Reproducibility of radiomic features in CT images of NSCLC patients: an integrative analysis on the impact of acquisition and reconstruction parameters.

BACKGROUND: We investigated to what extent tube voltage, scanner model, and reconstruction algorithm affect radiomic feature reproducibility in a single-institution retrospective database of computed tomography images of non-small-cell lung cancer patients. METHODS: This study was approved by the Institutional Review Board (UID 2412). Images of 103 patients were considered, being acquired on either among two scanners, at 100 or 120 kVp. For each patient, images were reconstructed with six iterative blending levels, and 1414 features were extracted from each reconstruction. At univariate analysis, Wilcoxon-Mann-Whitney test was applied to evaluate feature differences within scanners and voltages, whereas the impact of the reconstruction was established with the overall concordance correlation coefficient (OCCC). A multivariable mixed model was also applied to investigate the independent contribution of each acquisition/reconstruction parameter. Univariate and multivariable analyses were combined to analyse feature behaviour. RESULTS: Scanner model and voltage did not affect features significantly. The reconstruction blending level showed a significant impact at both univariate analysis (154/1414 features yielding an OCCC < 0.85) and multivariable analysis, with most features (1042/1414) revealing a systematic trend with the blending level (multiple comparisons adjusted p < 0.05). Reproducibility increased in association to image processing with smooth filters, nonetheless specific investigation in relation to clinical endpoints should be performed to ensure that textural information is not removed. CONCLUSIONS: Combining univariate and multivariable models is allowed to identify features for which corrections may be applied to reduce the trend with the algorithm and increase reproducibility. Subsequent clustering may be applied to eliminate residual redundancy.

Adjuvant radiotherapy in node positive prostate cancer patients: a debate still on. when, for whom?

OBJECTIVE: To evaluate the impact of adjuvant radiotherapy (aRT) in patients with prostate cancer (PCa) found to have pathological positive lymph nodes (pN1s) after radical prostatectomy (RP) and extended pelvic lymph node dissection (ePLND) with regard to distant recurrence-free survival (RFS), according to both main tumour pathological characteristics and number of positive lymph nodes. Biochemical RFS, local RFS, overall survival (OS) and acute and late toxicity were assessed as secondary endpoints. PATIENTS AND METHODS: A retrospective cohort of 187 consecutive patients with pN1 PCa were treated with aRT at the IEO, European Institute of Oncology IRCCS, Milan, Italy. aRT on the tumour bed and pelvis was administered within 6 months of RP. Androgen deprivation therapy was administered according to the guidelines. Univariate and multivariate Cox regression analyses predicting biochemical RFS, local RFS, distant RFS and OS rates were performed to assess whether the number of pN1s represented an independent prognostic factor. The Youden index was computed to find the optimal threshold for the number of pN1s able to discriminate between patients with or without biochemical and clinical relapse. RESULTS: At 5 years, local RFS, distant RFS, biochemical RFS and OS were 68%, 71%, 56% and 94%, respectively. The median follow-up was 49 months. The number of pN1s was significantly associated with biochemical RFS, local RFS and distant RFS. The best threshold for discriminating between patients with or without biochemical and clinical relapse was five pN1s. In multivariate analyses, the number of pN1s was confirmed to be an independent predictor of biochemical RFS, local RFS and distant RFS, but not of OS. Multivariate analyses also showed an increased risk of biochemical relapse for increasing values of initial prostate-specific antigen and for patients with tumour vascular invasion. Local and distant RFS were also inversely correlated with significantly reduced risk for International Society of Urological Pathology grade group <3 (group 1 or 2 compared to group 3). CONCLUSIONS: Our data confirmed the encouraging outcomes of patients with pN1 PCa treated with adjuvant treatments and the key role represented by the number of pN1s in predicting biochemical RFS, clinical RFS and distant RFS. Large prospective cohort studies and randomized clinical trials are needed to confirm these results and to identify the subgroup of patients with pN1 PCa who would most benefit from aRT.

Effects of MRI image normalization techniques in prostate cancer radiomics.

The variance in intensities of MRI scans is a fundamental impediment for quantitative MRI analysis. Intensity values are not only highly dependent on acquisition parameters, but also on the subject and body region being scanned. This warrants the need for image normalization techniques to ensure that intensity values are consistent within tissues across different subjects and visits. Many intensity normalization methods have been developed and proven successful for the analysis of brain pathologies, but evaluation of these methods for images of the prostate region is lagging. In this paper, we compare four different normalization methods on 49 T2-w scans of prostate cancer patients: 1) the well-established histogram normalization, 2) the generalized scale normalization, 3) an extension of generalized scale normalization called generalized ball-scale normalization, and 4) a custom normalization based on healthy prostate tissue intensities. The methods are compared qualitatively and quantitatively in terms of behaviors of intensity distributions as well as impact on radiomic features. Our findings suggest that normalization based on prior knowledge of the healthy prostate tissue intensities may be the most effective way of acquiring the desired properties of normalized images. In addition, the histogram normalization method outperform the generalized scale and generalized ball-scale methods which have proven superior for other body regions.