Liliane Ramus

DENTALMAPS: Automatic Dental Delineation for Radiotherapy Planning in Head and Neck Cancer

PURPOSE To propose an automatic atlas-based segmentation framework of the dental structures, called Dentalmaps, and to assess its accuracy and relevance to guide dental care in the context of intensity-modulated radiotherapy. METHODS AND MATERIALS A multi-atlas-based segmentation, less sensitive to artifacts than previously published head-and-neck segmentation methods, was used. The manual segmentations of a 21-patient database were first deformed onto the query using nonlinear registrations with the training images and then fused to estimate the consensus segmentation of the query. RESULTS The framework was evaluated with a leave-one-out protocol. The maximum doses estimated using manual contours were considered as ground truth and compared with the maximum doses estimated using automatic contours. The dose estimation error was within 2-Gy accuracy in 75% of cases (with a median of 0.9 Gy), whereas it was within 2-Gy accuracy in 30% of cases only with the visual estimation method without any contour, which is the routine practice procedure. CONCLUSIONS Dose estimates using this framework were more accurate than visual estimates without dental contour. Dentalmaps represents a useful documentation and communication tool between radiation oncologists and dentists in routine practice. Prospective multicenter assessment is underway on patients extrinsic to the database.

Construction of patient specific atlases from locally most similar anatomical pieces

Radiotherapy planning requires accurate delineations of the critical structures. To avoid manual contouring, atlas-based segmentation can be used to get automatic delineations. However, the results strongly depend on the chosen atlas, especially for the head and neck region where the anatomical variability is high. To address this problem, atlases adapted to the patients anatomy may allow for a better registration, and already showed an improvement in segmentation accuracy. However, building such atlases requires the definition of a criterion to select among a database the images that are the most similar to the patient. Moreover, the inter-expert variability of manual contouring may be high, and therefore bias the segmentation if selecting only one image for each region. To tackle these issues, we present an original method to design a piecewise most similar atlas. Given a query image, we propose an efficient criterion to select for each anatomical region the K most similar images among a database by considering local volume variations possibly induced by the tumor. Then, we present a new approach to combine the K images selected for each region into a piecewise most similar template. Our results obtained with 105 CT images of the head and neck show that our method reduces the over-segmentation seen with an average atlas while being robust to inter-expert manual segmentation variability.

Assessing selection methods in the context of multi-atlas based segmentation

In atlas-based segmentation, using one single atlas for segmenting all patients introduces a bias. Multi-atlas techniques overcome this drawback by selecting and fusing the most appropriate atlases among a database for a given patient. Globally assessing different multi-atlas strategies provides a biased evaluation of the atlas selection methods. To address this problem, we propose to evaluate atlas selection methods independently from the number of atlases selected and from the atlas fusion step. Briefly, we first cluster the selection methods on the basis of rank correlation and then assess each sub-group of methods with respect to a sub-group of reference selection methods. We apply our method to 105 images of the head and neck region.

Radiotherapy and radiology: Joint efforts for modern radiation planning and practice

With new irradiation techniques, the dose can be better matched to the contours of the tumour. The corollary is that greater precision is required. Recent intercomparison studies of treatment plans have emphasized the need to harmonise contouring practices. More of a consensus approach is based on using adaptive imaging modalities, expert group recommendations and automatic segmentation atlases, on harmonisation of dosimetric decisions through employing exhaustive nomograms for organs at risk, and on indexes for choosing optimal treatment plans. On another level, quality assurance and data pooling programmes have been set up, making use of DICOM-RT data transfer (image networks). The combination of several irradiation techniques (for example, intensity-modulated conformal radiation therapy plus CyberKnife(®) boost and re-irradiation), making it possible to irradiate tumours better, requires the cumulative doses to be recorded by dose summation software. Real awareness has been achieved in recent years as regards improving the quality of treatment, pooling data and harmonising practices.

Atlas de contourage automatique des dents pour l'optimisation des soins dentaires

ive de 40 à 54 Gy à raison de cinq fractions e 2 Gy par semaine, uis ou non un complément de 10 à 14 Gy dans les ganglions cerviaux atteints histologiquement. Une radiothérapie palliative de 30 y en 10 séances a été délinée à deux patients atteints pour deux ’un cancer médullaire et un d’un cancer indifférencié. Pour tous les as de cancers papillaires une irathérapie à 100 mCI a été délivrée vant la radiothérapie. ésultats.– L’évolution a été différente selon type histologique. En ce ui concerne le cancer papillaire ; quatre patients étaient en situaion de rémission, avec un recul variant entre neuf mois et cinq ans uis perdus de vue, deux patients ont vu se développer des métatases pulmonaires, hépatiques ± cérébrales et trois autres ont une écidive ganglionnaire avec métastase pulmonaire pour un avec un ecul de deux à six ans puis sont décédés. Quant au cancer médulaire, deux patients étaient en vie en situation de rémission avec es reculs de sept et neuf ans, une autre patiente a été perdue de ue en situation de rémission après 18 mois ; une récidive ganglionaire est survenue chez deux patients non irradies respectivement u bout d’un et quatre ans, un a été irradié et était en situation de émission complète depuis. Deux patients ont vu se développer des étastases osseuses et pulmonaires, respectivement après neuf et ix ans d’évolution. Deux patients sont décédés neuf mois après a fin de la radiothérapie et au cours de l’irradiation. Enfin pour le ancer indifférencié ; une patiente était en situation de rémission omplète avec un recul de 14 ans, une patiente était en situation de écidive ganglionnaire sept mois après la fin de l’irradiation puis a té perdue de vue, deux patients sont décédées une semaine après ’irradiation ; la dernière a refusé la radiothérapie et a été perdue e vue en mauvais état. onclusion.– Notre série était caractérisée par des tumeurs évoluées ue ce soit sur le plan ganglionnaire ou tumoral, ce qui explique en artie nos résultats thérapeutiques. La radiothérapie étant indiquée ans les formes évoluées, l’exérèse incomplète, les foyers résiduels t dans un but palliatif.

Using consensus measures for atlas construction

Atlas-based segmentation has been shown to provide promising results to delineate critical structures for radiotherapy planning. However, it requires to have a reference image with its reference segmentation available. Classical methods used to build an average segmentation can lead to over-segmentation in case of high variability among the manual segmentations. We propose in this paper a consensus-based approach to construct a reference segmentation from a database of manually delineated images. We first compute local consensus measures to estimate a variability map, and then deduct from it a consensus segmentation. Finally, the proposed method is evaluated using a dataset of 64 manually delineated images of the head and neck region.