A multicentric study of radiomics and artificial intelligence analysis on contrast-enhanced mammography to identify different histotypes of breast cancer.

OBJECTIVE: To evaluate the performance of radiomic analysis on contrast-enhanced mammography images to identify different histotypes of breast cancer mainly in order to predict grading, to identify hormone receptors, to discriminate human epidermal growth factor receptor 2 (HER2) and to identify luminal histotype of the breast cancer. METHODS: From four Italian centers were recruited 180 malignant lesions and 68 benign lesions. However, only the malignant lesions were considered for the analysis. All patients underwent contrast-enhanced mammography in cranium caudal (CC) and medium lateral oblique (MLO) view. Considering histological findings as the ground truth, four outcomes were considered: (1) G1 + G2 vs. G3; (2) HER2 + vs. HER2 - ; (3) HR + vs. HR - ; and (4) non-luminal vs. luminal A or HR + /HER2- and luminal B or HR + /HER2 + . For multivariate analysis feature selection, balancing techniques and patter recognition approaches were considered. RESULTS: The univariate findings showed that the diagnostic performance is low for each outcome, while the results of the multivariate analysis showed that better performances can be obtained. In the HER2 + detection, the best performance (73% of accuracy and AUC = 0.77) was obtained using a linear regression model (LRM) with 12 features extracted by MLO view. In the HR + detection, the best performance (77% of accuracy and AUC = 0.80) was obtained using a LRM with 14 features extracted by MLO view. In grading classification, the best performance was obtained by a decision tree trained with three predictors extracted by MLO view reaching an accuracy of 82% on validation set. In the luminal versus non-luminal histotype classification, the best performance was obtained by a bagged tree trained with 15 predictors extracted by CC view reaching an accuracy of 94% on validation set. CONCLUSIONS: The results suggest that radiomics analysis can be effectively applied to design a tool to support physician decision making in breast cancer classification. In particular, the classification of luminal versus non-luminal histotypes can be performed with high accuracy.

[18 F]-FDG PET radiomic model as prognostic biomarker in diffuse large B-cell lymphoma.

To evaluate the association between radiomic features (RFs) extracted from 18 F-FDG PET/CT (18 F-FDG-PET) with progression-free survival (PFS) and overall survival (OS) in diffuse large-B-cell lymphoma (DLBCL) patients eligible to first-line chemotherapy. DLBCL patients who underwent 18 F-FDG-PET prior to first-line chemotherapy were retrospectively analyzed. RFs were extracted from the lesion showing the highest uptake. A radiomic score to predict PFS and OS was obtained by multivariable Elastic Net Cox model. Radiomic univariate model, clinical and combined clinical-radiomic multivariable models to predict PFS and OS were obtained. 112 patients were analyzed. Median follow-up was 34.7 months (Inter-Quartile Range (IQR) 11.3-66.3 months) for PFS and 41.1 (IQR 18.4-68.9) for OS. Radiomic score resulted associated with PFS and OS (p < 0.001), outperforming conventional PET parameters. C-index (95% CI) for PFS prediction were 0.67 (0.58-0.76), 0.81 (0.75-0.88) and 0.84 (0.77-0.91) for clinical, radiomic and combined clinical-radiomic model, respectively. C-index for OS were 0.77 (0.66-0.89), 0.84 (0.76-0.91) and 0.90 (0.81-0.98). In the Kaplan-Meier analysis (low-IPI vs. high-IPI), the radiomic score was significant predictor of PFS (p < 0.001). The radiomic score was an independent prognostic biomarker of survival in DLBCL patients. The extraction of RFs from baseline 18 F-FDG-PET might be proposed in DLBCL to stratify high-risk versus low-risk patients of relapse after first-line therapy, especially in low-IPI patients.

Radiomics and artificial intelligence analysis by T2-weighted imaging and dynamic contrast-enhanced magnetic resonance imaging to predict Breast Cancer Histological Outcome.

OBJECTIVE: The objective of the study was to evaluate the accuracy of radiomics features obtained by MR images to predict Breast Cancer Histological Outcome. METHODS: A total of 217 patients with malignant lesions were analysed underwent MRI examinations. Considering histological findings as the ground truth, four different types of findings were used in both univariate and multivariate analyses: (1) G1 + G2 vs G3 classification; (2) presence of human epidermal growth factor receptor 2 (HER2 + vs HER2 -); (3) presence of the hormone receptor (HR + vs HR -); and (4) presence of luminal subtypes of breast cancer. RESULTS: The best accuracy for discriminating HER2 + versus HER2 - breast cancers was obtained considering nine predictors by early phase T1-weighted subtraction images and a decision tree (accuracy of 88% on validation set). The best accuracy for discriminating HR + versus HR - breast cancers was obtained considering nine predictors by T2-weighted subtraction images and a decision tree (accuracy of 90% on validation set). The best accuracy for discriminating G1 + G2 versus G3 breast cancers was obtained considering 16 predictors by early phase T1-weighted subtraction images in a linear regression model with an accuracy of 75%. The best accuracy for discriminating luminal versus non-luminal breast cancers was obtained considering 27 predictors by early phase T1-weighted subtraction images and a decision tree (accuracy of 94% on validation set). CONCLUSIONS: The combination of radiomics analysis and artificial intelligence techniques could be used to support physician decision-making in prediction of Breast Cancer Histological Outcome.

Single fraction ablative preoperative radiation treatment for early-stage breast cancer: the CRYSTAL study - a phase I/II clinical trial protocol.

BACKGROUND: Breast-conserving surgery (BCS) and whole breast radiation therapy (WBRT) are the standard of care for early-stage breast cancer (BC). Based on the observation that most local recurrences occurred near the tumor bed, accelerated partial breast irradiation (APBI), consisting of a higher dose per fraction to the tumor bed over a reduced treatment time, has been gaining ground as an attractive alternative in selected patients with low-risk BC. Although more widely delivered in postoperative setting, preoperative APBI has also been investigated in a limited, though increasing, and number of studies. The aim of this study is to test the feasibility, safety and efficacy of preoperative radiotherapy (RT) in a single fraction for selected BC patients. METHODS: This is a phase I/II, single-arm and open-label single-center clinical trial using CyberKnife. The clinical investigation is supported by a preplanning section which addresses technical and dosimetric issues. The primary endpoint for the phase I study, covering the 1st and 2nd year of the research project, is the identification of the maximum tolerated dose (MTD) which meets a specific target toxicity level (no grade 3-4 toxicity). The primary endpoint for the phase II study (3rd to 5th year) is the evaluation of treatment efficacy measured in terms of pathological complete response rate. DISCUSSION: The study will investigate the response of BC to the preoperative APBI from different perspectives. While preoperative APBI represents a form of anticipated boost, followed by WBRT, different are the implications for the scientific community. The study may help to identify good responders for whom surgery could be omitted. It is especially appealing for patients unfit for surgery due to advanced age or severe co-morbidities, in addition to or instead of systemic therapies, to ensure long-term local control. Moreover, patients with oligometastatic disease synchronous with primary BC may benefit from APBI on the intact tumor in terms of tumor progression free survival. The study of response to RT can provide useful information about BC radiobiology, immunologic reactions, genomic expression, and radiomics features, to be tested on a larger scale. TRIAL REGISTRATION: The study was prospectively registered at clinicaltrials.gov ( NCT04679454 ).

A multicenter study on radiomic features from T2 -weighted images of a customized MR pelvic phantom setting the basis for robust radiomic models in clinics.

PURPOSE: To investigate the repeatability and reproducibility of radiomic features extracted from MR images and provide a workflow to identify robust features. METHODS: T2 -weighted images of a pelvic phantom were acquired on three scanners of two manufacturers and two magnetic field strengths. The repeatability and reproducibility of features were assessed by the intraclass correlation coefficient and the concordance correlation coefficient, respectively, and by the within-subject coefficient of variation, considering repeated acquisitions with and without phantom repositioning, and with different scanner and acquisition parameters. The features showing intraclass correlation coefficient or concordance correlation coefficient >0.9 were selected, and their dependence on shape information (Spearman's ρ > 0.8) analyzed. They were classified for their ability to distinguish textures, after shuffling voxel intensities of images. RESULTS: From 944 two-dimensional features, 79.9% to 96.4% showed excellent repeatability in fixed position across all scanners. A much lower range (11.2% to 85.4%) was obtained after phantom repositioning. Three-dimensional extraction did not improve repeatability performance. Excellent reproducibility between scanners was observed in 4.6% to 15.6% of the features, at fixed imaging parameters. In addition, 82.4% to 94.9% of the features showed excellent agreement when extracted from images acquired with echo times 5 ms apart, but decreased with increasing echo-time intervals, and 90.7% of the features exhibited excellent reproducibility for changes in pulse repetition time. Of nonshape features, 2.0% was identified as providing only shape information. CONCLUSION: We showed that radiomic features are affected by MRI protocols and propose a general workflow to identify repeatable, reproducible, and informative radiomic features to ensure robustness of clinical studies.

MRI-based radiomics signature for localized prostate cancer: a new clinical tool for cancer aggressiveness prediction? Sub-study of prospective phase II trial on ultra-hypofractionated radiotherapy (AIRC IG-13218).

OBJECTIVES: Radiomic involves testing the associations of a large number of quantitative imaging features with clinical characteristics. Our aim was to extract a radiomic signature from axial T2-weighted (T2-W) magnetic resonance imaging (MRI) of the whole prostate able to predict oncological and radiological scores in prostate cancer (PCa). METHODS: This study included 65 patients with localized PCa treated with radiotherapy (RT) between 2014 and 2018. For each patient, the T2-W MRI images were normalized with the histogram intensity scale standardization method. Features were extracted with the IBEX software. The association of each radiomic feature with risk class, T-stage, Gleason score (GS), extracapsular extension (ECE) score, and Prostate Imaging Reporting and Data System (PI-RADS v2) score was assessed by univariate and multivariate analysis. RESULTS: Forty-nine out of 65 patients were eligible. Among the 1702 features extracted, 3 to 6 features with the highest predictive power were selected for each outcome. This analysis showed that texture features were the most predictive for GS, PI-RADS v2 score, and risk class; intensity features were highly associated with T-stage, ECE score, and risk class, with areas under the receiver operating characteristic curve (ROC AUC) ranging from 0.74 to 0.94. CONCLUSIONS: MRI-based radiomics is a promising tool for prediction of PCa characteristics. Although a significant association was found between the selected features and all the mentioned clinical/radiological scores, further validations on larger cohorts are needed before these findings can be applied in the clinical practice. KEY POINTS: • A radiomic model was used to classify PCa aggressiveness. • Radiomic analysis was performed on T2-W magnetic resonance images of the whole prostate gland. • The most predictive features belong to the texture (57%) and intensity (43%) domains.

The Impact of Sarcopenia on Postoperative Course following Pancreatoduodenectomy: Single-Center Experience of 110 Consecutive Cases.

BACKGROUND: Despite that mortality following pancreatoduodenectomy (PD) has gradually dropped during the past few decades, the incidence of postoperative complications remains high, ranging from 30-60%. Many studies have been focused on identification of perioperative risk factors for morbidity, and in recent years, sarcopenia has been pointed out as a valid predictor of postoperative complication. MATERIALS AND METHODS: Perioperative data from 110 consecutive patients who underwent PD were retrieved, and the presence of sarcopenia was assessed by the measurement of Hounsfield unit average calculation on preoperative CT scans. Postoperative complications were graded according to Clavien-Dindo classification, and the morbidity burden was assessed by comprehensive complication index (CCI) calculation. RESULTS: Sarcopenia was associated with advanced age (72 vs. 66 years; p = 0.014) and lower preoperative albumin levels (3.5 vs. 3.7 g/dL; p = 0.010); it represented an independent risk factor for clinically relevant complications (relative risk: 1.71; p = 0.015) and was related to a higher rate of Grade C postoperative pancreatic fistula (50.0 vs. 11.4%; p = 0.005) and a higher CCI (47.6 vs. 29.6; p = 0.001). CONCLUSIONS: Sarcopenia represents a valid indicator of increased morbidity risk and may play a central role in preoperative risk stratification, allowing the selection of patients who may benefit from prehabilitation programs.

Compliance to Adjuvant Chemotherapy of Patients Who Underwent Surgery for Rectal Cancer: Report from a Multi-institutional Research Network.

INTRODUCTION: Adjuvant chemotherapy for locally advanced rectal cancer is associated with improved overall survival. However, recent evidence from randomized trials showed a compliance rate of 43 to 73%, which may affect efficacy. The aim of this multicenter retrospective analysis was to investigate the compliance rate to adjuvant treatment for patients who underwent rectal surgery for cancer. METHODS: Patients who underwent surgery with curative intent for rectal cancer in six Italian colorectal centers between January 2013 and December 2017 were retrospectively reviewed. Exclusion criteria were age less than 18 years, palliative or emergency surgery, and stage IV disease. Parameters of interest were patients' characteristics, preoperative tumor stage, neo-adjuvant chemoradiation therapy, intra-operative and postoperative outcomes. Although the participating centers referred to the same treatment guidelines for treatment, the chemotherapy regiment was not standardized across the institutions. Reasons for not starting adjuvant chemotherapy when indicated, interruption, and modification of drug regimen were collected to investigate compliance. RESULTS: A total of 572 patients were included in the analysis. Two hundred and fifty-two (44.1%) patients received neo-adjuvant chemoradiation therapy. All patients underwent high anterior rectal resection, low anterior rectal resection, or Miles' procedure. Of 399 patients with an indication to adjuvant chemotherapy, 176 (44.1%) completed the treatment as planned. Compliance for patients who started chemotherapy was 56% (95% CI 50.4-61.6%). Sixty-six patients interrupted the treatment, 76 patients significantly reduced the drug dose, and 41 patients had to switch to other therapeutic regimens. CONCLUSIONS: The present multicenter investigation reports a low compliance rate to adjuvant chemotherapy after rectal resection for cancer. Multidisciplinary teams should focus on future effort to improve compliance for these patients.

Liver Grafts From Donors After Circulatory Death on Regional Perfusion With Extended Warm Ischemia Compared With Donors After Brain Death.

Donation after circulatory death (DCD) in Italy constitutes a relatively unique population because of the requirement of a no-touch period of 20 minutes. The first aim of this study was to compare liver transplantations from donors who were maintained on normothermic regional perfusion after circulatory death and suffered extended warm ischemia (DCD group, n = 20) with those from donors who were maintained on extracorporeal membrane oxygenation (ECMO) and succumbed to brain death (ECMO group, n = 17) and those from standard donors after brain death (donation after brain death [DBD] group, n = 52). Second, we conducted an explorative analysis on the DCD group to identify relationships between the donor characteristics and the transplant outcomes. The 1-year patient survival for the DCD group (95%) was not significantly different from that of the ECMO group (87%; P = 0.47) or the DBD group (94%; P = 0.94). Graft survival was slightly inferior in the DCD group (85%) because of a high rate of primary nonfunction (10%) and retransplantation (15%) but was not significantly different from the ECMO group (87%; P = 0.76) or the DBD group (91%; P = 0.20). Although ischemic cholangiopathy was more frequent in the DCD group (10%), this issue did not adversely impact graft survival because none of the recipients underwent retransplantation due to biliary complications. Moreover, the DCD recipients were more likely to develop posttransplant renal dysfunction with the need for renal replacement therapy. Further analysis of the DCD group showed that warm ischemia >125 minutes and an Ishak fibrosis score of 1 at liver biopsy negatively impacted serum creatinine and alanine transaminase levels in the first posttransplant week, respectively. In conclusion, our findings encourage the use of liver grafts from DCD donors maintained by regional perfusion after proper selection.