Background/Objectives: Diffusion-weighted imaging (DWI) is a magnetic resonance technique used to map the apparent diffusion coefficient (ADC) of water in human tissue. ADC assessment plays a central role in clinical diagnostics, as malignant tissues typically exhibit reduced water mobility and, thus, lower ADC values. Accurately measuring the ADC requires effective fat suppression to prevent contamination from the residual fat signal, which is commonly believed to cause ADC underestimation. This study aimed to demonstrate that ADC overestimation may occur as well. Methods: Our theoretical analysis shows that out-of-phase conditions between fat and water signals lead to ADC overestimations. We performed demonstration experiments on fat-water phantoms and the breasts of 10 healthy female volunteers. In particular, we considered three out-of-phase conditions: First and second, short-time inversion recovery (STIR) fat suppression with incorrect inversion time and incorrect flip angle, respectively. Third, phase differences due to spectral fat saturation. The ADC values were assessed in regions of interest (ROIs) that included both water and residual fat signals. Results: In the phantoms and the volunteer data, ROIs containing both fat and water signals consistently exhibited lower ADC values under in-phase conditions and higher ADC values under out-of-phase conditions. Conclusions: We demonstrated that out-of-phase conditions can result in ADC overestimation in the presence of residual fat signals, potentially resulting in false-negative classifications where malignant lesions are misinterpreted as benign due to an elevated ADC. Out-of-phase fat and water signals might also reduce lesion conspicuity in high b-value images, potentially masking clinically relevant findings.

Objectives: To develop two different radiomic models based on preoperative contrast-enhanced computed tomography (PP CT) to predict microsatellite instability (MSI) in patients with colorectal cancer (CRC) before surgery. Methods: PP CT scans of 115 CC patients were segmented using 3DSlicer (v5.6.1). Model I included images from three different scanners (GE, Siemens, Philips), while Model II used only one scanner (GE). For Model I, 80 patients were used for training and 35 for internal validation; for Model II, 46 and 24 patients were used, respectively. Data on sex, age, tumour location, and MSI genomic status were collected. A total of 107 radiomic features (RFs) were extracted, and 30 and 35 RFs were identified as relevant for Models I and II, respectively, using the t-test or Mann-Whitney test (p < 0.05). The most robust RFs were selected using the LASSO regression method. Both models were internally validated. Results: Model I, based on 2 RFs and 1 clinical feature (LOCATION) achieved an AUC of 0.76 (95% CI: 0.65-0.87) in the training cohort and 0.74 (95% CI: 0.56-0.92) in the validation cohort. Model II, based on 3 RFs, achieved an AUC of 0.85 (95% CI: 0.73-0.96) in the training cohort and 0.72 (95% CI: 0.50-0.94) in the validation cohort. Conclusions: Both radiomic models showed good performance in distinguishing between MSI and non-MSI tumours, potentially reducing the need for invasive histological testing and improving treatment timing. Despite achieving a higher AUC, Model II showed signs of overfitting when compared to Model I, which incorporated two RFs and one clinical feature (LOCATION). Radiomics may function as a non-invasive preoperative screening tool to inform decisions regarding MSI testing and treatment. Building radiomic models on larger, more diverse datasets is preferable to enhance generalizability and reduce overfitting.

Background/Objectives: The recent development of four-dimensional X-ray velocimetry (4DXV) technology (three-dimensional space and time) provides a unique opportunity to obtain preclinical quantitative functional lung images. Only single-scan measurements in non-survival studies have been obtained to date; thus, methodologies enabling animal survival for repeated imaging to be accomplished over weeks or months from the same animal would establish new opportunities for the assessment of pathophysiology drivers and treatment response in advanced preclinical drug-screening efforts. Methods: An anesthesia protocol developed for animal recovery to allow for repetitive, longitudinal scanning of individual animals over time. Test–retest imaging scans from the lungs of healthy mice were performed over 8 weeks to assess the repeatability of scanner-derived quantitative imaging metrics and variability. Results: Using a murine model of fibroproliferative lung disease, this longitudinal scanning approach captured heterogeneous progressive changes in pulmonary function, enabling the visualization and quantitative measurement of averaged whole lung metrics and spatial/regional change. Radiation dosimetry studies evaluated the effects of imaging acquisition protocols on X-ray dosage to further adapt protocols for the minimization of radiation exposure during repeat imaging sessions using these newly developed image acquisition protocols. Conclusions: Overall, we have demonstrated that the 4DXV advanced imaging scanner allows for repeat measurements from the same animal over time to enable the high-resolution, noninvasive mapping of quantitative lung airflow dysfunction in mouse models with heterogeneous pulmonary disease. The animal anesthesia and image acquisition protocols described will serve as the foundation on which further applications of the 4DXV technology can be used to study a diverse array of murine pulmonary disease models. Together, 4DXV provides a novel and significant advancement for the longitudinal, noninvasive interrogation of pulmonary disease to assess spatial/regional disease initiation, progression, and response to therapeutic interventions.

Breast cancer detection remains a significant challenge, with traditional mammography presenting barriers such as discomfort, radiation exposure, high false-positive rates, and financial burden. Moreover, younger women frequently fall outside routine mammographic screening guidelines, leaving critical gaps in early detection. Objectives: This study investigates the potential of quantitative transmission breast acoustic computed tomography scanner imaging (QT3D) as an innovative, non-invasive imaging modality for characterizing and evaluating breast masses. Methods: A comparative analysis between QT3D imaging and magnetic resonance imaging (MRI) was conducted in a cohort of patients with biopsy-proven benign or malignant breast lesions, comparing key metrics in quantifying breast masses for the purposes of breast mass characterization. Results: The findings in this study highlight its capability in identifying relatively small tumors, multiple lesions, satellite lesions, intraductal extensions, and calcifications, in addition to offering valuable diagnostic insights. Conclusions: This work is a first step toward studies essential for confirming its clinical feasibility, establishing its role in breast cancer tumor characterization, and potentially improving patient outcomes.

This review explores how multimodal foundation models (MFMs) are transforming biliary tract cancer (BTC) research. BTCs are aggressive malignancies with poor prognosis, presenting unique challenges due to difficult diagnostic methods, molecular complexity, and rarity. Importantly, intrahepatic cholangiocarcinoma (iCCA), perihilar cholangiocarcinoma (pCCA), and distal bile duct cholangiocarcinoma (dCCA) represent fundamentally distinct clinical entities, with iCCA presenting as mass-forming lesions amenable to biopsy and targeted therapies, while pCCA manifests as infiltrative bile duct lesions with challenging diagnosis and primarily palliative management approaches. MFMs offer potential to advance research by integrating radiological images, histopathology, multi-omics profiles, and clinical data into unified computational frameworks, with applications tailored to these distinct BTC subtypes. Key applications include enhanced biomarker discovery that identifies previously unrecognizable cross-modal patterns, potential for improving currently limited diagnostic accuracy—though validation in BTC-specific cohorts remains essential—accelerated drug repurposing, and advanced patient stratification for personalized treatment. Despite promising results, challenges such as data scarcity, high computational demands, and clinical workflow integration remain to be addressed. Future research should focus on standardized data protocols, architectural innovations, and prospective validation studies. The integration of artificial intelligence (AI)-based methodologies offers new solutions for these historically challenging malignancies. However, current evidence for BTC-specific applications remains largely theoretical, with most studies limited to proof-of-concept designs or related cancer types. Comprehensive clinical validation studies and prospective trials demonstrating patient benefit are essential prerequisites for clinical implementation. The timeline for evidence-based clinical adoption likely extends 7–10 years, contingent on successful completion of validation studies addressing current evidence gaps.

Background: Accurate subtype identification of lymphoma cancer is crucial for effective diagnosis and treatment planning. Although standard deep learning algorithms have demonstrated robustness, they are still prone to overfitting and limited generalization, necessitating more reliable and robust methods. Objectives: This study presents an autoencoder-augmented stacked ensemble learning (SEL) framework integrating deep feature extraction (DFE) and ensembles of machine learning classifiers to improve lymphoma subtype identification. Methods: Convolutional autoencoder (CAE) was utilized to obtain high-level feature representations of histopathological images, followed by dimensionality reduction via Principal Component Analysis (PCA). Various models were utilized for classifying extracted features, i.e., Random Forest (RF), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), AdaBoost, and Extra Trees classifiers. A Gradient Boosting Machine (GBM) meta-classifier was utilized in an SEL approach to further fine-tune final predictions. Results: All the models were tested using accuracy, area under the curve (AUC), and Average Precision (AP) metrics. The stacked ensemble classifier performed better than all the individual models with a 99.04% accuracy, 0.9998 AUC, and 0.9996 AP, far exceeding what regular deep learning (DL) methods would achieve. Of standalone classifiers, MLP (97.71% accuracy, 0.9986 AUC, 0.9973 AP) and Random Forest (96.71% accuracy, 0.9977 AUC, 0.9953 AP) provided the best prediction performance, while AdaBoost was the poorest performer (68.25% accuracy, 0.8194 AUC, 0.6424 AP). PCA and t-SNE plots confirmed that DFE effectively enhances class discrimination. Conclusion: This study demonstrates a highly accurate and reliable approach to lymphoma classification by using autoencoder-assisted ensemble learning, reducing the misclassification rate and significantly enhancing the accuracy of diagnosis. AI-based models are designed to assist pathologists by providing interpretable outputs such as class probabilities and visualizations (e.g., Grad-CAM), enabling them to understand and validate predictions in the diagnostic workflow. Future studies should enhance computational efficacy and conduct multi-centre validation studies to confirm the model’s generalizability on extensive collections of histopathological datasets.

Background/Objectives: Myelofibrosis (MF) is a myeloproliferative neoplasm characterized by the replacement of healthy bone marrow (BM) with malignant and fibrotic tissue. In a healthy state, bone marrow is composed of approximately 60–70% fat cells, which are replaced as disease progresses. Proton density fat fraction (PDFF), a non-invasive and quantitative MRI metric, enables analysis of BM architecture by measuring the percentage of fat versus cells in the environment. Our objective is to investigate variance in quantitative PDFF-MRI values over time as a marker of disease progression and response to treatment. Methods: We analyzed existing data from three cohorts of mice: two groups with MF that failed to respond to therapy with approved drugs for MF (ruxolitinib, fedratinib), investigational compounds (navitoclax, balixafortide), or vehicle and monitored over time by MRI; the third group consisted of healthy controls imaged at a single time point. Using in-house MATLAB programs, we performed a voxel-wise analysis of PDFF values in lower extremity bone marrow, specifically comparing the variance of each voxel within and among mice. Results: Our findings revealed a significant difference in PDFF values between healthy and diseased BM. With progressive disease non-responsive to therapy, the expansion of hematopoietic cells in BM nearly completely replaced normal fat, as determined by a markedly reduced PDFF and notable reduction in the variance in PDFF values in bone marrow over time. Conclusions: This study validated our hypothesis that the variance in PDFF in BM decreases with disease progression, indicating pathologic expansion of hematopoietic cells. We can conclude that disease progression can be tracked by a decrease in PDFF values. Analyzing variance in PDFF may improve the assessment of disease progression in pre-clinical models and ultimately patients with MF.

Objectives: To evaluate the agreement between AI-CAD-guided mammographic and MRI measurements of tumor size and T stage in breast cancer patients being considered for neoadjuvant chemotherapy (NAC). Methods: This retrospective study included 144 women (mean age, 52 ± 11 years) with invasive breast cancer who subsequently received NAC and underwent both AI-CAD mammography (score ≥ 10) and pre-treatment MRI. Tumor sizes from AI-CAD contours were compared with MRI using Pearson correlation, intraclass correlation coefficients (ICCs), and Bland–Altman analysis. Concordance was defined as a ±0.5 cm difference. The contour showing the highest agreement was used to compare T stage with MRI using weighted kappa. Results: The mean AI-CAD abnormality score was 86.3 ± 22.2. Tumor sizes on mammography were 3.0 ± 1.2 cm (inner), 3.8 ± 1.5 cm (middle), and 4.8 ± 2.2 cm (outer), while the MRI-measured tumor size was 4.0 ± 1.9 cm. The middle contour showed the strongest correlation with MRI (r = 0.897; ICC = 0.866), the smallest mean difference (–0.19 cm; limits of agreement, –1.87 to 1.49), and the highest concordance (61.1%). Agreement was higher in mass-only lesions than in NME-involved lesions (ICC = 0.883 vs. 0.775; concordance, 70.9% vs. 46.6%). T stage comparison using the middle contour showed substantial agreement with MRI (κ = 0.743 [95% CI, 0.634–0.852]; agreement, 88.2%), with higher concordance in mass-only lesions (93.0%) than NME-involved lesions (81.0%) and more frequent understaging in the latter (17.2% vs. 2.3%). Conclusions: AI-CAD-guided mammographic assessment using the middle contour demonstrated good agreement with MRI for tumor size and T stage, indicating its value as a supportive tool for clinical staging in MRI-limited settings.

Background: This study aimed to evaluate whether low-concentration iodine contrast-enhanced multiphase low-monoenergetic computed tomography (LCLM CT; 270 mg I/mL, 40 keV) is non-inferior to standard-dose computed tomography (SDCT; 350 mg I/mL) in image quality and lesion detectability for chronic liver disease patients. Methods: Sixty-seven patients underwent both protocols. Image quality was assessed using a 5-point scale with a non-inferiority margin of −0.5. Quantitative metrics included signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). Lesion detectability was evaluated using jackknife free-response receiver operating characteristic (JAFROC) analysis with a −0.1 margin. Results: LCLM CT reduced iodine dose per kilogram by 21.9%. Despite higher image noise, it achieved higher CNR for the aorta and hepatic lesions, as well as superior hepatic artery clarity. Image quality was non-inferior (difference: −0.119; 95% CI: −0.192 to −0.047), and lesion detectability (FOM: 0.744 vs. 0.721; difference: 0.023; 95% CI: −0.170 to 0.218) also showed non-inferiority. Conclusions: LCLM CT maintains diagnostic performance and improves vascular contrast while reducing iodine burden, supporting its clinical utility in longitudinal HCC surveillance.

Background: Deep learning (DL) reconstruction techniques have shown promise in reducing MRI acquisition times while maintaining image quality. However, the impact of different acceleration factors on diagnostic accuracy in shoulder MRI remains unexplored in clinical practice. Purpose: The purpose of this study was to evaluate the diagnostic accuracy of 2-fold and 4-fold DL-accelerated shoulder MRI protocols compared to standard protocols in clinical practice. Materials and Methods: In this prospective single-center study, 88 consecutive patients (49 males, 39 females; mean age, 51 years) underwent shoulder MRI examinations using standard, 2-fold (DL2), and 4-fold (DL4) accelerated protocols between June 2023 and January 2024. Four independent radiologists (experience range: 4–25 years) evaluated the presence of bone marrow edema (BME), rotator cuff tears, and labral lesions. The sensitivity, specificity, and interobserver agreement were calculated. Diagnostic confidence was assessed using a 4-point scale. The impact of reader experience was analyzed by stratifying the radiologists into ≤10 and >10 years of experience. Results: Both accelerated protocols demonstrated high diagnostic accuracy. For BME detection, DL2 and DL4 achieved 100% sensitivity and specificity. In rotator cuff evaluation, DL2 showed a sensitivity of 98–100% and specificity of 99–100%, while DL4 maintained a sensitivity of 95–98% and specificity of 99–100%. Labral tear detection showed perfect sensitivity (100%) with DL2 and slightly lower sensitivity (89–100%) with DL4. Interobserver agreement was excellent across the protocols (Kendall’s W = 0.92–0.98). Reader experience did not significantly impact diagnostic performance. The area under the ROC curve was 0.94 for DL2 and 0.90 for DL4 (p = 0.32). Clinical Implications: The implementation of DL-accelerated protocols, particularly DL2, could improve workflow efficiency by reducing acquisition times by 50% while maintaining diagnostic reliability. This could increase patient throughput and accessibility to MRI examinations without compromising diagnostic quality. Conclusions: DL-accelerated shoulder MRI protocols demonstrate high diagnostic accuracy, with DL2 showing performance nearly identical to that of the standard protocol. While DL4 maintains acceptable diagnostic accuracy, it shows a slight sensitivity reduction for subtle pathologies, particularly among less experienced readers. The DL2 protocol represents an optimal balance between acquisition time reduction and diagnostic confidence.