Volumetric and linear measurements of lung tumor burden from non-gated micro-CT imaging correlate with histological analysis in a genetically engineered mouse model of non-small cell lung cancer

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 Value of Micro-CT in the Diagnosis of Lung Carcinoma: A Radio-Histopathological Perspective

Micro-computed tomography (micro-CT) is a relatively new imaging modality and the three-dimensional (3D) images obtained via micro-CT allow researchers to collect both quantitative and qualitative information on various types of samples. Micro-CT could potentially be used to examine human diseases and several studies have been published on this topic in the last decade. In this study, the potential uses of micro-CT in understanding and evaluating lung carcinoma and the relevant studies conducted on lung and other tumors are summarized. Currently, the resolution of benchtop laboratory micro-CT units has not reached the levels that can be obtained with light microscopy, and it is not possible to detect the histopathological features (e.g., tumor type, adenocarcinoma pattern, spread through air spaces) required for lung cancer management. However, its ability to provide 3D images in any plane of section, without disturbing the integrity of the specimen, suggests that it can be used as an auxiliary technique, especially in surgical margin examination, the evaluation of tumor invasion in the entire specimen, and calculation of primary and metastatic tumor volume. Along with future developments in micro-CT technology, it can be expected that the image resolution will gradually improve, the examination time will decrease, and the relevant software will be more user friendly. As a result of these developments, micro-CT may enter pathology laboratories as an auxiliary method in the pathological evaluation of lung tumors. However, the safety, performance, and cost effectiveness of micro-CT in the areas of possible clinical application should be investigated. If micro-CT passes all these tests, it may lead to the convergence of radiology and pathology applications performed independently in separate units today, and the birth of a new type of diagnostician who has equal knowledge of the histological and radiological features of tumors.

Micro-CT acquisition and image processing to track and characterize pulmonary nodules in mice

X-ray computed tomography is a reliable technique for the detection and longitudinal monitoring of pulmonary nodules. In preclinical stages of diagnostic or therapeutic development, the miniaturized versions of the clinical computed tomography scanners are ideally suited for carrying out translationally-relevant research in conditions that closely mimic those found in the clinic. In this Protocol, we provide image acquisition parameters optimized for low radiation dose, high-resolution and high-throughput computed tomography imaging using three commercially available micro-computed tomography scanners, together with a detailed description of the image analysis tools required to identify a variety of lung tumor types, characterized by specific radiological features. For each animal, image acquisition takes 4-8 min, and data analysis typically requires 10-30 min. Researchers with basic training in animal handling, medical imaging and software analysis should be able to implement this protocol across a wide range of lung cancer models in mice for investigating the molecular mechanisms driving lung cancer development and the assessment of diagnostic and therapeutic agents.

Virtual monoenergetic micro-CT imaging in mice with artificial intelligence

Micro cone-beam computed tomography (µCBCT) imaging is of utmost importance for carrying out extensive preclinical research in rodents. The imaging of animals is an essential step prior to preclinical precision irradiation, but also in the longitudinal assessment of treatment outcomes. However, imaging artifacts such as beam hardening will occur due to the low energetic nature of the X-ray imaging beam (i.e., 60 kVp). Beam hardening artifacts are especially difficult to resolve in a ‘pancake’ imaging geometry with stationary source and detector, where the animal is rotated around its sagittal axis, and the X-ray imaging beam crosses a wide range of thicknesses. In this study, a seven-layer U-Net based network architecture (vMonoCT) is adopted to predict virtual monoenergetic X-ray projections from polyenergetic X-ray projections. A Monte Carlo simulation model is developed to compose a training dataset of 1890 projection pairs. Here, a series of digital anthropomorphic mouse phantoms was derived from the reference DigiMouse phantom as simulation geometry. vMonoCT was trained on 1512 projection pairs (= 80%) and tested on 378 projection pairs (= 20%). The percentage error calculated for the test dataset was 1.7 ± 0.4%. Additionally, the vMonoCT model was evaluated on a retrospective projection dataset of five mice and one frozen cadaver. It was found that beam hardening artifacts were minimized after image reconstruction of the vMonoCT-corrected projections, and that anatomically incorrect gradient errors were corrected in the cranium up to 15%. Our results disclose the potential of Artificial Intelligence to enhance the µCBCT image quality in biomedical applications. vMonoCT is expected to contribute to the reproducibility of quantitative preclinical applications such as precision irradiations in X-ray cabinets, and to the evaluation of longitudinal imaging data in extensive preclinical studies.

Mouse lung automated segmentation tool for quantifying lung tumors after micro-computed tomography

Unlike the majority of cancers, survival for lung cancer has not shown much improvement since the early 1970s and survival rates remain low. Genetically engineered mice tumor models are of high translational relevance as we can generate tissue specific mutations which are observed in lung cancer patients. Since these tumors cannot be detected and quantified by traditional methods, we use micro-computed tomography imaging for longitudinal evaluation and to measure response to therapy. Conventionally, we analyze microCT images of lung cancer via a manual segmentation. Manual segmentation is time-consuming and sensitive to intra- and inter-analyst variation. To overcome the limitations of manual segmentation, we set out to develop a fully-automated alternative, the Mouse Lung Automated Segmentation Tool (MLAST). MLAST locates the thoracic region of interest, thresholds and categorizes the lung field into three tissue categories: soft tissue, intermediate, and lung. An increase in the tumor burden was measured by a decrease in lung volume with a simultaneous increase in soft and intermediate tissue quantities. MLAST segmentation was validated against three methods: manual scoring, manual segmentation, and histology. MLAST was applied in an efficacy trial using a Kras/Lkb1 non-small cell lung cancer model and demonstrated adequate precision and sensitivity in quantifying tumor growth inhibition after drug treatment. Implementation of MLAST has considerably accelerated the microCT data analysis, allowing for larger study sizes and mid-study readouts. This study illustrates how automated image analysis tools for large datasets can be used in preclinical imaging to deliver high throughput and quantitative results.

Reporting animal research: Explanation and elaboration for the ARRIVE guidelines 2.0

Improving the reproducibility of biomedical research is a major challenge. Transparent and accurate reporting is vital to this process; it allows readers to assess the reliability of the findings and repeat or build upon the work of other researchers. The ARRIVE guidelines (Animal Research: Reporting In Vivo Experiments) were developed in 2010 to help authors and journals identify the minimum information necessary to report in publications describing in vivo experiments. Despite widespread endorsement by the scientific community, the impact of ARRIVE on the transparency of reporting in animal research publications has been limited. We have revised the ARRIVE guidelines to update them and facilitate their use in practice. The revised guidelines are published alongside this paper. This explanation and elaboration document was developed as part of the revision. It provides further information about each of the 21 items in ARRIVE 2.0, including the rationale and supporting evidence for their inclusion in the guidelines, elaboration of details to report, and examples of good reporting from the published literature. This document also covers advice and best practice in the design and conduct of animal studies to support researchers in improving standards from the start of the experimental design process through to publication.

Monitoring treatment effects in lung cancer-bearing mice: clinical CT and clinical MRI compared to micro-CT

Background

Compared to histology-based methods, imaging can reduce animal usage in preclinical studies. However, availability of dedicated scanners is limited. We evaluated clinical computed tomography (CT) and magnetic resonance imaging (MRI) in comparison to dedicated CT (micro-CT) for assessing therapy effects in lung cancer-bearing mice.

Methods

Animals received cisplatin (n = 10), sham (n = 12), or no treatment (n = 9). All were examined via micro-CT, CT, and MRI before and after treatment. Semiautomated tumour burden (TB) calculation was performed. The Bland-Altman, receiver operating characteristic (ROC), and Spearman statistics were used.

Results

All modalities always allowed localising and measuring TB. At all modalities, mice treated with cisplatin showed a TB reduction (p ≤ 0.012) while sham-treated and untreated individuals presented tumour growth (p < 0.001). Mean relative difference (limits of agreement) between TB on micro-CT and clinical scanners was 24.7% (21.7–27.7%) for CT and 2.9% (−4.0–9.8%) for MRI. Relative TB changes before/after treatment were not different between micro-CT and CT (p = 0.074) or MRI (p = 0.241). Mice with cisplatin treatment were discriminated from those with sham or no treatment at all modalities (p ≤ 0.001). Using micro-CT as reference standard, ROC areas under the curves were 0.988–1.000 for CT and 0.946–0.957 for MRI. TB changes were highly correlated across modalities (r ≥ 0.900, p < 0.001).

Conclusions

Clinical CT and MRI are suitable for treatment response evaluation in lung cancer-bearing mice. When dedicated scanners are unavailable, they should be preferred to improve animal welfare.

Classification of Breast Cancer Cells Using the Integration of High-Frequency Single-Beam Acoustic Tweezers and Convolutional Neural Networks

Single-beam acoustic tweezers (SBAT) is a widely used trapping technique to manipulate microscopic particles or cells. Recently, the characterization of a single cancer cell using high-frequency (>30 MHz) SBAT has been reported to determine its invasiveness and metastatic potential. Investigation of cell elasticity and invasiveness is based on the deformability of cells under SBAT’s radiation forces, and in general, more physically deformed cells exhibit higher levels of invasiveness and therefore higher metastatic potential. However, previous imaging analysis to determine substantial differences in cell deformation, where the SBAT is turned ON or OFF, relies on the subjective observation that may vary and requires follow-up evaluations from experts. In this study, we propose an automatic and reliable cancer cell classification method based on SBAT and a convolutional neural network (CNN), which provides objective and accurate quantitative measurement results. We used a custom-designed 50 MHz SBAT transducer to obtain a series of images of deformed human breast cancer cells. CNN-based classification methods with data augmentation applied to collected images determined and validated the metastatic potential of cancer cells. As a result, with the selected optimizers, precision, and recall of the model were found to be greater than 0.95, which highly validates the classification performance of our integrated method. CNN-guided cancer cell deformation analysis using SBAT may be a promising alternative to current histological image analysis, and this pretrained model will significantly reduce the evaluation time for a larger population of cells.

A step towards valid detection and quantification of lung cancer volume in experimental mice with contrast agent-based X-ray microtomography

Tumor volume is a parameter used to evaluate the performance of new therapies in lung cancer research. Conventional methods that are used to estimate tumor size in mouse models fail to provide fast and reliable volumetric data for tumors grown non-subcutaneously. Here, we evaluated the use of iodine-staining combined with micro-computed tomography (micro-CT) to estimate the tumor volume of ex vivo tumor-burdened lungs. We obtained fast high spatial resolution three-dimensional information of the lungs, and we demonstrated that iodine-staining highlights tumors and unhealthy tissue. We processed iodine-stained lungs for histopathological analysis with routine hematoxylin and eosin (H&E) staining. We compared the traditional tumor burden estimation performed manually with H&E histological slices with a semi-automated method using micro-CT datasets. In mouse models that develop lung tumors with well precise boundaries, the method that we describe here enables to perform a quick estimation of tumorous tissue volume in micro-CT images. Our method overestimates the tumor burden in tumors surrounded by abnormal tissue, while traditional histopathological analysis underestimates tumor volume. We propose to embed micro-CT imaging to the traditional workflow of tumorous lung analyses in preclinical cancer research as a strategy to obtain a more accurate estimation of the total lung tumor burden.