In vivo MRS for the assessment of mouse colon using a dedicated endorectal coil: initial findings.

Inflammatory bowel disease is a common group of inflammation conditions that can affect the colon and the rectum. These pathologies require a careful follow-up of patients to prevent the development of colorectal cancer. Currently, conventional endoscopy is used to depict alterations of the intestinal walls, and biopsies are performed on suspicious lesions for further analysis (histology). MRS enables the in vivo analysis of biochemical content of tissues (i.e. without removing any samples). Combined with dedicated endorectal coils (ERCs), MRS provides new ways of characterizing alterations of tissues. An MRS in vivo protocol was specifically set up on healthy mice and on mice chemically treated to induce colitis. Acquisitions were performed on a 4.7 T system using a linear volume birdcage coil for the transmission of the B1 magnetic field, and a dedicated ERC was used for signal reception. Colon-wall complex, lumen and visceral fat were assessed on healthy and treated mice with voxel sizes ranging from 0.125 µL to 2 µL while keeping acquisition times below 3 min. The acquired spectra show various biochemical contents such as α- and ß-methylene but also glycerol backbone and diacyl. Choline was detected in tumoral regions. Visceral fat regions display a high lipid content with no water, whereas colon-wall complex exhibits both high lipid and high water contents. To the best of our knowledge, this is the first time that in vivo MRS using an ERC has been performed in the assessment of colon walls and surrounding structures. It provides keys for the in vivo characterization of small local suspicious lesions and offers complementary solutions to biopsies.

Endoluminal high-resolution MR imaging protocol for colon walls analysis in a mouse model of colitis.

OBJECTIVE: An endoluminal magnetic resonance (MR) imaging protocol including the design of an endoluminal coil (EC) was defined for high-spatial-resolution MR imaging of mice gastrointestinal walls at 4.7 T. MATERIALS AND METHODS: A receive-only radiofrequency single-loop coil was developed for mice colon wall imaging. Combined with a specific protocol, the prototype was first characterized in vitro on phantoms and on vegetables. Signal-to-noise ratio (SNR) profiles were compared with a quadrature volume birdcage coil (QVBC). Endoluminal MR imaging protocol combined with the EC was assessed in vivo on mice. RESULTS: The SNR measured close to the coil is significantly higher (10 times and up to 3 mm of the EC center) than the SNR measured with the QVBC. The gain in SNR can be used to reduce the in-plane pixel size up to 39 × 39 µm(2) (234 µm slice thickness) without time penalty. The different colon wall layers can only be distinguished on images acquired with the EC. CONCLUSION: Dedicated EC provides suitable images for the assessment of mice colon wall layers. This proof of concept provides gains in spatial resolution and leads to adequate protocols for the assessment of human colorectal cancer, and can now be used as a new imaging tool for a better understanding of the pathology.

Automatic brain extraction and brain tissues segmentation on multi-contrast animal MRI.

For many neuroscience applications, brain extraction in MRI images is the first pre-processing step of a quantification pipeline. Once the brain is extracted, further post-processing calculations become faster, more specific and easier to implement and interpret. It is the case, for example, of functional MRI brain studies, or relaxation time mappings and brain tissues classifications to characterise brain pathologies. Existing brain extraction tools are mostly adapted to work on the human anatomy, this gives poor results when applied to animal brain images. We have developed an atlas-based Veterinary Images Brain Extraction (VIBE) algorithm that encompasses a pre-processing step to adapt the atlas to the patient's image, and a subsequent registration step. We show that the brain extraction is achieved with excellent results in terms of Dice and Jaccard metrics. The algorithm is automatic, with no need to adapt the parameters in a broad range of situations: we successfully tested multiple MRI contrasts (T1-weighted, T2-weighted, T2-weighted FLAIR), all the acquisition planes (sagittal, dorsal, transverse), different animal species (dogs and cats) and canine cranial conformations (brachycephalic, mesocephalic, dolichocephalic). VIBE can be successfully extended to other animal species, provided that an atlas for that specific species exists. We show also how brain extraction, as a preliminary step, can help to segment brain tissues with a K-Means clustering algorithm.

Machine Learning-Based Classification of the Health State of Mice Colon in Cancer Study from Confocal Laser Endomicroscopy.

In this article, we address the problem of the classification of the health state of the colon's wall of mice, possibly injured by cancer with machine learning approaches. This problem is essential for translational research on cancer and is a priori challenging since the amount of data is usually limited in all preclinical studies for practical and ethical reasons. Three states considered including cancer, health, and inflammatory on tissues. Fully automated machine learning-based methods are proposed, including deep learning, transfer learning, and shallow learning with SVM. These methods addressed different training strategies corresponding to clinical questions such as the automatic clinical state prediction on unseen data using a pre-trained model, or in an alternative setting, real-time estimation of the clinical state of individual tissue samples during the examination. Experimental results show the best performance of 99.93% correct recognition rate obtained for the second strategy as well as the performance of 98.49% which were achieved for the more difficult first case.