Objectives: Accurate kidney and tumor segmentation of computed tomography (CT) scans is vital for diagnosis and treatment, but manual methods are time-consuming and inconsistent, highlighting the value of AI automation. This study develops a fully automated AI model using vision transformers (ViTs) and convolutional neural networks (CNNs) to detect and segment kidneys and kidney tumors in Contrast-Enhanced (CECT) scans, with a focus on improving sensitivity for small, indistinct tumors. Methods: The segmentation framework employs a ViT-based model for the kidney organ, followed by a 3D UNet model with enhanced connections and attention mechanisms for tumor detection and segmentation. Two CECT datasets were used: a public dataset (KiTS23: 489 scans) and a private institutional dataset (Private: 592 scans). The AI model was trained on 389 public scans, with validation performed on the remaining 100 scans and external validation performed on all 592 private scans. Tumors were categorized by TNM staging as small (≤4 cm) (KiTS23: 54%, Private: 41%), medium (>4 cm to ≤7 cm) (KiTS23: 24%, Private: 35%), and large (>7 cm) (KiTS23: 22%, Private: 24%) for detailed evaluation. Results: Kidney and kidney tumor segmentations were evaluated against manual annotations as the reference standard. The model achieved a Dice score of 0.97 ± 0.02 for kidney organ segmentation. For tumor detection and segmentation on the KiTS23 dataset, the sensitivities and average false-positive rates per patient were as follows: 0.90 and 0.23 for small tumors, 1.0 and 0.08 for medium tumors, and 0.96 and 0.04 for large tumors. The corresponding Dice scores were 0.84 ± 0.11, 0.89 ± 0.07, and 0.91 ± 0.06, respectively. External validation on the private data confirmed the model’s effectiveness, achieving the following sensitivities and average false-positive rates per patient: 0.89 and 0.15 for small tumors, 0.99 and 0.03 for medium tumors, and 1.0 and 0.01 for large tumors. The corresponding Dice scores were 0.84 ± 0.08, 0.89 ± 0.08, and 0.92 ± 0.06. Conclusions: The proposed model demonstrates consistent and robust performance in segmenting kidneys and kidney tumors of various sizes, with effective generalization to unseen data. This underscores the model’s significant potential for clinical integration, offering enhanced diagnostic precision and reliability in radiological assessments.

Quantitative imaging biomarkers (QIB) are increasingly used in clinical research to advance precision medicine approaches in oncology. Computed tomography (CT) is a modality of choice for cancer diagnosis, prognosis, and response assessment due to its reliability and global accessibility. Here, we contribute to the cancer imaging community through The Cancer Imaging Archive (TCIA) by providing investigator-initiated, same-day repeat CT scan images of 32 non–small cell lung cancer (NSCLC) patients, along with radiologist-annotated lesion contours as a reference standard. Each scan was reconstructed into 6 image settings using various combinations of three slice thicknesses (1.25 mm, 2.5 mm, 5 mm) and two reconstruction kernels (lung, standard; GE CT equipment), which spans a wide range of CT imaging reconstruction parameters commonly used in lung cancer clinical practice and clinical trials. This holds considerable value for advancing the development of robust Radiomics, Artificial Intelligence (AI) and machine learning (ML) methods.

Background: Radiomics can provide quantitative descriptors of tumor phenotype, but translation is often limited by feature instability across scanners and protocols. We aimed to develop and internally validate a protocol-specific CT-radiomics model using preoperative imaging to predict 5-year recurrence in patients with stage I lung adenocarcinoma after complete surgical resection. Methods: The retrospective study included 270 patients with completely resected stage I lung adenocarcinoma from January 2010–December 2021, among whom 23 (8.5%) experienced recurrence within five years. Radiomic features were extracted from routine preoperative CT scans. After preprocessing to remove highly constant and highly correlated features, the Synthetic Minority Over-sampling Technique addressed class imbalance in the training set. Recursive Feature Elimination identified the most predictive radiomic features. An XGBoost classifier was trained using optimized hyperparameters identified through RandomizedSearchCV with cross-validation. Model performance was evaluated using the ROC curve and predictive metrics. Results: Five radiomic features differed significantly between recurrence groups (p = 0.007 to <0.001): Shape Sphericity, first-order 90Percentile, GLCM Autocorrelation, GLCM Cluster Shade, and GLDM Large Dependence Low Gray Level Emphasis. The radiomics model showed excellent discriminatory ability with AUC values of 0.99 (95% CI: 0.98–1.00), 0.97 (95% CI: 0.91–1.00), and 0.96 (95% CI: 0.85–1.00) on the training, validation, and test sets, respectively. On the test set, the model achieved sensitivity of 100% (95% CI: 51–100%), specificity of 94% (95% CI: 81–98%), PPV of 67% (95% CI: 30–90%), NPV of 100% (95% CI: 90–100%), and overall accuracy of 95% (95% CI: 83–99%). Conclusions: Under protocol-homogeneous imaging conditions, CT radiomics accurately predicted recurrence in patients with completely resected stage I lung adenocarcinoma. External multi-vendor validation is needed before broader deployment.

Purpose: In cancers imaged using contrast-enhanced protocols, such as hepatocellular carcinoma (HCC), formal guidelines rely on measurements of lesion size (in mm) and radiographic density (in Hounsfield units [HU]) to evaluate response to treatment. However, the variability of these measurements across different contrast enhancement phases remains poorly understood. This limits the ability of clinicians to discern whether measurement changes are accurate. Methods: In this study, we investigated the variability of maximal lesion diameter and mean lesion density of HCC lesions on CT scans across four different contrast enhancement phases: non-contrast-enhanced phase (NCE), early arterial phase (E-AP), late arterial phase (L-AP), and portal venous phase (PVP). HCC lesions were independently segmented by two expert radiologists. For each pair of a lesion’s scan timepoints, one was selected randomly as the baseline measurement and the other as the repeat measurement. Both absolute and relative differences in measurements were calculated, as were the coefficients of variance (CVs). Analysis was further stratified by both contrast enhancement phase and lesion diameter. Results: Lesion diameter was found to have a CV of 5.11% (95% CI: 4.20–6.01%). About a fifth of the measurement’s relative changes were greater than 10%. Although there was no significant difference in diameter measurements across different phases, there was a significant negative correlation (R = −0.303, p-value = 0.030) between lesion diameter and percent difference in diameter measurement. Lesion density measurements varied significantly across all phases, with the greatest relative difference of 47% in the late arterial phase and a CV of 22.84% (21.48–24.20%). The overall CV for lesion density measurements was 26.19% (24.66–27.72%). Conclusions: Changes in tumor diameter measurements within 10% may simply be due to variability, and lesion density is highly sensitive to contrast timing. This highlights the importance of paying attention to these two variables when evaluating tumor response in both clinical trials and practice.

Contrast-enhanced computed tomography scans (CECT) are routinely used in the evaluation of different clinical scenarios, including the detection and characterization of hepatocellular carcinoma (HCC). Quantitative medical image analysis has been an exponentially growing scientific field. A number of studies reported on the effects of variations in the contrast enhancement phase on the reproducibility of quantitative imaging features extracted from CT scans. The identification and labeling of phase enhancement is a time-consuming task, with a current need for an accurate automated labeling algorithm to identify the enhancement phase of CT scans. In this study, we investigated the ability of machine learning algorithms to label the phases in a dataset of 59 HCC patients scanned with a dynamic contrast-enhanced CT protocol. The ground truth labels were provided by expert radiologists. Regions of interest were defined within the aorta, the portal vein, and the liver. Mean density values were extracted from those regions of interest and used for machine learning modeling. Models were evaluated using accuracy, the area under the curve (AUC), and Matthew’s correlation coefficient (MCC). We tested the algorithms on an external dataset (76 patients). Our results indicate that several supervised learning algorithms (logistic regression, random forest, etc.) performed similarly, and our developed algorithms can accurately classify the phase of contrast enhancement.