Deep Learning Based Automated Orthotopic Lung Tumor Segmentation in Whole-Body Mouse CT-Scans

Targeted nutritional intervention attenuates experimental lung cancer cachexia

BACKGROUND

Cachexia, a syndrome with high prevalence in non-small cell lung cancer patients, impairs quality of life and reduces tolerance and responsiveness to cancer therapy resulting in decreased survival. Optimal nutritional care is pivotal in the treatment of cachexia and a recommended cornerstone of multimodal therapy. Here, we investigated the therapeutic effect of an intervention diet consisting of a specific combination of high protein, leucine, fish oil, vitamin D, galacto-oligosaccharides, and fructo-oligosaccharides on the development and progression of cachexia in an orthotopic lung cancer mouse model.

METHODS

Eleven-week-old male 129S2/Sv mice were orthotopically implanted with 344P lung epithelial tumour cells or vehicle (control). Seven days post-implantation tumour-bearing (TB) mice were allocated to either intervention- or isocaloric control diet. Cachexia was defined as 5 days of consecutive body weight loss, after which mice were euthanized for tissue analyses.

RESULTS

TB mice developed cachexia accompanied by significant loss of skeletal muscle mass and epididymal fat mass compared with sham operated mice. The cachectic endpoint was significantly delayed (46.0 ± 15.2 vs. 34.7 ± 11.4 days), and the amount (-1.57 ± 0.62 vs. -2.13 ± 0.57 g) and progression (-0.26 ± 0.14 vs. -0.39 ± 0.11 g/day) of body weight loss were significantly reduced by the intervention compared with control diet. Moreover, systemic inflammation (pentraxin-2 plasma levels) and alterations in molecular markers for proteolysis and protein synthesis, indicative of muscle atrophy signalling in TB-mice, were suppressed in skeletal muscle by the intervention diet.

CONCLUSIONS

Together, these data demonstrate the potential of this multinutrient intervention, targeting multiple components of cachexia, as integral part of lung cancer management.

3D whole body preclinical micro-CT database of subcutaneous tumors in mice with annotations from 3 annotators

A pivotal animal model for development of anticancer molecules is mice with subcutaneous tumors, grown by injection of xenografted tumor cells, where micro-Computed Tomography (µCT) of the mice is used to analyze the efficacy of the anticancer molecule. Manual delineation of the tumor region is necessary for the analysis, which is time-consuming and inconsistent, highlighting the need for automatic segmentation (AS) tools. This study introduces a preclinical µCT database, comprising 452 whole-body scans from 223 individual mice with subcutaneous tumors, spanning ten diverse µCT datasets conducted between 2014 and 2020 on a preclinical PET/CT scanner, making it the hitherto largest dataset of its kind. Each tumor is annotated manually by three expert annotators, allowing for robust model development. Inter-annotator agreement was analyzed, and we report an overall annotation agreement of 0.903 ± 0.046 (mean ± std) Fleiss' Kappa and a mean deviation in volume estimation of 0.015 ± 0.010 cm3 (6.9% ± 4.7), which establishes a human baseline accuracy for delineation of subcutaneous tumors, while showing good inter-annotator agreement.

Deep Learning-Based Automated Measurement of Murine Bone Length in Radiographs

Genetic mouse models of skeletal abnormalities have demonstrated promise in the identification of phenotypes relevant to human skeletal diseases. Traditionally, phenotypes are assessed by manually examining radiographs, a tedious and potentially error-prone process. In response, this study developed a deep learning-based model that streamlines the measurement of murine bone lengths from radiographs in an accurate and reproducible manner. A bone detection and measurement pipeline utilizing the Keypoint R-CNN algorithm with an EfficientNet-B3 feature extraction backbone was developed to detect murine bone positions and measure their lengths. The pipeline was developed utilizing 94 X-ray images with expert annotations on the start and end position of each murine bone. The accuracy of our pipeline was evaluated on an independent dataset test with 592 images, and further validated on a previously published dataset of 21,300 mouse radiographs. The results showed that our model performed comparably to humans in measuring tibia and femur lengths (R2 > 0.92, p-value = 0) and significantly outperformed humans in measuring pelvic lengths in terms of precision and consistency. Furthermore, the model improved the precision and consistency of genetic association mapping results, identifying significant associations between genetic mutations and skeletal phenotypes with reduced variability. This study demonstrates the feasibility and efficiency of automated murine bone length measurement in the identification of mouse models of abnormal skeletal phenotypes.

Applying deep learning to segmentation of murine lung tumors in pre-clinical micro-computed tomography

Lung cancer remains a leading cause of cancer-related death, but scientists have made great strides in developing new treatments recently, partly owing to the use of genetically engineered mouse models (GEMMs). GEMM tumors represent a translational model that recapitulates human disease better than implanted models because tumors develop spontaneously in the lungs. However, detection of these tumors relies on in vivo imaging tools, specifically micro-Computed Tomography (micro-CT or µCT), and image analysis can be laborious with high inter-user variability. Here we present a deep learning model trained to perform fully automated segmentation of lung tumors without the interference of other soft tissues. Trained and tested on 100 3D µCT images (18,662 slices) that were manually segmented, the model demonstrated a high correlation to manual segmentations on the testing data (r2=0.99, DSC=0.78) and on an independent dataset (n = 12 3D scans or 2328 2D slices, r2=0.97, DSC=0.73). In a comparison against manual segmentation performed by multiple analysts, the model (r2=0.98, DSC=0.78) performed within inter-reader variability (r2=0.79, DSC=0.69) and close to intra-reader variability (r2=0.99, DSC=0.82), all while completing 5+ hours of manual segmentations in 1 minute. Finally, when applied to a real-world longitudinal study (n = 55 mice), the model successfully detected tumor progression over time and the differences in tumor burden between groups induced with different virus titers, aligning well with more traditional analysis methods. In conclusion, we have developed a deep learning model which can perform fast, accurate, and fully automated segmentation of µCT scans of murine lung tumors.

The Tian-Men-Dong decoction suppresses the tumour-infiltrating G-MDSCs via IL-1β-mediated signalling in lung cancer

ETHNOPHARMACOLOGICAL RELEVANCE

The traditional Chinese medicine (TCM) Tian-Men-Dong decoction (TD) has been able to effectively treat lung cancer in China for thousands of years. TD improves the quality of life in lung cancer patients by promoting nourishment of yin and reducing dryness, clearing the lung and removing toxins. Pharmacological studies show that TD contains active antitumour ingredients, but its underlying mechanism remains unknown.

AIM OF THE STUDY

This study aims at exploring potential mechanisms of TD in the treatment of lung cancer by regulating granulocytic-myeloid-derived suppressor cells (G-MDSCs).

MATERIALS AND METHODS

An orthotopic lung cancer mouse model was generated by intrapulmonary injection with LLC-luciferase cells in immunocompetent C57BL/6 mice or immunodeficient nude mice. TD/saline was orally administered once to the model mice daily for 4 weeks. Live imaging was conducted to monitor tumour growth. Immune profiles were detected by flow cytometry. H&E and ELISA were applied to test the cytotoxicity of the TD treatment. RT-qPCR and western blotting were performed to detect apoptosis-related proteins in G-MDSCs. A neutralizing antibody (anti-Ly6G) was utilized to exhaust the G-MDSCs via intraperitoneal injection. G-MDSCs were adoptively transferred from wild-type tumour-bearing mice. Immunofluorescence, TUNEL and Annexin V/PI staining were conducted to analyse apoptosis-related markers. A coculture assay of purified MDSCs and T cells labelled with CFSE was performed to test the immunosuppressive activity of MDSCs. The presence of TD/IL-1β/TD + IL-1β in purified G-MDSCs cocultured with the LLC system was used for ex vivo experiments to detect IL-1β-mediated apoptosis of G-MDSCs.

RESULTS

TD prolonged the survival of immune competent C57BL/6 mice in an orthotopic lung cancer model, but did not have the same effect in immunodeficient nude mice, indicating that its antitumour properties of TD are exerted by regulating immunity. TD induced G-MDSC apoptosis via the IL-1β-mediated NF-κB signalling cascade leading to effectively weaken the immunosuppressive activity of G-MDSCs and promote CD8⁺ T-cell infiltration, which was supported by both the depletion and adoptive transfer of G-MDSCs assays. In addition, TD also showed minimal cytotoxicity both in vivo and in vitro.

CONCLUSION

This study reveals for the first time that TD, a classic TCM prescription, is able to regulate G-MDSC activity and trigger its apoptosis via the IL-1β-mediated NF-κB signalling pathway, reshaping the tumour microenvironment and demonstrating antitumour effects. These findings provide a scientific foundation the clinical treatment of lung cancer with TD.

Measurement of mouse head and neck tumors by automated analysis of CBCT images

Animal experiments are often used to determine effects of drugs and other biological conditions on cancer progression, but poor accuracy and reproducibility of established tumor measurement methods make results unreliable. In orthotopic mouse models of head and neck cancer, tumor volumes approximated from caliper measurements are conventionally used to compare groups, but geometrical challenges make the procedure imprecise. To address this, we developed software to better measure these tumors by automated analysis of cone-beam computed tomography (CBCT) scans. This allows for analyses of tumor shape and growth dynamics that would otherwise be too inaccurate to provide biological insight. Monitoring tumor growth by calipers and imaging in parallel, we find that caliper measurements of small tumors are weakly correlated with actual tumor volume and highly susceptible to experimenter bias. The method presented provides a unique window to sources of error in a foundational aspect of preclinical head and neck cancer research and a valuable tool to mitigate them.

A novel orthotopic mouse model replicates human lung cancer cachexia

INTRODUCTION

Cancer cachexia, highly prevalent in lung cancer, is a debilitating syndrome characterized by involuntary loss of skeletal muscle mass and is associated with poor clinical outcome, decreased survival and negative impact on tumour therapy. Various lung tumour-bearing animal models have been used to explore underlying mechanisms of cancer cachexia. However, these models do not simulate anatomical and immunological features key to lung cancer and associated muscle wasting. Overcoming these shortcomings is essential to translate experimental findings into the clinic. We therefore evaluated whether a syngeneic, orthotopic lung cancer mouse model replicates systemic and muscle-specific alterations associated with human lung cancer cachexia.

METHODS

Immune competent, 11 weeks old male 129S2/Sv mice, were randomly allocated to either (1) sham control group or (2) tumour-bearing group. Syngeneic lung epithelium-derived adenocarcinoma cells (K-rasG12D ; p53R172HΔG ) were inoculated intrapulmonary into the left lung lobe of the mice. Body weight and food intake were measured daily. At baseline and weekly after surgery, grip strength was measured and tumour growth and muscle volume were assessed using micro cone beam CT imaging. After reaching predefined surrogate survival endpoint, animals were euthanized, and skeletal muscles of the lower hind limbs were collected for biochemical analysis.

RESULTS

Two-third of the tumour-bearing mice developed cachexia based on predefined criteria. Final body weight (-13.7 ± 5.7%; P < 0.01), muscle mass (-13.8 ± 8.1%; P < 0.01) and muscle strength (-25.5 ± 10.5%; P < 0.001) were reduced in cachectic mice compared with sham controls and median survival time post-surgery was 33.5 days until humane endpoint. Markers for proteolysis, both ubiquitin proteasome system (Fbxo32 and Trim63) and autophagy-lysosomal pathway (Gabarapl1 and Bnip3), were significantly upregulated, whereas markers for protein synthesis (relative phosphorylation of Akt, S6 and 4E-BP1) were significantly decreased in the skeletal muscle of cachectic mice compared with control. The cachectic mice exhibited increased pentraxin-2 (P < 0.001) and CXCL1/KC (P < 0.01) expression levels in blood plasma and increased mRNA expression of IκBα (P < 0.05) in skeletal muscle, indicative for the presence of systemic inflammation. Strikingly, RNA sequencing, pathway enrichment and miRNA expression analyses of mouse skeletal muscle strongly mirrored alterations observed in muscle biopsies of patients with lung cancer cachexia.

CONCLUSIONS

We developed an orthotopic model of lung cancer cachexia in immune competent mice. Because this model simulates key aspects specific to cachexia in lung cancer patients, it is highly suitable to further investigate the underlying mechanisms of lung cancer cachexia and to test the efficacy of novel intervention strategies.

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

Lungs are the most frequent site of metastases growth. The amount and size of pulmonary metastases acquired from MRI imaging data are the important criteria to assess the efficacy of new drugs in preclinical models. While efficient solutions both for MR imaging and the downstream automatic segmentation have been proposed for human patients, both MRI lung imaging and segmentation in preclinical animal models remains challenging due to the physiological motion (respiratory and cardiac movements), 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. In this work, we have developed a complete methodological pipeline for automated analysis of lungs and metastases in mice, consisting of an MR sequence for image acquisition and a deep learning method for automatic segmentation of both lungs and metastases. On one hand, we optimized an MR sequence for mouse lung imaging with high contrast for high detection sensitivity. On the other hand we developed DeepMeta, a multiclass U-Net 3+ deep learning model to automatically segment the images. To assess if the proposed deep learning pipeline is able to provide an accurate segmentation of both lungs and pulmonary metastases, we have 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 (self-gated balanced steady state free precession) sequence at different time points after the injection of cancer cells. Both 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 on a separate test dataset of MR images. Thanks to the SG method, 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 by DeepMeta as soon as they reached the volume of ∼ 0.02 m m 3 . 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 combining SG-bSSFP with deep learning, enables processing of the whole animal lungs and is thus a viable alternative to histology alone.

A Framework for Interactive Medical Image Segmentation Using Optimized Swarm Intelligence with Convolutional Neural Networks

Recent improvements in current technology have had a significant impact on a wide range of image processing applications, including medical imaging. Classification, detection, and segmentation are all important aspects of medical imaging technology. An enormous need exists for the segmentation of diagnostic images, which can be applied to a wide variety of medical research applications. It is important to develop an effective segmentation technique based on deep learning algorithms for optimal identification of regions of interest and rapid segmentation. To cover this gap, a pipeline for image segmentation using traditional Convolutional Neural Network (CNN) as well as introduced Swarm Intelligence (SI) for optimal identification of the desired area has been proposed. Fuzzy C-means (FCM), K-means, and improvisation of FCM with Particle Swarm Optimization (PSO), improvisation of K-means with PSO, improvisation of FCM with CNN, and improvisation of K-means with CNN are the six modules examined and evaluated. Experiments are carried out on various types of images such as Magnetic Resonance Imaging (MRI) for brain data analysis, dermoscopic for skin, microscopic for blood leukemia, and computed tomography (CT) scan images for lungs. After combining all of the datasets, we have constructed five subsets of data, each of which had a different number of images: 50, 100, 500, 1000, and 2000. Each of the models was executed and trained on the selected subset of the datasets. From the experimental analysis, it is observed that the performance of K-means with CNN is better than others and achieved 96.45% segmentation accuracy with an average time of 9.09 seconds.

Inter-observer variability of organ contouring for preclinical studies with cone beam Computed Tomography imaging

Background and purpose

In preclinical radiation studies, there is great interest in quantifying the radiation response of healthy tissues. Manual contouring has significant impact on the treatment-planning because of variation introduced by human interpretation. This results in inconsistencies when assessing normal tissue volumes. Evaluation of these discrepancies can provide a better understanding on the limitations of the current preclinical radiation workflow. In the present work, interobserver variability (IOV) in manual contouring of rodent normal tissues on cone-beam Computed Tomography, in head and thorax regions was evaluated.

Materials and methods

Two animal technicians performed manually (assisted) contouring of normal tissues located within the thorax and head regions of rodents, 20 cases per body site. Mean surface distance (MSD), displacement of center of mass (ΔCoM), DICE similarity coefficient (DSC) and the 95th percentile Hausdorff distance (HD₉₅) were calculated between the contours of the two observers to evaluate the IOV.

Results

For the thorax organs, right lung had the lowest IOV (ΔCoM: 0.08 ± 0.04 mm, DSC: 0.96 ± 0.01, MSD:0.07 ± 0.01 mm, HD₉₅:0.20 ± 0.03 mm) while spinal cord, the highest IOV (ΔCoM:0.5 ± 0.3 mm, DSC:0.81 ± 0.05, MSD:0.14 ± 0.03 mm, HD₉₅:0.8 ± 0.2 mm). Regarding head organs, right eye demonstrated the lowest IOV (ΔCoM:0.12 ± 0.08 mm, DSC: 0.93 ± 0.02, MSD: 0.15 ± 0.04 mm, HD₉₅: 0.29 ± 0.07 mm) while complete brain, the highest IOV (ΔCoM: 0.2 ± 0.1 mm, DSC: 0.94 ± 0.02, MSD: 0.3 ± 0.1 mm, HD₉₅: 0.5 ± 0.1 mm).

Conclusions

Our findings reveal small IOV, within the sub-mm range, for thorax and head normal tissues in rodents. The set of contours can serve as a basis for developing an automated delineation method for e.g., treatment planning.