Automatic Localization of the Pons and Vermis on Fetal Brain MR Imaging Using a U-Net Deep Learning Model.

BACKGROUND AND PURPOSE: An MRI of the fetus can enhance the identification of perinatal developmental disorders, which improves the accuracy of ultrasound. Manual MRI measurements require training, time, and intra-variability concerns. Pediatric neuroradiologists are also in short supply. Our purpose was developing a deep learning model and pipeline for automatically identifying anatomic landmarks on the pons and vermis in fetal brain MR imaging and suggesting suitable images for measuring the pons and vermis. MATERIALS AND METHODS: We retrospectively used 55 pregnant patients who underwent fetal brain MR imaging with a HASTE protocol. Pediatric neuroradiologists selected them for landmark annotation on sagittal single-shot T2-weighted images, and the clinically reliable method was used as the criterion standard for the measurement of the pons and vermis. A U-Net-based deep learning model was developed to automatically identify fetal brain anatomic landmarks, including the 2 anterior-posterior landmarks of the pons and 2 anterior-posterior and 2 superior-inferior landmarks of the vermis. Four-fold cross-validation was performed to test the accuracy of the model using randomly divided and sorted gestational age-divided data sets. A confidence score of model prediction was generated for each testing case. RESULTS: Overall, 85% of the testing results showed a ≥90% confidence, with a mean error of <2.22 mm, providing overall better estimation results with fewer errors and higher confidence scores. The anterior and posterior pons and anterior vermis showed better estimation (which means fewer errors in landmark localization) and accuracy and a higher confidence level than other landmarks. We also developed a graphic user interface for clinical use. CONCLUSIONS: This deep learning-facilitated pipeline practically shortens the time spent on selecting good-quality fetal brain images and performing anatomic measurements for radiologists.

Automatic Ventriculomegaly Detection in Fetal Brain MRI: A Step-by-Step Deep Learning Model for Novel 2D-3D Linear Measurements.

In this study, we developed an automated workflow using a deep learning model (DL) to measure the lateral ventricle linearly in fetal brain MRI, which are subsequently classified into normal or ventriculomegaly, defined as a diameter wider than 10 mm at the level of the thalamus and choroid plexus. To accomplish this, we first trained a UNet-based deep learning model to segment the brain of a fetus into seven different tissue categories using a public dataset (FeTA 2022) consisting of fetal T2-weighted images. Then, an automatic workflow was developed to perform lateral ventricle measurement at the level of the thalamus and choroid plexus. The test dataset included 22 cases of normal and abnormal T2-weighted fetal brain MRIs. Measurements performed by our AI model were compared with manual measurements performed by a general radiologist and a neuroradiologist. The AI model correctly classified 95% of fetal brain MRI cases into normal or ventriculomegaly. It could measure the lateral ventricle diameter in 95% of cases with less than a 1.7 mm error. The average difference between measurements was 0.90 mm in AI vs. general radiologists and 0.82 mm in AI vs. neuroradiologists, which are comparable to the difference between the two radiologists, 0.51 mm. In addition, the AI model also enabled the researchers to create 3D-reconstructed images, which better represent real anatomy than 2D images. When a manual measurement is performed, it could also provide both the right and left ventricles in just one cut, instead of two. The measurement difference between the general radiologist and the algorithm (p = 0.9827), and between the neuroradiologist and the algorithm (p = 0.2378), was not statistically significant. In contrast, the difference between general radiologists vs. neuroradiologists was statistically significant (p = 0.0043). To the best of our knowledge, this is the first study that performs 2D linear measurement of ventriculomegaly with a 3D model based on an artificial intelligence approach. The paper presents a step-by-step approach for designing an AI model based on several radiological criteria. Overall, this study showed that AI can automatically calculate the lateral ventricle in fetal brain MRIs and accurately classify them as abnormal or normal.

Automated quality control assessment of clinical chest images.

PURPOSE: The purpose of this study was to determine whether a proposed suite of objective image quality metrics for digital chest radiographs is useful for monitoring image quality in a clinical setting unique from the one where the metrics were developed. METHODS: Seventeen gridless AP chest radiographs from a GE Optima portable digital radiography (DR) unit ("sub-standard" images; Group 2) and 17 digital PA chest radiographs ("standard-of-care" images; Group 1) and 15 gridless (non-routine) PA chest radiographs (images with a gross technical error; Group 3) from a Discovery DR unit were chosen for analysis. Group 2 images were acquired with a lower kVp (100 vs 125) and shorter source-to-image distance (127 cm vs 183 cm) and were expected to have lower quality than Group 1 images. Group 3 images were expected to have degraded contrast vs Group 1 images. Images were anonymized and securely transferred to the Duke University Clinical Imaging Physics Group for analysis using software described and validated previously. Individual image quality was reported in terms of lung gray level, lung detail, lung noise, rib-lung contrast, rib sharpness, mediastinum detail, mediastinum noise, mediastinum alignment, subdiaphragm-lung contrast, and subdiaphragm area. Metrics were compared across groups. To improve precision of means and confidence intervals for routine exams, an additional 66 PA images were acquired, processed, and pooled with Group 1. Three observer studies were conducted to assess whether humans were able to identify images classified by the algorithm as abnormal. RESULTS: Metrics agreed with published Quality Consistency Ranges with three exceptions: higher lung gray level, lower rib-lung contrast, and lower subdiaphragm-lung contrast. Higher (stored) bit depth (14 vs 12) accounted for higher lung gray level values in our images. Values were most internally consistent for Group 1. The most sensitive metric for distinguishing between groups was mediastinum noise, followed closely by lung noise. The least sensitive metrics were mediastinum detail and rib-lung contrast. The algorithm was more sensitive than human observers at detecting suboptimal diagnostic quality images. CONCLUSIONS: The software appears promising for objectively and automatically identifying suboptimal images in a clinical imaging operation. The results can be used to establish local quality consistency ranges and action limits per facility preferences.