Journal of Digital Imaging最新文献

Radiogenomics has shown potential to predict genomic phenotypes from medical images. The development of models using standard-of-care pre-operative MRI images, as opposed to advanced MRI images, enables a broader reach of such models. In this work, a radiogenomics model for IDH mutation status prediction from standard-of-care MRIs in patients with glioma was developed and validated using multicentric data. A cohort of 142 (wild-type: 32.4%) patients with glioma retrieved from the TCIA/TCGA was used to train a logistic regression model to predict the IDH mutation status. The model was evaluated using retrospective data collected in two distinct hospitals, comprising 36 (wild-type: 63.9%) and 53 (wild-type: 75.5%) patients. Model development utilized ROC analysis. Model discrimination and calibration were used for validation. The model yielded an AUC of 0.741 vs. 0.716 vs. 0.938, a sensitivity of 0.784 vs. 0.739 vs. 0.875, and a specificity of 0.657 vs. 0.692 vs. 1.000 on the training, test cohort 1, and test cohort 2, respectively. The assessment of model fairness suggested an unbiased model for age and sex, and calibration tests showed a p < 0.05. These results indicate that the developed model allows the prediction of the IDH mutation status in gliomas using standard-of-care MRI images and does not appear to hold sex and age biases.

Leukoaraiosis (LA) is strongly associated with impaired cognition and increased dementia risk. Determining effective and robust methods of identifying LA patients with mild cognitive impairment (LA-MCI) is important for clinical intervention and disease monitoring. In this study, an ensemble learning method that combines multiple magnetic resonance imaging (MRI) morphological features is proposed to distinguish LA-MCI patients from LA patients lacking cognitive impairment (LA-nCI). Multiple comprehensive morphological measures (including gray matter volume (GMV), cortical thickness (CT), surface area (SA), cortical volume (CV), sulcus depth (SD), fractal dimension (FD), and gyrification index (GI)) are extracted from MRI to enrich model training on disease characterization information. Then, based on the general extreme gradient boosting (XGBoost) classifier, we leverage a weighted soft-voting ensemble framework to ensemble a data-level resampling method (Fusion + XGBoost) and an algorithm-level focal loss (FL)-improved XGBoost model (FL-XGBoost) to overcome class-imbalance learning problems and provide superior classification performance and stability. The baseline XGBoost model trained on an original imbalanced dataset had a balanced accuracy (Bacc) of 78.20%. The separate Fusion + XGBoost and FL-XGBoost models achieved Bacc scores of 80.53 and 81.25%, respectively, which are clear improvements (i.e., 2.33% and 3.05%, respectively). The fused model distinguishes LA-MCI from LA-nCI with an overall accuracy of 84.82%. Sensitivity and specificity were also well improved (85.50 and 84.14%, respectively). This improved model has the potential to facilitate the clinical diagnosis of LA-MCI.

Accurately segmenting the structure of the fetal head (FH) and performing biometry measurements, including head circumference (HC) estimation, stands as a vital requirement for addressing abnormal fetal growth during pregnancy under the expertise of experienced radiologists using ultrasound (US) images. However, accurate segmentation and measurement is a challenging task due to image artifact, incomplete ellipse fitting, and fluctuations due to FH dimensions over different trimesters. Also, it is highly time-consuming due to the absence of specialized features, which leads to low segmentation accuracy. To address these challenging tasks, we propose an automatic density regression approach to incorporate appearance and shape priors into the deep learning-based network model (DR-ASPnet) with robust ellipse fitting using fetal US images. Initially, we employed multiple pre-processing steps to remove unwanted distortions, variable fluctuations, and a clear view of significant features from the US images. Then some form of augmentation operation is applied to increase the diversity of the dataset. Next, we proposed the hierarchical density regression deep convolutional neural network (HDR-DCNN) model, which involves three network models to determine the complex location of FH for accurate segmentation during the training and testing processes. Then, we used post-processing operations using contrast enhancement filtering with a morphological operation model to smooth the region and remove unnecessary artifacts from the segmentation results. After post-processing, we applied the smoothed segmented result to the robust ellipse fitting-based least square (REFLS) method for HC estimation. Experimental results of the DR-ASPnet model obtain 98.86% dice similarity coefficient (DSC) as segmentation accuracy, and it also obtains 1.67 mm absolute distance (AD) as measurement accuracy compared to other state-of-the-art methods. Finally, we achieved a 0.99 correlation coefficient (CC) in estimating the measured and predicted HC values on the HC18 dataset.

Pressure ulcers are a common, painful, costly, and often preventable complication associated with prolonged immobility in bedridden patients. It is a significant health problem worldwide because it is frequently seen in inpatients and has high treatment costs. For the treatment to be effective and to ensure an international standardization for all patients, it is essential that the diagnosis of pressure ulcers is made in the early stages and correctly. Since invasive methods of obtaining information can be painful for patients, different methods are used to make a correct diagnosis. Image-based diagnosis method is one of them. By using images obtained from patients, it will be possible to obtain successful results by keeping patients away from such painful situations. At this stage, disposable wound rulers are used in clinical practice to measure the length, width, and depth of patients’ wounds. The information obtained is then entered into tools such as the Braden Scale, the Norton Scale, and the Waterlow Scale to provide a formal assessment of risk for pressure ulcers. This paper presents a novel benchmark dataset containing pressure ulcer images and a semi-two-stream approach that uses the original images and the cropped wound areas together for diagnosing the stage of pressure ulcers. Various state-of-the-art convolutional neural network (CNN) architectures are evaluated on this dataset. Our experimental results (test accuracy of 93%, the precision of 93%, the recall of 92%, and the F1-score of 93%) show that the proposed semi-two-stream method improves recognition results compared to the base CNN architectures.

We aim to conduct a meta-analysis on studies that evaluated the diagnostic performance of artificial intelligence (AI) algorithms in the detection of primary bone tumors, distinguishing them from other bone lesions, and comparing them with clinician assessment. A systematic search was conducted using a combination of keywords related to bone tumors and AI. After extracting contingency tables from all included studies, we performed a meta-analysis using random-effects model to determine the pooled sensitivity and specificity, accompanied by their respective 95% confidence intervals (CI). Quality assessment was evaluated using a modified version of Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) and Prediction Model Study Risk of Bias Assessment Tool (PROBAST). The pooled sensitivities for AI algorithms and clinicians on internal validation test sets for detecting bone neoplasms were 84% (95% CI: 79.88) and 76% (95% CI: 64.85), and pooled specificities were 86% (95% CI: 81.90) and 64% (95% CI: 55.72), respectively. At external validation, the pooled sensitivity and specificity for AI algorithms were 84% (95% CI: 75.90) and 91% (95% CI: 83.96), respectively. The same numbers for clinicians were 85% (95% CI: 73.92) and 94% (95% CI: 89.97), respectively. The sensitivity and specificity for clinicians with AI assistance were 95% (95% CI: 86.98) and 57% (95% CI: 48.66). Caution is needed when interpreting findings due to potential limitations. Further research is needed to bridge this gap in scientific understanding and promote effective implementation for medical practice advancement.

Abstract

Flagging the presence of metal devices before a head MRI scan is essential to allow appropriate safety checks. There is an unmet need for an automated system which can flag aneurysm clips prior to MRI appointments. We assess the accuracy with which a machine learning model can classify the presence or absence of an aneurysm clip on CT images. A total of 280 CT head scans were collected, 140 with aneurysm clips visible and 140 without. The data were used to retrain a pre-trained image classification neural network to classify CT localizer images. Models were developed using fivefold cross-validation and then tested on a holdout test set. A mean sensitivity of 100% and a mean accuracy of 82% were achieved. Predictions were explained using SHapley Additive exPlanations (SHAP), which highlighted that appropriate regions of interest were informing the models. Models were also trained from scratch to classify three-dimensional CT head scans. These did not exceed the sensitivity of the localizer models. This work illustrates an application of computer vision image classification to enhance current processes and improve patient safety.

To assess the effect of digital enhancement on the image quality of radiographs obtained with photostimulable phosphor (PSP) plates partially damaged by ambient light. Radiographs of an aluminum step wedge were obtained using the VistaScan and Express systems. Half of the PSP plates was exposed to ambient light for 0, 10, 30, 60, or 90 s before being scanned. The resulting radiographs were exported with and without digital enhancement. Metrics for brightness, contrast, and contrast-to-noise ratio (CNR) were derived, and the ratio of each metric between the exposed-to-light and non-exposed-to-light halves of the radiographs was calculated. The resulting ratios of the radiographs with digital enhancement were subtracted from those without digital enhancement and compared among each other. For the VistaScan system, digital enhancement partially restored brightness, contrast, and CNR. For the Express system, digital enhancement only restored CNR and not the impact of ambient light on brightness and contrast. Specifically, digital enhancement restored 23.48% of brightness for the VistaScan, while percentages below 1% were observed for the Express. Digital enhancement restored 53.25% of image contrast for the VistaScan and 5.79% for the Express; 40.71% of CNR was restored for the VistaScan, and 35% for the Express. Digital enhancement can partially restore the damage caused by ambient light on the brightness and contrast of PSP-based radiographs obtained with the VistaScan, as well as on CNR for the VistaScan and Express systems. The exposure of PSP plates to light can lead to unnecessary retakes and increased patient exposure to X-rays.

Natural language processing (NLP) can be used to process and structure free text, such as (free text) radiological reports. In radiology, it is important that reports are complete and accurate for clinical staging of, for instance, pulmonary oncology. A computed tomography (CT) or positron emission tomography (PET)-CT scan is of great importance in tumor staging, and NLP may be of additional value to the radiological report when used in the staging process as it may be able to extract the T and N stage of the 8th tumor–node–metastasis (TNM) classification system. The purpose of this study is to evaluate a new TN algorithm (TN-PET-CT) by adding a layer of metabolic activity to an already existing rule-based NLP algorithm (TN-CT). This new TN-PET-CT algorithm is capable of staging chest CT examinations as well as PET-CT scans. The study design made it possible to perform a subgroup analysis to test the external validation of the prior TN-CT algorithm. For information extraction and matching, pyContextNLP, SpaCy, and regular expressions were used. Overall TN accuracy score of the TN-PET-CT algorithm was 0.73 and 0.62 in the training and validation set (N = 63, N = 100). The external validation of the TN-CT classifier (N = 65) was 0.72. Overall, it is possible to adjust the TN-CT algorithm into a TN-PET-CT algorithm. However, outcomes highly depend on the accuracy of the report, the used vocabulary, and its context to express, for example, uncertainty. This is true for both the adjusted PET-CT algorithm and for the CT algorithm when applied in another hospital.

A critical clinical indicator for basal cell carcinoma (BCC) is the presence of telangiectasia (narrow, arborizing blood vessels) within the skin lesions. Many skin cancer imaging processes today exploit deep learning (DL) models for diagnosis, segmentation of features, and feature analysis. To extend automated diagnosis, recent computational intelligence research has also explored the field of Topological Data Analysis (TDA), a branch of mathematics that uses topology to extract meaningful information from highly complex data. This study combines TDA and DL with ensemble learning to create a hybrid TDA-DL BCC diagnostic model. Persistence homology (a TDA technique) is implemented to extract topological features from automatically segmented telangiectasia as well as skin lesions, and DL features are generated by fine-tuning a pre-trained EfficientNet-B5 model. The final hybrid TDA-DL model achieves state-of-the-art accuracy of 97.4% and an AUC of 0.995 on a holdout test of 395 skin lesions for BCC diagnosis. This study demonstrates that telangiectasia features improve BCC diagnosis, and TDA techniques hold the potential to improve DL performance.

Abstract

The human body’s largest organ is the skin which covers the entire body. The facial skin is one area of the body that needs careful handling. It can cause several facial skin diseases like acne, eczema, moles, melanoma, rosacea, and many other fungal infections. Diagnosing these diseases has been difficult due to challenges like the high cost of medical equipment and the lack of medical competence. However, various existing systems are utilized to detect the type of facial skin disease, but those approaches are time-consuming and inaccurate to detect the disease at early stages. To address various issues, a deep learning-based gate recurrent unit (GRU) has been developed. Non-linear diffusion is used to acquire and pre-process raw pictures, adaptive histogram equalization (AHE) and high boost filtering (HBF). The image noise is removed by using non-linear diffusion. The contrast of the image is maximized using AHE. The image’s edges are sharpened by using HBF. After pre-processing, textural and colour features are extracted by applying a grey level run-length matrix (GLRM) and chromatic co-occurrence local binary pattern (CCoLBP). Then, appropriate features are selected using horse herd optimization (HOA). Finally, selected features are classified using GRU to identify the types of facial skin disease. The proposed model is investigated using the Kaggle database that consists of different face skin disease images such as rosacea, eczema, basal cell carcinoma, acnitic keratosis, and acne. Further, the acquired dataset is split into training and testing. Considering the investigation’s findings, the proposed method yields 98.2% accuracy, 1.8% error, 97.1% precision, and 95.5% f1-score. In comparison to other current techniques, the proposed technique performs better. The created model is, therefore, the best choice for classifying the various facial skin conditions.