Search

Objective: To investigate a deep learning model for predicting hepatic decompensation using computed tomography (CT) imaging in patients with primary sclerosing cholangitis (PSC). Patients and Methods: Retrospective cohort study involving 277 adult patients with large-duct PSC who underwent an abdominal CT scan. The portal venous phase CT images were used as input to a 3D-DenseNet121 model, which was trained using 5-fold crossvalidation to classify hepatic decompensation. To further investigate the role of each anatomic region in the model’s decision-making process, we trained the model on different sections of 3-dimensional CT images. This included training on the right, left, anterior, posterior, inferior, and superior halves of the image data set. For each half, as well as for the entire scan, we performed area under the receiving operating curve (AUROC) analysis. Results: Hepatic decompensation occurred in 128 individuals after a median (interquartile range) of 1.5 years (142-1318 days) after the CT scan. The deep learning model exhibited promising results, with a mean ± SD AUROC of 0.89±0.04 for the baseline model. The mean ± SD AUROC for left, right, anterior, posterior, superior, and inferior halves were 0.83±0.03, 0.83±0.03, 0.82±0.09, 0.79±0.02, 0.78±0.02, and 0.76±0.04, respectively. Conclusion: The study illustrates the potential of examining CT imaging using 3D-DenseNet121 deep learning model to predict hepatic decompensation in patients with PSC.

Objective: To conduct a study comparing the performance of automated segmentation techniques using 2 different contrast-enhanced T1-weighted (CET1) magnetic resonance imaging (MRI) acquisition protocol. Patients and Methods: We collected 100 preoperative glioblastoma (GBM) MRIs consisting of 50 IR-GRE and 50 3-dimensional fast spin echo (3D-FSE) image sets. Their gold-standard tumor segmentation mask was created based on the expert opinion of a neuroradiologist. Cases were randomly divided into training and test sets. We used the no new UNet (nnUNet) architecture pretrained on the 501-image public data set containing IR-GRE sequence image sets, followed by 2 training rounds with the IR-GRE and 3D-FSE images, respectively. For each patient, in the IR-GRE and 3D-FSE test sets, we had 2 prediction masks, one from the model fine-tuned with the IR-GRE training set and one with 3D-FSE. The dice similarity coefficients (DSCs) of the 2 sets of results for each case in the test sets were compared using the Wilcoxon tests. Results: Models trained on 3D-FSE images outperformed IR-GRE models in lesion segmentation, with mean DSC differences of 0.057 and 0.022 in the respective test sets. For the 3D-FSE and IR-GRE test sets, the calculated P values comparing DSCs from 2 models were .02 and .61, respectively. Conclusion: Including 3D-FSE MRI in the training data set improves segmentation performance when segmenting 3D-FSE images.

Abstract Meningiomas are the most common primary intracranial tumors and can be associated with significant morbidity and mortality. Radiologists, neurosurgeons, neuro-oncologists, and radiation oncologists rely on brain MRI for diagnosis, treatment planning, and longitudinal treatment monitoring. However, automated, objective, and quantitative tools for non-invasive assessment of meningiomas on multi-sequence MR images are not available. Here we present the BraTS Pre-operative Meningioma Dataset, as the largest multi-institutional expert annotated multilabel meningioma multi-sequence MR image dataset to date. This dataset includes 1,141 multi-sequence MR images from six sites, each with four structural MRI sequences (T2-, T2/FLAIR-, pre-contrast T1-, and post-contrast T1-weighted) accompanied by expert manually refined segmentations of three distinct meningioma sub-compartments: enhancing tumor, non-enhancing tumor, and surrounding non-enhancing T2/FLAIR hyperintensity. Basic demographic data are provided including age at time of initial imaging, sex, and CNS WHO grade. The goal of releasing this dataset is to facilitate the development of automated computational methods for meningioma segmentation and expedite their incorporation into clinical practice, ultimately targeting improvement in the care of meningioma patients.

Background: Dual-energy CT (DECT) is a non-invasive way to determine the presence of monosodium urate (MSU) crystals in the workup of gout. Color-coding distinguishes MSU from calcium following material decomposition and post-processing. Most software labels MSU as green and calcium as blue. There are limitations in the current image processing methods of segmenting green-encoded pixels. Additionally, identifying green foci is tedious, and automated detection would improve workflow. This study aimed to determine the optimal deep learning (DL) algorithm for segmenting green-encoded pixels of MSU crystals on DECTs. Methods: DECT images of positive and negative gout cases were retrospectively collected. The dataset was split into train (N = 28) and held-out test (N = 30) sets. To perform cross-validation, the train set was split into seven folds. The images were presented to two musculoskeletal radiologists, who independently identified green-encoded voxels. Two 3D Unet-based DL models, Segresnet and SwinUNETR, were trained, and the Dice similarity coefficient (DSC), sensitivity, and specificity were reported as the segmentation metrics. Results: Segresnet showed superior performance, achieving a DSC of 0.9999 for the background pixels, 0.7868 for the green pixels, and an average DSC of 0.8934 for both types of pixels, respectively. According to the post-processed results, the Segresnet reached voxel-level sensitivity and specificity of 98.72 % and 99.98 %, respectively. Conclusion: In this study, we compared two DL-based segmentation approaches for detecting MSU deposits in a DECT dataset. The Segresnet resulted in superior performance metrics. The developed algorithm provides a potential fast, consistent, highly sensitive and specific computer-aided diagnosis tool. Ultimately, such an algorithm could be used by radiologists to streamline DECT workflow and improve accuracy in the detection of gout.

Objective: To efficiently store, transfer, and analyze whole slide imaging (WSI), we developed an image-processing algorithm to remove the unneeded background in a WSI and assemble tissue-containing parts into smaller WSIs without any change in tissue area image resolution. Patients and Methods: We used histology slides of nondysplastic Barrett esophagus, low-grade dysplasia, and high-grade dysplasia, which were digitized using Aperio AT2 Scanner from January 1992 to September 2020. The algorithm involved converting color images to grayscale images, binarizing images by assigning zero to the background and 1 to the foreground, filling the holes and dilating the foreground masks, and extracting connected components. Using the coordinates of each component, the vertices of the smallest surrounding bounding box were calculated, and tissue-containing parts were cropped from the original slide. The smallest possible rectangle that encloses all bounding boxes containing tissue was found using the rectangle-packer package. Results: The algorithm resulted in a mean reduction of 7.11×. The performance of a previously developed deep learning model for the detection of Barrett esophagus dysplasia grade on the size-reduced WSIs was comparable with that on the original WSIs. Conclusion: Our algorithm for WSI size reduction can assist researchers in storing, transferring, and analyzing WSIs while optimally using them in their workflow.

IntroductionDual-energy CT (DECT) is a non-invasive way to determine the presence of monosodium urate (MSU) crystals in the workup of gout. Color-coding distinguishes MSU from calcium following material decomposition and post-processing. Manually identifying these foci (most commonly labeled green) is tedious, and an automated detection system could streamline the process. This study aims to evaluate the impact of a deep-learning (DL) algorithm developed for detecting green pixelations on DECT on reader time, accuracy, and confidence.MethodsWe collected a sample of positive and negative DECTs, reviewed twice—once with and once without the DL tool—with a 2-week washout period. An attending musculoskeletal radiologist and a fellow separately reviewed the cases, simulating clinical workflow. Metrics such as time taken, confidence in diagnosis, and the tool's helpfulness were recorded and statistically analyzed.ResultsWe included thirty DECTs from different patients. The DL tool significantly reduced the reading time for the trainee radiologist (p = 0.02), but not for the attending radiologist (p = 0.15). Diagnostic confidence remained unchanged for both (p = 0.45). However, the DL model identified tiny MSU deposits that led to a change in diagnosis in two cases for the in-training radiologist and one case for the attending radiologist. In 3/3 of these cases, the diagnosis was correct when using DL.ConclusionsThe implementation of the developed DL model slightly reduced reading time for our less experienced reader and led to improved diagnostic accuracy. There was no statistically significant difference in diagnostic confidence when studies were interpreted without and with the DL model.

Summary: Background: The causes for immune-mediated inflammatory diseases (IMIDs) are diverse and the incidence trends of IMIDs from specific causes are rarely studied. The study aims to investigate the pattern and trend of IMIDs from 1990 to 2019. Methods: We collected detailed information on six major causes of IMIDs, including asthma, inflammatory bowel disease, multiple sclerosis, rheumatoid arthritis, psoriasis, and atopic dermatitis, between 1990 and 2019, derived from the Global Burden of Disease study in 2019. The average annual percent change (AAPC) in number of incidents and age standardized incidence rate (ASR) on IMIDs, by sex, age, region, and causes, were calculated to quantify the temporal trends. Findings: In 2019, rheumatoid arthritis, atopic dermatitis, asthma, multiple sclerosis, psoriasis, inflammatory bowel disease accounted 1.59%, 36.17%, 54.71%, 0.09%, 6.84%, 0.60% of overall new IMIDs cases, respectively. The ASR of IMIDs showed substantial regional and global variation with the highest in High SDI region, High-income North America, and United States of America. Throughout human lifespan, the age distribution of incident cases from six IMIDs was quite different. Globally, incident cases of IMIDs increased with an AAPC of 0.68 and the ASR decreased with an AAPC of −0.34 from 1990 to 2019. The incident cases increased across six IMIDs, the ASR of rheumatoid arthritis increased (0.21, 95% CI 0.18, 0.25), while the ASR of asthma (AAPC = −0.41), inflammatory bowel disease (AAPC = −0.72), multiple sclerosis (AAPC = −0.26), psoriasis (AAPC = −0.77), and atopic dermatitis (AAPC = −0.15) decreased. The ASR of overall and six individual IMID increased with SDI at regional and global level. Countries with higher ASR in 1990 experienced a more rapid decrease in ASR. Interpretation: The incidence patterns of IMIDs varied considerably across the world. Innovative prevention and integrative management strategy are urgently needed to mitigate the increasing ASR of rheumatoid arthritis and upsurging new cases of other five IMIDs, respectively. Funding: The Global Burden of Disease Study is funded by the Bill and Melinda Gates Foundation. The project funded by Scientific Research Fund of Sichuan Academy of Medical Sciences & Sichuan Provincial People's Hospital (2022QN38).

Abstract Background Stroke is one of the leading causes of disability worldwide. Recently, stroke prognosis estimation has received much attention. This study investigates the prognostic role of aspartate transaminase/alanine transaminase (De Ritis, AAR), alkaline phosphatase/alanine transaminase (ALP/ALT), and aspartate transaminase/alkaline phosphatase (AST/ALP) ratios in acute ischemic stroke (AIS). Methods This retrospective cohort study involved patients who experienced their first-ever AIS between September 2019 and June 2021. Clinical and laboratory data were collected within the first 24 hours after admission. Functional and mortality outcomes were evaluated 90 days after hospital discharge in clinical follow-up. Functional outcome was assessed by a modified Rankin Scale (mRS). The correlation between the laboratory data and study outcomes was evaluated using univariate analysis. In addition, regression models were developed to evaluate the predictive role of AST/ALP, ALP/ALT, and AAR ratios on the study outcomes. Results Two hundred seventy-seven patients (mean age 69.10 ± 13.55, 53.1% female) were included. According to univariate analysis, there was a weak association between 3-months mRS, and both AST/ALT (r = 0.222, P

Oropharyngeal Squamous Cell Carcinoma (OPSCC) is one of the common forms of heterogeneity in head and neck cancer. Infection with human papillomavirus (HPV) has been identified as a major risk factor for OPSCC. Therefore, differentiating the HPV-positive and negative cases in OPSCC patients is an essential diagnostic factor influencing future treatment decisions. In this study, we investigated the accuracy of a deep learning-based method for image interpretation and automatically detected the HPV status of OPSCC in routinely acquired Computed Tomography (CT) and Positron Emission Tomography (PET) images. We introduce a 3D CNN-based multi-modal feature fusion architecture for HPV status prediction in primary tumor lesions. The architecture is composed of an ensemble of CNN networks and merges image features in a softmax classification layer. The pipeline separately learns the intensity, contrast variation, shape, texture heterogeneity, and metabolic assessment from CT and PET tumor volume regions and fuses those multi-modal features for final HPV status classification. The precision, recall, and AUC scores of the proposed method are computed, and the results are compared with other existing models. The experimental results demonstrate that the multi-modal ensemble model with soft voting outperformed single-modality PET/CT, with an AUC of 0.76 and F1 score of 0.746 on publicly available TCGA and MAASTRO datasets. In the MAASTRO dataset, our model achieved an AUC score of 0.74 over primary tumor volumes of interest (VOIs). In the future, more extensive cohort validation may suffice for better diagnostic accuracy and provide preliminary assessment before the biopsy.

Abstract Objective To evaluate the performance of the automated abstract screening tool Rayyan. Methods The records obtained from the search for three systematic reviews were manually screened in four stages. At the end of each stage, Rayyan was used to predict the eligibility score for the remaining records. At two different thresholds (≤2.5 and

Machine-learning (ML) and deep-learning (DL) algorithms are part of a group of modeling algorithms that grasp the hidden patterns in data based on a training process, enabling them to extract complex information from the input data. In the past decade, these algorithms have been increasingly used for image processing, specifically in the medical domain. Cardiothoracic imaging is one of the early adopters of ML/DL research, and the COVID-19 pandemic resulted in more research focus on the feasibility and applications of ML/DL in cardiothoracic imaging. In this scoping review, we systematically searched available peer-reviewed medical literature on cardiothoracic imaging and quantitatively extracted key data elements in order to get a big picture of how ML/DL have been used in the rapidly evolving cardiothoracic imaging field. During this report, we provide insights on different applications of ML/DL and some nuances pertaining to this specific field of research. Finally, we provide general suggestions on how researchers can make their research more than just a proof-of-concept and move toward clinical adoption.