Primary clinical study of radiomics for diagnosing simple bone cyst of the jaw

2021 ◽  
pp. 20200384
Author(s):  
Zhe-Yi Jiang ◽  
Tian-Jun Lan ◽  
Wei-Xin Cai ◽  
Qian Tao
Keyword(s):  
Bone Cyst ◽  
Maxillofacial Surgery ◽  
Correlation Coefficients ◽  
Texture Features ◽  
Image Features ◽  
Control Group ◽  
Imaging Features ◽  
Bone Cysts ◽  
Difference Matrix ◽  
Occurrence Matrix

Objective: To screen the radiomic features of simple bone cysts of the jaws and explore the potential application of radiomics in pre-operative diagnosis of jaw simple bone cysts. Methods: The investigators designed and implemented a case–control study. 19 patients with simple bone cysts who were admitted to the Department of Maxillofacial Surgery, Sun Yat-sen University Affiliated Stomatology Hospital from 2013 to 2019 were included in this study. Their clinical data and cone-beam computed tomography (CBCT) images were examined. The control group consisted of patients with odontogenic keratocyst. CBCT imaging features were analyzed and compared between the patient and control groups. Results: Overall, 10,323 image features were extracted through feature analysis. A subset of 25 radiomic features obtained after feature selection were analyzed further. These 25 features were significantly different between the 2 groups (p < 0.05). The absolute value of correlation coefficient was 0.487–0.775. Gray-level co-occurrence matrix (GLCM) contrast, neighborhood gray tone difference matrix (NGTDM) contrast, and GLCM variance were the features with the highest correlation coefficients. Conclusions: Pre-operative radiomics analysis showed the differences between simple bone cysts and odontogenic keratocysts, can help to diagnose simple bone cysts. Three specific texture features—GLCM contrast, NGTDM contrast, and GLCM variance—may be the characteristic imaging features of simple bone cysts of the jaw.

NIMG-56. USING RADIOMIC FEATURES FROM DAILY MAGNETIC RESONANCE IMAGING TO PREDICT RESPONSE TO RADIATION THERAPY IN GLIOBLASTOMA PATIENTS: A PILOT STUDY

2021 ◽  
Vol 23 (Supplement_6) ◽  
pp. vi142-vi142
Author(s):  
Kaylie Cullison ◽  
Garrett Simpson ◽  
Danilo Maziero ◽  
Kolton Jones ◽  
Radka Stoyanova ◽  
...  
Keyword(s):  
Radiation Therapy ◽  
Tumor Growth ◽  
Texture Feature ◽  
Texture Features ◽  
Gray Level ◽  
Difference Matrix ◽  
Patient Response ◽  
Significant Difference ◽  
Occurrence Matrix ◽  
Surrounding Areas

Abstract A dilemma in treating glioblastoma is that MRI after chemotherapy and radiation therapy (chemoRT) shows areas of presumed tumor growth in up to 50% of patients. These areas can represent true progression (TP), tumor growth with tumors non-responsive to treatment, or pseudoprogression (PP), edema and tumor necrosis with favorable treatment response. On imaging, TP and PP are usually not discernable. Patients in this study undergo six weeks of chemoRT on a combination MRI/RT device, receiving daily MRIs. The goal of this study is to explore the correlation of radiomics features with progression. The tumor lesion and surrounding areas of growth/edema were manually outlined as regions of interest (ROIs) for each daily T2-weighted MRI scan. The ROIs were used to calculate texture features: statistical features based on the gray-level co-occurrence matrix (GLCM), the gray-level zone size matrix (GLZSM), the gray-level run length matrix (GLRLM), and the neighborhood gray-tone difference matrix (NGTDM). Each of these matrix classes describe the probability of spatial relationships of gray levels occurring within the ROI. Daily texture features were averaged per week of treatment for each patient. Patient response was retrospectively defined as no progression (NP), TP, or PP. A Kruskal-Wallis test was performed to identify texture features that correlated most strongly with patient response. Forty texture features were calculated for 12 patients (19 treated, 7 excluded due to no T2 lesion or progression status unknown, 6 NP, 3 TP, 3 PP). There was a trend of more texture features correlating significantly with response in weeks 4-6 of treatment, compared to weeks 1-3. A particular texture feature, GLSZM Small Zone Low Gray-Level Emphasis, showed increasing difference between PP and TP over time, with significant difference during week 6 of treatment (p=0.0495). Future directions include correlating early outcomes with greater numbers of patients and daily multiparametric MRI.

scholarly journals Patellofemoral Morphology and Imaging Features of Patellar Tumors and Tumor-Like Lesions

2020 ◽  
Vol 17 (4) ◽  
Author(s):  
Tian-Hao Wu ◽  
Shu-Man Han ◽  
Tao Sun ◽  
Lei Cao ◽  
Yun-Heng Shi ◽  
...  
Keyword(s):  
Giant Cell ◽  
Patellofemoral Joint ◽  
Malignant Tumors ◽  
Bone Cyst ◽  
Bone Destruction ◽  
Control Group ◽  
Imaging Features ◽  
Benign Lesions ◽  
Joint Parameters ◽  
Tumor Like Lesions

Background: The patellofemoral joint parameters and imaging presentations of patellar tumors and tumor-like lesions are not clear. Objectives: The aim of this case-control study was to investigate patellofemoral joint parameters, clinical data and findings in patients with patellar tumors and tumor-like lesions. Patients and Methods: Twenty-nine patients with patellar diseases were enrolled. Morphological measurement was performed and analyzed in fourteen patients with patellar tumors (tumor group) and another fifteen patients without patellar diseases (control) who had complete computed tomography data as the control group. Results: Among 29 patients, there were twenty benign lesions (69.0%) and nine malignant tumors (31.0%). Benign lesions included chondroblastoma in nine patients (31.0%), giant cell tumor of bone in four (13.8%), chondroma in one (3.4%), hemangioma in one (3.4%), parosteal lipoma in one (3.4%), bone cyst in two (6.8%), aneurysmal bone cyst in one (3.4%), and fibrous dysplasia in one (3.4%). Malignant tumors were bone metastasis in four patients (13.8%), osteosarcoma in three (10.3%) including common osteosarcoma in two and well-differentiated osteosarcoma in the remaining one, chondrosarcoma in one (3.4%) and hemangiopericytoma in one (3.4%) patient. Chondroblastomas, giant cell tumors and fibrous dysplasia showed findings of expansile bone destruction lesions in imaging. Malignant tumors had bone destruction with ill-defined margins. The femoral trochlear angle was significantly greater in the tumor than the control group (P < 0.001, 159.19º ± 9.42º vs. 135.00º ± 5.50º), whereas the lateral pulley inclination (P = 0.01, 14.69º ± 8.91º vs. 20.73º ± 3.51º) and trochlear depth (P < 0.001, 3.10 ± 1.79 vs. 6.67 ± 1.26 mm) were significantly smaller in the tumor than the control group. Conclusion: The patellar tumors are mainly benign and rarely malignant. Comprehensive understanding of the distribution, incidence and imaging features of patellar tumors and patellofemoral morphological parameters can improve the diagnosis accuracy.

scholarly journals Impact of Lesion Delineation and Intensity Quantisation on the Stability of Texture Features from Lung Nodules on CT: A Reproducible Study

Diagnostics ◽  
2021 ◽  
Vol 11 (7) ◽  
pp. 1224
Author(s):  
Francesco Bianconi ◽  
Mario Luca Fravolini ◽  
Isabella Palumbo ◽  
Giulia Pascoletti ◽  
Susanna Nuvoli ◽  
...  
Keyword(s):  
Predictive Models ◽  
Clinical Decision Making ◽  
Texture Features ◽  
Lung Nodules ◽  
Computer Assisted ◽  
Imaging Features ◽  
Grey Level ◽  
Difference Matrix ◽  
Research Attention ◽  
The Stability

Computer-assisted analysis of three-dimensional imaging data (radiomics) has received a lot of research attention as a possible means to improve the management of patients with lung cancer. Building robust predictive models for clinical decision making requires the imaging features to be stable enough to changes in the acquisition and extraction settings. Experimenting on 517 lung lesions from a cohort of 207 patients, we assessed the stability of 88 texture features from the following classes: first-order (13 features), Grey-level Co-Occurrence Matrix (24), Grey-level Difference Matrix (14), Grey-level Run-length Matrix (16), Grey-level Size Zone Matrix (16) and Neighbouring Grey-tone Difference Matrix (five). The analysis was based on a public dataset of lung nodules and open-access routines for feature extraction, which makes the study fully reproducible. Our results identified 30 features that had good or excellent stability relative to lesion delineation, 28 to intensity quantisation and 18 to both. We conclude that selecting the right set of imaging features is critical for building clinical predictive models, particularly when changes in lesion delineation and/or intensity quantisation are involved.

scholarly journals Patient-Reported Dysphagia in Adults with Eosinophilic Esophagitis: Translation and Validation of the Swedish Eosinophilic Esophagitis Activity Index

Dysphagia ◽  
2021 ◽  
Author(s):  
Sofie Albinsson ◽  
Lisa Tuomi ◽  
Christine Wennerås ◽  
Helen Larsson
Keyword(s):  
Eosinophilic Esophagitis ◽  
Activity Index ◽  
Intraclass Correlation ◽  
Correlation Coefficients ◽  
Control Group ◽  
Cronbach’S Alpha ◽  
Intraclass Correlation Coefficients ◽  
Cronbach's Alpha ◽  
Patient Reported ◽  
Eortc Qlq

AbstractThe lack of a Swedish patient-reported outcome instrument for eosinophilic esophagitis (EoE) has limited the assessment of the disease. The aims of the study were to translate and validate the Eosinophilic Esophagitis Activity Index (EEsAI) to Swedish and to assess the symptom severity of patients with EoE compared to a nondysphagia control group. The EEsAI was translated and adapted to a Swedish cultural context (S-EEsAI) based on international guidelines. The S-EEsAI was validated using adult Swedish patients with EoE (n = 97) and an age- and sex-matched nondysphagia control group (n = 97). All participants completed the S-EEsAI, the European Organization for Research and Treatment of Cancer Quality of Life Questionnaire-Oesophageal Module 18 (EORTC QLQ-OES18), and supplementary questions regarding feasibility and demographics. Reliability and validity of the S-EEsAI were evaluated by Cronbach’s alpha and Spearman correlation coefficients between the domains of the S-EEsAI and the EORTC QLQ-OES18. A test–retest analysis of 29 patients was evaluated through intraclass correlation coefficients. The S-EEsAI had sufficient reliability with Cronbach’s alpha values of 0.83 and 0.85 for the “visual dysphagia question” and the “avoidance, modification and slow eating score” domains, respectively. The test–retest reliability was sufficient, with good to excellent intraclass correlation coefficients (0.60–0.89). The S-EEsAI domains showed moderate correlation to 6/10 EORTC QLQ-OES18 domains, indicating adequate validity. The patient S-EEsAI results differed significantly from those of the nondysphagia controls (p < 0.001). The S-EEsAI appears to be a valid and reliable instrument for monitoring adult patients with EoE in Sweden.

scholarly journals Multi-scale characterizations of colon polyps via computed tomographic colonography

2019 ◽  
Vol 2 (1) ◽  
Author(s):  
Weiguo Cao ◽  
Marc J. Pomeroy ◽  
Yongfeng Gao ◽  
Matthew A. Barish ◽  
Almas F. Abbasi ◽  
...  
Keyword(s):  
Area Under The Curve ◽  
Texture Features ◽  
Learning Model ◽  
Colon Polyps ◽  
Texture Descriptor ◽  
Operating Characteristics ◽  
Computed Tomographic ◽  
Multi Scale ◽  
Definition Of ◽  
Occurrence Matrix

AbstractTexture features have played an essential role in the field of medical imaging for computer-aided diagnosis. The gray-level co-occurrence matrix (GLCM)-based texture descriptor has emerged to become one of the most successful feature sets for these applications. This study aims to increase the potential of these features by introducing multi-scale analysis into the construction of GLCM texture descriptor. In this study, we first introduce a new parameter - stride, to explore the definition of GLCM. Then we propose three multi-scaling GLCM models according to its three parameters, (1) learning model by multiple displacements, (2) learning model by multiple strides (LMS), and (3) learning model by multiple angles. These models increase the texture information by introducing more texture patterns and mitigate direction sparsity and dense sampling problems presented in the traditional Haralick model. To further analyze the three parameters, we test the three models by performing classification on a dataset of 63 large polyp masses obtained from computed tomography colonoscopy consisting of 32 adenocarcinomas and 31 benign adenomas. Finally, the proposed methods are compared to several typical GLCM-texture descriptors and one deep learning model. LMS obtains the highest performance and enhances the prediction power to 0.9450 with standard deviation 0.0285 by area under the curve of receiver operating characteristics score which is a significant improvement.

scholarly journals POS1391 MEASURING SUBCLINICAL INFLAMMATION IN HAND AND FOREFOOT IN PATIENTS WITH ARTHRALGIA USING 1.5T OR 3.0T MRI: DOES FIELD STRENGTH MATTER?

2021 ◽  
Vol 80 (Suppl 1) ◽  
pp. 978.1-978
Author(s):  
D. Krijbolder ◽  
M. Verstappen ◽  
F. Wouters ◽  
L. R. Lard ◽  
P. D. De Buck ◽  
...  
Keyword(s):  
Field Strength ◽  
Scientific Evidence ◽  
Correlation Coefficients ◽  
Daily Practice ◽  
Scientific Data ◽  
Imaging Features ◽  
Subclinical Inflammation ◽  
The Individual ◽  
3.0T Mri ◽  
Inflammation Score

Background:Magnetic resonance imaging (MRI) of small joints sensitively detects inflammation. MRI-detected subclinical inflammation, and tenosynovitis in particular, has been shown predictive for RA development in patients with arthralgia. These scientific data are mostly acquired on 1.0T-1.5T MRI scanners. However, 3.0T MRI is nowadays increasingly used in practice. Evidence on the comparability of these field strengths is scarce and it has never been studied in arthralgia where subclinical inflammation is subtle. Moreover, comparisons never included tenosynovitis, which is, of all imaging features, the strongest predictor for progression to RA.Objectives:To determine if there is a difference between 1.5T and 3.0T MRI in detecting subclinical inflammation in arthralgia patients.Methods:2968 locations (joints, bones or tendon sheaths) in hands and forefeet of 28 arthralgia patients were imaged on both 1.5T and 3.0T MRI. Two independent readers scored for erosions, osteitis, synovitis (according to RAMRIS) and tenosynovitis (as described by Haavaardsholm et al.). Scores were also summed as total inflammation (osteitis, synovitis and tenosynovitis) and total RAMRIS (erosions, osteitis, synovitis and tenosynovitis) scores. Interreader reliability (comparing both readers) and field strength agreement (comparing 1.5T and 3.0T) was assessed with interclass correlation coefficients (ICCs). Next, field strength agreement was assessed after dichotomization into presence or absence of inflammation. Analyses were performed on patient- and location-level.Results:ICCs between readers were excellent (>0.90). Comparing 1.5 and 3.0T revealed excellent ICCs of 0.90 (95% confidence interval 0.78-0.95) for the total inflammation score and 0.90 (0.78-0.95) for the total RAMRIS score. ICCs for individual inflammation features were: tenosynovitis: 0.87 (0.74-0.94), synovitis 0.65 (0.24-0.84) and osteitis 0.96 (0.91-0.98). The field strength agreement on dichotomized scores was 83% for the total inflammation score and 89% for the total RAMRIS score. Of the individual features, agreement for tenosynovitis was the highest (89%). Analyses on location- level showed similar results.Conclusion:Agreement of subclinical inflammation scores on 1.5T and 3.0T were good to excellent, in particular for tenosynovitis. This suggests that scientific evidence on predictive power of MRI in arthralgia patients, obtained on 1.5T, can be generalized to 3.0T when this field strength would be used for diagnostic purposes in daily practice.Disclosure of Interests:None declared

Comparison of Dental Caries Prevalence in Patients with Cleft Lip and/or Palate and Their Sibling Controls

2009 ◽  
Vol 46 (5) ◽  
pp. 529-531 ◽  
Author(s):  
Mahmoud Al-Dajani
Keyword(s):  
Dental Caries ◽  
Cleft Lip ◽  
Cleft Lip And Palate ◽  
Maxillofacial Surgery ◽  
Permanent Teeth ◽  
Control Group ◽  
Oral And Maxillofacial Surgery ◽  
Caries Prevalence ◽  
Dmft Index ◽  
And Control

Objective: To evaluate the prevalence of dental caries in patients with cleft lip and/or palate and their cleft-free sibling controls. Methods: The two subject groups (patient and control) comprised 106 participants. The former group consisted of 53 patients with cleft lip and/or palate, aged 12 to 29 years, who visited the Oral and Maxillofacial Surgery Hospital at Damascus University of Syria. The control group consisted of the patients’ siblings who had no clefts, and they were sex matched to the patient group. Dental caries were examined clinically and were reported using the decayed, missing, and filled permanent teeth (DMFT) index. The DMFT scores were compared between the two groups. Results: The author found an overall association of dental caries with the presence of cleft lip and/or palate (odds ratio  =  2.52; 95% confidence interval  =  1.389–4.574; p < .05). The DMFT index scores were proportionally higher in patients with cleft lip and/or palate compared with the control group (p < .001). Conclusion: Subjects with cleft lip and palate are susceptible to dental caries independently of socioeconomic status.

Aneurysmal Bone Cyst: A Review of 150 Patients

2005 ◽  
Vol 23 (27) ◽  
pp. 6756-6762 ◽  
Author(s):  
Henry J. Mankin ◽  
Francis J. Hornicek ◽  
Eduardo Ortiz-Cruz ◽  
Jorge Villafuerte ◽  
Mark C. Gebhardt
Keyword(s):  
Aneurysmal Bone Cyst ◽  
Local Recurrence Rate ◽  
Bone Cyst ◽  
Secondary Development ◽  
Bone Cysts ◽  
Resonance Imaging ◽  
Imaging Studies ◽  
Treatment Protocols ◽  
Imaging Appearance ◽  
Aneurysmal Bone Cysts

PurposeWe have reviewed a series of 150 aneurysmal bone cysts treated over the last 20 years.Patients and MethodsThe lesions were principally located in the tibia, femur, pelvis, humerus, and spine and, in most cases, presented the imaging appearance originally described by Jaffe and Lichtenstein as a blowout with thin cortices.ResultsOnly one of the patients was believed to have an osteoblastoma of the spine with secondary development of an aneurysmal bone cyst, and none of the patients developed additional lesions. The patients were treated primarily with curettage and implantation of allograft chips or polymethylmethacrylate, but some patients were treated with insertion of autografts or allografts. The local recurrence rate was 20%, which is consistent with that reported by other centers.ConclusionAneurysmal bone cysts are enigmatic lesions of unknown cause and presentation and are difficult to distinguish from other lesions. Overall, the treatment is satisfactory, but it is possible that newer approaches, such as improved magnetic resonance imaging studies, may help diagnose the lesions and allow the physicians to plan for more effective treatment protocols.

Nipple Localization in Automated Whole Breast Ultrasound Coronal Scans Using Ensemble Learning

2020 ◽  
Vol 43 (1) ◽  
pp. 29-45
Author(s):  
Alex Noel Joseph Raj ◽  
Ruban Nersisson ◽  
Vijayalakshmi G. V. Mahesh ◽  
Zhemin Zhuang
Keyword(s):  
Texture Features ◽  
Breast Ultrasound ◽  
Support Vector ◽  
Ultrasound Images ◽  
Shadow Area ◽  
Hu Moments ◽  
Artificial Neural Network Ann ◽  
Cade System ◽  
Occurrence Matrix ◽  
Shape Complexity

Nipple is a vital landmark in the breast lesion diagnosis. Although there are advanced computer-aided detection (CADe) systems for nipple detection in breast mediolateral oblique (MLO) views of mammogram images, few academic works address the coronal views of breast ultrasound (BUS) images. This paper addresses a novel CADe system to locate the Nipple Shadow Area (NSA) in ultrasound images. Here the Hu Moments and Gray-level Co-occurrence Matrix (GLCM) were calculated through an iterative sliding window for the extraction of shape and texture features. These features are then concatenated and fed into an Artificial Neural Network (ANN) to obtain probable NSA’s. Later, contour features, such as shape complexity through fractal dimension, edge distance from the periphery and contour area, were computed and passed into a Support Vector Machine (SVM) to identify the accurate NSA in each case. The coronal plane BUS dataset is built upon our own, which consists of 64 images from 13 patients. The test results show that the proposed CADe system achieves 91.99% accuracy, 97.55% specificity, 82.46% sensitivity and 88% F-score on our dataset.

A prospective randomized study to assess the efficacy of post-operative nasal medication after endonasal surgery

1995 ◽  
Vol 109 (7) ◽  
pp. 618-621 ◽  
Author(s):  
Paul D. R. Spraggs ◽  
Marcelle Macnamara ◽  
Theo Joseph
Keyword(s):  
Randomized Study ◽  
Correlation Coefficients ◽  
Control Group ◽  
Time Intervals ◽  
Treatment Groups ◽  
Ephedrine Hydrochloride ◽  
Patent Airway ◽  
Significant Difference ◽  
Blood Clots ◽  
Betamethasone Sodium Phosphate

AbstractPost-operative nasal medications are commonly used following routine septal or turbinate surgery but their efficacy in removing blood clots, improving the sensation of a patent airway and promoting healing are unknown. This prospective randomized trial of patients undergoing septal and/or turbinate surgery assessed the efficacy of three commonly used nasal medicines, 0.5 per cent ephedrine hydrochloride nasal drops, betamethasone sodium phosphate (Betnosol®) nose drops and alkaline nasal douches, in producing the sensation of a patent airway in the 14 days following surgery. Ninety-seven patients were randomized into the three treatment groups and a control group who received no nasal medication. Patients assessed their nasal patency by means of a visual analogue scale (VAS) and any complications of treatment were recorded. Statistical analysis of the 76 complete sets of results using the Mann-Whitney U-test showed that there was a significant difference in the distribution of all of the treatments for each of the time intervals (p<0.05). Glass rank biserial correlation coefficients were all small (rg<0.085) but the most significant differences were between ephedrine and the control group at two hours, two, seven and 10 days (0.02, 0.054, 0.057, 0.085 respectively), alkaline nasal douches being most significant at four and 14 days (0.06 and 0.0722 respectively).

Sign in / Sign up

Export Citation Format

Share Document