CT Texture Features Research Articles

Could CT Radiomic Analysis of Benign Adrenal Incidentalomas Suggest the Need for Further Endocrinological Evaluation?

We studied the application of CT texture analysis in adrenal incidentalomas with baseline characteristics of benignity that are highly suggestive of adenoma to find whether there is a correlation between the extracted features and clinical data. Patients with hormonal hypersecretion may require medical attention, even if it does not cause any symptoms. A total of 206 patients affected by adrenal incidentaloma were retrospectively enrolled and divided into non-functioning adrenal adenomas (NFAIs, n = 115) and mild autonomous cortisol secretion (MACS, n = 91). A total of 136 texture parameters were extracted in the unenhanced phase for each volume of interest (VOI). Random Forest was used in the training and validation cohorts to test the accuracy of CT textural features and cortisol-related comorbidities in identifying MACS patients. Twelve parameters were retained in the Random Forest radiomic model, and in the validation cohort, a high specificity (81%) and positive predictive value (74%) were achieved. Notably, if the clinical data were added to the model, the results did not differ. Radiomic analysis of adrenal incidentalomas, in unenhanced CT scans, could screen with a good specificity those patients who will need a further endocrinological evaluation for mild autonomous cortisol secretion, regardless of the clinical information about the cortisol-related comorbidities.

CT Texture-Based Nomogram in Ischemic Stroke to Differentiate Intracerebral Hemorrhage from Contrast Extravasation after Thrombectomy

Introduction: Post-thrombectomy intraparenchymal hyperdensity (PTIH) in patients with acute ischemic stroke is a common CT sign, making it difficult for physicians to distinguish intracerebral hemorrhage in the early post-thrombectomy period. The aim of this study was to develop an effective model to differentiate intracerebral hemorrhage from contrast extravasation in patients with PTIH. Methods: We retrospectively collected information on patients who underwent endovascular thrombectomy at two stroke centers between August 2017 and January 2023. A total of 222 patients were included in the study, including 118 patients in the development cohort, 52 patients in the internal validation cohort, and 52 patients in the external validation cohort. The nomogram was constructed using R software based on independent predictors derived from the multivariate logistic regression analysis, including clinical factors and CT texture features extracted from hyperdense areas on CT images. The performance and accuracy of the derived nomogram were assessed by the area under the receiver operating characteristic curve (AUC-ROC) and calibration curves. Additionally, decision curve analysis was conducted to appraise the clinical utility of the nomogram. Results: Our nomogram was derived from two clinical factors (ASPECT score and onset to reperfusion time) and two CT texture features (variance and uniformity), with AUC-ROC of 0.943, 0.930, and 0.937 in the development, internal validation, and external validation cohorts, respectively. Furthermore, the calibration plot exhibited a strong agreement between the predicted outcome and the actual outcome. In addition, the decision curve analysis revealed the clinical utility of the nomogram in accurately predicting hemorrhage in patients with PTIH. Conclusion: The developed nomogram, based on clinical factors and CT texture features, proves to be effective in distinguishing intracerebral hemorrhage from contrast extravasation in patients with PTIH.

A CT texture-based nomogram for predicting futile reperfusion in patients with intraparenchymal hyperdensity after endovascular thrombectomy for acute anterior circulation large vessel occlusion.

Post-thrombectomy intraparenchymal hyperdensity (PTIH) in patients with acute anterior circulation large vessel occlusion is a common CT sign associated with a higher incidence of futile reperfusion (FR). We aimed to develop a nomogram to predict FR specifically in patients with PTIH. We retrospectively collected information on patients with acute ischemic stroke who underwent endovascular thrombectomy (EVT) at two stroke centers. A total of 398 patients with PTIH were included to develop and validate the nomogram, including 214 patients in the development cohort, 92 patients in the internal validation cohort and 92 patients in the external validation cohort. The nomogram was developed according to the independent predictors obtained from multivariate logistic regression analysis, including clinical factors and CT texture features extracted from hyperdense areas on CT images within half an hour after EVT. The performance of the nomogram was evaluated with integrated discrimination improvement (IDI), category-free net reclassification improvement (NRI), the area under the receiver operating characteristic curve (AUC-ROC), calibration plots, and decision curve analyses for discrimination, calibration ability, and clinical net benefits, respectively. Our nomogram was constructed based on three clinical factors (age, NIHSS score and ASPECT score) and two CT texture features (entropy and kurtosis), with AUC-ROC of 0.900, 0.897, and 0.870 in the development, internal validation, and external validation cohorts, respectively. NRI and IDI further validated the superior predictive ability of the nomogram compared to the clinical model. The calibration plot revealed good consistency between the predicted and the actual outcome. The decision curve indicated good positive net benefit and clinical validity of the nomogram. The nomogram enables clinicians to accurately predict FR specifically in patients with PTIH within half an hour after EVT and helps to formulate more appropriate treatment plans in the early post-EVT period.

Diagnosing postoperative lymph node metastasis in thyroid cancer with multimodal radiomics and clinical features.

This study aims to evaluate the diagnostic value of texture analysis for lymph node metastasis after thyroid cancer surgery. We retrospectively analyzed patients who underwent positron emission tomography/computed tomography (PET/CT) examination before 131I treatment at Shanghai Tenth People's Hospital between 2017 and 2020. Clinical follow-up results were used as the criterion for determining the presence of lymph node metastasis. The study included 119 patients, who were then randomly divided into training and test groups in a 7:3 ratio. Regions of interest were identified, and radiomics features were extracted using LIFEx 7.3.0. Mann-Whitney U test and LASSO regression were employed to screen radiomics parameters for modeling. Subsequently, a nomogram model was built by combining radscore and clinical features. SPSS 26.0 software was utilized for statistical analysis, and p < 0.05 was considered statistically significant. Follow-up confirmed 54 patients with thyroid cancer lymph node metastasis and 65 patients in the non-metastasis group. A total of 119 lymph nodes were delineated. For each lesion, 164 CT texture features and 164 PET texture features were extracted, and 107 significant parameters were identified, including 16 CT texture parameters and 91 PET texture parameters. After screening, 3 CT parameters, 4 PET parameters and 12 PET/CT parameters were selected to establish three radiomic models. The AUC values were as follows: AUC (CT) = 0.730, AUC (PET) = 0.759 and AUC (PET/CT) = 0.864. We then combined clinical features and radscore to construct a nomogram, resulting in a C-index of 0.915 in the training group. In the test group, the C-index was confirmed to be 0.868. Radiomics may enhance the diagnostic efficiency of lymph node metastases after thyroid cancer surgery and could potentially assist clinicians in future diagnoses. The developed nomogram, which combines radiomics and clinical features, offers relatively high accuracy in helping clinicians assess the risk of metastasis in thyroid patients after surgery.

CT texture features and lung shunt fraction measured using 99mTc-macroaggregated albumin SPECT/CT before trans-arterial radioembolization for hepatocellular carcinoma patients

The aim of this study is to determine whether contrast-enhanced computed tomography (CECT)-based texture parameters can predict high (> 30 Gy) expected lung dose (ELD) calculated using 99mTc macroaggregated albumin single-photon emission computed tomography/computed tomography (SPECT/CT) for pre-trans-arterial radioembolization (TARE) dosimetry. 35 patients were analyzed, with a treatable planned dose of ≥ 200 Gy for unresectable hepatocellular carcinoma (HCC). Lung shunt fraction (LSF) was obtained from planar and SPECT/CT scans. Texture features of the tumor lesion on CECT before TARE were analyzed. Univariate and multivariate linear regression analyses were performed to determine potential ELD > 30 Gy predictors. Among the 35 patients, nine (25.7%) had ELD > 30 Gy, and had a higher LSF than the ELD ≤ 30 Gy group using the planar (20.7 ± 8.0% vs. 6.3 ± 3.3%; P < 0.001) and SPECT/CT (12.4 ± 5.1% vs. 3.5 ± 2.0%; P < 0.001) scans. The tumor integral total (HU × L) value was a predictor for high LSF using SPECT/CT, with an area under the curve, sensitivity, and specificity of 0.983 (95% confidence interval: 0.869–1.000, P < 0.001), 100%, and 88.5%, respectively. The tumor integral total value is an imaging marker for predicting ELD > 30 Gy. Applying CECT texture analysis may assist in reducing time and cost in patient selection and modifying TARE treatment plans.

Machine Learning and CT Texture Features in Ex-smokers with no CT Evidence of Emphysema and Mildly Abnormal Diffusing Capacity

Ex-smokers without spirometry or CT evidence of chronic obstructive pulmonary disease (COPD) but with mildly abnormal diffusing capacity of the lungs for carbon monoxide (DLCO) are at higher risk of developing COPD. It remains difficult to make clinical management decisions for such ex-smokers without other objective assessments consistent with COPD. Hence, our objective was to develop a machine-learning and CT texture-analysis pipeline to dichotomize ex-smokers with normal and abnormal DLCO (DLCO≥75%pred and DLCO<75%pred). In this retrospective study, 71 ex-smokers (50-85yrs) without COPD underwent spirometry, plethysmography, thoracic CT, and 3He MRI to generate ventilation defect percent (VDP) and apparent diffusion coefficients (ADC). PyRadiomics was utilized to extract 496 CT texture-features; Boruta and principal component analysis were used for feature selection and various models were investigated for classification. Machine-learning classifiers were evaluated using area under the receiver operator characteristic curve (AUC), sensitivity, specificity, and F1-measure. Of 71 ex-smokers without COPD, 29 with mildly abnormal DLCO had significantly different MRI ADC (p<.001), residual-volume to total-lung-capacity ratio (p=.003), St. George's Respiratory Questionnaire (p=.029), and six-minute-walk distance (6MWD) (p<.001), but similar relative area of the lung <-950 Hounsfield-units (RA950) (p=.9) compared to 42 ex-smokers with normal DLCO. Logistic-regression machine-learning mixed-model trained on selected texture-features achieved the best classification accuracy of 87%. All clinical and imaging measurements were outperformed by high-high-pass filter high-gray-level-run-emphasis texture-feature (AUC=0.81), which correlated with DLCO (ρ=-0.29, p=.02), MRI ADC (ρ=0.23, p=.048), and 6MWD (ρ=-0.25, p=.02). In ex-smokers with no CT evidence of emphysema, machine-learning models exclusively trained on CT texture-features accurately classified ex-smokers with abnormal diffusing capacity, outperforming conventional quantitative CT measurements.

CT texture analysis for predicting pseudoprogression in metastatic clear cell renal cell carcinoma during PD-1 inhibitor therapy

Objective: To evaluate the effectiveness of enhanced CT texture feature analysis in predicting pseudoprogression in patients with metastatic clear cell renal cell carcinoma (mccRCC) undergoing programmed cell death protein 1 (PD-1) inhibitor therapy. Methods: A cross-sectional study. Data from 32 patients with mccRCC were retrospectively collected who received monotherapy with PD-1 inhibitors after standard treatment failure at Henan Cancer Hospital, from June 2015 to January 2021. Clinical information and enhanced CT images were analyzed to assess target lesion response. The lesions were divided into pseudoprogression and non-pseudoprogression groups. Manual segmentation of target lesions was performed using ITK-Snap software on baseline enhanced CT, and texture analysis was conducted using A.K. software to extract feature parameters. Differences in texture features between the pseudoprogression and non-pseudoprogression groups were analyzed using univariate and multivariate logistic regression. A predictive model for pseudoprogression was constructed, and its performance was evaluated using ROC curve analysis. Results: A total of 32 patients with 89 lesions were included in the study. Statistical analysis revealed significant differences in seven texture features between the pseudoprogression and non-pseudoprogression groups. These features included"original_ngtdm_Strength"(0.49 vs. -0.61,P=0.006), "wavelet-HLH_glszm_ZonePercentage"(0.67 vs. -0.22,P=0.024),"wavelet-LHL_ngtdm_Strength"(1.20 vs. -0.51,P=0.002), "wavelet-HLL_gldm_LargeDependenceEmphasis"(-0.84 vs. 0.19,P=0.002), "wavelet-HLH_glcm_Id" (-0.30 vs. 0.43,P=0.037),"wavelet- HLH_glrlm_RunPercentage"(0.45 vs. -0.01,P=0.032),"wavelet-LHH_firstorder_Skewness"(0.25 vs. -0.27, P=0.011). Based on these features, a pseudoprogression prediction model was developed with a P-value of 0.000 2 and an odds ratio of 0.045 (95%CI 0.009-0.227). The model exhibited a high predictive performance with an AUC of 0.907 (95%CI 0.817-0.997) according to ROC curve analysis. Conclusions: Enhanced CT texture feature analysis shows promise in predicting lesion pseudoprogression in patients with metastatic ccRCC undergoing PD-1 inhibitor therapy. The developed predictive model based on texture features demonstrates good performance and may assist in evaluating treatment response in these patients.

Evaluation of calcification distribution by CT-based textural analysis for discrimination of immature teratoma

BackgroundMature and immature teratomas are differentiated based on tumor markers and calcification or fat distribution. However, no study has objectively quantified the differences in calcification and fat distributions between these tumors. This study aimed to evaluate the diagnostic potential of CT-based textural analysis in differentiating between mature and immature teratomas in patients aged < 20 years.Materials and methodsThirty-two patients with pathologically proven mature cystic (n = 28) and immature teratomas (n = 4) underwent transabdominal ultrasound and/or abdominal and pelvic CT before surgery. The diagnostic performance of CT for assessing imaging features, including subjective manual measurement and objective textural analysis of fat and calcification distributions in the tumors, was evaluated by two experienced readers. The histopathological results were used as the gold standard. The Mann–Whitney U test was used for statistical analysis.ResultsWe evaluated 32 patients (mean age, 14.5 years; age range, 6–19 years). The mean maximum diameter and number of calcifications of immature teratomas were significantly larger than those of mature cystic teratomas (p < 0.01). The mean number of fats of immature teratomas was significantly larger than that of mature cystic teratomas (p < 0.01); however, no significant difference in the maximum diameter of fats was observed. CT textural features for calcification distribution in the tumors showed that mature cystic teratomas had higher homogeneity and energy than immature teratomas. However, immature teratomas showed higher correlation, entropy, and dissimilarity than mature cystic teratomas among features derived from the gray-level co-occurrence matrix (GLCM) (p < 0.05). No significant differences were observed in the CT features of fats derived from GLCM.ConclusionOur results demonstrate that calcification distribution on CT is a potential diagnostic biomarker to discriminate mature from immature teratomas, thus enabling optimal therapeutic selection for patients aged < 20 years.

Radiomics model based on contrast-enhanced CT texture features for pretreatment prediction of overall survival in esophageal neuroendocrine carcinoma.

Limited studies have observed the prognostic value of CT images for esophageal neuroendocrine carcinoma (NEC) due to rare incidence and low treatment experience in clinical. In this study, the pretreatment enhanced CT texture features and clinical characteristics were investigated to predict the overall survival of esophageal NEC. This retrospective study included 89 patients with esophageal NEC. The training and testing cohorts comprised 61 (70%) and 28 (30%) patients, respectively. A total of 402 radiomics features were extracted from the tumor region that segmented pretreatment venous phase CT images. The least absolute shrinkage and selection operator (LASSO) Cox regression was applied to feature dimension reduction, feature selection, and radiomics signature construction. A radiomics nomogram was constructed based on the radiomics signature and clinical risk factors using a multivariable Cox proportional regression. The performance of the nomogram for the pretreatment prediction of overall survival (OS) was evaluated for discrimination and calibration. Only the enhancement degree was an independent factor in clinical variable influenced OS. The radiomics signatures demonstrated good predictability for prognostic status discrimination. The radiomics nomogram integrating texture signatures was slightly superior to the nomogram derived from the combined model with a C-index of 0.844 (95%CI: 0.783-0.905) and 0.847 (95% CI: 0.782-0.912) in the training set, and 0.805 (95%CI: 0.707-0.903) and 0.745 (95% CI: 0.639-0.851) in the testing set, respectively. The radiomics nomogram based on pretreatment CT radiomics signature had better prognostic power and predictability of the overall survival in patients with esophageal NEC than the model using combined variables.

Using Texture Analysis of Neck Computed Tomography Images to Differentiate Primary Hyperparathyroidism From Normal Controls.

To investigate the utility of texture analysis in detecting osseous changes associated with hyperparathyroidism on neck CT examinations compared with control patients and to explore the best regions in the head and neck to evaluate changes in the trabecular architecture secondary to hyperparathyroidism. Patients with hyperparathyroidism who underwent a 4D CT of the neck with contrast were included in this study. Age-matched control patients with no history of hyperparathyroidism who underwent a contrast-enhanced neck CT were also included. Mandibular condyles, bilateral mandibular bodies, the body of the C4 vertebra, the manubrium of the sternum, and bilateral clavicular heads were selected for analysis, and oval-shaped regions of interest were manually placed. These segmented areas were imported into an in-house developed texture analysis program, and 41 texture analysis features were extracted. A mixed linear regression model was used to compare differences in the texture analysis features contoured at each of the osseous structures between patients with hyperparathyroidism and age-matched control patients. A total of 30 patients with hyperparathyroidism and 30 age-matched control patients were included in this study. Statistically significant differences in texture features between patients with hyperparathyroidism and control patients in all 8 investigated osseous regions. The sternum showed the greatest number of texture features with statistically significant differences between these groups. Some CT texture features demonstrated statistically significant differences between patients with hyperparathyroidism and control patients. The results suggest that texture features may discriminate changes in the osseous architecture of the head and neck in patients with hyperparathyroidism.

Reproducibility of CT and MRI texture features of hepatocellular carcinoma

Purpose: To compare the reproducibility of texture features during segmentation of CT and MR images of hepatocellular cancer (HCC) by two radiologists. Evaluate the possibility of images pre-processing to improve the reproducibility of texture features. Material and methods. We included 66 patients with preoperative CT and MR images, followed by surgical liver resection for HCC, indicating the tumor histologic grade. Two radiologists with 3 and 6 years of abdominal imaging experience independently segmented the entire tumor volume on CT and MR images. The calculation of texture features was performed without the use of images pre-processing and using a spatial resampling with fixed voxel size of 1 mm3 (RES), a Laplace Gaussian filter, and for CT images, also with a density threshold from 0 to 300 HU (0–300 HU). The agreement between measurements of radiologists in relation to texture features was carried out using the type 2 intra-class correlation coefficient (ICC). Results. The highest percentage of reproducible texture features with the use of image preprocessing was observed with CT in the arterial phase (0–300 HU + RES) (89.1%), and with MRI in the hepatobiliary phase (RES) (86.6%). At the same time, spatial resampling with fixed voxel size of 1 mm3 increased the percentage of reproducible texture features in the native, arterial, and delayed phases in CT, as well as in T2-WI, DWI, and in the hepatobiliary phase for MRI. Conclusion. Thus, both techniques, CT and MRI, make it possible to extract reproducible texture features, especially with the use of spatial resampling with fixed voxel size. In this case, preference should be given to a postcontrast images, including the hepatobiliary phase. In CT, it is also advisable to use a density threshold from 0 to 300 HU for the selected area of interest, which will avoid affecting the texture features of adjacent organs and adipose tissue and increase the reproducibility of textural features.

Reproducibility in Radiomics: A Comparison of Feature Extraction Methods and Two Independent Datasets.

Radiomics involves the extraction of information from medical images that are not visible to the human eye. There is evidence that these features can be used for treatment stratification and outcome prediction. However, there is much discussion about the reproducibility of results between different studies. This paper studies the reproducibility of CT texture features used in radiomics, comparing two feature extraction implementations, namely the MATLAB toolkit and Pyradiomics, when applied to independent datasets of CT scans of patients: (i) the open access RIDER dataset containing a set of repeat CT scans taken 15 min apart for 31 patients (RIDER Scan 1 and Scan 2, respectively) treated for lung cancer; and (ii) the open access HN1 dataset containing 137 patients treated for head and neck cancer. Gross tumor volume (GTV), manually outlined by an experienced observer available on both datasets, was used. The 43 common radiomics features available in MATLAB and Pyradiomics were calculated using two intensity-level quantization methods with and without an intensity threshold. Cases were ranked for each feature for all combinations of quantization parameters, and the Spearman's rank coefficient, rs, calculated. Reproducibility was defined when a highly correlated feature in the RIDER dataset also correlated highly in the HN1 dataset, and vice versa. A total of 29 out of the 43 reported stable features were found to be highly reproducible between MATLAB and Pyradiomics implementations, having a consistently high correlation in rank ordering for RIDER Scan 1 and RIDER Scan 2 (rs > 0.8). 18/43 reported features were common in the RIDER and HN1 datasets, suggesting they may be agnostic to disease site. Useful radiomics features should be selected based on reproducibility. This study identified a set of features that meet this requirement and validated the methodology for evaluating reproducibility between datasets.

Based on CT radiomics model for predicting the response to first-line chemotherapy of diffuse large B-cell lymphoma

Objective: To investigate the potential value of CT Radiomics model in predicting the response to first-line chemotherapy in diffuse large B-cell lymphoma (DLBCL). Methods: Pre-treatment CT images and clinical data of DLBCL patients treated at Shanxi Cancer Hospital from January 2013 to May 2018 were retrospectively analyzed and divided into refractory patients (73 cases) and non-refractory patients (57 cases) according to the Lugano 2014 efficacy evaluation criteria. The least absolute shrinkage and selection operator (LASSO) regression algorithm, univariate and multivariate logistic regression analyses were used to screen out clinical factors and CT radiomics features associated with efficacy response, followed by radiomics model and nomogram model. Receiver operating characteristic (ROC) curve, calibration curve and clinical decision curve were used to evaluate the models in terms of the diagnostic efficacy, calibration and clinical value in predicting chemotherapy response. Results: Based on pre-chemotherapy CT images, 850 CT texture features were extracted from each patient, and 6 features highly correlated with the first-line chemotherapy effect of DLBCL were selected, including 1 first order feature, 1 gray level co-occurence matrix, 3 grey level dependence matrix, 1 neighboring grey tone difference matrix. Then, the corresponding radiomics model was established, whose ROC curves showed AUC values of 0.82 (95% CI: 0.76-0.89) and 0.73 (95% CI: 0.60-0.86) in the training and validation groups, respectively. The nomogram model, built by combining validated clinical factors (Ann Arbor stage, serum LDH level) and CT radiomics features, showed an AUC of 0.95 (95% CI: 0.90-0.99) and 0.91 (95% CI: 0.82-1.00) in the training group and the validation group, respectively, with significantly better diagnostic efficacy than that of the radiomics model. In addition, the calibration curve and clinical decision curve showed that the nomogram model had good consistency and high clinical value in the assessment of DLBCL efficacy. Conclusion: The nomogram model based on clinical factors and radiomics features shows potential clinical value in predicting the response to first-line chemotherapy of DLBCL patients.

Noninvasive assessment of significant liver fibrosis in rabbits by spectral CT parameters and texture analysis.

Noninvasive assessment of significant liver fibrosis in rabbits by spectral CT parameters and texture analysis. Thirty-three rabbits were randomly divided into 27 carbon tetrachloride-induced liver fibrosis group and 6 control group. Spectral CT contrast-enhanced scan was performed in batches, and the liver fibrosis was staged according to the histopathological results. The portal venous phase spectral CT parameters [70keV CT value, normalized iodine concentration (NIC), spectral HU curve slope (λHU)] were measured, and MaZda texture analysis was performed on 70keV monochrome images. Three dimensionality reduction methods and four statistical methods in B11 module were used to perform discriminant analysis and calculate misclassified rate (MCR), and ten texture features under the lowest combination of MCR were statistically analyzed. Receiver operating characteristic curve (ROC) was used to calculate the diagnostic performance of spectral parameters and texture features for significant liver fibrosis. Finally, the binary logistic regression was used to further screen independent predictors and establish model. A total of 23 experimental rabbits and 6 control rabbits were included, of which 16 had significant liver fibrosis. Three spectral CT parameters with significant liver fibrosis were significantly lower than those of non-significant liver fibrosis (p < 0.05), and the AUC ranged from 0.846 to 0.913. The combination analysis of mutual information (MI) and nonlinear discriminant analysis (NDA) had the lowest MCR, which with 0%. In the filtered texture features, four were statistically significant and AUC > 0.5, ranges from 0.764 to 0.875. The logistic regression model showed that Perc.90% and NIC could be used as independent predictors, the overall prediction accuracy of the model was 89.7% and the AUC was 0.976. Spectral CT parameters and texture features have high diagnostic value for predicting significant liver fibrosis in rabbits, and the combination of the two can improve its diagnostic efficiency.

Analysis of HER2 protein expression and clinical prognosis based on CT texture analysis in the arterial phase of gastric cancer

ObjectiveTo assess the relationship of CT texture feature parameters in the arterial phase of gastric cancer with the expression of HER2 protein. MethodsA total of 39 patients with gastric cancer confirmed by pathology were included and further divided into the HER2 negative and positive groups. According to tumor invasion depth, they were assigned to the early and advanced groups. The maximum diameter of the tumor lesions on the CT axial plane was measured, and 3-year survival was followed up and recorded. ResultsThe maximum axial diameter of early gastric cancer was 4.84 ± 0.52 cm, and the 3-year follow-up survival time was 2.41 ± 0.56 years; the maximum diameter of advanced gastric cancer was 6.58 ± 0.42 cm, and the 3-year follow-up survival time was 1.21 ± 0.21 years with a significance between them (P < 0.05). The CT texture parameters in the arterial phase elucidated significant differences in the 10th percentile, 90th percentile, maximum, median, average, and minimum value between HER2 positive group and negative group (P < 0.05) without difference in texture features between the two groups (P > 0.05). ROC curve showed when the 10th percentile was 13.5, the 90th percentile was 70.2, the maximum value was 101.5, the median was 24.2, the average was 39.4, and the minimum of −7 was the best cut-off value. The specificity and sensitivity for distinguishing HER2-negative or positive were high, and the area under curve (AUC) was about 0.707–0.813, of which the 90th percentile was the most significant. ConclusionThe maximum diameter of the tumor in the CT axial plane is related to early and advanced gastric cancer and the prognosis. Based on CT arterial phase texture parameters, HER2 expression in gastric cancer can be judged to provide a basis for clinical diagnosis and treatment.

A novel nomogram model combining CT texture features and urine energy metabolism to differentiate single benign from malignant pulmonary nodule.

To investigate a novel diagnostic model for benign and malignant pulmonary nodule diagnosis based on radiomic and clinical features, including urine energy metabolism index. A total of 107 pulmonary nodules were prospectively recruited and pathologically confirmed as malignant in 86 cases and benign in 21 cases. A chest CT scan and urine energy metabolism test were performed in all cases. A nomogram model was established in combination with radiomic and clinical features, including urine energy metabolism levels. The nomogram model was compared with the radiomic model and the clinical feature model alone to test its diagnostic validity, and receiver operating characteristic (ROC) curves were plotted to assess diagnostic validity. The nomogram was established using a logistic regression algorithm to combine radiomic features and clinical characteristics including urine energy metabolism results. The predictive performance of the nomogram was evaluated using the area under the ROC and calibration curve, which showed the best performance, area under the curve (AUC) = 0.982, 95% CI = 0.940-1.000, compared to clinical and radiomic models in the testing cohort. The clinical benefit of the model was assessed using the decision curve analysis (DCA) and using the nomogram for benign and malignant pulmonary nodules, and preoperative prediction of benign and malignant pulmonary nodules using nomograms showed better clinical benefit. This study shows that a coupled model combining CT imaging features and clinical features (including urine energy metabolism) in combination with the nomogram model has higher diagnostic performance than the radiomic and clinical models alone, suggesting that the combination of both methods is more advantageous in identifying benign and malignant pulmonary nodules.

Practical nomogram based on comprehensive CT texture analysis to preoperatively predict peritoneal occult metastasis of gastric cancer patients.

This study aims to evaluate whether a nomogram based on comprehensive CT texture analysis of primary tumor and peritoneotome combined with conventional CT signs can preoperatively predict peritoneal occult metastasis in gastric cancer patients. A total of 1,251 patients with gastric cancer (GC) were retrospectively analyzed in Fujian Province Hospital between 2008 and 2020. Patients from the occult peritoneal metastasis (PM) group were initially diagnosed as PM-negative on CT and later confirmed as PM-positive through laparoscopy or surgery. The group without PM was randomly sampled from patients without PM. The preoperative CT signs and texture features and clinical characteristics of patients were retrospectively analyzed. Hazard factors of occult PM were identified by univariate analysis and multivariate logistic regression analysis, which were intended for creating prediction models. A nomogram was established based on the model with the highest predictive efficacy and clinical application value. A total of 31 patients with occult PM and 165 patients without PM were enrolled in this study. The maximum size, thickness, enhancement, serous involvement of primary GC tumor and ascites on CT, and texture features such as inhomogeneity of the primary tumor, standard deviation, and inhomogeneity of the peritoneum were determined as independent predictors that could be jointly applied to predict occult PM. We separately constructed five forecast models using CT signs, primary tumor texture, peritoneum texture, primary tumor texture + peritoneum texture, and their combination for predicting occult PM. These five prediction models achieved an AUC value of 0.832, 0.70, 0.784, 0.838, and 0.941, respectively. The DeLong test and Decision Curve Analysis (DCA) showed that the joint model, containing three meaningful CT signs (maximum size, thickness, and ascites) and two meaningful texture parameters (inhomogeneity of the primary tumor and inhomogeneity of the peritoneum), possessed the best predictive performance and clinical application (p<0.05). A forecast nomogram was subsequently established from the model above-mentioned. The calibration curves of the nomogram indicated a good consistency (a concordance index of 0.807) between the projection and the actual observation of occult PM. A practical projection nomogram based on the comprehensive CT texture analysis of a primary tumor and peritoneotome combined with conventional CT signs was constructed in our study, which can be conveniently used in preoperative personalized prediction of occult PM for GC patients, and acts as a recommendation for the optimization of clinical management.

The value of CT radiomics features to predict visceral pleural invasion in ≤3 cm peripheral type early non-small cell lung cancer.

To investigate predictive value of CT-based radiomics features on visceral pleural invasion (VPI) in ≤3.0 cm peripheral type early non-small cell lung cancer (NSCLC). A total of 221 NSCLC cases were collected. Among them, 115 are VPI-positive and 106 are VPI-negative. Using a stratified random sampling method, 70% cases were assigned to training dataset (n = 155) and 30% cases (n = 66) were assigned to validation dataset. First, CT findings, imaging features, clinical data and pathological findings were retrospectively analyzed, the size, location and density characteristics of nodules and lymph node status, the relationship between lesions and pleura (RAP) were assessed, and their mean CT value and the shortest distance between lesions and pleura (DLP) were measured. Next, the minimum redundancy-maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) features were extracted from the imaging features. Then, CT imaging prediction model, texture feature prediction model and joint prediction model were built using multifactorial logistic regression analysis method, and the area under the ROC curve (AUC) was applied to evaluate model performance in predicting VPI. Mean diameter, density, fractal relationship with pleura, and presence of lymph node metastasis were all independent predictors of VPI. When applying to the validation dataset, the CT imaging model, texture feature model, and joint prediction model yielded AUC = 0.882, 0.824 and 0.894, respectively, indicating that AUC of the joint prediction model was the highest (p < 0.05). The study demonstrates that the joint prediction model containing CT morphological features and texture features enables to predict the presence of VPI in early NSCLC preoperatively at the highest level.

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.

Contrast-Enhanced CT Texture Analysis in Colon Cancer: Correlation with Genetic Markers.

Background: The purpose of the study was to determine whether contrast-enhanced CT texture features relate to, and can predict, the presence of specific genetic mutations involved in CRC carcinogenesis. Materials and methods: This retrospective study analyzed the pre-operative CT in the venous phase of patients with CRC, who underwent testing for mutations in the KRAS, NRAS, BRAF, and MSI genes. Using a specific software based on CT images of each patient, for each slice including the tumor a region of interest was manually drawn along the margin, obtaining the volume of interest. A total of 56 texture parameters were extracted that were compared between the wild-type gene group and the mutated gene group. A p-value of <0.05 was considered statistically significant. Results: The study included 47 patients with stage III-IV CRC. Statistically significant differences between the MSS group and the MSI group were found in four parameters: GLRLM RLNU (area under the curve (AUC) 0.72, sensitivity (SE) 77.8%, specificity (SP) 65.8%), GLZLM SZHGE (AUC 0.79, SE 88.9%, SP 65.8%), GLZLM GLNU (AUC 0.74, SE 88.9%, SP 60.5%), and GLZLM ZLNU (AUC 0.77, SE 88.9%, SP 65.8%). Conclusions: The findings support the potential role of the CT texture analysis in detecting MSI in CRC based on pre-treatment CT scans.