Contrast-enhanced Imaging Research Articles

Imaging Findings of Human Papillomavirus-Positive and Human Papillomavirus-Negative Oropharyngeal Squamous Cell Carcinoma Associated with Recurrence

Objectives: This study aimed to compare the imaging findings associated with the recurrence of HPV-positive and HPV-negative oropharyngeal squamous cell carcinoma (OPSCC). Methods: In total, 68 patients (51 men; mean age, 64.4 years; age range, 41–86 years; 48 HPV-positive patients and 20 HPV-negative patients) with histopathologically proven OPSCC who underwent CT, MRI, and 18F-FDG-PET/CT before treatment between October 2014 and July 2022 were enrolled in this study. The imaging findings were retrospectively evaluated and statistically compared. Results: HPV-positive OPSCC had a significantly lower recurrence rate compared with that of HPV-negative OPSCC (p < 0.01). Among HPV-positive OPSCCs, patients with recurrence were considerably older than those without recurrence (p < 0.05); however, the T and N categories did not differ between the two groups. Meanwhile, among HPV-negative OPSCCs, the T and N categories were associated with recurrence (p < 0.05). Furthermore, the attenuation on contrast-enhanced CT (p < 0.05) and signal intensity on contrast-enhanced T1-weighted images (p < 0.05) of nodal metastases were significantly lower in recurrence patients compared to those in nonrecurrence patients. Cystic change in nodal metastases in HPV-positive and HPV-negative OPSCCs were similar in patients with and without recurrence. Conclusions: The T and N categories were associated with recurrence in HPV-negative OPSCC but not in HPV-positive OPSCC. Prognostic factors differed significantly between HPV-positive and HPV-negative OPSCC.

Impact of contrast enhancement phase on CT-based radiomics analysis for predicting post-surgical recurrence in renal cell carcinoma.

To investigate the effect of CT enhancement phase on radiomics features for predicting post-surgical recurrence of clear cell renal cell carcinoma (ccRCC). This retrospective study included 144 patients who underwent radical or partial nephrectomy for ccRCC. Preoperative multiphase abdominal CT scans (non-contrast, corticomedullary, and nephrographic phases) were obtained for each patient. Automated segmentation of renal masses was performed using the nnU-Net framework. Radiomics signatures (RS) were developed for each phase using ensembles of machine learning-based models (Random Survival Forests [RSF], Survival Support Vector Machines [S-SVM], and Extreme Gradient Boosting [XGBoost]) with and without feature selection. Feature selection was performed using Affinity Propagation Clustering. The primary endpoint was disease-free survival, assessed by concordance index (C-index). The study included 144 patients. Radical and partial nephrectomies were performed in 81% and 19% of patients, respectively, with 81% of tumors classified as high grade. Disease recurrence occurred in 74 patients (51%). A total of 1,316 radiomics features were extracted per phase per patient. Without feature selection, C-index values for RSF, S-SVM, XGBoost, and Penalized Cox models ranged from 0.43 to 0.61 across phases. With Affinity Propagation feature selection, C-index values improved to 0.51-0.74, with the corticomedullary phase achieving the highest performance (C-index up to 0.74). The results of our study indicate that radiomics analysis of corticomedullary phase contrast-enhanced CT images may provide valuable predictive insight into recurrence risk for non-metastatic ccRCC following surgical resection. However, the lack of external validation is a limitation, and further studies are needed to confirm these findings in independent cohorts.

Deep learning radiomics nomogram for preoperatively identifying moderate-to-severe chronic cholangitis in children with pancreaticobiliary maljunction: a multicenter study

BackgroundLong-term severe cholangitis can lead to dense adhesions and increased fragility of the bile duct, complicating surgical procedures and elevating operative risk in children with pancreaticobiliary maljunction (PBM). Consequently, preoperative diagnosis of moderate-to-severe chronic cholangitis is essential for guiding treatment strategies and surgical planning. This study aimed to develop and validate a deep learning radiomics nomogram (DLRN) based on contrast-enhanced CT images and clinical characteristics to preoperatively identify moderate-to-severe chronic cholangitis in children with PBM.MethodsA total of 323 pediatric patients with PBM who underwent surgery were retrospectively enrolled from three centers, and divided into a training cohort (n = 153), an internal validation cohort (IVC, n = 67), and two external test cohorts (ETC1, n = 58; ETC2, n = 45). Chronic cholangitis severity was determined by postoperative pathology. Handcrafted radiomics features and deep learning (DL) radiomics features, extracted using transfer learning with the ResNet50 architecture, were obtained from portal venous-phase CT images. Multivariable logistic regression was used to establish the DLRN, integrating significant clinical factors with handcrafted and DL radiomics signatures. The diagnostic performances were evaluated in terms of discrimination, calibration, and clinical usefulness.ResultsBiliary stones and peribiliary fluid collection were selected as important clinical factors. 5 handcrafted and 5 DL features were retained to build the two radiomics signatures, respectively. The integrated DLRN achieved satisfactory performance, achieving area under the curve (AUC) values of 0.913 (95% CI, 0.834–0.993), 0.916 (95% CI, 0.845–0.987), and 0.895 (95% CI, 0.801–0.989) in the IVC, and two ETCs, respectively. In comparison, the clinical model, handcrafted signature, and DL signature had AUC ranges of 0.654–0.705, 0.823–0.857, and 0.840–0.872 across the same cohorts. The DLRN outperformed single-modality clinical, handcrafted radiomics, and DL radiomics models, with all integrated discrimination improvement values > 0 and P < 0.05. The Hosmer–Lemeshow test and calibration curves showed good consistency of the DLRN (P > 0.05), and the decision curve analysis and clinical impact curve further confirmed its clinical utility.ConclusionsThe integrated DLRN can be a useful and non-invasive tool for preoperatively identifying moderate-to-severe chronic cholangitis in children with PBM, potentially enhancing clinical decision-making and personalized management strategies.

Acetic acid enabled nuclear contrast enhancement in epi-mode quantitative phase imaging.

The acetowhitening effect of acetic acid (AA) enhances light scattering of cell nuclei, an effect that has been widely leveraged to facilitate tissue inspection for (pre)cancerous lesions. Here, we show that a concomitant effect of acetowhitening-changes in refractive index composition-yields nuclear contrast enhancement in quantitative phase imaging (QPI) of thick tissue samples. We aim to explore how changes in refractive index composition during acetowhitening can be captured through a novel epi-mode 3D QPI technique called quantitative oblique back-illumination microscopy (qOBM). We also aim to demonstrate the potential of using a machine learning-based approach to convert qOBM images of fresh tissues into virtually AA-stained images. We implemented qOBM, an imaging technique that allows for epi-mode 3D QPI to observe phase changes induced by AA in thick tissue samples. We focus on detecting nuclear contrast changes caused by AA in mouse brain samples. As a proof of concept, we also applied a Cycle-GAN algorithm to convert the acquired qOBM images into virtually AA-stained images, simulating the effect of AA staining. Our findings demonstrate that AA-induced acetowhitening leads to significant nuclear contrast enhancement in qOBM images of thick tissue samples. In addition, the Cycle-GAN algorithm successfully converted qOBM images into virtually AA-stained images, further facilitating the nuclear enhancement process without any physical stains. We show that the acetowhitening effect of acetic acid induces changes in refractive index composition that significantly enhance nuclear contrast in QPI. The application of qOBM with AA, along with the use of a Cycle-GAN algorithm to virtually stain tissues, highlights the potential of this approach for advancing label-free and slide-free, ex vivo, and in vivo histology.

Automatic cervical lymph nodes detection and segmentation in heterogeneous computed tomography images using deep transfer learning

To develop a deep learning model using transfer learning for automatic detection and segmentation of neck lymph nodes (LNs) in computed tomography (CT) images, the study included 11,013 annotated LNs with a short-axis diameter ≥ 3 mm from 626 head and neck cancer patients across four hospitals. The nnUNet model was used as a baseline, pre-trained on a large-scale head and neck dataset, and then fine-tuned with 4,729 LNs from hospital A for detection and segmentation. Validation was conducted on an internal testing cohort (ITC A) and three external testing cohorts (ETCs B, C, and D), with 1684 and 4600 LNs, respectively. Detection was evaluated via sensitivity, positive predictive value (PPV), and false positive rate per case (FP/vol), while segmentation was assessed using the Dice similarity coefficient (DSC) and Hausdorff distance (HD95). For detection, the sensitivity, PPV, and FP/vol in ITC A were 54.6%, 69.0%, and 3.4, respectively. In ETCs, the sensitivity ranged from 45.7% at 3.9 FP/vol to 63.5% at 5.8 FP/vol. Segmentation achieved a mean DSC of 0.72 in ITC A and 0.72 to 0.74 in ETCs, as well as a mean HD95 of 3.78 mm in ITC A and 2.73 mm to 2.85 mm in ETCs. No significant sensitivity difference was found between contrast-enhanced and unenhanced CT images (p = 0.502) or repeated CT images (p = 0.815) during adaptive radiotherapy. The model’s segmentation accuracy was comparable to that of experienced oncologists. The model shows promise in automatically detecting and segmenting neck LNs in CT images, potentially reducing oncologists’ segmentation workload.

Artificial intelligence-assisted precise preoperative prediction of lateral cervical lymph nodes metastasis in papillary thyroid carcinoma via a clinical-CT radiomic combined model.

This study aimed to develop an artificial intelligence-assisted model for the preoperative prediction of lateral cervical lymph node metastasis (LCLNM) in papillary thyroid carcinoma (PTC) using computed tomography (CT) radiomics, providing a new noninvasive and accurate diagnostic tool for PTC patients with LCLNM. This retrospective study included 389 confirmed PTC patients, randomly divided into a training set (n = 272) and an internal validation set (n = 117), with an additional 40 patients from another hospital as an external validation set. Patient demographics were evaluated to establish a clinical model. Radiomic features were extracted from preoperative contrast-enhanced CT images (venous phase) for each patient. Feature selection was performed using analysis of variance and the least absolute shrinkage and selection operator algorithm. We employed support vector machine, random forest (RF), logistic regression, and XGBoost algorithms to build CT radiomic models for predicting LCLNM. A radiomics score (Rad-score) was calculated using a radiomic signature-based formula. A combined clinical-radiomic model was then developed. The performance of the combined model was evaluated using the receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA). A total of 1724 radiomic features were extracted from each patient's CT images, with 13 features selected based on nonzero coefficients related to LCLNM. Four clinically relevant factors (age, tumor location, thyroid capsule invasion, and central cervical lymph node metastasis) were significantly associated with LCLNM. Among the algorithms tested, the RF algorithm outperformed the others with five-fold cross-validation on the training set. After integrating the best algorithm with clinical factors, the areas under the ROC curves for the training, internal validation, and external validation sets were 0.910 (95% confidence interval [CI]: 0.729-0.851), 0.876 (95% CI: 0.747-0.911), and 0.821 (95% CI: 0.555-0.802), respectively, with DCA demonstrating the clinical utility of the combined radiomic model. This study successfully established a clinical-CT radiomic combined model for predicting LCLNM, which may significantly enhance surgical decision-making for lateral cervical lymph node dissection in patients with PTC.

An international survey of diffusion and perfusion magnetic resonance imaging implementation in the head and neck.

The goal of this international survey was to understand how diffusion (DWI) and perfusion imaging (PWI) are being applied to clinical head and neck imaging. An online questionnaire focusing on acquisition, clinical indications, analysis, and reporting of qualitative DWI (QlDWI), quantitative DWI (QnDWI) and dynamic contrast-enhanced PWI (DCE-PWI) in the head and neck was circulated to members of the American Society of Head and Neck Radiology (ASHNR) and European Society of Head and Neck Radiology (ESHNR) over a 3-month period. Descriptive statistics and group comparisons were calculated with SPSS® v27. There were 294 unique respondents (17.6% response rate) from 256 institutions (182 ESHNR, 74 ASHNR). DWI was routinely acquired for some head and neck indications at 95.7% of the respondents' institutions, with 92.5% of radiologists interpreting QlDWI but only 36.7% analysing QnDWI. QlDWI was most frequently applied to primary mucosal masses or the middle ear, whilst QnDWI was routinely used to distinguish tumour histologies, and primary or recurrent carcinoma. DCE-PWI was routinely acquired at 53.6% of institutions and used by 40.8% of respondents, however, there was no clinical scenario in which it was routinely applied by most users. DCE-PWI analysis methods varied, with time-intensity curve classifications being the most frequently reported. Lack of standardisation was identified as a key reason for not implementing QnDWI, whilst numerous factors prevented the adoption of DCE-PWI. There is widespread routine interpretation of QlDWI by head and neck radiologists, but there is considerable variation in the application and analysis of head and neck QnDWI and DCE-PWI. Question How are diffusion (DWI) and dynamic contrast-enhanced perfusion imaging (DCE-PWI) being utilised by head and neck radiologists across a wide range of practices? Findings An international survey demonstrated widespread routine interpretation of qualitativeDWI but variable application and analysis of quantitative DWI and DCE-PWI with numerous barriers to implementation. Clinical relevance The survey results will aid discussion on how to standardise and optimally disseminate these MRI techniques in day-to-day practice. More focused education and resource allocation may be required to accelerate the adoption of quantitative DWI and DCE-PWI.

Microwave Ablation of T1a and T1b Renal Masses: A Retrospective Study

AbstractThe aim of this study was to evaluate the efficacy and safety of microwave ablation (MWA) for the treatment of T1a and T1b renal masses, with size ranges between 1.2 and 6.5 cm. A retrospective review was performed at a single tertiary comprehensive cancer center between June 2019 and June 2023 of 49 consecutive patients (53 total procedures) who underwent MWA for renal masses. The Solero microwave tissue ablation system (Angiodynamics, Latham, NY, United States) was utilized. Patient demographics, renal mass characteristics, and procedural outcomes were collected. Serum creatinine and estimated glomerular filtration rate (eGFR) were utilized to assess renal functional outcomes. Oncologic outcomes were assessed using evidence of local tumor recurrence on contrast-enhanced cross-sectional imaging, local recurrence-free probability at 1 and 2 years, and overall survival (OS) using the Kaplan–Meier analysis.Forty-nine patients (57% males and 43% females) with a median age of 72 years (range, 38–84 years) underwent 53 MWA procedures. The mean renal mass size was 2.8 ± 0.94 cm (range, 1.2–6.5 cm). Most of the renal tumors were T1a. Three of the 53 total renal tumors were larger than 4 cm (T1b) and the remaining 50 were less than 4 cm in size (T1a). The largest tumor that was ablated was 6.5 cm in size. All the patients were placed under general anesthesia (intubated) before the MWA procedure. A median microwave energy of 100 W (range, 60–140 W) was used. The mean duration of the MWA was 3.9 ± 1.5 minutes, with a 100% technical success rate. Four patients (8.2%) experienced complications, two (4.1%) of whom experienced a major complication. There was no clinically significant change in renal function from pre- to postablation on day 1 or at 3 months. Furthermore, local tumor recurrence was observed in three (6.1%) patients at 2.5, 15, and 25 months postablation. Local recurrence-free probability was 98 and 93% at 1 and 2 years, respectively. The OS was 98 and 87% at 1 and 2 years, respectively. MWA continues to prove to be an effective technique that can be used to treat small renal masses including oncocytomas, with high technical success, low complication rate, low risk of adverse renal functional outcomes, and encouraging results for sustained tumor control.

Advanced Multiparametric MRI Strategies for Tumor Restaging After Neoadjuvant Therapy in Locally Advanced Gastric Cancer.

This study tested the diagnostic accuracy of multiparametric magnetic resonance imaging (mpMRI) in restaging locally advanced gastric cancer after neoadjuvant therapy (NAT) using pathologic T stage (ypT) and pathologic N stage (ypN) as the reference standard. Between August 2022 and September 2023, the study enrolled a prospective cohort of 70 gastric cancer patients who underwent NAT and subsequent surgical resection. MRI procedures, including DLSB T2-weighted imaging (T2WI), ZOOMit diffusion-weighted imaging (DWI), and XD-VIBE dynamic contrast-enhanced imaging (DCE), were performed after NAT and before surgery. Four abdominal radiologists independently assigned radiologic T stage (yrT) and radiologic N stage (yrN) based on individual and combined sequences. Inter-reader agreement was quantified using Kendall's coefficient. Diagnostic accuracy was determined by comparing MRI assessments and pathologic outcomes, with pairwise comparisons analyzed via the McNemar test. Subgroup analysis evaluated the performance in identifying good responders to NAT. Inter-reader agreement was almost perfect for T restaging and substantial for N restaging. Diagnostic accuracy for T restaging was 0.432 using DLSB-T2WI, 0.586 using ZOOMit DWI, 0.557 using XD-VIBE DCE, and 0.586 using mpMRI. The accuracy demonstrated by DWI, DCE and mpMRI was superior to that of T2WI (all P < 0.05). For N restaging, the accuracy of the mpMRI protocol was 0.443. Notably, mpMRI achieved an AUC of 0.879 (95% confidence interval 0.835-0.915) for differentiating ypT0-1 tumors. Advanced mpMRI strategies can serve as a valuable tool for restaging gastric cancer after NAT. Accurately differentiating good responders to neoadjuvant therapy through mpMRI holds significant clinical implications for personalized treatment strategies and improved patient outcomes.

Associations of Postencephalitic Epilepsy Using Multi-Contrast Whole Brain MRI: A Large Self-Supervised Vision Foundation Model Strategy.

Postencephalitic epilepsy (PEE) is a severe neurological complication following encephalitis. Early identification of individuals at high risk for PEE is important for timely intervention. To develop a large self-supervised vision foundation model using a big dataset of multi-contrast head MRI scans, followed by fine-tuning with MRI data and follow-up outcomes from patients with PEE to develop a PEE association model. Retrospective. Fifty-seven thousand six hundred twenty-one contrast-enhanced head MRI scans from 34,871 patients for foundation model construction, and head MRI scans from 144 patients with encephalitis (64 PEE, 80 N-PEE) for the PEE association model. 1.5-T, 3-T, T1-weighted imaging, T2-weighted imaging, fluid attenuated inversion recovery, T1-weighted contrast-enhanced imaging. The foundation model was developed using self-supervised learning and cross-contrast context recovery. Patients with encephalitis were monitored for a median of 3.7 years (range 0.7-7.5 years), with epilepsy diagnosed according to International League Against Epilepsy. Occlusion sensitivity mapping highlighted brain regions involved in PEE classifications. Model performance was compared with DenseNet without pre-trained weights. Performance was assessed via confusion matrices, accuracy, sensitivity, specificity, precision, F1 score, and area under the receiver operating characteristic curve (AUC). The DeLong test evaluated AUC between the two models (P < 0.05 for statistical significance). The PEE association model achieved accuracy, sensitivity, specificity, precision, F1 score, and AUC of 79.3% (95% CI: 0.71-0.92), 92.3% (95% CI: 0.80-1.00), 68.8% (95% CI: 0.55-0.87), 70.6% (95% CI: 0.61-0.90), 80.0% (95% CI: 0.71-0.93), and 81.0% (95% CI: 0.68-0.92), respectively. A significant AUC improvement was found compared to DenseNet (Delong test, P = 0.03). The association model focused on brain regions affected by encephalitis. Using extensive unlabeled data via self-supervised learning addressed the limitations of supervised tasks with limited data. The fine-tuned foundation model outperformed DenseNet, which was trained exclusively on task data. This research develops a model to assess the occurrence epilepsy after encephalitis, a severe brain inflammation condition. By using over 57,000 brain scans, the study trains a computer program to recognize patterns in brain images. The model analyzes whole-brain scans to identify areas commonly affected by the disease, such as the temporal and frontal lobes. It was tested on data from patients with encephalitis and showed better performance than older methods. The model can assess the risk of secondary epilepsy in patients with encephalitis, allowing doctors to intervene early and improve treatment outcomes for those affected by this condition. 4 TECHNICAL EFFICACY: Stage 1.

Multi-Scale Adaptive Contrast Enhancement (MSACE) for Color Images: A Comparative Analysis with Conventional Techniques

This study introduces a novel contrast enhancement algorithm, Multi-Scale Adaptive Con- trast Enhancement (MSACE), which adapts contrast adjustments across multiple brightness scales in color images while preserving fine details. MSACE employs brightness segmenta- tion, adaptive scaling, and edge-based detail preservation to deliver enhanced contrast with- out overexposure or detail loss, addressing limitations found in conventional methods. Com- parative results between MSACE and traditional methods—Simple Contrast Scaling, Gamma Correction, Histogram Equalization, and Adaptive Histogram Equalization (CLAHE)—are validated through quantitative metrics and visual assessments. MSACE consistently outper- forms the other methods in delivering superior visual quality, preserving edge details, and achieving balanced contrast distribution.

Noncontrast imaging for the surveillance of treated and untreated meningiomas.

Patients with meningiomas require serial MRI for surveillance of tumor size and growth rate. The cost and resource requirements for contrast-enhanced MRI include intravenous cannulation, the contrast agent, risk of adverse reaction, and the time needed to acquire, review, and report the additional sequences. With repeated doses, gadolinium is known to accumulate in neural tissues. The authors compared the correlation and accuracy of axial T2-weighted imaging (T2WI) sequences alone for assessing tumor growth, dimensions, and dural venous sinus invasion compared with the current clinical practice of assessing both contrast-enhanced T1-weighted imaging (CE-T1WI) and T2WI sequences. The authors retrospectively identified 136 adult patients (65 patients with treated and 71 patients with untreated meningiomas) with two MRI scans obtained at least 6 months apart. For each patient, the two CE-T1WI sequences separated by time were paired, as were the two T2WI sequences, and assessed independently. The paired scans were assessed by a neuroradiologist and advanced radiology trainee blinded to clinical data. Tumor location, dimensions, growth, and venous invasion were evaluated. Peritumoral edema was assessed on T2WI only. Agreement between assessments on both CE-T1WI and T2WI sequences compared with T2WI alone was evaluated using Cohen's kappa (κ), the intraclass correlation coefficient (ICC), and Bland-Altman plots. Growth was detected in 36 tumors on T2WI compared with 39 when both CE-T1WI and T2WI were assessed. Growth assessed on T2WI alone showed near-perfect agreement with growth assessed on CE-T1WI and T2WI together (κ = 0.945). T2WI alone had an accuracy of 97.8%, specificity of 100%, and sensitivity of 92.3%. Interrater correlation between the radiologists for tumor dimensions was good to excellent (ICC > 0.843). Intrarater agreement between T2WI and CE-T1WI measurements of anteroposterior and transverse tumor dimensions was good (ICC > 0.883 for observer 1, > 0.767 for observer 2). There was substantial agreement between venous invasion on T2WI and both CE-T1WI and T2WI (κ = 0.771). Subgroup analysis for skull base (58.1%), treated (47.8%), and large (> 20-mm diameter; 38.2%) meningiomas did not show any significant difference in agreement between T2WI only and CE-T1WI and T2WI assessments of growth, venous invasion, or tumor dimension. In patients with treated and untreated meningiomas, unenhanced T2WI can assess tumor dimensions, detect growth, and detect venous invasion with comparable reliability and accuracy to the current clinical practice of using both CE-T1WI and T2WI.

A Comprehensive Strategy for the Identification of Arachnoid Cysts in the Brain Utilizing Image Processing Segmentation Methods

This study focuses on the segmentation and characterization of arachnoid cysts in brain MRI images, aiming to enhance diagnostic accuracy through advanced image processing techniques. Arachnoid cysts are cerebrospinal fluid-filled sacs located between the brain or spinal cord and the arachnoid membrane. These cysts can be asymptomatic but may also cause neurological symptoms such as headaches, seizures, or cognitive impairments when they increase in size or pressure. Accurate detection and characterization are essential for timely intervention and treatment. In this research, 269 brain MRI images were analyzed using connected component analysis (CCA) and contrast-limited adaptive histogram equalization (CLAHE). CLAHE was employed to enhance image contrast, particularly in regions with subtle intensity differences, while CCA facilitated the segmentation of connected regions corresponding to cysts. The smallest connected components were identified and analyzed to isolate arachnoid cysts with high precision. Post-segmentation, quantitative analysis was performed to extract features such as size, shape, and density, enabling comprehensive cyst characterization. Additionally, calculations for area and approximate volume were conducted, providing critical information for clinical assessment. Visual validation of segmentation outcomes confirmed the effectiveness of the applied methods in accurately delineating cyst boundaries. This research addresses a significant gap in the existing literature. While most studies focus on brain tumor segmentation, there is limited work on arachnoid cyst detection and volume estimation. By integrating image processing techniques tailored for arachnoid cysts, this study offers a novel approach to their diagnosis and monitoring. The findings demonstrate the potential for automated diagnostic tools, reducing subjectivity and improving efficiency in clinical workflows. The proposed methodology aligns with advancements in medical imaging and contributes to the development of improved tools for neuroimaging diagnostics, paving the way for more precise and reliable assessments in the detection of brain pathologies.

Fully automated segmentation and classification of renal tumors on CT scans via machine learning

BackgroundTo develop and test the performance of a fully automated system for classifying renal tumor subtypes via deep machine learning for automated segmentation and classification.Materials and methodsThe model was developed using computed tomography (CT) images of pathologically proven renal tumors collected from a prospective cohort at a medical center between March 2016 and December 2020. A total of 561 renal tumors were included: 233 clear cell renal cell carcinomas (RCCs), 82 papillary RCCs, 74 chromophobe RCCs, and 172 angiomyolipomas. Renal tumor masks manually drawn on contrast-enhanced CT images were used to develop a 3D U-Net-based deep learning model for fully automated tumor segmentation. After segmentation, the entire classification pipeline, including feature extraction and subtype classification, was conducted without any manual intervention. Both conventional radiological features (Hounsfield units, HUs) and radiomic features extracted from areas predicted by the deep learning models were used to develop an algorithm for classifying renal tumor subtypes via a random forest classifier. The performance of the segmentation model was evaluated using the Dice similarity coefficient, while the classification model was assessed based on accuracy, sensitivity, and specificity.ResultsFor tumors larger than 4 cm, the Dice similarity coefficient (DSC) for automated segmentation was 0.83, while for tumors smaller than 4 cm, the DSC was 0.65. The classification accuracy (ACC) for distinguishing RCC subtypes was 0.77 for tumors larger than 4 cm and 0.68 for tumors smaller than 4 cm. Additionally, the accuracy for benign versus malignant classification was 0.85.ConclusionsOur automatic segmentation and classifier model showed promising results for renal tumor segmentation and classification.

End-to-End Deep Learning Prediction of Neoadjuvant Chemotherapy Response in Osteosarcoma Patients Using Routine MRI.

This study aims to develop an end-to-end deep learning (DL) model to predict neoadjuvant chemotherapy (NACT) response in osteosarcoma (OS) patients using routine magnetic resonance imaging (MRI). We retrospectively analyzed data from 112 patients with histologically confirmed OS who underwent NACT prior to surgery. Multi-sequence MRI data (including T2-weighted and contrast-enhanced T1-weighted images) and physician annotations were utilized to construct an end-to-end DL model. The model integrates ResUNet for automatic tumor segmentation and 3D-ResNet-18 for predicting NACT efficacy. Model performance was assessed using area under the curve (AUC) and accuracy (ACC). Among the 112 patients, 51 exhibited a good NACT response, while 61 showed a poor response. No statistically significant differences were found in age, sex, alkaline phosphatase levels, tumor size, or location between these groups (P > 0.05). The ResUNet model achieved robust performance, with an average Dice coefficient of 0.579 and average Intersection over Union (IoU) of 0.463. The T2-weighted 3D-ResNet-18 classification model demonstrated superior performance in the test set with an AUC of 0.902 (95% CI: 0.766-1), ACC of 0.783, sensitivity of 0.909, specificity of 0.667, and F1 score of 0.800. Our proposed end-to-end DL model can effectively predict NACT response in OS patients using routine MRI, offering a potential tool for clinical decision-making.

Uncertainty quantification in multi-parametric MRI-based meningioma radiotherapy target segmentation

PurposeThis work investigates the use of a spherical projection-based U-Net (SPU-Net) segmentation model to improve meningioma segmentation performance and allow for uncertainty quantification.MethodsA total of 76 supratentorial meningioma patients treated with radiotherapy were studied. Gross tumor volumes (GTVs) were contoured by a single experienced radiation oncologist on high-resolution contrast-enhanced T1 MRI scans (T1ce), and both T1 and T1ce images were utilized for segmentation. SPU-Net, an adaptation of U-Net incorporating spherical image projection to map 2D images onto a spherical surface, was proposed. As an equivalence of a nonlinear image transform, projections enhance locoregional details while maintaining the global field of view. By employing multiple projection centers, SPU-Net generates various GTV segmentation predictions, the variance indicating the model’s uncertainty. This uncertainty is quantified on a pixel-wise basis using entropy calculations and aggregated through Otsu’s method for a final segmentation.Results/conclusionThe SPU-Net model poses an advantage over traditional U-Net models by providing a quantitative method of displaying segmentation uncertainty. Regarding segmentation performance, SPU-Net demonstrated comparable results to a traditional U-Net in sensitivity (0.758 vs. 0.746), Dice similarity coefficient (0.760 vs. 0.742), reduced mean Hausdorff distance (mHD) (0.612 cm vs 0.744 cm), and reduced 95% Hausdorff distance (HD95) (2.682 cm vs 2.912 cm). SPU-Net not only is comparable to U-Net in segmentation performance but also offers a significant advantage by providing uncertainty quantification. The added SPU-Net uncertainty mapping revealed low uncertainty in accurate segments (e.g., within GTV or healthy tissue) and higher uncertainty in problematic areas (e.g., GTV boundaries, dural tail), providing valuable insights for potential manual corrections. This advancement is particularly valuable given the complex extra-axial nature of meningiomas and involvement with dural tissue. The capability to quantify uncertainty makes SPU-Net a more advanced and informative tool for segmentation, without sacrificing performance.

Scanning K-edge subtraction (SKES) imaging with laser-compton x-ray sources.

K-edge subtraction (KES) imaging is a dual-energy imaging technique that enhances contrast by subtracting images taken with x-rays that are above and below the K-edge energy of a specified contrast agent. The resulting reconstruction spatially identifies where the contrast agent accumulates, even when obscured by complex and heterogeneous distributions of human tissue. This method is most successful when x-ray sources are quasimonoenergetic and tunable, conditions that have traditionally only been met at synchrotrons. Laser-Compton x-ray sources (LCSs) are a compact alternative to synchrotron radiation with a quasimonoenergetic x-ray spectrum. One limitation in the clinical application of KES imaging with LCSs has been the extensive time required to tune the x-ray spectrum to two differentenergies. We introduce an imaging technique called scanning K-edge subtraction (SKES) that leverages the angle-correlated laser-Compton x-ray spectrum in the setting of mammography. The feasibility and utility of this technique will be evaluated through a series of simulation studies. The goal of SKES imaging is to enable rapid K-edge subtraction imaging using a laser-Compton x-ray source. The technique does not rely on the time-consuming process of tuning laser-Compton interactionparameters. Laser-Compton interaction physics are modeled using conditions based on an X-band linear electron accelerator architecture currently under development using a combination of 3D particle tracking software and Mathematica. The resulting angle-correlated laser-Compton x-ray beam is propagated through digitally compressed breast phantoms containing iodine contrast-enhanced inserts and then to a digital flat-panel detector using a Matlab Monte Carlo propagation software. This scanning acquisition technique is compared to the direct energy tuning method (DET), as well as to a clinically available dual-energy contrast-enhanced mammography (CEM)system. KES imaging in a scanning configuration using an LCS was able to generate a KES image of comparable quality to the direct energy tuning method. SKES was able to detect tumors with iodine contrast concentrations lower than what is clinically available today including lesions that are typically obscured by dense fibroglandular tissue. After normalizing to mean glandular dose, SKES is able to generate a KES image with equal contrast to CEM using only 3% of thedose. By leveraging the unique quasimonochromatic and angle-correlated x-ray spectrum offered by LCSs, a contrast-enhanced subtraction image can be obtained with significantly more contrast and less dose compared to conventional systems, and improve tumor detection in patients with dense breast tissue. The scanning configuration of this technique could accelerate the clinical translation of thistechnology.

Nonlinear Harmonics: A Gateway to Enhanced Image Contrast and Material Discrimination.

Recent advancements in atomic force microscopy (AFM) have enabled detailed exploration of materials at the molecular and atomic levels. These developments, however, pose a challenge: the data generated by microscopic and spectroscopic experiments are increasing rapidly in both size and complexity. Extracting meaningful physical insights from these datasets is challenging, particularly for multilayer heterogeneous nanoscale structures. In this paper, an unsupervised approach is presented to enhance AFM image contrast by analyzing the nonlinear response of a cantilever interacting with a material's surface using a wavelet-based AFM. This method simultaneously measures different frequencies and harmonics in a single scan, without the need for additional hardware and exciting multiple cantilevers' eigenmodes. This developed AFM image contrast enhancement (AFM-ICE) approach employs unsupervised learning, image processing, and image fusion techniques. The method is applied to interpret complex multilayer structures consist of defects, deposited nanoparticles and heterogeneities. Its substantial capability is demonstrated to improve image contrast and differentiate between various components. This methodology can pave the way for rapid and precise determination of material properties with enhancedresolution.

A preoperative predictive model based on multi-modal features to predict pathological complete response after neoadjuvant chemoimmunotherapy in esophageal cancer patients

BackgroundThis study aimed to develop a multi-modality model by incorporating pretreatment computed tomography (CT) radiomics and pathomics features along with clinical variables to predict pathologic complete response (pCR) to neoadjuvant chemoimmunotherapy in patients with locally advanced esophageal cancer (EC).MethodA total of 223 EC patients who underwent neoadjuvant chemoimmunotherapy followed by surgical intervention between August 2021 and December 2023 were included in this study. Radiomics features were extracted from contrast-enhanced CT images using PyrRadiomics, while pathomics features were derived from whole-slide images (WSIs) of pathological specimens using a fine-tuned deep learning model (ResNet-50). After feature selection, three single-modality prediction models and a combined multi-modality model integrating two radiomics features, 11 pathomics features, and two clinicopathological features were constructed using the support vector machine (SVM) algorithm. The performance of the models were evaluated using receiver operating characteristic (ROC) analysis, calibration plots, and decision curve analysis (DCA). Shapley values were also utilized to explain the prediction model.ResultsThe predictive capability of the multi-modality model in predicting pCR yielded an area under the curve (AUC) of 0.89 (95% confidence interval [CI], 0.75-1.00), outperforming the radiomics model (AUC 0.70 [95% CI 0.54-0.85]), pathomics model (AUC 0.77 [95% CI 0.53-1.00]), and clinical model (AUC 0.63 [95% CI 0.46-0.80]). Additionally, both the calibration plot and DCA curves support the clinical utility of the integrated multi-modality model.ConclusionsThe combined multi-modality model we propose can better predict the pCR status of esophageal cancer and help inform clinical treatment decisions.

O-02 A RARE COLLISION TUMOR OF THE PITUITARY: CO-EXISTENCE OF CRANIOPHARYNGIOMA AND PROLACTINOMA

Abstract Introduction Pituitary adenomas are the most common lesions of the sellar region. The most common (40%) functional pituitary adenomas are prolactinomas. Craniopharyngiomas are epithelial tumors of embryonal origin originating from Rathke's sac. Very few cases of collision tumors co-existing with pituitary adenoma and craniopharyngioma have been described in the literature. Clinical Case We present a case of histopathologically proven craniopharyngioma accompanying prolactinoma in a 63-year-old female patient diagnosed with prolactinoma 40 years ago. She was treated with bromocriptine after the diagnosis, and the treatment was switched to cabergoline four years later. Although the biochemical remission was achieved, there was no significant decrease in tumor size. She had not received any treatment during last 4 years before the administration. She was admitted to our clinic with a complaint of headache. Her serum prolactin level was 1550 ng/ml ((Reference:4,79-23 ng/ml). According to the pituitary Magnetic Resonans Imaging(MRI); reports were as follows in 2007; an isolated 8x6x13 mm adenoma was observed, and then in 2015; another cystic lesion (craniopharyngioma?) was detected adjacent to the infindibular stalk in addition to the defined pituitary adenoma (Figure 1a). In the last pituitary MRI (2022); a cystic lesion extending from the sellar cavity to the suprasellar cistern and a solid mass lesion located left to the cavernous sinus, was observed (Figure 1b). Upon a dramatic increase of the tumor volume on pituitary MRI, she underwent pituitary surgery. The histopathological diagnosis was adamantinomatous craniopharyngioma. Postoperative prolactin level decreased to 10 ng/ml. Since prolactin levels decreased after the diagnosis of craniopharyngioma, the surgical material was re-evaluated by the pathologist. No evidence of prolactinoma was found. Significant regression was observed in the patient's 1st month follow-up pituitary MRI compared to the preoperative MRI. Postoperatively, prolactin levels remained within the normal range for the first 6 months. After the 6th month, cabergoline treatment was started when prolactin levels increased to 497 ng/ml. Conclusion Pituitary adenoma and craniopharyngioma collision tumors are extremely rare. Only 6 patients with the coexistence of craniopharyngioma and prolactinoma have been reported in the literature, including our case. Histopathological diagnosis may be necessary to differentiate craniopharyngioma from cystic macroprolactinoma.Figure 1:Magnetic Resonans ImagingFigure 1: a. Post-contrast coronal pituitary MRI examination revealed a pituitary adenoma (thick arrow) located in the left cavernous sinus. aAnother cystic mass lesion (thin arrow) was detected adjacent to the infindibular stalk.; b. Coronal contrast-enhanced pituitary MRI image showed cystic (arrow) and