Predicting severe radiation-induced oral mucositis in head and neck cancer patients using integrated baseline CT radiomic, dosimetry, and clinical features: A machine learning approach.

Purpose: To establish the early prediction models of radiation-induced oral mucositis (RIOM) based on baseline CT-based radiomic features (RFs), dosimetric data, and clinical features by machine learning models for head and neck cancer (HNC) patients. Methods: In this single-center prospective study, 49 HNCs treated with curative intensity modulated radiotherapy (IMRT) were enrolled. Baseline CT images (i.e., CT simulation), dosimetric, and clinical features were collected. RIOM was assessed using CTCAE v.5.0. RFs were extracted from manually-contoured oral mucosa structures. Minimum-redundancy-maximum-relevance (mRMR) method was applied to select the most informative radiomics, dosimetric, and clinical features. Then, binary prediction models were constructed for predicting acute RIOM based on the top mRMR-ranked radiomics, dosimetric, and clinical features alone or in combination, using random forest classifier algorithm. The predictive performance of models was assessed using the area under the receiver operating curve (AUC), accuracy, weighted-average based sensitivity, precision, and F1-measure. Results: Among extracted features, the top 10 RFs, the top 5 dose-volume features, and the top 5 clinical features were selected using mRMR method. The model exploiting the integrated features (10-radiomics + 5-dosimetric + 5-clinical) achieved the best prediction with AUC, accuracy, sensitivity, precision, and F1-measure values of 91.7 %, 90.0 %, 83.0 % 100.0 %, and 91.0 %, respectively. The model developed using baseline CT RFs alone provided the best performance compared to dose-volume features or clinical features alone, with an AUC of 87.0 %. Conclusion: Our results suggest that the integration of baseline CT radiomic features with dosimetric and clinical features showed promising potential to improve the performance of machine learning models in early prediction of RIOM. The ultimate goal is to personalize radiotherapy for HNC patients.

Deep Learning-based Non-rigid Image Registration for High-dose Rate Brachytherapy in Inter-fraction Cervical Cancer.

In this study, an inter-fraction organ deformation simulation framework for the locally advanced cervical cancer (LACC), which considers the anatomical flexibility, rigidity, and motion within an image deformation, was proposed. Data included 57 CT scans (7202 2D slices) of patients with LACC randomly divided into the train (n = 42) and test (n = 15) datasets. In addition to CT images and the corresponding RT structure (bladder, cervix, and rectum), the bone was segmented, and the coaches were eliminated. The correlated stochastic field was simulated using the same size as the target image (used for deformation) to produce the general random deformation. The deformation field was optimized to have a maximum amplitude in the rectum region, a moderate amplitude in the bladder region, and an amplitude as minimum as possible within bony structures. The DIRNet is a convolutional neural network that consists of convolutional regressors, spatial transformation, as well as resampling blocks. It was implemented by different parameters. Mean Dice indices of 0.89 ± 0.02, 0.96 ± 0.01, and 0.93 ± 0.02 were obtained for the cervix, bladder, and rectum (defined as at-risk organs), respectively. Furthermore, a mean average symmetric surface distance of 1.61 ± 0.46 mm for the cervix, 1.17 ± 0.15 mm for the bladder, and 1.06 ± 0.42 mm for the rectum were achieved. In addition, a mean Jaccard of 0.86 ± 0.04 for the cervix, 0.93 ± 0.01 for the bladder, and 0.88 ± 0.04 for the rectum were observed on the test dataset (15 subjects). Deep learning-based non-rigid image registration is, therefore, proposed for the high-dose-rate brachytherapy in inter-fraction cervical cancer since it outperformed conventional algorithms.

Pediatric effective dose assessment for routine computed tomography examinations in Tehran, Iran.

Background: The purpose of this study is to evaluate the effective dose (ED) for computed tomography (CT) examination in different age groups and medical exposure in pediatric imaging centers in Tehran, Iran. Methods: Imaging data were collected from 532 pediatric patients from four age groups subjected to three prevalent procedures. National Cancer Institute CT (NCICT) software was used to calculate the ED value. Results: The mean ED values were 1.60, 4.16, and 10.56 mSv for patients' procedures of head, chest, and abdomen-pelvis, respectively. This study showed a significant difference of ED value among five pediatric medical imaging centers (P < 0.05). In head, chest, and abdomen-pelvis exams, a reduction in ED was evident with decreasing patients' age. Conclusion: As there were significant differences among ED values in five pediatric medical imaging centers, optimizing this value is necessary to decrease this variation. For head CT in infants and also abdomen-pelvis, further reduction in radiation exposure is required.

Deep learning-based automatic detection of tuberculosis disease in chest X-ray images.

Purpose: To train a convolutional neural network (CNN) model from scratch to automatically detect tuberculosis (TB) from chest X-ray (CXR) images and compare its performance with transfer learning based technique of different pre-trained CNNs. Material and methods: We used two publicly available datasets of postero-anterior chest radiographs, which are from Montgomery County, Maryland, and Shenzhen, China. A CNN (ConvNet) from scratch was trained to automatically detect TB on chest radiographs. Also, a CNN-based transfer learning approach using five different pre-trained models, including Inception_v3, Xception, ResNet50, VGG19, and VGG16 was utilized for classifying TB and normal cases from CXR images. The performance of models for testing datasets was evaluated using five performances metrics, including accuracy, sensitivity/recall, precision, area under curve (AUC), and F1-score. Results: All proposed models provided an acceptable accuracy for two-class classification. Our proposed CNN architecture (i.e., ConvNet) achieved 88.0% precision, 87.0% sensitivity, 87.0% F1-score, 87.0% accuracy, and AUC of 87.0%, which was slightly less than the pre-trained models. Among all models, Exception, ResNet50, and VGG16 provided the highest classification performance of automated TB classification with precision, sensitivity, F1-score, and AUC of 91.0%, and 90.0% accuracy. Conclusions: Our study presents a transfer learning approach with deep CNNs to automatically classify TB and normal cases from the chest radiographs. The classification accuracy, precision, sensitivity, and F1-score for the detection of TB were found to be more than 87.0% for all models used in the study. Exception, ResNet50, and VGG16 models outperformed other deep CNN models for the datasets with image augmentation methods.

MRI-based machine learning for determining quantitative and qualitative characteristics affecting the survival of glioblastoma multiforme.

PURPOSE: Our current study aims to consider the image biomarkers extracted from the MRI images for exploring their effects on glioblastoma multiforme (GBM) patients' survival. Determining its biomarker helps better manage the disease and evaluate treatments. It has been proven that imaging features could be used as a biomarker. The purpose of this study is to investigate the features in MRI and clinical features as the biomarker association of survival of GBM. METHODS: 55 patients were considered with five clinical features, 10 qualities pre-operative MRI image features, and six quantitative features obtained using BraTumIA software. It was run ANN, C5, Bayesian, and Cox models in two phases for determining important variables. In the first phase, we selected the quality features that occur at least in three models and quantitative in two models. In the second phase, models were run with the extracted features, and then the probability value of variables in each model was calculated. RESULTS: The mean of accuracy, sensitivity, specificity, and area under curve (AUC) after running four machine learning techniques were 80.47, 82.54, 79.78, and 0.85, respectively. In the second step, the mean of accuracy, sensitivity, specificity, and AUC were 79.55, 78.71, 79.83, and 0.87, respectively. CONCLUSION: We found the largest size of the width, the largest size of length, radiotherapy, volume of enhancement, volume of nCET, satellites, enhancing margin, and age feature are important features.

Neural Network Performance Evaluation of Simulated and Genuine Head-and-Neck Computed Tomography Images to Reduce Metal Artifacts.

Background: This study evaluated the performances of neural networks in terms of denoizing metal artifacts in computed tomography (CT) images to improve diagnosis based on the CT images of patients. Methods: First, head-and-neck phantoms were simulated (with and without dental implants), and CT images of the phantoms were captured. Six types of neural networks were evaluated for their abilities to reduce the number of metal artifacts. In addition, 40 CT patients' images with head-and-neck cancer (with and without teeth artifacts) were captured, and mouth slides were segmented. Finally, simulated noisy and noise-free patient images were generated to provide more input numbers (for training and validating the generative adversarial neural network [GAN]). Results: Results showed that the proposed GAN network was successful in denoizing artifacts caused by dental implants, whereas more than 84% improvement was achieved for images with two dental implants after metal artifact reduction (MAR) in patient images. Conclusion: The quality of images was affected by the positions and numbers of dental implants. The image quality metrics of all GANs were improved following MAR comparison with other networks.

Investigating dose homogeneity in radiotherapy of oral cancers in the presence of a dental implant system: an in vitro phantom study.

BACKGROUND: Materials with high atomic numbers are part of the composition of dental implant systems. In radiotherapy of oral cavity cancers, an implant can cause dose perturbations that affect target definition, dose calculation, and dose distribution. In consequence, this may result in poor tumor control and higher complications. In this study, we evaluated dose homogeneity when a dental implant replaced a normal tooth. We also aimed to evaluate the concordance of dose calculations with dose measurements. MATERIALS AND METHODS: In this study, 2 sets of planning CT scans of a phantom with a normal tooth and the same phantom with the tooth replaced by a Z1 TBR dental implant system were used. The implant system was composed of a porcelain-fused-to-metal crown and titanium with a zirconium collar. Three radiotherapy plans were designed when the density of the implant material was corrected to match their elements, or when all were set to the density of water, or when using the default density conversion. Gafchromic EBT-3 films at the level of isocenter and crowns were used for measurements. RESULTS: At the level of crowns, upstream and downstream dose calculations were reduced when metal kernels were applied (M-plan). Moreover, relatively measured dose distribution patterns were most similar to M-plan. At this level, relative to the non-implanted phantom, mean doses values were higher with the implant (215.93 vs. 192.25), also, new high-dose areas appeared around a low-dose streak forward to the implant (119% vs. 95%). CONCLUSIONS: Implants can cause a high dose to the oral cavity in radiotherapy because of extra scattered radiation. Knowledge of the implant dimensions and defining their material enhances the accuracy of calculations.

Automated detection of dental artifacts for large-scale radiomic analysis in radiation oncology.

BACKGROUND AND PURPOSE: Computed tomography (CT) is one of the most common medical imaging modalities in radiation oncology and radiomics research, the computational voxel-level analysis of medical images. Radiomics is vulnerable to the effects of dental artifacts (DA) caused by metal implants or fillings and can hamper future reproducibility on new datasets. In this study we seek to better understand the robustness of quantitative radiomic features to DAs. Furthermore, we propose a novel method of detecting DAs in order to safeguard radiomic studies and improve reproducibility. MATERIALS AND METHODS: We analyzed the correlations between radiomic features and the location of dental artifacts in a new dataset containing 3D CT scans from 3211 patients. We then combined conventional image processing techniques with a pre-trained convolutional neural network to create a three-class patient-level DA classifier and slice-level DA locator. Finally, we demonstrated its utility in reducing the correlations between the location of DAs and certain radiomic features. RESULTS: We found that when strong DAs were present, the proximity of the tumour to the mouth was highly correlated with 36 radiomic features. We predicted the correct DA magnitude yielding a Matthews correlation coefficient of 0.73 and location of DAs achieving the same level of agreement as human labellers. CONCLUSIONS: Removing radiomic features or CT slices containing DAs could reduce the unwanted correlations between the location of DAs and radiomic features. Automated DA detection can be used to improve the reproducibility of radiomic studies; an important step towards creating effective radiomic models for use in clinical radiation oncology.

Prediction of Human Papillomavirus (HPV) Association of Oropharyngeal Cancer (OPC) Using Radiomics: The Impact of the Variation of CT Scanner.

Studies have shown that radiomic features are sensitive to the variability of imaging parameters (e.g., scanner models), and one of the major challenges in these studies lies in improving the robustness of quantitative features against the variations in imaging datasets from multi-center studies. Here, we assess the impact of scanner choice on computed tomography (CT)-derived radiomic features to predict the association of oropharyngeal squamous cell carcinoma with human papillomavirus (HPV). This experiment was performed on CT image datasets acquired from two different scanner manufacturers. We demonstrate strong scanner dependency by developing a machine learning model to classify HPV status from radiological images. These experiments reveal the effect of scanner manufacturer on the robustness of radiomic features, and the extent of this dependency is reflected in the performance of HPV prediction models. The results of this study highlight the importance of implementing an appropriate approach to reducing the impact of imaging parameters on radiomic features and consequently on the machine learning models, without removing features which are deemed non-robust but may contain learning information.

Lifetime attributable cancer risk related to prevalent CT scan procedures in pediatric medical imaging centers.

PURPOSE: Evaluation of the organ dose in pediatric patients up to 15 years old and Estimation of lifetime attributable risk (LAR) of cancer incidence in pediatric computed tomography procedures. MATERIALS AND METHODS: Data from 532 patients below 15 years old was collected and they were categorized into four age groups of <1, 1-5, 5-10, and 10-15 years old. NCICT software was used to calculate the organ dose, and LAR of cancer incidence has been estimated according to the BEIR VII report. RESULTS: The highest median dose in all age groups was related to eye lens (head scan), thyroid (chest scan), and colon (abdomen-pelvic scan). The highest average LAR of cancer incidence was observed for breast cancer and colon cancer following a chest CT scan of the youngest group (<1-year-olds) [68.23 per 100,000] and abdomen-pelvic scans of the oldest group (10- to 15-year-olds) [57.30 per 100,000]. CONCLUSION: This study shows that the average LAR is higher in females and it decreases with age in both genders. Although CT scan has an indispensable application in diagnosis, the patient dose should be taken into account before any examination specifically in pediatric patients.

Automated detection of pneumonia cases using deep transfer learning with paediatric chest X-ray images.

OBJECTIVE: Pneumonia is a lung infection and causes the inflammation of the small air sacs (Alveoli) in one or both lungs. Proper and faster diagnosis of pneumonia at an early stage is imperative for optimal patient care. Currently, chest X-ray is considered as the best imaging modality for diagnosing pneumonia. However, the interpretation of chest X-ray images is challenging. To this end, we aimed to use an automated convolutional neural network-based transfer-learning approach to detect pneumonia in paediatric chest radiographs. METHODS: Herein, an automated convolutional neural network-based transfer-learning approach using four different pre-trained models (i.e. VGG19, DenseNet121, Xception, and ResNet50) was applied to detect pneumonia in children (1-5 years) chest X-ray images. The performance of different proposed models for testing data set was evaluated using five performances metrics, including accuracy, sensitivity/recall, Precision, area under curve, and F1 score. RESULTS: All proposed models provide accuracy greater than 83.0% for binary classification. The pre-trained DenseNet121 model provides the highest classification performance of automated pneumonia classification with 86.8% accuracy, followed by Xception model with an accuracy of 86.0%. The sensitivity of the proposed models was greater than 91.0%. The Xception and DenseNet121 models achieve the highest classification performance with F1-score greater than 89.0%. The plotted area under curve of receiver operating characteristics of VGG19, Xception, ResNet50, and DenseNet121 models are 0.78, 0.81, 0.81, and 0.86, respectively. CONCLUSION: Our data showed that the proposed models achieve a high accuracy for binary classification. Transfer learning was used to accelerate training of the proposed models and resolve the problem associated with insufficient data. We hope that these proposed models can help radiologists for a quick diagnosis of pneumonia at radiology departments. Moreover, our proposed models may be useful to detect other chest-related diseases such as novel Coronavirus 2019. ADVANCES IN KNOWLEDGE: Herein, we used transfer learning as a machine learning approach to accelerate training of the proposed models and resolve the problem associated with insufficient data. Our proposed models achieved accuracy greater than 83.0% for binary classification.

The impact of the variation of imaging parameters on the robustness of Computed Tomography radiomic features: A review.

The field of radiomics is at the forefront of personalized medicine. However, there is concern that high variation in imaging parameters will impact robustness of radiomic features and subsequently the performance of the predictive models built upon them. Therefore, our review aims to evaluate the impact of imaging parameters on the robustness of radiomic features. We also provide insights into the validity and discrepancy of different methodologies applied to investigate the robustness of radiomic features. We selected 47 papers based on our predefined inclusion criteria and grouped these papers by the imaging parameter under investigation: (i) scanner parameters, (ii) acquisition parameters and (iii) reconstruction parameters. Our review highlighted that most of the imaging parameters are disruptive parameters, and shape along with First order statistics were reported as the most robust radiomic features against variation in imaging parameters. This review identified inconsistencies related to the methodology of the reviewed studies such as the metrics used for robustness, the feature extraction techniques, the reporting style, and their outcome inclusion. We hope this review will aid the scientific community in conducting research in a way that is more reproducible and avoids the pitfalls of previous analyses.

CovidCTNet: an open-source deep learning approach to diagnose covid-19 using small cohort of CT images.

Coronavirus disease 2019 (Covid-19) is highly contagious with limited treatment options. Early and accurate diagnosis of Covid-19 is crucial in reducing the spread of the disease and its accompanied mortality. Currently, detection by reverse transcriptase-polymerase chain reaction (RT-PCR) is the gold standard of outpatient and inpatient detection of Covid-19. RT-PCR is a rapid method; however, its accuracy in detection is only ~70-75%. Another approved strategy is computed tomography (CT) imaging. CT imaging has a much higher sensitivity of ~80-98%, but similar accuracy of 70%. To enhance the accuracy of CT imaging detection, we developed an open-source framework, CovidCTNet, composed of a set of deep learning algorithms that accurately differentiates Covid-19 from community-acquired pneumonia (CAP) and other lung diseases. CovidCTNet increases the accuracy of CT imaging detection to 95% compared to radiologists (70%). CovidCTNet is designed to work with heterogeneous and small sample sizes independent of the CT imaging hardware. To facilitate the detection of Covid-19 globally and assist radiologists and physicians in the screening process, we are releasing all algorithms and model parameter details as open-source. Open-source sharing of CovidCTNet enables developers to rapidly improve and optimize services while preserving user privacy and data ownership.

Analysis of trace elements in human hair through X-ray fluorescence spectroscopy for screening of prostate cancer.

Background: Use of hair samples to analyze the trace element concentrations is one of the interesting fields among many researchers. X-ray fluorescence (XRF) is considered as one of the most common methods in studying the concentration of elements in tissues and also crystalline materials, using low energy X-ray. In the present study, we aimed to evaluate the concentration of the trace elements in the scalp hair sample through XRF spectroscopy using signal processing techniques as a screening tool for prostate cancer. Methods: Hair samples of 22 men (including 11 healthy and 11 patients) were analyzed. All the sample donors were Iranian men. EDXRF method was used for the measurements. Signals were analyzed, and signal features such as mean, root-mean-square (RMS), variance, and standard deviation, skewness, and energy were investigated. The Man-Whitney U test was used to compare the trace element concentrations. The analysis of variance (ANOVA) test was used to identify which extracted feature could help to identify healthy and patient people. P values ≤ 0.05 were considered statistically significant. Statistical analysis was performed using SPSS 16.0 software. Results: The mean±SD age was 67.8±8.7 years in the patient group and 61.4±6.9 years in the healthy group. There were statistically significant differences in the aluminum (Al, P<0.001), silicon (Si, P=0.006), and phosphorus (P, P=0.028) levels between healthy and patient groups. Skewness and variance were found to be relevant in identifying people with cancer, as signal features. Conclusion: The use of EDXRF is a feasible method to study the concentration of elements in the hair sample, and this technique may be effective in prostate cancer screening. Further study with a large sample size will be required to elucidate the efficacy of the present method in prostate cancer screening.

PEDIATRIC REGIONAL DRL ASSESSMENT IN COMMON CT EXAMINATIONS FOR MEDICAL EXPOSURE OPTIMIZATION IN TEHRAN, IRAN.

The main purpose of this pilot study was to assess the regional diagnostic reference level (RDRL) of computed tomography (CT) examinations to optimise medical exposure in five pediatric medical imaging centers in Tehran, Iran where the most frequent CT examinations were investigated. For each patient, CT volume dose indexes (CTDIvol) and dose length product (DLP) in each group were recorded and their third quartile was calculated and set as RDRL. Pediatrics were divided into four age groups (<1; 1-5; 5-10 and 10-15 years). Then, the third quartile values for head, chest and abdomen-pelvic CTs were, respectively, calculated for each group in terms of CTDIvol: 21.3, 24.4, 24.2 and 36.3 mGy; 2.9, 3.2, 3.7 and 5.7 mGy; 3.7, 5.7, 6.3 and 6.8 mGy; and in terms of DLP: 322.2, 390.1, 424.9 and 694.1 mGy.cm; 53.1, 115.2, 145.3 and 167.6 mGy.cm and 128.7, 317.7, 460.2 and 813.8 mGy.cm. Finally, RDRLs were compared with other countries and preceding data in Iran. As a result, CTDIVOL values were lower than other national and international studies except for chest and abdomen-pelvic values obtained in Europe. Moreover, this matter applied to DLP so that other formerly reported values were higher than the present study but European values for chest and abdomen-pelvic scans and also Tehran studies conducted in 2012. Variation of scan parameters (tube voltage (kVp), tube current (mAs) and scan length), CTDIvol and DLP of different procedures among different age groups were statistically significant (P-value < 0.05). The variations in dose between CT departments as well as between identical scanners suggest a large potential for optimization of examinations relative to which this study provides helpful data.

Artificial intelligence in automatic classification of invasive ductal carcinoma breast cancer in digital pathology images.

Background: Breast cancer is one of the most causes of death in women. Early diagnosis and detection of Invasive Ductal Carcinoma (IDC) is an important key for the treatment of IDC. Computer-aided approaches have great potential to improve diagnosis accuracy. In this paper, we proposed a deep learning-based method for the automatic classification of IDC in whole slide images (WSI) of breast cancer. Furthermore, different types of deep neural networks training such as training from scratch and transfer learning to classify IDC were evaluated. Methods: In total, 277524 image patches with 50×50-pixel size form original images were used for model training. In the first method, we train a simple convolutional neural network (named it baseline model) on these images. In the second approach, we used the pre-trained VGG-16 CNN model via feature extraction and fine-tuning for the classification of breast pathology images. Results: Our baseline model achieved a better result for the automatic classification of IDC in terms of F-measure and accuracy (83%, 85%) in comparison with original paper on this data set and achieved a comparable result with a new study that introduced accepted-rejected pooling layer. Also, transfer learning via feature extraction yielded better results (81%, 81%) in comparison with handcrafted features. Furthermore, transfer learning via feature extraction yielded better classification results in comparison with the baseline model. Conclusion: The experimental results demonstrate that using deep learning approaches yielded better results in comparison with handcrafted features. Also, using transfer learning in histopathology image analysis yielded significant results in comparison with training from scratch in much less time.

Evaluation of deformable image registration algorithm for determination of accumulated dose for brachytherapy of cervical cancer patients.

PURPOSE: This study was designed to assess the dose accumulation (DA) of bladder and rectum between brachytherapy fractions using hybrid-based deformable image registration (DIR) and compare it with the simple summation (SS) approach of GEC-ESTRO in cervical cancer patients. MATERIAL AND METHODS: Patients (n = 137) with cervical cancer treated with 3D conformal radiotherapy and three fractions of high-dose-rate brachytherapy were selected. CT images were acquired to delineate organs at risk and targets according to GEC-ESTRO recommendations. In order to determine the DA for the bladder and rectum, hybrid-based DIR was done for three different fractions of brachytherapy and the results were compared with the standard GEC-ESTRO method. Also, we performed a phantom study to calculate the uncertainty of the hybrid-based DIR algorithm for contour matching and dose mapping. RESULTS: The mean ± standard deviation (SD) of the Dice similarity coefficient (DICE), Jaccard, Hausdorff distance (HD) and mean distance to agreement (MDA) in the DIR process were 0.94 ±0.02, 0.89 ±0.03, 8.44 ±3.56 and 0.72 ±0.22 for bladder and 0.89 ±0.05, 0.80 ±0.07, 15.46 ±10.14 and 1.19 ±0.59 for rectum, respectively. The median (Q1, Q3; maximum) GyEQD2 differences of total D2cc between DIR-based and SS methods for the bladder and rectum were reduced by -1.53 (-0.86, -2.98; -9.17) and -1.38 (-0.80, -2.14; -7.11), respectively. The mean ± SD of DICE, Jaccard, HD, and MDA for contour matching were 0.98 ±0.008, 0.97 ±0.01, 2.00 ±0.70 and 0.20 ±0.04, respectively for large deformation. Maximum uncertainty of dose mapping was about 3.58%. CONCLUSIONS: The hybrid-based DIR algorithm demonstrated low registration uncertainty for both contour matching and dose mapping. The DA difference between DIR-based and SS approaches was statistically significant for both bladder and rectum and hybrid-based DIR showed potential to assess DA between brachytherapy fractions.

Rectal retractor application during image-guided dose-escalated prostate radiotherapy.

PURPOSE: To investigate efficacy of a rectal retractor (RR) on rectal dose during image-guided dose-escalated prostate three-dimensional conformal radiotherapy (3DCRT). PATIENTS AND METHODS: In all, 21 patients with localized prostate cancer were treated with a RR for 3DCRT in 40â€¯× 2 Gy. Patient underwent two scans for radiotherapy planning, without and with RR. RR was used for the first half of the treatment sessions. Two plans were created for each patient to compare the effect of RR on rectal doses. PTW-31014 Pinpoint chamber embedded within RR was used for in vivo dosimetry in 6 of 21 patients. The patient tolerance and acute rectal toxicity were surveyed during radiotherapy using Common Terminology Criteria for Adverse Events (CTCAE) v.4.0. RESULTS: Patients tolerated the RR well during 20 fractions with mild degree of anal irritation. Using a RR significantly reduced the rectal wall (RW), anterior RW and posterior RW dose-volume parameters. The average RW Dmean was 29.4 and 43.0 Gy for plans with and without RR, respectively. The mean discrepancy between the measured dose and planned dose was -3.8% (±4.9%). Grade 1 diarrhea, rectal urgency and proctitis occurred in 4, 2 and 3 cases, respectively. There were no grade ≥2 acute rectal toxicities during the treatment. CONCLUSION: Rectal retraction resulted in a significant reduction of rectal doses with a safe toxicity profile, which may reduce rectal toxicity. Dosimeter inserted into the RR providing a practical method for in vivo dosimetric verification. Further prospective clinical studies will be necessary to demonstrate the clinical advantage of RR.

Scintigraphic texture analysis for assessment of renal allograft function.

PURPOSE: Early detection and monitoring of kidney function during the post-transplantation period is one of the most important issues for improving the accuracy of an initial diagnosis. The aim of this study was to evaluate texture analysis (TA) in scintigraphic imaging to detect changes in kidney status after transplantation. MATERIAL AND METHODS: Scintigraphic images were used for TA from a total of 94 kidney allografts (39 rejected and 55 non-rejected). Images corresponding to the frames at the 2nd, 5th, and 20th minute of the study were used to determine the optimum time point for analysis of differences in texture features between the rejected and non-rejected allografts. RESULTS: Linear discriminant analysis indicated the best performance at the fifth minute frame for classification of the rejected and non-rejected allografts with receiver operating characteristic curve (Az) of 0.982, corresponding to 91.89% sensitivity, 96.49% specificity, and 94.68% accuracy. Also, TA can differentiate acute tubular necrosis from acute rejection with Az of 0.953 corresponding to 88% sensitivity, 92.31% specificity, and 90.62% accuracy at the 5th minute frame. The best correlation between texture feature and kidney function was achieved at the 20th minute frame (r = -0.396) for glomerular filtration rate. CONCLUSIONS: TA has good potential for the characterisation of kidney failure after transplantation and can improve clinical diagnosis.

A Clinical Decision Support System Using Ultrasound Textures and Radiologic Features to Distinguish Metastasis From Tumor-Free Cervical Lymph Nodes in Patients With Papillary Thyroid Carcinoma.

OBJECTIVES: This study investigated the potential of a clinical decision support approach for the classification of metastatic and tumor-free cervical lymph nodes (LNs) in papillary thyroid carcinoma on the basis of radiologic and textural analysis through ultrasound (US) imaging. METHODS: In this research, 170 metastatic and 170 tumor-free LNs were examined by the proposed clinical decision support method. To discover the difference between the groups, US imaging was used for the extraction of radiologic and textural features. The radiologic features in the B-mode scans included the echogenicity, margin, shape, and presence of microcalcification. To extract the textural features, a wavelet transform was applied. A support vector machine classifier was used to classify the LNs. RESULTS: In the training set data, a combination of radiologic and textural features represented the best performance with sensitivity, specificity, accuracy, and area under the curve (AUC) values of 97.14%, 98.57%, 97.86%, and 0.994, respectively, whereas the classification based on radiologic and textural features alone yielded lower performance, with AUCs of 0.964 and 0.922. On testing the data set, the proposed model could classify the tumor-free and metastatic LNs with an AUC of 0.952, which corresponded to sensitivity, specificity, and accuracy of 93.33%, 96.66%, and 95.00%. CONCLUSIONS: The clinical decision support method based on textural and radiologic features has the potential to characterize LNs via 2-dimensional US. Therefore, it can be used as a supplementary technique in daily clinical practice to improve radiologists' understanding of conventional US imaging for characterizing LNs.