Application of radial ray based segmentation to cervical lymph nodes in CT images.

The 3D-segmentation of lymph nodes in computed tomography images is required for staging and disease progression monitoring. Major challenges are shape and size variance, as well as low contrast, image noise, and pathologies. In this paper, radial ray based segmentation is applied to lymph nodes. From a seed point, rays are cast into all directions and an optimization technique determines a radius for each ray based on image appearance and shape knowledge. Lymph node specific appearance cost functions are introduced and their optimal parameters are determined. For the first time, the resulting segmentation accuracy of different appearance cost functions and optimization strategies is compared. Further contributions are extensions to reduce the dependency on the seed point, to support a larger variety of shapes, and to enable interaction. The best results are obtained using graph-cut on a combination of the direction weighted image gradient and accumulated intensities outside a predefined intensity range. Evaluation on 100 lymph nodes shows that with an average symmetric surface distance of 0.41 mm the segmentation accuracy is close to manual segmentation and outperforms existing radial ray and model based methods. The method's inter-observer-variability of 5.9% for volume assessment is lower than the 15.9% obtained using manual segmentation.

Merging person-specific bio-markers for predicting oral cancer recurrence through an ontology.

One of the major problems related to cancer treatment is its recurrence. Without knowing in advance how likely the cancer will relapse, clinical practice usually recommends adjuvant treatments that have strong side effects. A way to optimize treatments is to predict the recurrence probability by analyzing a set of bio-markers. The NeoMark European project has identified a set of preliminary bio-markers for the case of oral cancer by collecting a large series of data from genomic, imaging, and clinical evidence. This heterogeneous set of data needs a proper representation in order to be stored, computed, and communicated efficiently. Ontologies are often considered the proper mean to integrate biomedical data, for their high level of formality and for the need of interoperable, universally accepted models. This paper presents the NeoMark system and how an ontology has been designed to integrate all its heterogeneous data. The system has been validated in a pilot in which data will populate the ontology and will be made public for further research.

Automated skeleton based multi-modal deformable registration of head&neck datasets.

This paper presents a novel skeleton based method for the registration of head&neck datasets. Unlike existing approaches it is fully automated, spatial relation of the bones is considered during their registration and only one of the images must be a CT scan. An articulated atlas is used to jointly obtain a segmentation of the skull, the mandible and the vertebrae C1-Th2 from the CT image. These bones are then successively rigidly registered with the moving image, beginning at the skull, resulting in a rigid transformation for each of the bones. Linear combinations of those transformations describe the deformation in the soft tissue. The weights for the transformations are given by the solution of the Laplace equation. Optionally, the skin surface can be incorporated. The approach is evaluated on 20 CT/MRI pairs of head&neck datasets acquired in clinical routine. Visual inspection shows that the segmentation of the bones was successful in all cases and their successive alignment was successful in 19 cases. Based on manual segmentations of lymph nodes in both modalities, the registration accuracy in the soft tissue was assessed. The mean target registration error of the lymph node centroids was 5.33 +/- 2.44 mm when the registration was solely based on the deformation of the skeleton and 5.00 +/- 2.38 mm when the skin surface was additionally considered. The method's capture range is sufficient to cope with strongly deformed images and it can be modified to support other parts of the body. The overall registration process typically takes less than 2 minutes.

Enabling heterogeneous data integration and biomedical event prediction through ICT: the test case of cancer reoccurrence.

Early prediction of cancer reoccurrence constitutes a challenge for oncologists and surgeons. This chapter describes one ongoing experience, the EU-Project NeoMark, where scientists from different medical and biology research fields joined efforts with Information Technology experts to identify methods and algorithms that are able to early predict the reoccurrence risk for one of the most devastating tumors, the oral cavity squamous cell carcinoma (OSCC). The challenge of NeoMark is to develop algorithms able to identify a "signature" or bio-profile of the disease, by integrating multiscale and multivariate data from medical images, genomic profile from tissue and circulating cells RNA, and other medical parameters collected from patients before and after treatment. A limited number of relevant biomarkers will be identified and used in a real-time PCR device for early detection of disease reoccurrence.

3D Assessment of Lymph Nodes vs. RECIST 1.1.

RATIONALE AND OBJECTIVES: In today's clinical practice, the size of lymph nodes is assessed by measuring the long and the short axis in the axial plane. This study compares this approach with three-dimensional (3D) assessment. MATERIALS AND METHODS: For a representative set of 49 lymph nodes, the axes in the axial plane have been measured and a 3D model has been created manually. Based on the 3D model, the real axial long and short axis as well as the three 3D axes and the volume have been computed and compared to the measured axial axes. RESULTS: The inter-observer variability is around 10% for all measured lengths and almost 16% for the computed volume. The average relative error of the measured long (short) axial axis is 9.73% (24.57%) to the computed axial axis and 25.05% (19.97%) to the computed 3D axis, respectively. The product of the axial long axis and the square of the axial short axis provides best correlation to the volume. CONCLUSION: This study confirms Response Evaluation Criteria In Solid Tumours 1.1 that measuring the short axis is more robust than measuring the long axis because of less impact of the node's spatial orientation. Nonetheless it is shown that considering both axes is a better prognostic factor for the volume than measuring the short axis only.