Radiomics is a technique that extracts quantitative features from medical images using data‐characterization algorithms. Radiomic features can be used to identify tissue characteristics and radiologic phenotyping that is not observable by clinicians. A typical workflow for a radiomics study includes cohort selection, radiomic feature extraction, feature and predictive model selection, and model training and validation. While there has been increasing attention given to radiomic feature extraction, standardization, and reproducibility, currently, there is a lack of rigorous evaluation of feature selection methods and predictive models. Herein, we review the published radiomics investigations in CT lung cancer and provide an overview of the commonly used radiomic feature selection methods and predictive models. We also compare limitations of various methods in clinical applications and present sources of uncertainty associated with those methods. This review is expected to help raise awareness of the impact of radiomic feature and model selection methods on the integrity of radiomics studies.

With the ever‐increasing use of computed tomography (CT), concerns about its radiation dose have become a significant public issue. To address the need for radiation dose reduction, CT denoising methods have been widely investigated and applied in low‐dose CT images. Numerous noise reduction algorithms have emerged, such as iterative reconstruction and most recently, deep learning (DL)‐based approaches. Given the rapid advancements in Artificial Intelligence techniques, we recognize the need for a comprehensive review that emphasizes the most recently developed methods. Hence, we have performed a thorough analysis of existing literature to provide such a review. Beyond directly comparing the performance, we focus on pivotal aspects, including model training, validation, testing, generalizability, vulnerability, and evaluation methods. This review is expected to raise awareness of the various facets involved in CT image denoising and the specific challenges in developing DL‐based models.

Background: Enteral nutrition through feeding tubes serves as the primary method of nutritional supplementation for patients unable to feed themselves. Plain radiographs are routinely used to confirm the position of the Nasoenteric feeding tubes the following insertion and before the commencement of tube feeds. Convolutional neural networks (CNNs) have shown encouraging results in assisting the tube positioning assessment. However, robust CNNs are often trained using large amounts of manually annotated data, which challenges applying CNNs on enteral feeding tube positioning assessment. Method: We build a CNN model for feeding tube positioning assessment by pre-training the model under a weakly supervised fashion on large quantities of radiographs. Since most of the model was pre-trained, a small amount of labeled data is needed when fine-tuning the model for tube positioning assessment. We demonstrate the proposed method using a small dataset with 175 radiographs. Result: The experimental result shows that the proposed model improves the area under the receiver operating characteristic curve (AUC) by up to 35.71% , from 0.56 to 0.76, and 14.49% on the accuracy, from 0.69 to 0.79 when compared with the no pre-trained method. The proposed method also has up to 40% less error when estimating its prediction confidence. Conclusion: Our evaluation results show that the proposed model has a high prediction accuracy and a more accurate estimated prediction confidence when compared to the no pre-trained model and other baseline models. The proposed method can be potentially used for assessing the enteral tube positioning. It also provides a strong baseline for future studies.

For pulmonary applications of Electrical Impedance Tomography (EIT) systems, the electrodes are placed around the chest in a 2D ring, and the images are reconstructed based on the assumptions that the object is rigid and the measured resistivity change in EIT images is only caused by the actual resistivity change of tissue. Structural changes are rarely considered. Previous studies have shown that structural changes which result in tissue/organ and electrode position changes tend to introduce artefacts to EIT images of the thorax. Since EIT reconstruction is an ill-posed inverse problem, any small inaccurate assumptions of object may cause large artefacts in reconstructed images. Accurate information on structure/electrode position changes is a need to understand factors contributing to the measured resistivity changes and to improve EIT reconstruction algorithm. Our previous study using MRI technique showed that chest expansion leads to electrode and tissue/organ movements but not significant as proposed. The accuracy of the measurements by MRI may be limited by its relatively low temporal and spatial resolution. In this study, structure/electrode position changes during respiration cycle in patients who underwent chest CT scans are further investigated. For each patient, sixteen fiduciary markers are equally spaced around the surface, the same as the electrode placement for EIT measurements. A CT scanner with respiration-gated ability is used to acquire images of the thorax. CT thoracic images are retrospectively reconstructed corresponding temporally to specific time periods within respiration cycle (from 0% to 90%, every 10%). The average chest expansions are 2 mm in anterior-posterior and -1.6 mm in lateral directions. Inside tissue/organ move down 9.0±2.5 mm with inspiration of tidal volume (0.54±0.14 liters), ranging from 6 mm to 12 mm. During normal quiet respiration, electrode position changes are smaller than expected. No general patterns of electrode position changes are observed. The results in this study provide guidelines for accommodating the motion that may introduce artefacts to EIT images.