALARA) for radiation protection, we can decrease the injection activity to 740 MBq. The image quality remains almost the same for clinical applications.

The role of functional dopamine-transporter SPECT imaging in parkinsonian syndromes, part 1

SUMMARY

As we defeat infectious diseases and cancer, one of the greatest medical challenges facing us in the mid-21st century will be the increasing prevalence of degenerative disease. Those diseases, which affect movement and cognition, can be the most debilitating. Dysfunction of the extrapyramidal system results in increasing motor disability often manifest as tremor, bradykinesia, and rigidity. The common pathologic pathway of these diseases, collectively described as parkinsonian syndromes, such as Parkinson disease, multiple system atrophy, progressive supranuclear palsy, corticobasal degeneration, and dementia with Lewy bodies, is degeneration of the presynaptic dopaminergic pathways in the basal ganglia. Conventional MR imaging is insensitive, especially in early disease, so functional imaging has become the primary method used to differentiate a true parkinsonian syndrome from vascular parkinsonism, drug-induced changes, or essential tremor. Unusually for a modern functional imaging technique, the method most widely used in European clinics depends on SPECT and not PET. This SPECT technique (described in the first of 2 parts) commonly reports dopamine-transporter function, with decreasing striatal uptake demonstrating increasingly severe disease.

Feasibility of PET Template-Based Analysis on F-18 FP-CIT PET in Patients with De Novo Parkinson's Disease

PURPOSE

The aim of this study was to evaluate the feasibility of FP-CIT PET template-based quantitative analysis on F-18 FP-CIT PET in patients with de novo Parkinson's disease (PD), compared with MR-based and manual methods. We also assessed the correlation of quantitative parameters of those methods with clinical severity of the disease.

METHODS

Forty patients with de novo PD underwent both MRI and F-18 FP-CIT PET. Images were spatially normalized to a standardized PET template. Mean counts of 4 ROIs: putamen, caudate, occipital cortex and cerebellum, were obtained using the quantification program, Korean Statistical Probabilistic Anatomical Map (KSPAM). Putamen-to-caudate ratio (PCR), asymmetry index (ASI), specific-to-nonspecific ratios with two different references: to occipital cortex (SOR) and cerebellum (SCR) were compared. Parameters were also calculated from manually drawn ROI method and MR-coregistrated method.

RESULTS

All quantitative parameters showed significant correlations across the three different methods, especially between the PET-based and manual methods. Among them, PET-based SOR and SCR values showed an excellent correlation and concordance with those of manual method. In relationship with clinical severity, only ASI achieved significantly inverse correlations with H&Y stage and UPDRS motor score. There was no significant difference between the quantitative parameters of both occipital cortex and cerebellum in all three methods, which implied that quantitation using PET-based method could be reproducible regardless of the reference region.

CONCLUSIONS

Quantitative parameters using FP-CIT PET template-based method correlated well with those using laborious manual method with excellent concordance. Moreover, PET-based quantitation was less influenced by the reference region than MR-based method. It suggests that PET-based method can provide objective and quantitative parameters quickly and easily as a feasible analysis in place of conventional method.

Smoking, dopamine transporter, and hand tremor

AIM

The purpose of the study was to evaluate the relationship between the number of packs smoked per day and specific uptake ratio (SUR) in the striatum on Tc-99m TRODAT, and frequency of hand tremor.

METHODS

It was a prospective, cross-sectional study. In all, 23 healthy nonsmokers and 37 current smokers were recruited in the study. All subjects underwent Tc-99m TRODAT SPECT, brain CT scan, thyroid function test, tremor measurement system, and neurologic examinations.

RESULTS

There were significant differences in the SUR in the striatum on Tc-99m TRODAT and in the frequency of hand tremor in rest state and in arm extended state among nonsmokers (grade I), current smokers with less than 1 pack smoked per day (grade II), and current smokers with equal or more than 1 pack smoked per day (grade III) by ANOVA (all P < 0.001). After adjusting for age and gender, there was a significantly negative correlation between smoke grade and SUR in the striatum on Tc-99m TRODAT by multiple linear regression (β = -0.45, P < 0.001). Smoke grade was the significant predictor for the frequency of hand tremor in rest state and in arm extended state, after adjusting for age and gender by multiple linear regression (β = 14.70, P < 0.001; β = 15.37, P < 0.001).

CONCLUSIONS

There is a dose-response relationship between the number of packs smoked per day and SUR in the striatum, and the frequency of hand tremor. Decreased dopamine transporter binding in the striatum and increased frequency of hand tremor in smokers may have important implications for evaluating the impact of smoking on the central and peripheral nerve systems.

Dose-response relationship between cumulative mercury exposure index and specific uptake ratio in the striatum on Tc-99m TRODAT SPECT

PURPOSE

Tc-99m TRODAT is an agent for dopamine transporters and measuring dopamine innervation of the striatum. An association between Parkinson disease and body burden mercury level has been reported in the scientific published data. The purpose of this study was to investigate the effect of mercury exposure on dopamine transporters in the striatum measured by Tc-99m TRODAT single-photon emission computed tomography (SPECT).

METHOD AND MATERIALS

Study subjects included 17 workers who worked in a lamp factory at risk for mercury vapor exposure and 15 age-matched healthy controls. All subjects received Tc-99m TRODAT SPECT, brain computed tomography scan, and neurologic examinations. Biologic urine mercury levels at the end of a work week were assessed for workers.

RESULTS

There were significant differences in specific uptake ratio (SUR) in the striatum, caudate, and putamen between mercury exposure workers and healthy controls on Tc-99m TRODAT SPECT (all P < 0.001). The results showed a significantly negative correlation between urine and cumulative mercury levels and SUR in the striatum on Tc-99m TRODAT SPECT by Pearson analysis (r = -0.501, P = 0.040; r = -0.563, P = 0.019). After adjusting for age, gender, and body mass index, cumulative mercury exposure index (Cum Hg) was demonstrated to be the statistically significant predictor for SUR in the striatum, caudate, and putamen on Tc-99m TRODAT SPECT by multiple linear regression analysis (β = -0.543, P = 0.018; β = -0.521, P = 0.033; β = -0.465, P = 0.048).

CONCLUSION

Mercury exposure has significantly negative effect on dopamine transporters in the striatum. There is dose-response relationship between cumulative mercury exposure index (Cum Hg) and SUR in the striatum on Tc-99m TRODAT brain SPECT.

Interobserver reproducibility of the interpretation of I-123 FP-CIT single-photon emission computed tomography

OBJECTIVES

I-123 ioflupane (FP-CIT) single-photon emission computed tomography is a recognized tool in the diagnosis of Parkinsonian syndromes. In practice, data interpretation relies on visual and semiquantitative analyses. Good interobserver reproducibility is a prerequisite before claiming the robustness of a technique. This study aimed at evaluating interobserver reproducibility of this approach.

METHODS

Thirty nuclear medicine physicians participated in the study. Data included FP-CIT images and semiquantitative measurements of 12 cases, covering a wide spectrum of scintigraphic patterns and for which a 'true' clinical diagnosis based on long-term follow-up was available. Interobserver agreement was defined, for each case, as the highest percentage reached among the three proposed answers with complete agreement arbitrarily set at 80% or more. Variability in an individual observer's sensitivity to assess data as normal, equivocal or abnormal was scored using a three-point scale.

RESULTS

Response rate was 99.7%. Among the three possible answers,'normal' accounted for 41.2% of the total, 'abnormal' for 49.8% and 'equivocal' for 8.1%. The mean interobserver agreement was 76% (range: 37-100%), with complete agreement being reached only in five cases. The interpretation proposed by most observers accorded to clinical diagnosis in 75% of the cases. Abnormalities of the central nervous system were encountered in all the cases with disagreement between the observer's interpretation and clinical diagnoses. An important variability in the observers' sensitivity was seen.

CONCLUSION

In the particular setting of this preliminary study evaluating the reproducibility of FP-CIT single-photon emission computed tomography interpretation in a group of nuclear medicine physicians with various experiences, interobserver agreement was suboptimal. Collegial discussion and standardized interpretation criteria could contribute to an improved reproducibility.

A direct ROI quantification method for inherent PVE correction: accuracy assessment in striatal SPECT measurements

PURPOSE

The clinical potential of striatal imaging with dopamine transporter (DAT) SPECT tracers is hampered by the limited capability to recover activity concentration ratios due to partial volume effects (PVE). We evaluated the accuracy of a least squares method that allows retrieval of activity in regions of interest directly from projections (LS-ROI).

METHODS

An Alderson striatal phantom was filled with striatal to background ratios of 6:1, 9:1 and 28:1; the striatal and background ROIs were drawn on a coregistered X-ray CT of the phantom. The activity ratios of these ROIs were derived both with the LS-ROI method and with conventional SPECT EM reconstruction (EM-SPECT). Moreover, the two methods were compared in seven patients with motor symptoms who were examined with N-3-fluoropropyl-2-beta-carboxymethoxy-3-beta-(4-iodophenyl) (FP-CIT) SPECT, calculating the binding potential (BP).

RESULTS

In the phantom study, the activity ratios obtained with EM-SPECT were 3.5, 5.3 and 17.0, respectively, whereas the LS-ROI method resulted in ratios of 6.2, 9.0 and 27.3, respectively. With the LS-ROI method, the BP in the seven patients was approximately 60% higher than with EM-SPECT; a linear correlation between the LS-ROI and the EM estimates was found (r=0.98, p=0.03).

CONCLUSION

The LS-ROI PVE correction capability is mainly due to the fact that the ill-conditioning of the LS-ROI approach is lower than that of the EM-SPECT one. The LS-ROI seems to be feasible and accurate in the examination of the dopaminergic system. This approach can be fruitful in monitoring of disease progression and in clinical trials of dopaminergic drugs.

Artificial neural network classifier for the diagnosis of Parkinson's disease using [99mTc]TRODAT-1 and SPECT

Imaging the dopaminergic neurotransmitter system with positron emission tomography (PET) or single photon emission tomography (SPECT) is a powerful tool for the diagnosis of Parkinson's disease (PD). Previous studies have indicated that human observers have a diagnostic accuracy similar to conventional ROI analysis of SPECT imaging data. Consequently, it has been hypothesized that an artificial neural network (ANN), which can mimic the pattern recognition skills of human observers, may provide similar results. A set of patients with PD, and normal healthy control subjects, were studied using the dopamine transporter tracer [(99m)Tc]TRODAT-1 and SPECT. The sample was comprised of 81 patients (mean age +/- SD: 63.4 +/- 10.4 years; age range: 39.0-84.2 years) and 94 healthy controls (mean age +/- SD: 61.8 +/- 11.0 years; age range: 40.9-83.3 years). The images were processed to extract the striatum and the striatal pixel values were used as inputs to a three-layer ANN. The same set of data was used to both train and test the ANN, in a 'leave one out' procedure. The diagnostic accuracy of the ANN was higher than any previous analysis method applied to the same data (94.4% total accuracy, 97.5% specificity and 91.4% sensitivity). However, it should be stressed that, as with all applications of an ANN, it was difficult to interpret precisely what triggers in the images were being detected by the network.