New Software and Platforms
Bilateral Contracts and Grants with Industry
Partnerships and Cooperations
Bibliography
 PDF e-Pub

## Section: New Results

### Medical Image Analysis

#### 3D/2D Coronary Arteries Registration

Participants : Thomas Benseghir [correspondent] , Grégoire Malandain [Morpheme Team] , Régis Vaillant [GE-Healthcare] , Nicholas Ayache.

This work has been performed in colaboration with GE-Healthcare (Buc) and the Morpheme team at Inria SAM.

3D/2D Registration, Computed Tomography Angiography, X-ray Fluoroscopy, Coronary Arteries, Vascular Tree

Integrating vessel calcifications and occlusion information, extracted from pre-operative 3D CT angiography images into a live fluoroscopic 2D image can greatly improve the guidance of percutaneous coronary interventions. Such task requires a registration step that must provide relevant correspondences between these two complementary modalities. We are developing a framework aiming at preserving the topology of the vascular structures matched between both images.

Figure 3. From left to right: 1. initial pose estimate (3D centerlines projection in blue); 2. iterative closest point algorithm registered position (point-pairings in yellow); 3: proposed method registered position; 4: resulting fusion between the two modalities

#### Video Synchronization: An Approach Towards Endoscopic Re-localization

Participants : Anant Suraj Vemuri [correspondent] , Nicholas Ayache.

Endoscopy, Barrett's Esophagus, Re-localization, Electromagnetic Tracking

• Barrett’s esophagus is the pre-malignant lesion for the majority of patients with esophageal adenocarcinoma. The evolution of the disease involves endoscopic surveillance for patients every 3-6 months, according to the Seattle protocol.

• The approach is labor-intensive and the primary problem is the inter-operative re-localization of these biopsy sites to guide the treatment.

• In an earlier work we had proposed a general framework for inter-operative biopsy site re-localization framework by introducing an Electro-magnetic tracking system (EMTS) into the loop and providing a way to inter-operatively register video sequences to provide a guided navigation in the esophagus.

• This work has been extended further to fit the operating room workflow. Two external landmarks have been added to the system setup as shown in Fig.4 , to obtain a complete reference frame with respect to the patient and to make the registration, patient specific [38] . The patient-localized reference frame allows the recovery of complete $SE\left(3\right)$ including the roll angle about the esophageal axis.

Figure 4. (Left) The orange circular markings indicate the position of the sensors taken as anatomical landmarks to form the reference frame for the patient. (Right) System setup in the operating room.

#### A sparse Bayesian framework for non-rigid registration

Participants : Loic Le Folgoc [correspondent] , Hervé Delingette, Antonio Criminisi, Nicholas Ayache.

This work has been partly supported by Microsoft Research - Inria joint laboratory through its PhD Scholarship Programme and the European Research Council through the ERC Advanced Grant MedYMA (on Biophysical Modeling and Analysis of Dynamic Medical Images).

Registration, Automatic Relevance Determination, Uncertainty Quantification

Figure 5. (Left) Mesh contour propagated to end systole via the registration output; (Right) Spatial uncertainty visualized as a tensor map.

#### Segmentation and anatomic variability of the cochlea and other temporal bone structures from medical images

Participants : Thomas Demarcy [correspondent] , Hervé Delingette, Clair Vandersteen, Dan Gnansia [Oticon Medical] , Nicholas Ayache.

This work is funded by a CIFRE grant involving Oticon Medical (Vallauris) and performed in collaboration with the IUFC Nice (Pr. Guevara) and CHU Nice (Pr. Raffaelli) .

image segmentation ; surgery planning ; shape modelling ; anatomic variability ; cochlear implant ; temporal bone

• We applied semi-automatic segmentation methods to extract anatomical structures on the inner ear on both micro-CT and CT scan images.

• $\mu$-CT and CT images acquired on the same subject were fused with their segmentation.

• We designed a teaching tool[37] for advanced visualization of temporal bone structures (see Fig. 6 ).

Figure 6. Virtual view of the posterior tympanotomy approach fused with a CT-scan

#### Understanding cardiac planes of acquisition

Participants : Jan Margeta [correspondent] , Nicholas Ayache, Daniel C Lee [Northwestern University] , Antonio Criminisi [Microsoft Research Cambridge] .

This work has been partly supported by Microsoft Research through its PhD Scholarship Programme, by ERC Advanced Grant MedYMA (on Biophysical Modeling and Analysis of Dynamic Medical Images), and by the VP2HF FP7 research project.

Cardiac imaging, Machine learning, Magnetic resonance, Data wrangling

DICOM image format defines several tags by which the images can be queried and filtered. Many useful tags are however not standardized and must be cleaned prior to any large scale analysis.

• We developed a machine learning method for automatic recognition of cardiac planes of acquisition (See Fig. 7 for sample predictions).

• Our image based method achieved state of the art performance.

• This work was presented[23] at the Medical Image Understanding and Analysis conference in London.

Figure 7. Examples of cardiac acquisition plane predictions and confidences