Publications

PURPOSE: To constrain the risk of severe toxicity in radiotherapy and radiosurgery, precise volume delineation of organs at risk is required. This task is still manually performed, which is time-consuming and prone to observer variability. To address these issues, and as alternative to atlas-based segmentation methods, machine learning techniques, such as support vector machines (SVM), have been recently presented to segment subcortical structures on magnetic resonance images (MRI). METHODS: SVM is proposed to segment the brainstem on MRI in multicenter brain cancer context. A dataset composed by 14 adult brain MRI scans is used to evaluate its performance. In addition to spatial and probabilistic information, five different image intensity values (IIVs) configurations are evaluated as features to train the SVM classifier. Segmentation accuracy is evaluated by computing the Dice similarity coefficient (DSC), absolute volumes difference (AVD) and percentage volume difference between automatic and manual contours. RESULTS: Mean DSC for all proposed IIVs configurations ranged from 0.89 to 0.90. Mean AVD values were below 1.5 cm(3), where the value for best performing IIVs configuration was 0.85 cm(3), representing an absolute mean difference of 3.99% with respect to the manual segmented volumes. CONCLUSION: Results suggest consistent volume estimation and high spatial similarity with respect to expert delineations. The proposed approach outperformed presented methods to segment the brainstem, not only in volume similarity metrics, but also in segmentation time. Preliminary results showed that the approach might be promising for adoption in clinical use.

PURPOSE: Accurate delineation of organs at risk (OARs) on computed tomography (CT) image is required for radiation treatment planning (RTP). Manual delineation of OARs being time consuming and prone to high interobserver variability, many (semi-) automatic methods have been proposed. However, most of them are specific to a particular OAR. Here, an interactive computer-assisted system able to segment various OARs required for thoracic radiation therapy is introduced. METHODS: Segmentation information (foreground and background seeds) is interactively added by the user in any of the three main orthogonal views of the CT volume and is subsequently propagated within the whole volume. The proposed method is based on the combination of watershed transformation and graph-cuts algorithm, which is used as a powerful optimization technique to minimize the energy function. The OARs considered for thoracic radiation therapy are the lungs, spinal cord, trachea, proximal bronchus tree, heart, and esophagus. The method was evaluated on multivendor CT datasets of 30 patients. Two radiation oncologists participated in the study and manual delineations from the original RTP were used as ground truth for evaluation. RESULTS: Delineation of the OARs obtained with the minimally interactive approach was approved to be usable for RTP in nearly 90% of the cases, excluding the esophagus, which segmentation was mostly rejected, thus leading to a gain of time ranging from 50% to 80% in RTP. Considering exclusively accepted cases, overall OARs, a Dice similarity coefficient higher than 0.7 and a Hausdorff distance below 10 mm with respect to the ground truth were achieved. In addition, the interobserver analysis did not highlight any statistically significant difference, at the exception of the segmentation of the heart, in terms of Hausdorff distance and volume difference. CONCLUSIONS: An interactive, accurate, fast, and easy-to-use computer-assisted system able to segment various OARs required for thoracic radiation therapy has been presented and clinically evaluated. The introduction of the proposed system in clinical routine may offer valuable new option to radiation oncologists in performing RTP.

Delineation of organs at risk (OARs) is a crucial step in surgical and treatment planning in brain cancer, where precise OARs volume delineation is required. However, this task is still often manually performed, which is time-consuming and prone to observer variability. To tackle these issues a deep learning approach based on stacking denoising auto-encoders has been proposed to segment the brainstem on magnetic resonance images in brain cancer context. Additionally to classical features used in machine learning to segment brain structures, two new features are suggested. Four experts participated in this study by segmenting the brainstem on 9 patients who underwent radiosurgery. Analysis of variance on shape and volume similarity metrics indicated that there were significant differences (p<0.05) between the groups of manual annotations and automatic segmentations. Experimental evaluation also showed an overlapping higher than 90% with respect to the ground truth. These results are comparable, and often higher, to those of the state of the art segmentation methods but with a considerably reduction of the segmentation time.

OBJECTIVES: There are no guidelines regarding the surgical approach for spontaneous pneumothorax. It has been reported, however, that the risk of recurrence following video-assisted thoracic surgery is higher than that following open thoracotomy (OT). The objective of this study was to determine whether this higher risk of recurrence following video-assisted thoracic surgery could be attributable to differences in intraoperative parenchymal resection and the pleurodesis technique. METHODS: Data for 7647 patients operated on for primary or secondary spontaneous pneumothorax between 1 January 2005 and 31 December 2012 were extracted from Epithor(R), the French national database. The type of pleurodesis and parenchymal resection was collected. Outcomes were (i) bleeding, defined as postoperative pleural bleeding; (ii) pulmonary and pleural complications, defined as atelectasis, pneumonia, empyema, prolonged ventilation, acute respiratory distress syndrome and prolonged air leaks; (iii) in-hospital length of stay and (iv) recurrence, defined as chest drainage or surgery for a second pneumothorax. RESULTS: Of note, 6643 patients underwent videothoracoscopy and 1004 patients underwent OT. When compared with the thoracotomy group, the videothoracoscopy group was associated with more parenchymal resections (62.4 vs 80%, P = 0.01), fewer mechanical pleurodesis procedures (93 vs 77.5%, P < 10(-3)), fewer postoperative respiratory complications (12 vs 8.2%, P = 0.01), fewer cases of postoperative pleural bleeding (2.3 vs 1.4%, P = 0.04) and shorter hospital lengths of stay (16 vs 9 days, P = 0.01). The recurrence rate was 1.8% (n = 18) in the thoracotomy group versus 3.8% (n = 254) in the videothoracoscopy group (P = 0.01). The median time between surgery and recurrence was 3 months (range: 1-76 months). CONCLUSIONS: In the surgical management of spontaneous pneumothorax, videothoracoscopy is associated with a higher rate of recurrence than OT. This difference might be attributable to differences in the pleurodesis technique rather than differences in the parenchymal resection.

Previous studies reported a 2- to 17-fold higher risk of aortic complications (dilation or dissection) in patients with giant-cell arteritis (GCA). We aimed to determine whether or not GCA patients with large-vessel involvement demonstrated by positron emission tomography with F-fluorodeoxyglucose combined with computed tomography (FDG-PET/CT) have a higher risk of aortic complications. We conducted a retrospective multicenter study between 1995 and 2014. Patients were included if they fulfilled at least 3 American College of Rheumatology criteria for GCA, or 2 criteria associated with extratemporal biopsy-proven giant-cell vasculitis; they underwent at least 1 FDG-PET/CT scan at diagnosis or during follow-up; and the morphology of the aorta was assessed by medical imaging at diagnosis. Patients with an aortic complication at the time of diagnosis were excluded. Of the 130 patients included [85 women (65%), median age 70 (50-86)], GCA was biopsy proven in 77 (59%). FDG-PET/CT was performed at diagnosis in 63 (48%) patients and during the follow-up period in the 67 (52%) remaining patients. FDG-PET/CT was positive in 38/63 (60%) patients at diagnosis and in 31/67 (46%) patients when performed during follow-up (P = NS). One hundred four patients (80%) underwent at least 1 morphological assessment of the aorta during follow-up. Nine (9%) patients developed aortic complications (dilation in all and dissection in 1) at a median time of 33 (6-129) months after diagnosis. All of them displayed large-vessel inflammation on previous FDG-PET/CT. A positive FDG-PET/CT was significantly associated with a higher risk of aortic complications (P = 0.004).In our study, a positive FDG-PET/CT was associated with an increased risk of aortic complications at 5 years.