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.

Repeatability and reproducibility of MRI-radiomic features: A phantom experiment on a 1.5 T scanner.

PURPOSE: Aim of this study is to assess the repeatability of radiomic features on magnetic resonance images (MRI) and their stability to variations in time of repetition (TR), time of echo (TE), slice thickness (ST), and pixel spacing (PS) using vegetable phantoms. METHODS: The organic phantom was realized using two cucumbers placed inside a cylindrical container, and the analysis was performed using T1-weighted (T1w), T2-weighted (T2w), and diffusion-weighted images. One dataset was used to test the repeatability of the radiomic features, whereas other four datasets were used to test the sensitivity of the different MRI sequences to image acquisition parameters (TR, TE, ST, and PS). Four regions of interest (ROIs) were segmented: two for the central part of each cucumber and two for the external parts. Radiomic features were extracted from each ROI using Pyradiomics. To assess the effect of preprocessing on the reduction of variability, features were extracted both before and after the preprocessing. The coefficient of variation (CV) and intra-class correlation coefficient (ICC) were used to evaluate variability. RESULTS: The use of intensity standardization increased the stability for the first-order statistics features. Shape and size features were always stable for all the analyses. Textural features were particularly sensitive to changes in ST and PS, although some increase in stability could be obtained by voxel size resampling. When images underwent image preprocessing, the number of stable features (ICC > 0.75 and mean absolute CV < 0.3) was 33 for apparent diffusion coefficient (ADC), 52 for T1w, and 73 for T2w. CONCLUSIONS: The most critical source of variability is related to changes in voxel size (either caused by changes in ST or PS). Preprocessing increases features stability to both test-retest and variation of the image acquisition parameters for all the types of analyzed MRI (T1w, T2w, and ADC), except for ST.

Stability of Multi-Parametric Prostate MRI Radiomic Features to Variations in Segmentation.

Stability analysis remains a fundamental step in developing a successful imaging biomarker to personalize oncological strategies. This study proposes an in silico contour generation method for simulating segmentation variations to identify stable radiomic features. Ground-truth annotation provided for the whole prostate gland on the multi-parametric MRI sequences (T2w, ADC, and SUB-DCE) were perturbed to mimic segmentation differences observed among human annotators. In total, we generated 15 synthetic contours for a given image-segmentation pair. One thousand two hundred twenty-four unfiltered/filtered radiomic features were extracted applying Pyradiomics, followed by stability assessment using ICC(1,1). Stable features identified in the internal population were then compared with an external population to discover and report robust features. Finally, we also investigated the impact of a wide range of filtering strategies on the stability of features. The percentage of unfiltered (filtered) features that remained robust subjected to segmentation variations were T2w-36% (81%), ADC-36% (94%), and SUB-43% (93%). Our findings suggest that segmentation variations can significantly impact radiomic feature stability but can be mitigated by including pre-filtering strategies as part of the feature extraction pipeline.

Methodology and technology for the development of a prognostic MRI-based radiomic model for the outcome of head and neck cancer patients.

The purpose of this study was to establish a methodology and technology for the development of an MRI-based radiomic signature for prognosis of overall survival (OS) in nasopharyngeal cancer from non-endemic areas. The signature was trained using 1072 features extracted from the main tumor in T1-weighted and T2-weighted images of 142 patients. A model with 2 radiomic features was obtained (RAD model). Tumor volume and a signature obtained by training the model on permuted survival data (RADperm model) were used as a reference. A 10-fold cross-validation was used to validate the signature. Harrel's C-index was used as performance metric. A statistical comparison of the RAD, RADperm and volume was performed using Wilcoxon signed rank tests. The C-index for the RAD model was higher compared to the one of the RADperm model (0.69±0.08 vs 0.47±0.05), which ensures absence of overfitting. Also, the signature obtained with the RAD model had an improved C-index compared to tumor volume alone (0.69±0.08 vs 0.65±0.06), suggesting that the radiomic signature provides additional prognostic information.

Role of IMRT/VMAT-Based Dose and Volume Parameters in Predicting 5-Year Local Control and Survival in Nasopharyngeal Cancer Patients.

Objective: This study aimed to look into the relationship between intensity-modulated-radiotherapy (IMRT)- or volumetric-modulated-arc-therapy (VMAT)-based dose-volume parameters and 5-year outcome for a consecutive series of non-metastatic nasopharyngeal cancer (NPC) patients (pts) treated in a single institution in a non-endemic area in order to identify potential prognostic factors. Materials and methods: A retrospective analysis of consecutive non-metastatic NPC pts treated curatively with IMRT or VMAT and chemotherapy (CHT) between 2004 and 2014 was conducted. One patient was in stage I (0.7%), and 24 pts (17.5%) were in stage II, 38 pts (27.7%) in stage III, 29 pts (21.2%) in stage IVA, and 45 pts (32.8%) in stage IVB. Five pts (3.6%) received radiotherapy (RT) alone. Of the remaining 132 pts (96.4%), 30 pts (21.9%) received CHT concomitant to RT, and 102 pts (74.4%) were treated with induction CHT followed by RT-CHT. IMRT was given with standard fractionation at a total dose of 70 Gy. Clinical outcomes investigated in the study were local control (LC), disease-free survival (DFS), and overall survival (OS). Kaplan-Meier (KM) analysis was performed for the outcomes considering dose and coverage parameters, staging, and RT technique. Results: Overall, 137 pts were eligible for this retrospective analysis. With a median follow-up of 70 months (range 12-143), actuarial rates at 5 years were LC 90.4, DFS 77.2, and OS 82.8%. For this preliminary study, T stage was dichotomized as T1, T2, T3 vs. T4. At 5 years, the group T1-T2-T3 reported an LC of 93%, a DFS of 79%, and an OS of 88%, whereas T4 pts reported LC, DFS, and OS, respectively, of 56, 50, and 78%. Pts with V95% > 95.5% had better LC (p = 0.006). Pts with D99% > 63.8 Gy had better LC (p = 0.034) and OS (p = 0.005). The threshold value of 43.2 cm3 of GTVT was prognostic for LC (p = 0.016). To predict the risk of local recurrence at 5 years, we constructed a nomogram which combined GTVT with D99% relative to HRPTV. Conclusions: We demonstrated the prognostic value of some dose-volume parameters, although in a retrospective series, this is potentially useful to improve planning procedure. In addition, for the first time in a non-endemic area, a threshold value of GTVT, prognostic for LC, has been confirmed.

Baseline MRI-Radiomics Can Predict Overall Survival in Non-Endemic EBV-Related Nasopharyngeal Carcinoma Patients.

Advanced stage nasopharyngeal cancer (NPC) shows highly variable treatment outcomes, suggesting the need for independent prognostic factors. This study aims at developing a magnetic resonance imaging (MRI)-based radiomic signature as a prognostic marker for different clinical endpoints in NPC patients from non-endemic areas. A total 136 patients with advanced NPC and available MRI imaging (T1-weighted and T2-weighted) were selected. For each patient, 2144 radiomic features were extracted from the main tumor and largest lymph node. A multivariate Cox regression model was trained on a subset of features to obtain a radiomic signature for overall survival (OS), which was also applied for the prognosis of other clinical endpoints. Validation was performed using 10-fold cross-validation. The added prognostic value of the radiomic features to clinical features and volume was also evaluated. The radiomics-based signature had good prognostic power for OS and loco-regional recurrence-free survival (LRFS), with C-index of 0.68 and 0.72, respectively. In all the cases, the addition of radiomics to clinical features improved the prognostic performance. Radiomic features can provide independent prognostic information in NPC patients from non-endemic areas.

An innovative gynecological HDR brachytherapy applicator system for treatment delivery and real-time verification.

The multichannel vaginal cylinder (MVC) applicator employed for gynecological high dose rate (HDR) brachytherapy increases dose delivery complexity, and thus makes the treatment more prone to errors. A quality assurance (QA) procedure tracking the source throughout dose delivery can detect dwell position and time errors in the multiple channels of the applicator. A new MVC system with integrated real time in vivo treatment delivery QA has been developed based on diodes embedded on the outer surface of the MVC. It has been pre-calibrated and verified using a non-clinical treatment plan with consecutive test positions and dwell times within each catheter, followed by the delivery of ten clinical plans of adjuvant vaginal cuff brachytherapy following hysterectomy for endometrial cancer. The non-clinical verification showed overall mean dwell position and time discrepancies between the nominal and measured treatment of -0.2 ±â€¯0.5 mm and -0.1 ±â€¯0.1 s (k = 1), respectively. The clinical plans showed mean positional discrepancies of 0.2 ±â€¯0.4 and 0.0 ±â€¯0.8 mm, for the central and peripheral catheters, respectively, and mean dwell time discrepancies of -0.1 ±â€¯0.2 and -0.0 ±â€¯0.1 s for central and peripheral catheters, respectively. The innovative prototype of the MVC system has shown the ability to track the source with sub-mm and sub-second accuracy, and demonstrated potential for its incorporation into the clinical routine.

High-dose-rate brachytherapy for high-grade vaginal intraepithelial neoplasia: a dosimetric analysis.

PURPOSE: Due to the rarity of vaginal intraepithelial neoplasia (VAIN), it is impossible to define the best treatment approach or to assess vaginal morbidity. However, brachytherapy (BT) could be a valuable choice for VAIN grade 3 (VAIN3). The aim of this paper was to report a single-institution study of the application of high-dose-rate BT and to evaluate clinical outcomes as well as to investigate the dose-effect relationship for vaginal stenosis. MATERIAL AND METHODS: We retrospectively collected hospital records and treatment plans of 14 consecutive women treated in our department from August 2010 to August 2016, with HDR-BT delivered using iridium-192 by a remote after-loading system. Doses in 3D-planned treatment based on computed tomography (CT) were prescribed in high-risk clinical target volume (HR-CTV) at the vaginal wall. Vaginal stenosis was defined as vaginal shortening/narrowing according to CTCAE4.1. The International Commission on Radiation Units & Measurements (ICRU) bladder and rectal points were used for dose report analysis. The posterior-inferior border of the symphysis points was used to derive reference points. The median age of the enrolled women was 60 years, and the median total radiation dose delivered was 35 Gy. RESULTS: During a median period of 15 days, the treatment was well tolerated, and no interruption was necessary. Acute toxicity was minimal, whereas late toxicity appeared in 4 patients as G2 and in 3 patients as G3 vaginal stenosis. Patients with stenosis G ≥ 2 received a higher median dose to the rectal point and were mainly over 60 years old. CONCLUSIONS: Patients with VAIN3 seemed to benefit from BT. It is generally assumed that the vagina is radio-resistant, and no constraints have yet been set, but sexual dysfunction after BT is an important cause of long-term distress. Finding applicable dose limits to the vagina could improve patients' quality of life.

Pre-implant magnetic resonance and transrectal ultrasound imaging in high-dose-rate prostate brachytherapy: comparison of prostate volumes, craniocaudal extents, and contours.

PURPOSE: The purpose of this study was to compare the prostate contours drawn by two radiation oncologists and one radiologist on magnetic resonance (MR) and transrectal ultrasound (TRUS) images. TRUS intra- and inter-fraction variability as well as TRUS vs. MR inter-modality and inter-operator variability were studied. MATERIAL AND METHODS: Thirty patients affected by localized prostate cancer and treated with interstitial high-dose-rate (HDR) prostate brachytherapy at the National Cancer Institute in Milan were included in this study. Twenty-five patients received an exclusive two-fraction (14 Gy/fraction) treatment, while the other 5 received a single 14 Gy fraction as a boost after external beam radiotherapy. The prostate was contoured on TRUS images acquired before (virtual US) and after (real US) needle implant by two radiation oncologists, whereas on MR prostate was independently contoured by the same radiation oncologists (MR1, MR2) and by a dedicated radiologist (MR3). Absolute differences of prostate volumes (│ΔV│) and craniocaudal extents (│Δdz│) were evaluated. The Dice's coefficient (DC) was calculated to quantify spatial overlap between MR contours. RESULTS: Significant difference was found between Vvirtual and Vlive (p < 0.001) for the first treatment fractions and between VMR1 and VMR2 (p = 0.043). Significant difference between cranio-caudal extents was found between dzvirtual and dzlive (p < 0.033) for the first treatment fractions, between dzvirtual of the first treatment fractions and dzMR1 (p < 0.001) and between dzMR1 and dzMR3 (p < 0.01). Oedema might be responsible for some of the changes in US volumes. Average DC values resulting from the comparison MR1 vs. MR2, MR1 vs. MR3 and MR2 vs. MR3 were 0.95 ± 0.04 (range, 0.82-0.99), 0.87 ± 0.04 (range, 0.73-0.91) and 0.87 ± 0.04 (range, 0.72-0.91), respectively. CONCLUSIONS: Our results demonstrate the importance of a multiprofessional approach to TRUS-guided HDR prostate brachytherapy. Specific training in MR and US prostate imaging is recommended for centers that are unfamiliar with HDR prostate brachytherapy.

Semiconductor real-time quality assurance dosimetry in brachytherapy.

With the increase in complexity of brachytherapy treatments, there has been a demand for the development of sophisticated devices for delivery verification. The Centre for Medical Radiation Physics (CMRP), University of Wollongong, has demonstrated the applicability of semiconductor devices to provide cost-effective real-time quality assurance for a wide range of brachytherapy treatment modalities. Semiconductor devices have shown great promise to the future of pretreatment and in vivo quality assurance in a wide range of brachytherapy treatments, from high-dose-rate (HDR) prostate procedures to eye plaque treatments. The aim of this article is to give an insight into several semiconductor-based dosimetry instruments developed by the CMRP. Applications of these instruments are provided for breast and rectal wall in vivo dosimetry in HDR brachytherapy, urethral in vivo dosimetry in prostate low-dose-rate (LDR) brachytherapy, quality assurance of HDR brachytherapy afterloaders, HDR pretreatment plan verification, and real-time verification of LDR and HDR source dwell positions.

Comparison of different treatment planning optimization methods for vaginal HDR brachytherapy with multichannel applicators: A reduction of the high doses to the vaginal mucosa is possible.

PURPOSE: A direct planning approach with multi-channel vaginal cylinders (MVCs) used for HDR brachytherapy of vaginal cancers is particularly challenging. Purpose of this study was to compare the dosimetric performances of different forward and inverse methods used for the optimization of MVC-based vaginal treatments for endometrial cancer, with a particular attention to the definition of strategies useful to limit the high doses to the vaginal mucosa. METHODS: Twelve postoperative vaginal HDR brachytherapy treatments performed with MVCs were considered. Plans were retrospectively optimized with three different methods: Dose Point Optimization followed by Graphical Optimization (DPO + GrO), Inverse Planning Simulated Annealing with two different class solutions as starting conditions (surflPSA and homogIPSA) and Hybrid Inverse Planning Optimization (HIPO). Several dosimetric parameters related to target coverage, hot spot extensions and sparing of organs at risk were analyzed to evaluate the quality of the achieved treatment plans. Dose homogeneity index (DHI), conformal index (COIN) and a further parameter quantifying the proportion of the central catheter loading with respect to the overall loading (i.e., the central catheter loading index: CCLI) were also quantified. RESULTS: The achieved PTV coverage parameters were highly correlated with each other but uncorrelated with the hot spot quantifiers. HomogIPSA and HIPO achieved higher DHIs and CCLIs and lower volumes of high doses than DPO + GrO and surflPSA. CONCLUSIONS: Within the investigated optimization methods, HIPO and homoglPSA showed the highest dose homogeneity to the target. In particular, homogIPSA resulted also the most effective in reducing hot spots to the vaginal mucosa.

Physicists' views on hadrontherapy: a survey of members of the Italian Association of Medical Physics (AIFM).

BACKGROUND: This study was based on a survey to investigate perceptions of hadrontherapy of the members of the Italian Association of Medical Physics (AIFM). The survey was digitally submitted to the 991 members between the end of January and the beginning of April 2016. METHODS: A 19-item questionnaire was designed focusing on advantages and disadvantages of hadrontherapy, current status and possible future improvements, and need and opportunities for future investments in Italy and abroad. Information about professional qualifications, main fields of clinical involvement and specific competencies of the respondents was also collected. RESULTS: The survey was completed by 121 AIFM members (response rate 12.2%). In the answers collected, it was shown that medical physicists expressed interest in hadrontherapy mainly for reasons of personal interest rather than for professional needs (90% ± 2.5% vs. 52% ± 4.3% of the respondents, respectively), with a good knowledge of the related basic aspects as well as of the pros and cons of its application. However, poor knowledge of the current status of hadrontherapy was observed among the medical physicists not directly involved at a professional level, who were less than 3% of the physicists working in radiotherapy. CONCLUSIONS: In light of these results, the implementation of new training and education initiatives should be devised to promote a deeper and global knowledge of hadrontherapy-related issues, not only from a theoretical point of view but also in practical terms. Moreover, a close collaboration between highly specialized medical physicists employed in hadrontherapy centers and others in oncology hospitals should be -encouraged.

In vivo rectal wall measurements during HDR prostate brachytherapy with MOSkin dosimeters integrated on a trans-rectal US probe: Comparison with planned and reconstructed doses.

BACKGROUND AND PURPOSE: To study if MOSkin detectors coupled to a trans-rectal ultrasound (TRUS) probe may be used for in vivo dosimetry on the rectal wall surface during US-based HDR prostate brachytherapy and to quantify possible discrepancies between planned and delivered doses. MATERIALS AND METHODS: MOSkins are a specific type of MOSFET dosimeter optimized to measure dose in steep dose gradients on interfaces. Two MOSkins were assembled on a TRUS probe used for on-line treatment planning. Measurements of the dose to the rectal wall were performed over 18 treatment sessions and compared to the doses calculated on the pre-treatment plan (DPRE) and reconstructed on post-treatment images (DPOST). RESULTS: Averages of the absolute differences between MOSkin readings and DPRE, MOSkin readings and DPOST and DPRE and DPOST were 6.7 ± 5.1%, 3.6 ± 1.9% and 6.3 ± 4.7%, respectively. Agreement between measurements and DPOST was significantly better than between measurements and DPRE (p=0.002) and DPRE and DPOST (p=0.004). Discrepancy between DPOST and DPRE correlated with the time required for treatment planning. CONCLUSION: MOSkin dosimeters integrated to the TRUS probe proved to be an accurate instrument for measuring the dose delivered to the rectal wall in HDR prostate brachytherapy. The delivered doses may differ significantly from those calculated in the treatment plan.

The Mice Drawer System (MDS) experiment and the space endurance record-breaking mice.

The Italian Space Agency, in line with its scientific strategies and the National Utilization Plan for the International Space Station (ISS), contracted Thales Alenia Space Italia to design and build a spaceflight payload for rodent research on ISS: the Mice Drawer System (MDS). The payload, to be integrated inside the Space Shuttle middeck during transportation and inside the Express Rack in the ISS during experiment execution, was designed to function autonomously for more than 3 months and to involve crew only for maintenance activities. In its first mission, three wild type (Wt) and three transgenic male mice over-expressing pleiotrophin under the control of a bone-specific promoter (PTN-Tg) were housed in the MDS. At the time of launch, animals were 2-months old. MDS reached the ISS on board of Shuttle Discovery Flight 17A/STS-128 on August 28(th), 2009. MDS returned to Earth on November 27(th), 2009 with Shuttle Atlantis Flight ULF3/STS-129 after 91 days, performing the longest permanence of mice in space. Unfortunately, during the MDS mission, one PTN-Tg and two Wt mice died due to health status or payload-related reasons. The remaining mice showed a normal behavior throughout the experiment and appeared in excellent health conditions at landing. During the experiment, the mice health conditions and their water and food consumption were daily checked. Upon landing mice were sacrificed, blood parameters measured and tissues dissected for subsequent analysis. To obtain as much information as possible on microgravity-induced tissue modifications, we organized a Tissue Sharing Program: 20 research groups from 6 countries participated. In order to distinguish between possible effects of the MDS housing conditions and effects due to the near-zero gravity environment, a ground replica of the flight experiment was performed at the University of Genova. Control tissues were collected also from mice maintained on Earth in standard vivarium cages.

Mice Drawer System: phase c/d development and perspective.

MDS (Mice Drawer System) is the Facility that will support the research on board the International Space Station (ISS). Funded by ASI with Laben as industrial Prime Contractor, MDS will also permit its utilisation for other research programs with mice. The most attractive feature of MDS is that six mice can he kept separate inside dedicated and isolated cages. This permits to perform six experiments in parallel, one for each mouse. In the first utilisation flight of MDS facility the selected experiment is devoted to study human bone formation and specific countermeasures to prevent osteoporosis using mice under microgravity conditions as a model.