AUTHOR=Lefevre Edgar , Bouilhol Emmanuel , Chauvière Antoine , Souleyreau Wilfried , Derieppe Marie-Alix , Trotier Aurélien J. , Miraux Sylvain , Bikfalvi Andreas , Ribot Emeline J. , Nikolski Macha 

TITLE=Deep learning model for automatic segmentation of lungs and pulmonary metastasis in small animal MR images

JOURNAL=Frontiers in Bioinformatics

VOLUME=Volume 2 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2022.999700

DOI=10.3389/fbinf.2022.999700

ISSN=2673-7647

ABSTRACT=Lungs are the most frequent metastases site. The amount and size of pulmonary metastases are the important criteria to assess the efficacy of new drugs in preclinical models. Efficient solutions both for MR imaging and the automatic segmentation have been proposed for human patients, but MRI lung imaging and segmentation in preclinical animal models remains challenging due to the physiological motion, to the low amount of protons in this organ and to the particular challenge of precise segmentation of metastases. As a consequence post-mortem analysis is currently required to obtain information on metastatic volume.

We developed a methodological pipeline for automated analysis of lungs and metastases in mice, consisting of an MR sequence and a deep learning method for automatic segmentation of both lungs and metastases. We optimized an MR sequence for mouse lung imaging with high contrast for high detection sensitivity and developed DeepMeta, a multiclass U-Net 3+ deep learning model to automatically segment the images. To assess if the proposed pipeline is able to provide an accurate segmentation of both lungs and pulmonary metastases, we longitudinally imaged mice with fast- and slow-growing metastasis.

Fifty-five balb/c mice were injected with two different derivatives of renal carcinoma cells. Mice were imaged with a SG-bSSFP sequence at different time points after the injection of cancer cells. Lung and metastases segmentations were manually performed by experts. DeepMeta was trained to perform lung and metastases segmentation based on the resulting ground truth annotations. Volumes of lungs and of pulmonary metastases as well as the number of metastases per mouse were measured. 

The 3D bSSFP images of lungs were artifact-free, enabling the downstream detection and serial follow-up of metastases. Moreover, both lungs and metastases segmentation was accurately performed as soon as they reached the volume of ~0.02 mm3. Thus we were able to distinguish two groups of mice in terms of number and volume of pulmonary metastases as well as in terms of the slow versus fast patterns of growth of metastases. We have shown that our methodology enables  processing of the whole animal lungs and is thus a viable alternative to histology alone.