Automated segmentation of lungs and lung tumors in mouse micro-CT scans

Unveiling Another Dimension: Advanced Visualization of Cancer Invasion and Metastasis via Micro-CT Imaging

Invasion and metastasis are well-known hallmarks of cancer, with metastatic disease accounting for 60% to 90% of cancer-related deaths [...].

An unsupervised approach for projection binning to reduce motion artifacts in free-breathing animal models

BACKGROUND

Dynamic imaging holds great potential in the diagnosis and comprehensive evaluation of different diseases by capturing mechanical and dynamic characteristics of moving organs. Nonetheless, motion artifacts notably impair image quality, hindering accurate and localized analysis-particularly in free-breathing scenarios. In preclinical studies, traditional methods often necessitate artificial breathing control or use invasive techniques that do not permit functional lung assessment under normal physiological conditions, potentially biasing results and restricting longitudinal studies.

PURPOSE

This study aimed to mitigate motion artifacts and preserve temporal information, thus enhancing the spatiotemporal resolution of dynamic micro-CT images in free-breathing animals. We sought to combine the benefits of standard amplitude and phase binning within an unsupervised learning approach, without the need for iterative methods, prior knowledge, or alteration of the reconstruction process. Our approach facilitates accurate imaging of free-breathing animals under various protocols, without requiring artificial breathing control or invasive interventions, through a straightforward, immediately applicable retrospective analysis method.

METHODS

A novel periodic line-constrained K-means clustering technique was developed as an unsupervised method for projection/interleave binning. To validate this technique on preclinical micro-CT images, a syringe-spring system was engineered to simulate respiratory motion. Imaging was performed on this moving phantom with various breathing rates and inhale-to-exhale (I/E) ratios, as well as in free-breathing rats and rabbits. Additionally, we detail a method for extracting the breathing signal directly from the x-ray projection images and introduce a systematic approach for data imputation in limited-angle scenarios. We also established a metric for quantifying motion artifacts in our 4DCT images.

RESULTS

The clustering method effectively integrated the benefits of both amplitude and phase binning, leading to a marked reduction in motion artifacts across all tests. Notably, our method yielded enhanced image clarity and improved accuracy in capturing dynamic lung volumes, evidenced by sharper diaphragm edges, better visibility of blood vessels, and diminished blurring and motion artifacts. Quantitative analysis using linear regression of diaphragm speed versus blur measure showed a near-zero slope for both rats and rabbits, indicating a substantial decrease in motion artifact presence compared to traditional binning methods.

CONCLUSIONS

The periodic line-constrained K-means clustering method provides a robust solution for enhancing the quality of dynamic micro-CT imaging in preclinical studies. By reducing motion artifacts and improving image resolution, this approach enables more precise evaluations of lung function under physiologically relevant conditions. Future work will explore the application of this method to various respiratory disease models and assess its potential for broader clinical use in dynamic imaging of other organs.

A Thorough Review of the Clinical Applications of Artificial Intelligence in Lung Cancer

According to data from the World Health Organization (WHO), lung cancer is becoming a global epidemic. It is particularly high in the list of the leading causes of death not only in developed countries, but also worldwide; furthermore, it holds the leading place in terms of cancer-related mortality. Nevertheless, many breakthroughs have been made the last two decades regarding its management, with one of the most prominent being the implementation of artificial intelligence (AI) in various aspects of disease management. We included 473 papers in this thorough review, most of which have been published during the last 5-10 years, in order to describe these breakthroughs. In screening programs, AI is capable of not only detecting suspicious lung nodules in different imaging modalities-such as chest X-rays, computed tomography (CT), and positron emission tomography (PET) scans-but also discriminating between benign and malignant nodules as well, with success rates comparable to or even better than those of experienced radiologists. Furthermore, AI seems to be able to recognize biomarkers that appear in patients who may develop lung cancer, even years before this event. Moreover, it can also assist pathologists and cytologists in recognizing the type of lung tumor, as well as specific histologic or genetic markers that play a key role in treating the disease. Finally, in the treatment field, AI can guide in the development of personalized options for lung cancer patients, possibly improving their prognosis.

Automated recognition and segmentation of lung cancer cytological images based on deep learning

Compared with histological examination of lung cancer, cytology is less invasive and provides better preservation of complete morphology and detail. However, traditional cytological diagnosis requires an experienced pathologist to evaluate all sections individually under a microscope, which is a time-consuming process with low interobserver consistency. With the development of deep neural networks, the You Only Look Once (YOLO) object-detection model has been recognized for its impressive speed and accuracy. Thus, in this study, we developed a model for intraoperative cytological segmentation of pulmonary lesions based on the YOLOv8 algorithm, which labels each instance by segmenting the image at the pixel level. The model achieved a mean pixel accuracy and mean intersection over union of 0.80 and 0.70, respectively, on the test set. At the image level, the accuracy and area under the receiver operating characteristic curve values for malignant and benign (or normal) lesions were 91.0% and 0.90, respectively. In addition, the model was deemed suitable for diagnosing pleural fluid cytology and bronchoalveolar lavage fluid cytology images. The model predictions were strongly correlated with pathologist diagnoses and the gold standard, indicating the model's ability to make clinical-level decisions during initial diagnosis. Thus, the proposed method is useful for rapidly localizing lung cancer cells based on microscopic images and outputting image interpretation results.

Hybrid transformer-CNN and LSTM model for lung disease segmentation and classification

According to the World Health Organization (WHO) report, lung disorders are the third leading cause of mortality worldwide. Approximately three million individuals are affected with various types of lung disorders annually. This issue alarms us to take control measures related to early diagnostics, accurate treatment procedures, etc. The precise identification through the assessment of medical images is crucial for pulmonary disease diagnosis. Also, it remains a formidable challenge due to the diverse and unpredictable nature of pathological lung appearances and shapes. Therefore, the efficient lung disease segmentation and classification model is essential. By taking this initiative, a novel lung disease segmentation with a hybrid LinkNet-Modified LSTM (L-MLSTM) model is proposed in this research article. The proposed model utilizes four essential and fundamental steps for its implementation. The first step is pre-processing, where the input lung images are pre-processed using median filtering. Consequently, an improved Transformer-based convolutional neural network (CNN) model (ITCNN) is proposed to segment the affected region in the segmentation process. After segmentation, essential features such as texture, shape, color, and deep features are retrieved. Specifically, texture features are extracted using modified Local Gradient Increasing Pattern (LGIP) and Multi-texton analysis. Then, the classification step utilizes a hybrid model, the L-MLSTM model. This work leverages two datasets such as the COVID-19 normal pneumonia-CT images dataset (Dataset 1) and the Chest CT scan images dataset (Dataset 2). The dataset is crucial for training and evaluating the model, providing a comprehensive basis for robust and generalizable results. The L-MLSTM model outperforms several existing models, including HDE-NN, DBN, LSTM, LINKNET, SVM, Bi-GRU, RNN, CNN, and VGG19 + CNN, with accuracies of 89% and 95% at learning percentages of 70 and 90, respectively, for datasets 1 and 2. The improved accuracy achieved by the L-MLSTM model highlights its capability to better handle the complexity and variability in lung images. This hybrid approach enhances the model's ability to distinguish between different types of lung diseases and reduces diagnostic errors compared to existing methods.

Addressing Biological Questions with Preclinical Cancer Imaging

The broad application of noninvasive imaging has transformed preclinical cancer research, providing a powerful means to measure dynamic processes in living animals. While imaging technologies are routinely used to monitor tumor growth in model systems, their greatest potential lies in their ability to answer fundamental biological questions. Here we present the broad range of potential imaging applications according to the needs of a cancer biologist with a focus on some of the common biological processes that can be used to visualize and measure. Topics include imaging metastasis; biophysical properties such as perfusion, diffusion, oxygenation, and stiffness; imaging the immune system and tumor microenvironment; and imaging tumor metabolism. We also discuss the general ability of each approach and the level of training needed to both acquire and analyze images. The overall goal is to provide a practical guide for cancer biologists interested in answering biological questions with preclinical imaging technologies.

IL-4-induced SOX9 confers lineage plasticity to aged adult lung stem cells

Wound healing in response to acute injury is mediated by the coordinated and transient activation of parenchymal, stromal, and immune cells that resolves to homeostasis. Environmental, genetic, and epigenetic factors associated with inflammation and aging can lead to persistent activation of the microenvironment and fibrosis. Here, we identify opposing roles of interleukin-4 (IL-4) cytokine signaling in interstitial macrophages and type II alveolar epithelial cells (ATIIs). We show that IL4Ra signaling in macrophages promotes regeneration of the alveolar epithelium after bleomycin-induced lung injury. Using organoids and mouse models, we show that IL-4 directly acts on a subset of ATIIs to induce the expression of the transcription factor SOX9 and reprograms them toward a progenitor-like state with both airway and alveolar lineage potential. In the contexts of aging and bleomycin-induced lung injury, this leads to aberrant epithelial cell differentiation and bronchiolization, consistent with cellular and histological changes observed in interstitial lung disease.

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.

Ex Vivo Micro-CT in Ophthalmology: Preparation and Contrasting for Non-invasive 3D-Visualisation

X-ray-based micro-computed tomography (micro-CT) is a largely non-destructive imaging method for the visualisation and analysis of internal structures in the ex vivo eye and affords high resolution. In contrast to other high-resolution imaging methods, micro-CT enables spatial recording of larger and more complex tissue structures, such as the anterior chamber of the eye. Special contrasting methods help to enhance the absorption properties of soft tissue, that is otherwise only weakly radiopaque. Critical point drying (CPD), as primarily used in scanning electron microscopy, offers an additional tool for improving differential contrast properties in soft tissue. In the visualisation of intraosseous soft tissue, such as the efferent lacrimal ducts, sample treatment by decalcification with ethylenediaminetetraacetic acid and subsequent CPD provides good results for micro-CT. Micro-CT can be used for a wide range of questions in 1. basic research, 2. application-related studies in ophthalmology (e.g. evaluation of the preclinical application of microstents for glaucoma treatment or analysis of the positioning of intraocular lenses) but also 3. as a supplement to ophthalmological histopathology.

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.

Targeted alveolar regeneration with Frizzled-specific agonists

Wnt ligands oligomerize Frizzled (Fzd) and Lrp5/6 receptors to control the specification and activity of stem cells in many species. How Wnt signaling is selectively activated in different stem cell populations, often within the same organ, is not understood. In lung alveoli, we show that distinct Wnt receptors are expressed by epithelial (Fzd5/6), endothelial (Fzd4), and stromal (Fzd1) cells. Fzd5 is uniquely required for alveolar epithelial stem cell activity, whereas fibroblasts utilize distinct Fzd receptors. Using an expanded repertoire of Fzd-Lrp agonists, we could activate canonical Wnt signaling in alveolar epithelial stem cells via either Fzd5 or, unexpectedly, non-canonical Fzd6. A Fzd5 agonist (Fzd5ag) or Fzd6ag stimulated alveolar epithelial stem cell activity and promoted survival in mice after lung injury, but only Fzd6ag promoted an alveolar fate in airway-derived progenitors. Therefore, we identify a potential strategy for promoting regeneration without exacerbating fibrosis during lung injury.

Semi-automated micro-computed tomography lung segmentation and analysis in mouse models

Computed Tomography (CT) is a standard clinical tool utilized to diagnose known lung pathologies based on established grading methods. However, for preclinical trials and toxicity investigations in animal models, more comprehensive datasets are typically needed to determine discriminative features between experimental treatments, which oftentimes require analysis of multiple images and their associated differential quantification using manual segmentation methods. Furthermore, for manual segmentation of image data, three or more readers is the gold standard of analysis, but this requirement can be time-consuming and inefficient, depending on variability due to reader bias. In previous papers, microCT image manual segmentation was a valuable tool for assessment of lung pathology in several animal models; however, the manual segmentation approach and the commercial software used was typically a major rate-limiting step. To improve the efficiency, the semi-manual segmentation method was streamlined, and a semi-automated segmentation process was developed to produce:•Quantifiable segmentations: using manual and semi-automated analysis methods for assessing experimental injury and toxicity models,•Deterministic results and efficiency through automation in an unbiased and parameter free process, thereby reducing reader variance, user time, and increases throughput in data analysis,•Cost-Effectiveness: portable with low computational resource demand, based on a cross-platform open-source ImageJ program.