ABSTRACT
PURPOSE: To develop a deep learning (DL) model for classifying histological types of primary bone tumors (PBTs) using radiographs and evaluate its clinical utility in assisting radiologists. METHODS: This retrospective study included 878 patients with pathologically confirmed PBTs from two centers (638, 77, 80, and 83 for the training, validation, internal test, and external test sets, respectively). We classified PBTs into five categories by histological types: chondrogenic tumors, osteogenic tumors, osteoclastic giant cell-rich tumors, other mesenchymal tumors of bone, or other histological types of PBTs. A DL model combining radiographs and clinical features based on the EfficientNet-B3 was developed for five-category classification. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were calculated to evaluate model performance. The clinical utility of the model was evaluated in an observer study with four radiologists. RESULTS: The combined model achieved a macro average AUC of 0.904/0.873, with an accuracy of 67.5 %/68.7 %, a macro average sensitivity of 66.9 %/57.2 %, and a macro average specificity of 92.1 %/91.6 % on the internal/external test set, respectively. Model-assisted analysis improved accuracy, interpretation time, and confidence for junior (50.6 % vs. 72.3 %, 53.07[s] vs. 18.55[s] and 3.10 vs. 3.73 on a 5-point Likert scale [P < 0.05 for each], respectively) and senior radiologists (68.7 % vs. 75.3 %, 32.50[s] vs. 21.42[s] and 4.19 vs. 4.37 [P < 0.05 for each], respectively). CONCLUSION: The combined DL model effectively classified histological types of PBTs and assisted radiologists in achieving better classification results than their independent visual assessment.
Subject(s)
Bone Neoplasms , Deep Learning , Sensitivity and Specificity , Humans , Bone Neoplasms/diagnostic imaging , Bone Neoplasms/pathology , Bone Neoplasms/classification , Male , Female , Retrospective Studies , Middle Aged , Adult , Adolescent , Aged , Child , Radiologists , Young Adult , Child, Preschool , Reproducibility of ResultsABSTRACT
Background: Delayed gastric emptying is a common non-motor symptom of Parkinson's disease (PD). However, there is currently no objective evaluation and diagnostic method for this condition. Objectives: The purpose of this study was to evaluate the feasibility of gastric-filling ultrasonography for gastric motility in patients with PD and the relationship between gastric dynamics and gastrointestinal symptoms and motor symptoms of PD. Design setting and patients: We performed a case-control study with 38 patients with PD and 34 healthy controls. Methods: All patients underwent a 120-min ultrasonography examination using a 500-ml semi-liquid test meal. We determined the antral contraction amplitude (ACA), the antrum contraction frequency (ACF), the motility index (MI), and the gastric antral cross-sectional area (CSA). We acquired the CSA at six time points: fasting for 12 h (T0), immediately after drinking the semi-liquid test meal (T1); and at 30 (T30), 60 (T60), 90 (T90), and 120 (T120) min. We calculated the gastric emptying rate (GER) at different time points by using the CSA. We compared the GER between the groups and evaluated the correlation between the GER and gastrointestinal symptoms and motor symptoms of PD. Results: The MI and ACF were significantly lower in the PD group compared with the control group (P < 0.05). The GER at T30 and the ACA showed no significant difference between the groups (P > 0.05). At different time points, the GER was significantly different between the PD and control groups (P < 0.001). There was no significant association between the GER and gastrointestinal symptoms; none of them were risk factors for impaired gastric emptying (odds ratio > 1). The GER was negatively correlated with the severity of PD motor symptoms (P < 0.05). Conclusion: Patients with PD had significantly delayed gastric emptying, which was negatively correlated with the severity of PD motor symptoms. Measuring gastric emptying by gastric-filling ultrasound had good diagnostic value in clinical screening for delayed gastric motility in patients with PD. Clinical Trial Registration: https://www.chictr.org.cn/showproj.html?proj=126304.
ABSTRACT
INTRODUCTION: Parkinson's (PD) is a common degenerative disease of the central nervous system. It affects more than 6 million individuals worldwide. The typical clinical manifestations include static tremor, slow movement, and unstable posture. However, the correlation between head tremor and the severity of PD remains unclear. METHODS: In the current study, 18 patients and 18 healthy subjects were recruited to undergo a phonation test. Noldus facereader 7.0 software was used to analyze the range of head trembling between the two groups. RESULTS: The data revealed that patients with PD had significant differences in the x-, y-, and z-axis of head movement with respect to the specific pronunciation syllables compared with the normal group. Moreover, the head movement of the patients with PD was positively correlated with the severity of the disease in the single, double, and multiple syllable tests. In the phonetic test, the head displacement of patients with PD was significantly greater than that of healthy individuals, and the displacement range was positively correlated with the severity of the disease. CONCLUSION: These pieces of evidence suggested that the measurement of head displacement assists the early diagnosis and severity of the disease.
Subject(s)
Head Movements/physiology , Parkinson Disease/physiopathology , Tremor/physiopathology , Aged , Aged, 80 and over , Female , Humans , Male , Middle Aged , Parkinson Disease/complications , Patient Acuity , Tremor/diagnosis , Tremor/etiologyABSTRACT
Dysarthria is universal in Parkinson's disease (PD) during disease progression; however, the quality of vocalization changes is often ignored. Furthermore, the role of changes in the acoustic parameters of phonation in PD patients remains unclear. We recruited 35 PD patients and 26 healthy controls to perform single, double, and multiple syllable tests. A logistic regression was performed to differentiate between protective and risk factors among the acoustic parameters. The results indicated that the mean f0, max f0, min f0, jitter, duration of speech and median intensity of speaking for the PD patients were significantly different from those of the healthy controls. These results reveal some promising indicators of dysarthric symptoms consisting of acoustic parameters, and they strengthen our understanding about the significance of changes in phonation by PD patients, which may accelerate the discovery of novel PD biomarkers.
Subject(s)
Dysarthria/diagnosis , Dysarthria/etiology , Parkinson Disease/complications , Speech Acoustics , Aged , Case-Control Studies , Female , Humans , Male , Middle Aged , Risk Factors , Symptom Assessment , VoiceABSTRACT
Devon Great Consols (DGC) is a region in south west England where extensive mining for Cu, Sn and As took place in the nineteenth century. Because of its historical and geological significance, DGC has protected status and is part of the Cornwall and West Devon Mining Landscape UNESCO World Heritage Site. Recently, the region was opened up to the public with the construction or redevelopment of various trails, tracks and facilities for walking, cycling and field visits. We used portable x-ray fluorescence spectrometry to measure, in situ, the concentrations of As in soils and dusts in areas that are accessible to the public. Concentrations ranged from about 140 to 75,000 µg g-1 (n = 98), and in all but one case exceeded a Category 4 Screening Level for park-type soil of 179 µg g-1. Samples returned to the laboratory and fractionated to <63 µm were subjected to an in vitro assessment of both oral and inhalable bioaccessibility, with concentrations ranging from <10 to 25,500 µg g-1 and dependent on the precise nature and origin of the sample and the physiological fluid applied. Concentrations of As in PM10 collected along various transects of the region averaged over 30 ng m-3 compared with a typical concentration in UK air of <1 ng m-3. Calculations using default EPA and CLEA estimates and that factor in for bioaccessibility suggest a 6-h visit to the region results in exposure to As well in excess of that of minimum risk. The overall risk is exacerbated for frequent visitors to the region and for workers employed at the site. Based on our observations, we recommend that the remodelling or repurposing of historical mine sites require more stringent management and mitigation measures.