Prediction of Parkinson's disease by transcranial sonography-based deep learning

OBJECTIVES

Transcranial sonography has been used as a valid neuroimaging tool to diagnose Parkinson's disease (PD). This study aimed to develop a modified transcranial sonography (TCS) technique based on a deep convolutional neural network (DCNN) model to predict Parkinson's disease.

METHODS

This retrospective diagnostic study was conducted using 1529 transcranial sonography images collected from 854 patients with PD and 775 normal controls admitted to the Second Affiliated Hospital of Soochow University (Suzhou, Jiangsu, China) between September 2019 and May 2022. The data set was divided into training cohorts (570 PD patients and 541 normal controls), and the validation set (184 PD patients and 234 normal controls). Using these datasets, we developed four different DCNN models (ResNet18, ResNet50, ResNet152, and DenseNet121). We then assessed their diagnostic performance, including the area under the receiver operating characteristic (AUROC) curve, specificity, sensitivity, positive predictive value (PPV), negative predictive value (NPV), and F1 score and compared with traditional diagnostic criteria.

RESULTS

Among the 1529 TCS images, 570 PD patients and 541 normal controls from 4 of 6 sonographers of the TCS team were selected as the training cohort, and 184 PD patients and 234 normal controls from the other 2 sonographers were chosen as the validation cohort. There were no sex and age differences between PD patients and normal control subjects in the training and validation cohorts (P values > 0.05). All DCNN models achieved good performance in distinguishing PD patients from normal control subjects on the validation datasets, with diagnostic AUROCs and accuracy of 0.949 (95% CI 0.925, 0.965) and 86.60 for the RestNet18 model, 0.949 (95% CI 0.929, 0.971) and 87.56 for ResNet50, 0.945 (95% CI 0.931, 0.969) and 88.04 for ResNet152, 0.953 (95% CI 0.935, 0.971) and 87.80 for DenseNet121, respectively. On the other hand, the diagnostic accuracy of the traditional diagnostic method was 82.30. The accuracy of all DCNN models was higher than that of traditional diagnostic method. Moreover, the 5k-fold cross-validation results in train datasets showed that these DCNN models are robust.

CONCLUSION

The developed transcranial sonography-based DCNN models performed better than traditional diagnostic criteria, thus improving the sonographer's accuracy in diagnosing PD.

Correlation Between Substantia Nigra Hyperechogenicity and Iron Metabolism in the Postural Instability Gait Difficulty Subtype of Parkinson's Disease

OBJECTIVE

The correlation between substantia nigra (SN) hyperechogenicity on transcranial sonography (TCS) and serum iron metabolism parameters in patients with the postural instability gait difficulty (PIGD) subtype of Parkinson's disease (PD) was investigated so as to explore the pathological mechanism of SN hyperechogenicity.

METHODS

The study enrolled 95 PIGD patients recruited by the Parkinson's Disease Specialty in the Second Affiliated Hospital of Soochow University during June 2019-2021. On the basis of the TCS results, the PIGD patients were assigned to the PD with SN hyperechogenicity (SN+) group (n = 60) and PD without SN hyperechogenicity (SN-) group (n = 35). Meanwhile, 49 sex- and age-matched healthy individuals were included in the control group. All participants underwent blood tests. Differences in the iron metabolism parameters among the three groups and the correlation between SN hyperechogenicity and serum iron metabolism parameters were analyzed.

RESULTS

Serum ferritin, ceruloplasmin and transferrin levels were lower in the SN+ and SN- groups than in the control group (all p values <0.001). The serum ceruloplasmin level was lower in the SN+ group (0.23 [0.20, 0.25] g/L) than in the SN- group (0.25 [0.22, 0.29] g/L) (p = 0.001), and the proportion of patients with an abnormal ceruloplasmin level was higher in the SN+ group than in the SN- group (43.3% [26/60] vs. 14.3% [5/35], χ2 = 8.484, p = 0.004). Moreover, the SN hyperechogenicity area was negatively correlated with the serum transferrin level (r = -0.428, p < 0.001).

CONCLUSION

Decreased serum ceruloplasmin levels may be associated with SN hyperechogenicity development in PIGD patients. The SN hyperechogenicity area is negatively correlated with the serum transferrin level.

Association Between Asymmetry of Substantia Nigra Hyperechogenicity and Clinical Characteristics in Different Parkinson Disease Subtypes: A 5-Year Follow-up Study

Our study focused on three aspects to determine whether bilateral substantia nigra hyperechogenicity (SN+) is asymmetrical, whether the asymmetry of SN+ is related to the clinical features and whether there is variation in SN+ asymmetry during the progression of Parkinson disease (PD). This follow-up study included 234 patients with PD, who were divided into tremor PD (TD, n = 67) and non-tremor PD (NTD, n = 167) groups based on the Unified Parkinson's Disease Rating Scale (UPDRS) Part III. All participants underwent transcranial sonography (TCS) and clinical assessment. In both the TD and NTD groups, the initial SN+ was larger than the non-initial SN+. The initial SN+ was associated with Hoehn and Yahr (H&amp;Y) stage, PD duration and initial UPDRS III, and the SN+ asymmetry index was associated with motor asymmetry index in the TD group. In the NTD group, the initial SN+ was associated only with initial UPDRS III. After a 5-year follow-up, the area of SN+ on both sides was gradually inclining to symmetry in the NTD group. Our study determined that SN+ asymmetry could reflect asymmetrical characteristics of PD. Furthermore, we inferred that the dynamic change in SN+ asymmetry might reflect a dynamic change in motor asymmetry in the NTD group.

Diagnostic value of ultrasound and contrast-enhanced ultrasound in septic acute kidney injury

PURPOSE

This study aimed to explore the clinical value of ultrasonic Doppler examination and contrast-enhanced ultrasound (US) in the circulation of septic acute kidney injury (AKI).

METHODS

Patients with intensive care unit-related infection were divided into AKI group and control groups. The AKI group was divided into three subgroups according to the serum creatinine value: stage 1, stage 2, and stage 3. Relevant parameters and blood flow of the renal artery were measured, and further contrast-enhanced US was performed and time-intensity curve was analyzed.

RESULTS

The renal blood flow (RBF) and time-averaged velocity decreased significantly in the AKI group compared with the control group (p = .021 and p = .001). The peak value decreased and time to peak (TTP) prolonged in the AKI group (p < .001). With the aggravation of the disease, the RBF decreased slightly among subgroups (p = 0.124). However, the peak value gradually decreased and the TTP prolonged (all p < .05). The multiple linear regression model showed that only PI, RI, and TTP were independently and linearly correlated with the serum creatinine value.

CONCLUSIONS

Doppler US and contrast-enhanced US are of great help in the detection of condition changes and prognosis of patients with sepsis-induced AKI.

Association between homocysteine and third ventricle dilatation, mesencephalic area atrophy in Parkinson's disease with cognitive impairment

OBJECTIVES

This study aimed to explore the association of homocysteine (Hcy) with third ventricle (V3) dilatation and mesencephalic area (MA) atrophy as determined by transcranial sonography (TCS) in Parkinson's disease (PD) with cognitive impairment.

METHODS

The final statistical analysis included 101 PD patients and 20 age- and sex-matched controls. Using the Movement Disorder Society (MDS) level II criteria for PD with cognitive impairment, we categorized the PD patients into PD with normal cognition group (PD) and PD with cognitive impairment group (PDC). All subjects underwent TCS and laboratory analysis.

RESULTS

The V3 width (r = 0.349, P = 0.005) and the MA (r = -0.484, P < 0.001) were significantly correlated with the Hcy concentration in the PDC patients. Binary logistic regression analysis revealed that age (OR [95% CI] = 1.114 [0.991-1.251], P = 0.002), and Hcy level (OR [95% CI] = 0.931 [0.752-1.153], P = 0.411) were independent risk factors for V3 dilatation. Hcy level (OR [95% CI] = 0.557 [0.323-0.967], P = 0.035) were independent risk factors for MA atrophy. After adjustment for confounding factors, the odds ratio of V3 dilatation was 3.50 (95% CI 1.054-11.399, P = 0.031) and the odds ratio of MA atrophy was 4.67 (95% CI 1.395-15.602, P = 0.012) in the patients with higher Hcy level compared with the lower level.

CONCLUSIONS

The results revealed a close association between the V3 width, MA and Hcy concentration in PD patients with cognitive impairment. We hypothesized that increased Hcy concentration played a significant role in the development of brain atrophy in PD with cognitive impairment.

Shear wave elastography characteristics of upper limb muscle in rigidity-dominant Parkinson's disease

BACKGROUND

Rigidity is one of the major manifestations of Parkinson's disease (PD), but no quantitative and objective imaging method has been developed to measure rigidity. Ultrasound shear wave elastography (SWE) can reflect the stiffness of tissue by providing a quantitative index. Thus, we conducted this study to evaluate the potential clinical value of SWE in assessing rigidity in PD.

METHODS

A total of 63 subjects (44 patients with rigidity-dominant PD and 19 right-dominant-hand normal controls with matched age) were enrolled, and each underwent ultrasound SWE testing. The tests were conducted on the brachioradialis (BR) and biceps brachii (BB) on the more affected side in patients with PD and on the right side in normal controls. Differences in quantitative shear wave velocity (SWV) between patients with PD and normal controls were determined. The relationship of muscle SWV with joint rigidity, UPDRSIII, disease duration, sex, and age in patients with PD was analyzed. The intraclass correlation coefficient (ICC) was used to evaluate the reliability of SWE in assessing muscle stiffness in patients with PD.

RESULTS

The mean SWVs of the BB and BR were higher in the PD group (3.65±0.46 and 4.62±0.89 m/s, respectively) than in normal controls (2.79±0.37 and 3.26±0.40 m/s, respectively). Stiffness in BR and BB was correlated with the upper-limb joint rigidity, UPDRSIII, and disease duration but not with sex or age in the PD group. The intraobserver correlation coefficients (ICCs) for interobserver and intraobserver variations in measuring SWV were 0.85 (95% confidence interval 0.56-0.95) and 0.85 (95% confidence interval 0.58-0.95), respectively, for BR and 0.90 (95% confidence interval 0.73-0.97) and 0.86 (95% confidence interval 0.61-0.95), respectively, for BB.

CONCLUSIONS

SWV is associated with joint rigidity and disease duration, indicating that SWE can be potentially used as an objective and quantitative tool for evaluating rigidity.

[Thirty-two cases of nasal lymphoma CT and MRI analysis]

Objective:Analysis of nasal lymphoma CT and MRI data, summarize imaging characteristics, provide help for clinical diagnosis. Method:Retrospectively analyzed the image manifestations of 32 cases of nasal lymphoma diagnosed by surgery and pathology. Lesion locations, tumor extension, bone destruction and its density, signal characteristics, enhancement degree, the situation of adjacent tissues were evaluated. Result:NK/T cells, T cell NHL have the characteristics: the lesions to diffuse growth, widely existed in nasal breathing zone, often involving middle and inferior turbinate, local bone slightly damaged, and no obvious bony shift. Tumor of uneven density, fuzzy boundaries, mixed signalse. The characteristics of B cell NHL: the lesion originated in the front of the nasal cavity, on the surrounding adjacent tissue compression performance, local feature is swelling growth and bone have insect damage sample sample, the dotted line change, very mild osseous shift, the tumor boundary is relatively clear, lesions density is uniform, and part of the uniform tumors had signal. Conclusion:Nasal lymphoma imaging changes have its characteristics. Image change prompts the pathological classification, providing help for clinical diagnosis.