Search

PURPOSE Variability in computed tomography images intrinsic to individual scanners limits the application of radiomics in clinical and research settings. The development of reproducible and generalizable radiomics-based models to assess lesions requires harmonization of data. The purpose of this study was to develop, test, and analyze the efficacy of a radiomics data harmonization model. MATERIALS AND METHODS Radiomic features from biopsy-proven untreated hepatic metastasis (N = 380) acquired from 167 unique patients with pancreatic, colon, and breast cancers were analyzed. Radiomic features from volume-match 551 samples of normal liver tissue and 188 hepatic cysts were included as references. A novel linear mixed effect model was used to identify effects associated with lesion size, tissue type, and scanner model. Six separate machine learning models were then used to test the effectiveness of radiomic feature harmonization using multivariate analysis. RESULTS Proposed model identifies and removes scanner-associated effects while preserving cancer-specific functional dependence of radiomic features on the tumor size. Data harmonization improves the performance of classification models by reducing the scanner-associated variability. For example, the multiclass logistic regression model, LogitBoost, demonstrated the improvement in sensitivity in the range from 15% to 40% for each type of liver metastasis, whereas the overall model accuracy and the kappa coefficient increased by 5% and 8% accordingly. CONCLUSION The model removed scanner-associated effects while preserving cancer-specific functional dependence of radiomic features.

To review existing structured MRI reports for primary staging of rectal cancer and create a new, freely available structured report based on multidisciplinary expert opinion and literature review.Twenty abdominal imaging experts from the Society of Abdominal Radiology (SAR)'s Disease Focused Panel (DFP) on Rectal and Anal Cancer completed a questionnaire and participated in a subsequent consensus meeting based on the RAND-UCLA Appropriateness Method. Twenty-two items were classified via a group survey as "appropriate" or "inappropriate" (defined by ≥ 70% consensus), or "needs group discussion" (defined by 70% consensus). Certain items were also discussed with multidisciplinary team members from colorectal surgery, oncology and pathology.After completion of the questionnaire, 16 (72%) items required further discussion ( 70% consensus). Following group discussion, consensus was achieved for 21 (95%) of the items. Based on the consensus meeting, a revised structured report was developed. The most significant modifications included (1) Exclusion of the T2/early T3 category; (2) Replacement of the term "circumferential resection margin (CRM)" with "mesorectal fascia (MRF)"; (3) A revised definition of "mucinous content"; (4) Creation of two distinct categories for suspicious lymph nodes (LNs) and tumor deposits; and (5) Classification of suspicious extra-mesorectal LNs by anatomic location.The SAR DFP on Rectal and Anal Cancer recommends using this newly updated reporting template for primary MRI staging of rectal cancer.

To evaluate the effect of hepatic metastatic lesion size on inter-reader reproducibility of CT-based 2D radiomics imaging features.Computerized tomography (CT) scans of 59 liver metastases from 34 patients with colorectal cancer were evaluated. Image segmentation was performed manually by three readers blinded to each other's results. For each radiomics feature, we created two datasets by sorting measurements according to size, i.e., (i) from the smallest to the largest lesion and (ii) from the largest to the smallest lesion. The Lin concordance correlation coefficient (CCC) was employed to analyze the reproducibility of radiomics features. In particular, the CCC was computed as a function of a number of elements in the dataset, by gradually adding lesions from each sorted dataset. To evaluate the effect of lesion size, we analyzed the difference between these two functions thus assessing the contribution of small and large lesions into the reproducibility of radiomics features.Inter-reader reproducibility of CT-based 2D radiomics features assessed using Lin's CCC demonstrates tumor-size dependence. For example, the Lin CCC for GLCM contrast equals 0.88 (95% C.I. 0.84 to 0.92, p 0.003) and could change by an additional + / - 0.06 depending on the presence of large or small lesions.Groups of "large" and "small" lesions show different inter-reader reproducibility. The inter-reader reproducibility from the mixed group consisting of "large" and "small" lesions depends on the lesion-size distribution and can vary widely. This finding could partially explain variability in reproducibility of radiomics features in the literature.• Groups of "large" and "small" lesions show different inter-reader reproducibility. • The inter-reader reproducibility from the mixed group consisting of "large" and "small" lesions depends on the lesion-size distribution.