L. Boldrini

Recommendations on how to establish evidence from auto-segmentation software in radiotherapy

http://dx.doi.org/10.1016/j.radonc.2014.09.014 0167-8140/ 2014 Elsevier Ireland Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/3.0/). ⇑ Corresponding author. Address: Radiation Oncology Department – Gemelli ART, Università Cattolica del Sacro Cuore, Largo A. Gemelli, 1, 00168 Rome, Italy. E-mail address: lucaboldrini@hotmail.it (L. Boldrini). Vincenzo Valentini , Luca Boldrini a,⇑, Andrea Damiani , Ludvig P. Muren c

Clinical validation of atlas-based auto-segmentation of pelvic volumes and normal tissue in rectal tumors using auto-segmentation computed system

Abstract Purpose. To evaluate in two different settings – clinical practice and education/training – the reliability, time efficiency and the ideal sequence of an atlas-based auto-segmentation system in pelvic delineation of locally advanced rectal cancer. Methods. Fourteen consecutive patients were selected between October and December 2011. The images of four were used as an atlas and 10 used for validation. Two independent operators participated: a Delineator to contour and a Reviewer to perform an independent check (IC). The CTV, pelvic subsites and organs at risk were contoured in four different sequences. These included A: manual; B: auto-segmentation; C: auto-segmentation + manual revision; and D: manual + auto-segmentation + manual revision. Contouring was performed by the Delineator using the same planning CT. All of them underwent an IC by a Reviewer. The time required for all the contours were recorded and overlapping evaluation was assessed using a Dice coefficient. Results. In the clinical practice setting there have been 13 minutes time saved between sequences A versus sequences B (from 38 to 25 minutes, p = 0.002), a mean Dice coefficient in favor of sequences A for CTV and all subsites (p = 0.0195). In the educational/training setting there have been 35.2 minutes time saved between sequences C and D 8 (from 73.1 min to 37.9 min, p = 0.002). Conclusion. The preliminary data suggest that the use of an atlas-based auto-contouring system may help improve efficiencies in contouring in the clinical practice setting and could have a tutorial role in the educational/training setting.

Automatic delineation for replanning in nasopharynx radiotherapy: What is the agreement among experts to be considered as benchmark?

Abstract Background and purpose. Anatomic changes during head and neck radiotherapy require replanning. The primary aim of this study is the definition of the agreement among experts in the head and neck automatic delineation frame to use as benchmark. The secondary goal is to assess the reliability of automatic delineation for nasopharynx radiotherapy and time saving. Material and methods. A computed tomography (CT) scan was acquired in 10 nasopharynx patients along intensity-modulated radiotherapy (IMRT) treatment for replanning. Deformable registration with replanning autocontouring of the structures was performed using VelocityAI 2.3© software defining Structure Set A. The optimization of these contours was obtained through revision by a skilled operator, drawing Structure Set B. An ex novo Structure Set C was segmented on the replanning CT-scan by an expert delineation team. The mean Dices Similarity Index (mDSI) was calculated between Structure Set A and B, A and C, and between B and C for each volume. All segmentation times for organs at risk (OARs) and clinical target volume (CTV) were recorded and compared. Results. We validated the replanning autocontoured Structure Sets for 10 patients. For volumetric analysis we observed mDSI values of 0.87 for the OARs, 0.70 for nodes, 0.90 for CTV in the Structure Set A-B comparison and respectively of 0.74, 0.63 and 0.78 for the Structure Set A-C one, and 0.78, 0.78 and 0.85 for Structure Set B-C, which represents the existing expert based benchmark. We calculated a mean saved time in Structure Set B of 30 minutes. Conclusions. Autocontouring procedures offer considerable segmentation time saving with acceptable reliability of the contours, even if an independent check procedure for their optimization is still required to increase their adherence to referential benchmark gold standard among experts, which stands at a 0.80 DSI value.

Automatic segmentation software in locally advanced rectal cancer: READY (REsearch program in Auto Delineation sYstem)-RECTAL 02: prospective study.

To validate autocontouring software (AS) in a clinical practice including a two steps delineation quality assurance (QA) procedure. The existing delineation agreement among experts for rectal cancer and the overlap and time criteria that have to be verified to allow the use of AS were defined. Median Dice Similarity Coefficient (MDSC), Mean slicewise Hausdorff Distances (MSHD) and Total-Time saving (TT) were analyzed. Two expert Radiation Oncologists reviewed CT-scans of 44 patients and agreed the reference-CTV: the first 14 consecutive cases were used to populate the software Atlas and 30 were used as Test. Each expert performed a manual (group A) and an automatic delineation (group B) of 15 Test patients. The delineations were compared with the reference contours. The overlap between the manual and automatic delineations with MDSC and MSHD and the TT were analyzed. Three acceptance criteria were set: MDSC ≥ 0.75, MSHD ≤1mm and TT sparing ≥ 50%. At least 2 criteria had to be met, one of which had to be TT saving, to validate the system. The MDSC was 0.75, MSHD 2.00 mm and the TT saving 55.5% between group A and group B. MDSC among experts was 0.84. Autosegmentation systems in rectal cancer partially met acceptability criteria with the present version.

Moddicom: a Complete and Easily Accessible Library for Prognostic Evaluations Relying on Image Features

Decision Support Systems (DSSs) are increasingly exploited in the area of prognostic evaluations. For predicting the effect of therapies on patients, the trend is now to use image features, i.e. information that can be automatically computed by considering images resulting by analysis. The DSSs application as predictive tools is particularly suitable for cancer treatment, given the peculiarities of the disease -which is highly localised and lead to significant social costs- and the large number of images that are available for each patient. At the state of the art, there exists tools that allow to handle image features for prognostic evaluations, but they are not designed for medical experts. They require either a strong engineering or computer science background since they do not integrate all the required functions, such as image retrieval and storage. In this paper we fill this gap by proposing Moddicom, a user-friendly complete library specifically designed to be exploited by physicians. A preliminary experimental analysis, performed by a medical expert that used the tool, demonstrates the efficiency and the effectiveness of Moddicom.

Preliminary Data Analysis in Healthcare Multicentric Data Mining: a Privacy-preserving Distributed Approach

The new era of cognitive health care systems offers a large amount of patient data that can be used to develop prediction models and clinical decision support systems. In this frame, the multi-institutional approach is strongly encouraged in order to reach more numerous samples for data mining and more reliable statistics. For these purposes, shared ontologies need to be developed for data management to ensure database semantic coherence in accordance with the various centers’ ethical and legal policies. Therefore, we propose a privacy-preserving distributed approach as a preliminary data analysis tool to identify possible compliance issues and heterogeneity from the agreed multi-institutional research protocol before training a clinical prediction model. This kind of preliminary analysis appeared fast and reliable and its results corresponded to those obtained using the traditional centralized approach. A real time interactive dashboard has also been presented to show analysis results and make the workflow swifter and easier.

INTERACTS (INTErventional Radiotherapy ACtive Teaching School) guidelines for quality assurance in choroidal melanoma interventional radiotherapy (brachytherapy) procedures

Eye plaque brachytherapy represents a safe and effective therapeutic approach for choroidal melanoma, combining clinical outcomes with an eye and visual preservation. As it represents a complex procedure, a specific quality assurance program is strongly suggested to improve patients and operators safety, and to reduce possible complications linked to surgical procedure and radiation exposure. The aim of this paper is to describe the INTERACTS (Interventional Radiotherapy Active Teaching School) guidelines for quality assurance in choroidal melanoma interventional radiotherapy (brachytherapy) used in our institution.

RadioBio data: A Moddicom Module to Predict Tumor Control Probability and Normal Tissue Complication Probability in Radiotherapy

In this work a system for analysing radiotherapy treatment planning dose-volume data is proposed. The work starts from the definition of a framework inside a statistical scripting environment (R) used for creating a software package. The analysis of dose-volume data in radiotherapy of malignant tumours is mandatory for evaluating the prescribed treatment and for feedback analysis of outcome, both in the direction of tumour control and in detection of parameters for estimating and predicting toxicity outcome. The statistical analysis of large amount of clinical data can be slowed by the lack of practice in statistical tools needed, by clinicians, to perform such kind of analysis. This is the reason that lead our working group in the creation of such a tool. Finally an example of clinical application of our software is given for the analysis of the outcome of patients undergoing to radiotherapy for prostate cancer.

Hybrid Tri-Co-60 MRI radiotherapy for locally advanced rectal cancer: An in silico evaluation

Highlights • Tri-Co-60 MRI radiotherapy (RT) is feasible in locally advanced rectal cancer.• Larger volumes of normal tissue receive low-moderate doses in Tri-Co-60 MRI RT.• Further studies on functional imaging applications and LinacMRI approach are needed.• Tri-Co-60 MRI might represent a safe irradiation technique for pelvic tumors.

Predicting tumour motion during the whole radiotherapy treatment: a systematic approach for thoracic and abdominal lesions based on real time MR

INTRODUCTION Aim of this study was to investigate the ability of pre-treatment four dimensional computed tomography (4DCT) to capture respiratory-motion observed in thoracic and abdominal lesions during treatment. Treatment motion was acquired using full-treatment cine-MR acquisitions. Results of this analysis were compared to the ability of 30 seconds (s) cine Magnetic Resonance (MR) to estimate the same parameters. METHODS A 4DCT and 30 s cine-MR (ViewRay, USA) were acquired on the simulation day for 7 thoracic and 13 abdominal lesions. Mean amplitude, intra- and inter-fraction amplitude variability, and baseline drift were extracted from the full treatment data acquired by 2D cine-MR, and correlated to the motion on pre-treatment 30 s cine-MR and 4DCT. Using the full treatment data, safety margins on the ITV, necessary to account for all motion variability from 4DCT observed during treatment, were calculated. Mean treatment amplitudes were 2 ± 1 mm and 5 ± 3 mm in the anteroposterior (AP) and craniocaudal (CC) direction, respectively. Differences between mean amplitude during treatment and amplitude on 4DCT or during 30 s cine-MR were not significant, but 30 s cine-MR was more accurate than 4DCT. Intra-fraction amplitude variability was positively correlated with both 30 s cine-MR and 4DCT amplitude. Inter-fraction amplitude variability was minimal. RESULTS Mean baseline drift over all fractions and patients equalled 1 ± 1 mm in both CC and AP direction, but drifts per fraction up to 16 mm (CC) and 12 mm (AP) were observed. Margins necessary on the ITV ranged from 0 to 8 mm in CC and 0 to 5 mm in AP direction. Neither amplitude on 4DCT nor during 30 s cine MR is correlated to the magnitude of drift or the necessary margins in both directions. CONCLUSION Lesions moving with small amplitude show limited amplitude variability throughout treatment, making passive motion management strategies seem adequate. However, other variations such as baseline drifts and shifts still cause significant geometrical uncertainty, favouring real-time monitoring and an active approach for all lesions influenced by respiratory motion.