Gray Level Co-occurrence Research Articles

An Implementation and Design Framework of Disease Detection and Prediction of Tomato Plant Leaves Using Gray Level Co-Occurrence and Convolutional Neural Networks

An Implementation and Design Framework of Disease Detection and Prediction of Tomato Plant Leaves Using Gray Level Co-Occurrence and Convolutional Neural Networks

Clinical prediction of microvascular invasion in hepatocellular carcinoma using an MRI-based graph convolutional network model integrated with nomogram.

Based on enhanced MRI, a prediction model of microvascular invasion (MVI) for hepatocellular carcinoma (HCC) was developed using graph convolutional network (GCN) combined nomogram. We retrospectively collected 182 HCC patients confirmed histopathologically, all of them performed enhanced MRI before surgery. The patients were randomly divided into training and validation groups. Radiomics features were extracted from the arterial phase (AP), portal venous phase (PVP), and delayed phase (DP), respectively. After removing redundant features, the graph structure by constructing the distance matrix with the feature matrix was built. Screening the superior phases and acquired GCN Score (GS). Finally, combining clinical, radiological and GS established the predicting nomogram. 27.5% (50/182) patients were with MVI positive. In radiological analysis, intratumoural artery (P = 0.007) was an independent predictor of MVI. GCN model with grey-level cooccurrence matrix-grey-level run length matrix features exhibited area under the curves of the training group was 0.532, 0.690, and 0.885 and the validation group was 0.583, 0.580, and 0.854 for AP, PVP, and DP, respectively. DP was selected to develop final model and got GS. Combining GS with diameter, corona enhancement, mosaic architecture, and intratumoural artery constructed a nomogram which showed a C-index of 0.884 (95% CI: 0.829-0.927). The GCN model based on DP has a high predictive ability. A nomogram combining GS, clinical and radiological characteristics can be a simple and effective guiding tool for selecting HCC treatment options. GCN based on MRI could predict MVI on HCC.

Comparative analysis of paddy leaf diseases sensing with a hybrid convolutional neural network model

The major food in south India is Paddy. Early detection of leaf disease can increase the production of crops. In the agricultural field, farmers can control the spreading of leaf disease with the help of the modeling of automated disease classification. In comparison to the manual approach to paddy leaf infection detection via visual examination, automated identification of rice illnesses using an image of the paddy leaf may be advantageous. Deep learning, a highly well-liked and effective machine learning method, has recently demonstrated considerable promise in the categorization task of images. In this work, Contrast Limited Adaptive Histogram Equalization (CLAHE) pre-processes the augmented images of paddy leaves. The Gray level co-occurrence metrics (GLCM) model then extracts the features from an image of the pre-processed paddy leaves. The five disease classes of paddy leaves were finally identified using the hybrid CNN model as follows: Bacterial Leaf Blight (BLB), Sheath Rot (SR), Narrow Brown Leaf Spot (NBLS), Brown Spot (BS) and Leaf Smut (LS). MATLAB platforms handle implementation works. While compared to the previous approaches, the proposed model reveals the superiority of paddy leaves classification.

Automatic Detection of Brain Tumors Using Genetic Algorithms with Multiple Stages in Magnetic Resonance Images

Biomedicine is still working to solve the problem of detecting brain tumours, one of the biggest problems in the profession today. With improved technology or instrument, early diagnosis of brain cancers is feasible. Classifying brain tumour kinds using patent brain pictures enables automation in automated procedures. Furthermore, the suggested new method is utilised to tell the difference between brain tumours and other brain diseases. To split the tumour and other brain areas, the input picture is first pre-processed. After this, the pictures are divided into different colours and levels, and then they are run through the Gray Level Co-Occurrence and SURF extraction methods to uncover the important details in the photographs. Using genetic optimization, the retrieved characteristics are made smaller. For training and testing tumour classification, the cut-down characteristics are used using an advanced learning technique. The technique's accuracy, error, sensitivity, and specificity are all evaluated alongside the current method. The method has a 90%+ accuracy rate, with less than 2% inaccuracy for all kinds of cancers. Finally, the specificity and sensitivity of every kind are above 90% and 50% correspondingly. Using a genetic algorithm to support the approach is more efficient, since the method it uses has both higher accuracy and specificity than the other techniques.

Radiomics Model for Predicting Pulmonary Metastasis in Sarcoma Patients

The lung is the most common site of metastasis in localized extremity soft tissue sarcomas (STS). Indeterminant lung nodules leads to challenges for both patients and providers. As such, accuracy in the diagnosis of pulmonary metastasis (PM) is important for clinical decision making. The purpose of this is study is to develop and evaluate a CT-based radiomic model to predict PM in sarcoma patients with indeterminate pulmonary nodules. Fifty-seven stage I-III sarcoma patients with indeterminate lung nodules on unenhanced CT that were approved for this study by our institution's internal review board (IRB). Twenty-two developed and categorized as PM and 35 without PM. A total number of 322 indeterminate nodules were investigated, where 165 & 157 nodules were from patients with and without PM, respectively. A total of 96 radiomic features (RF) (including first order statistics, 2d shape features, gray level co-occurrence, gray level size zone, gray level run length, neighboring gray tone difference & gray level dependence matrices) were taken from unenhanced CT images of each patient. We included 2D shape features since the size and shape of indeterminate lung nodules may have some correlation with PM. Spearman correlation were used to rule out redundant features (r2>0.9). T-test statistics was used to determine feature with significant differences that can differentiate responders with and without PM. Support Vector Machine (SVM) model was fitted to combinations of groups of 2-3 radiomic features. The AUC of the ROC curve was used to evaluate the model performance. Pointwise confidence intervals (CI) for AUC were calculated using 100 bootstrap replicates. Four features were found significant after Spearman correlation and T-test statistical testing: 1. Maximum (MAX); 2. Minor Axis Length (MAL); 3. Gray Level Non-uniformity (GLNU); and 4. Interquartile Range (IR). The best performing 2-feature radiomic SVM model had an AUC of 0.69 (95% CI 0.61,0.74) for the MAX and GLNU features. The best performing 3-feature radiomic SVM model had an AUC of 0.74 (95% CI 0.70,0.80) for the MAX, MAL and IR features. CT-based radiomics model has the potential to be used to predict PM in sarcoma patients presenting with indeterminate lung nodules. Additional research will focus on investigating derived parameters for existing RF, such as the ratio of the max RF to mean RF, to see if they improve the predictive performance of the model, as well as testing the models on external patient cohort. These radiomic models could be useful tools in guiding PM screening and providing a patient specific monitoring of sarcoma patients.

Uniformity inspection of tack coats through measurement conducted on drone-collected images

Tack coat is a thin asphalt applied between the existing surface and asphalt overlay during road rehabilitation. Its coverage uniformity is vital in providing adhesive bonding between the two layers in the structure. This paper proposes a novel method for automatic uniformity inspection of tack coat coverage using images collected by drones. In this method, color thresholding is first performed to extract coarse region of the tack coat. Then, the boundaries of the tack coat are detected to refine the tack coat region by masking outliers. Next, the region of interest is processed to extract texture features using gray-level co-occurrence. Finally, the texture features are leveraged to grade the tack coat uniformity level using LightGBM. Experiments were conducted to examine the performance of the method. The resulting accuracy signifies the potential of this method in developing high-efficiency and cost-effective solutions to enhance the current tack coat inspection practice.

Effects of non-stationary blur on texture biomarkers of bone using Ultra-High Resolution CT.

To advance the development of radiomic models of bone quality using the recently introduced Ultra-High Resolution CT (UHR CT), we investigate inter-scan reproducibility of trabecular bone texture features to spatially-variant azimuthal and radial blurs associated with focal spot elongation and gantry rotation. The UHR CT system features 250×250 μm detector pixels and an x-ray source with a 0.4×0.5 mm focal spot. Visualization of details down to ~150 μm has been reported for this device. A cadaveric femur was imaged on UHR CT at three radial locations within the field-of-view: 0 cm (isocenter), 9 cm from the isocenter, and 18 cm from the isocenter; we expect the non-stationary blurs to worsen with increasing radial displacement. Gray level cooccurrence (GLCM) and gray level run length (GLRLM) texture features were extracted from 237 trabecular regions of interest (ROIs, 5 cm diameter) placed at corresponding locations in the femoral head in scans obtained at the different shifts. We evaluated concordance correlation coefficient (CCC) between texture features at 0 cm (reference) and at 9 cm and 18 cm. We also investigated whether the spatially-variant blurs affect K-means clustering of trabecular bone ROIs based on their texture features. The average CCCs (against the 0 cm reference) for GLCM and GLRM features were ~0.7 at 9 cm. At 18 cm, the average CCCs were reduced to ~0.17 for GLCM and ~0.26 for GLRM. The non-stationary blurs are incorporated in radiomic features of cancellous bone, leading to inconsistencies in clustering of trabecular ROIs between different radial locations: an intersection-over-union overlap of corresponding (most similar) clusters between 0 cm and 9 cm shift was >70%, but dropped to <60% for the majority of corresponding clusters between 0 cm and 18 cm shift. Non-stationary CT system blurs reduce inter-scan reproducibility of texture features of trabecular bone in UHR CT, especially for locations >15 cm from the isocenter. Radiomic models of bone quality derived from UHR CT measurements at isocenter might need to be revised before application in peripheral body sites such as the hips.

Brain Tumor: Hybrid Feature Extraction Based on UNet and 3DCNN

Automated segmentation of brain tumors using Magnetic Resonance Imaging (MRI) data is critical in the analysis and monitoring of disease development. As a result, gliomas are aggressive and diverse tumors that may be split into intra-tumoral groups by using effective and accurate segmentation methods. It is intended to extract characteristics from an image using the Gray Level Co-occurrence (GLC) matrix feature extraction method described in the proposed work. Using Convolutional Neural Networks (CNNs), which are commonly used in biomedical image segmentation, CNNs have significantly improved the precision of the state-of-the-art segmentation of a brain tumor. Using two segmentation networks, a U-Net and a 3D CNN, we present a major yet easy combinative technique that results in improved and more precise estimates. The U-Net and 3D CNN are used together in this study to get better and more accurate estimates of what is going on. Using the dataset, two models were developed and assessed to provide segmentation maps that differed fundamentally in terms of the segmented tumour sub-region. Then, the estimates was made by two separate models that were put together to produce the final prediction. In comparison to current state-of-the-art designs, the precision (percentage) was 98.35, 98.5, and 99.4 on the validation set for tumor core, enhanced tumor, and whole tumor, respectively.

Cone-beam computed tomography texture analysis can help differentiate odontogenic and non-odontogenic maxillary sinusitis.

This study aimed to assess texture analysis (TA) of cone-beam computed tomography (CBCT) images as a quantitative tool for the differential diagnosis of odontogenic and non-odontogenic maxillary sinusitis (OS and NOS, respectively). CBCT images of 40 patients diagnosed with OS (N=20) and NOS (N=20) were evaluated. The gray level co-occurrence (GLCM) matrix parameters, and gray level run length matrix texture (GLRLM) parameters were extracted using manually placed regions of interest on lesion images. Seven texture parameters were calculated using GLCM and 4 parameters using GLRLM. The Mann-Whitney test was used for comparisons between the groups, and the Levene test was performed to confirm the homogeneity of variance (α=5%). The results showed statistically significant differences (P<0.05) between the OS and NOS patients regarding 3 TA parameters. NOS patients presented higher values for contrast, while OS patients presented higher values for correlation and inverse difference moment. Greater textural homogeneity was observed in the OS patients than in the NOS patients, with statistically significant differences in standard deviations between the groups for correlation, sum of squares, sum of entropy, and entropy. TA enabled quantitative differentiation between OS and NOS on CBCT images by using the parameters of contrast, correlation, and inverse difference moment.

Audio-visual multi-modality driven hybrid feature learning model for crowd analysis and classification.

The high pace emergence in advanced software systems, low-cost hardware and decentralized cloud computing technologies have broadened the horizon for vision-based surveillance, monitoring and control. However, complex and inferior feature learning over visual artefacts or video streams, especially under extreme conditions confine majority of the at-hand vision-based crowd analysis and classification systems. Retrieving event-sensitive or crowd-type sensitive spatio-temporal features for the different crowd types under extreme conditions is a highly complex task. Consequently, it results in lower accuracy and hence low reliability that confines existing methods for real-time crowd analysis. Despite numerous efforts in vision-based approaches, the lack of acoustic cues often creates ambiguity in crowd classification. On the other hand, the strategic amalgamation of audio-visual features can enable accurate and reliable crowd analysis and classification. Considering it as motivation, in this research a novel audio-visual multi-modality driven hybrid feature learning model is developed for crowd analysis and classification. In this work, a hybrid feature extraction model was applied to extract deep spatio-temporal features by using Gray-Level Co-occurrence Metrics (GLCM) and AlexNet transferrable learning model. Once extracting the different GLCM features and AlexNet deep features, horizontal concatenation was done to fuse the different feature sets. Similarly, for acoustic feature extraction, the audio samples (from the input video) were processed for static (fixed size) sampling, pre-emphasis, block framing and Hann windowing, followed by acoustic feature extraction like GTCC, GTCC-Delta, GTCC-Delta-Delta, MFCC, Spectral Entropy, Spectral Flux, Spectral Slope and Harmonics to Noise Ratio (HNR). Finally, the extracted audio-visual features were fused to yield a composite multi-modal feature set, which is processed for classification using the random forest ensemble classifier. The multi-class classification yields a crowd-classification accurac12529y of (98.26%), precision (98.89%), sensitivity (94.82%), specificity (95.57%), and F-Measure of 98.84%. The robustness of the proposed multi-modality-based crowd analysis model confirms its suitability towards real-world crowd detection and classification tasks.

Abstract A040: CT Radiomics to predict early recurrence of margin-negative resectable pancreatic ductal adenocarcinoma

Abstract Radiographic CT/MRI staging is pivotal to accurate therapeutic decision-making, and guides the surgical resectability of pancreatic ductal adenocarcinoma (PDAC). The extent of vascular involvement of the lesion as seen through radiographic imaging, which differentiates the regional versus locally advanced disease, and therefore upfront resectability. Following standard criteria, only about 20% of PDAC patients qualify for an upfront surgery but half of them recur within a year, despite the complete removal (margin-negative R0 resection) of the primary tumor It underscores the necessity for a better deciphering of the CT/MRI-based clinical imaging of PDAC using radiomics—the process of extracting high dimensional quantitative imaging information from radiographic images. We have previously described a prospective cohort of resected PDAC (n=161) at Memorial Sloan Kettering Cancer Center for preoperative CT angiography collected between 2009 and 2012. We demonstrated that CT texture features are associated with overall survival. Utilizing the same cohort of resected PDAC, the current study aims to develop a much deeper case-controlled algorithm to further identify the texture features are predictive of early recurrence for margin-negative PDAC patients. We selected all patients following these criteria: margin negative (R0), Gemcitabine/nab-paclitaxel adjuvant chemotherapy (excluding neoadjuvant), clinical-stage IIB, moderate tumor differentiation by histopathology, and no lymph node and distant metastasis. Based on these criteria, a total of 27 patients were selected, where 16 patients had recurred within a year of surgery (high-risk group) and the remaining 11 patients did not recur in 2-years (low-risk group). We focused on Gray-level co-occurrence (GLCM) based on Haralick’s features. GLCM is most extensively used to characterize the texture of a tumor via encoding the spatial distribution of voxels—neighboring pixels of an image. A total of 18 GLCM features were extracted from manually segmented CT of PDAC primary tumors. Univariate analysis with Wilcoxon-rank-sum test (p&amp;lt;0.05) revealed 4 features –energy (GLCM1) and entropy (GLCM9, GLCM17, and GLCM18) based were associated with early recurrence. Energy, or angular speed moment, is a measure of local variation in an image; higher energy represents homogeneity between neighboring pixels. On the contrary, entropy characterizes randomness within an image; higher entropy represents more heterogeneity. The energy feature GLCM1 was significantly lower in high-risk group, whereas the entropy features (GLCM 9, 17, and 18) were significantly higher in high-risk group compared to the low-risk group – suggesting the relationship of tumor heterogeneity with early recurrence. While proposing these GLCM features as the measure of tumor heterogeneity and early recurrence, we are validating them on a larger independent cohort, estimating their benchmark measures of predictive ability. The long-term goal is to develop these as radiomic biomarkers for better guiding the therapeutic decision-making of PDAC. Citation Format: Anwesha Dhara, Liana Langdon-Embry, Michael I. D’Angelica, T. Peter Kingham, Natally Horvat, William R. Jarnagin, Alice C. Wei, Jayasree Chakraborty. CT Radiomics to predict early recurrence of margin-negative resectable pancreatic ductal adenocarcinoma [abstract]. In: Proceedings of the AACR Special Conference on Pancreatic Cancer; 2022 Sep 13-16; Boston, MA. Philadelphia (PA): AACR; Cancer Res 2022;82(22 Suppl):Abstract nr A040.

Prognostic value of texture analysis of the primary tumour in high-risk neuroblastoma: An 18 F-DOPA PET study.

To evaluate the prognostic value of texture analysis of the primary tumour with 18 fluorine-dihydroxyphenylalanine positron emission tomography/X-ray computed tomography (18 F-DOPA PET/CT) in patients affected by high-risk neuroblastoma (HR-NBL). We retrospectively analysed 18 patients with HR-NBL, which had been prospectively enrolled in the course of a previous trial investigating the diagnostic role of 18 F-DOPA PET/CT at the time of the first onset. Texture analysis of the primary tumour was carried out on the PET images using LifeX. Conventional indices, histogram parameters, grey level co-occurrence (GLCM), run-length (GLRLM), neighbouring difference (NGLDM) and zone-length (GLZLM) matrices parameter were extracted; their values were compared with the overall metastatic load, expressed by means of whole-body metabolic burden (WBMB) score and the progression-free/overall survival (PFS and OS). There was a direct correlation between WBMB and radiomics parameter describing uptake intensity (SUVmean : p=.004) and voxel heterogeneity (entropy: p=.026; GLCM_Contrast: p=.001). Conversely, texture indices of homogeneity showed an inverse correlation with WBMB (energy: p=.026; GLCM_Homogeneity: p=.006). On the multivariate model, WBMB (p<.01) and the first standardised uptake value (SUV) quartile (p<.001) predicted PFS; OS was predicted by WBMB and the N-myc proto-oncogene protein (MYCN) amplification (p<.05) for both. Textural parameters describing heterogeneity and metabolic intensity of the primary HR-NBL are closely associated with its overall metastatic burden. In turn, the whole-body tumour load appears to be one of the most relevant predictors of progression-free and overall survival.

Content Based Image Retrieval Using Artificial Neural Network

Digital Image Processing domain is constantly contributing to make digital era more concise. Specifically Image Retrieval is the trending research area now-a-days. The main problem is, with the increasing volume of digital data the complexity of searching a specific image and retrieving the particular data associated with it is increasing. In recent years the content based image retrieval system has been developing at enormous speed. This paper color , gray level co-occurrence and histogram features are obtain better retrieval efficiency from large database using these feature vectors near about similarly matched images are retrieved. We have retrieved using Euclidian distance and ANN, among of both ANN Shows better result compare to Euclidian Distance based image retrieval.

Speckle Analyzer: open-source package in MATLAB for finding metrics of physical quantities based on laser speckle pattern analyzing.

We provide an open-source user-friendly graphical-user interface software in a MATLAB environment, named Speckle Analyzer, as a tool for calculating and analyzing statistical parameters of a laser speckle pattern to find metrics for an object's physical quantity. The first- and second-order statistical functions containing gray-level co-occurrence and gray-level run-length matrices and speckle grains geometrical properties are included in Speckle Analyzer. To validate the software's operation, statistical parameters of the laser speckle pattern, to find metrics for the size and concentration of particles suspended in liquid, are investigated.

Cone Beam CT Based Delta-Radiomics of Prostate Cancer Patients and Their Correlation to Quality of Life, Genitourinary and Gastrointestinal Toxicities

For patients receiving external beam radiotherapy (EBRT) for prostate cancer (PCa), acute and late radiation-related toxicities can significantly impact short and long-term quality-of-life (QOL). Radiomics, an analytic technique that extracts patterns from medical imaging, has been incorporated into predictive models in diverse cancers. Daily cone beam CT (CBCT) images during EBRT allow for the study of changes in radiomics over time, known as delta-radiomics. We hypothesize that delta-radiomics of the prostate extracted from daily CBCTs could be predictive of genitourinary toxicity (GUT), gastrointestinal toxicity (GIT), and patient QOL.From an IRB approved database, 31 PCa patients were identified who received EBRT with daily CBCTs. Patients were treated on dose fractionation schemes of 76-91 Gy in 37-40 fractions and some received a 12 Gy boost. The prostate was contoured on all daily CBCTs and 42 radiomics features were extracted for analysis. Radiomic features included intensity-based, gray-level run length (GLRLM), gray-level co-occurrence (GLCM), neighborhood gray-level difference (NGTDM), and gray-level size zone (GLSZM) matrix classes. These radiomic features were averaged per week to decrease data granularity. Patient outcomes analyzed included the total International Prostate Symptom QOL score GUT, GIT, combined GU/GIT grades. Logistic and linear regression models were used to estimate effects of radiomics features on later occurring toxicity and QOL, respectively. Odds ratios (ORs), regression coefficients, 95% confidence intervals, and P-value were estimated. Area under the receiver operating characteristic curve (AUC) and R2 were obtained as a measure of models' goodness-of-fit. The statistical significance threshold was P < 1.5e-04 using an alpha level of 0.05 and applying the Bonferroni correction for multiple comparisons. All tests were two-sided. Parallel data sets were generated using standard (sCBCT) and iterative (iCBCT) CBCT reconstructions. Radiomic feature were preprocessed using Lloyd quantization with Collewet normalization.Five CBCT delta-radiomic features significantly correlated on week two with QOL occurring after. The results are summarized in Table 1. The R2 values indicate a moderate effect size. GUT and GIT were not found to correlate with the radiomic features. All significant radiomic features corresponded to sCBCT.Future short-term changes to QOL were detected as early as week two with CBCT delta-radiomics. However, the GUT, GIT, and GU/GIT toxicities were not predicted. These results can serve as preselection criteria of radiomic features to develop more sophisticated machine learning models with larger sample and improve statistical power.

Machine Learning Models for Sarcopenia Identification Based on Radiomic Features of Muscles in Computed Tomography.

The diagnosis of sarcopenia requires accurate muscle quantification. As an alternative to manual muscle mass measurement through computed tomography (CT), artificial intelligence can be leveraged for the automation of these measurements. Although generally difficult to identify with the naked eye, the radiomic features in CT images are informative. In this study, the radiomic features were extracted from L3 CT images of the entire muscle area and partial areas of the erector spinae collected from non-small cell lung carcinoma (NSCLC) patients. The first-order statistics and gray-level co-occurrence, gray-level size zone, gray-level run length, neighboring gray-tone difference, and gray-level dependence matrices were the radiomic features analyzed. The identification performances of the following machine learning models were evaluated: logistic regression, support vector machine (SVM), random forest, and extreme gradient boosting (XGB). Sex, coarseness, skewness, and cluster prominence were selected as the relevant features effectively identifying sarcopenia. The XGB model demonstrated the best performance for the entire muscle, whereas the SVM was the worst-performing model. Overall, the models demonstrated improved performance for the entire muscle compared to the erector spinae. Although further validation is required, the radiomic features presented here could become reliable indicators for quantifying the phenomena observed in the muscles of NSCLC patients, thus facilitating the diagnosis of sarcopenia.

Metastatic clear cell renal cell carcinoma: computed tomography texture analysis as predictive biomarkers of survival in patients treated with nivolumab.

To evaluate the value of image-based texture analysis for predicting progression-free survival (PFS) and overall survival (OS) in patients with metastatic clear cell renal carcinoma (cCCR) treated with nivolumab. This retrospective study included 48 patients with metastatic cCCR treated with nivolumab. Nivolumab was used as a second- or third-line monotherapy. Texture analysis of metastatic lesions was performed on CT scanners obtained within 1month before treatment. Texture features related to the gray-level histogram, gray-level co-occurrence, run-length matrix features, autoregressive model features, and Haar wavelet feature were extracted. Lasso penalized Cox regression analyses were performed to identify independent predictors of PFS and OS. Median PFS and OS were 5.7 and 13.8months. 39 patients experienced progression and 27 died. The Lasso penalized Cox regression analysis identified three texture parameters as potential predictors of PFS: skewness, S.2.2. Correlat and S.1.1. SumVarnc. Multivariate Cox regression analysis confirmed skewness (HR (95% CI) 1.49 [1.21-1.85], p < 0.001) as an independent predictor of PFS. Regarding OS, the Lasso penalized Cox regression analysis identified three texture parameters as potential predictors of OS: S20SumVarnc, S22Contrast and S22Entropy. Multivariate Cox regression analysis confirmed S22Entropy (HR (95% CI) 1.68 (1.31-2.14), p < 0.001) as an independent predictor of OS. Results from this preliminary study suggest that CT texture analysis might be a promising quantitative imaging tool that predicts oncological outcomes after starting nivolumab treatment.

K-Nearest Neighbor Algorithm to Identify Cucumber Maturity with Extraction of One-Order Statistical Features and Gray-Level Co-Occurrence

Determination of the maturity of cucumber fruit after harvest is subjective. The level of thoroughness of each individual’s cucumber selection is different. The maturity of cucumbers is seen from the age of the fruit, the resemblance of ripe cucumbers or old, raw or young is difficult to distinguish in terms of the texture of the fruit skin. The use of red, green, blue, and grayscale color modes from the cucumber imagery, is then processed using the extraction of the statistical features of the Order-One and Order-Two GLCM methods. Imagery using a 13 megapixels smartphone camera. Texture parameter values are used in the first order: mean, variance, skewness, kurtosis, entropy. Second order: energy, contrast, correlation, inverse different moments, angular second moments, variance 2, and entropy 2. The classification of the texture parameters of both order uses an algorithm from K-Nearest Neighbors as a comparison of test data values and training data. So that the system is made can identify the maturity of cucumbers old and young. The highest accuracy is found in grayscale imagery with a combination of two skewness and kurtosis parameters and euclidean distance calculation in K-Nearest Neighbor classification of 96.05%.

WITHDRAWN: Thyroid tissue segmentation and classification in ultrasound image of Artificial intelligence

This paper suggests that it be based on a new device method for benign or malignant ultrasound examination of thyroid tissues. Ultrasound imaging is a medical instrument that is mostly used to identify and classify thyroid disorders. The suggested solution consists of four essential phases: Segmentation, grouping, pre-processing and extraction of features. Rayleigh trimmed anisotropic diffusion filter is used for pre-processing purposes. An ABC algorithm is used to break down the nodule field. Artificial neural network (ANN) and support vector machine (SVM) classifiers are used for classification tasks, using feature vectors extracted from the Gray Level Co-occurrence (GLCM) functions. Classification findings are analyzed on the basis of precision, resilience and specificity. It is derived that the SVM classifier offers better performance than the ANN for distinguishing benign and malignant nodules, achieving precision of 92.5 per cent, and sensitivity of 96.66 per cent and specificity of 80 per cent.

Impact of inter-reader contouring variability on textural radiomics of colorectal liver metastases

BackgroundRadiomics is expected to improve the management of metastatic colorectal cancer (CRC). We aimed at evaluating the impact of liver lesion contouring as a source of variability on radiomic features (RFs).MethodsAfter Ethics Committee approval, 70 liver metastases in 17 CRC patients were segmented on contrast-enhanced computed tomography scans by two residents and checked by experienced radiologists. RFs from grey level co-occurrence and run length matrices were extracted from three-dimensional (3D) regions of interest (ROIs) and the largest two-dimensional (2D) ROIs. Inter-reader variability was evaluated with Dice coefficient and Hausdorff distance, whilst its impact on RFs was assessed using mean relative change (MRC) and intraclass correlation coefficient (ICC). For the main lesion of each patient, one reader also segmented a circular ROI on the same image used for the 2D ROI.ResultsThe best inter-reader contouring agreement was observed for 2D ROIs according to both Dice coefficient (median 0.85, interquartile range 0.78–0.89) and Hausdorff distance (0.21 mm, 0.14–0.31 mm). Comparing RF values, MRC ranged 0–752% for 2D and 0–1567% for 3D. For 24/32 RFs (75%), MRC was lower for 2D than for 3D. An ICC > 0.90 was observed for more RFs for 2D (53%) than for 3D (34%). Only 2/32 RFs (6%) showed a variability between 2D and circular ROIs higher than inter-reader variability.ConclusionsA 2D contouring approach may help mitigate overall inter-reader variability, albeit stable RFs can be extracted from both 3D and 2D segmentations of CRC liver metastases.