Kaba E, et al. Korean J Radiol. 2024 May;25(5):499-500. https://doi.org/10.3348/kjr.2024.0229

A 17-year-old female patient presented with complaints of fatigue and hair loss. A blood test revealed Thyroid Stimulating Hormone (TSH): 5.23 µU/ml and T4: 1.21 µU/ml. Subclinical hypothyroidism was considered and thyroid ultrasonography was performed. The left lobe of the thyroid and the left half of the isthmus were not observed. Right lobe parenchyma was normal. Doppler examination showed a normal pattern ( Figure 1). There was no history of any surgery. Therefore, the diagnosis was made as thyroid hemiagenesis.

Objectives: Differentiation of hyperdense areas on non-contrast computed tomography (NCCT) images as hemorrhagic transformation (HT) and contrast accumulation (CA) after endovascular thrombectomy (EVT) in acute ischemic stroke (AIS) patients are critical for early antiplatelet and anticoagulant therapy. This study aimed to predict HT and CA on initial NCCT using deep learning. Material and Methods: This study was conducted between January and December 2024. The study included 556 images of 52 patients (21 female and 31 male) who underwent EVT due to AIS, with hyperdense areas observed in the NCCT examination within the first 24 h post-EVT. The evaluated images were labeled as ‘contrast accumulation’ and ‘hemorrhagic transformation’. These labeled images were trained with nine different models under a convolutional neural network (CNN) architecture using a large dataset, such as ImageNet. These models are DenseNet201, InceptionResNet, InceptionV3, NASNetLarge, ResNet50, ResNet101, VGG16, VGG19 and Xception. After training the CNN models, their performance was evaluated using accuracy, loss, validation accuracy, validation loss, F1 score, Receiver Operating Characteristic (ROC) Curve, confusion matrix, confidence interval, and p-value analysis. Results: The models trained in the study were derived from 556 images in data sets obtained from 52 patients; 186 images in training data for CA and 186 images training data for HT (with an increase to 558 images), 115 images used for validation data, and 69 images were compared using test data. In the test set, the Area Under the Curve (AUC) metrics showing sensitivity and specificity values under different cutoff points for the models were as follows: DenseNet201 model AUC = 0.95, InceptionV3 model AUC = 0.93, NasNetLarge model AUC = 0.89, Xception model AUC = 0.91, Inception_ResNet model AUC = 0.84, Resnet50 and Resnet101 models AUC = 0.74. The InceptionV3 model demonstrates the best performance with an F1 score of 0.85. Recall scores generally ranged between 0.62 and 0.85. Conclusions: In our study, hyperdensity areas in initial NCCT images obtained after EVT in AIS patients were successfully differentiated from HT and CA with high accuracy using CNN architectures. Our findings may enable the early identification of patients who would benefit from anticoagulation or antiplatelet therapy to prevent re-occlusion or progression after EVT.

Background/Objectives: Magnetic resonance elastography (MRE) is a noninvasive imaging technique that quantitatively characterizes tissue mechanical properties. This study aimed to establish and validate a feasible parotid MRE protocol using 3T MRI, with potential relevance for oral and maxillofacial surgery (OMFS) and otorhinolaryngology practice. Methods: This study included 21 healthy volunteers (18 women, 3 men; mean age, 49 years) examined between January and May 2024. MRE was performed using a 3.0 Tesla MRI system (Discovery MR750w, GE Healthcare, Waukesha, WI, USA) with a passive driver positioned over the parotid gland in a 16-channel head/neck coil. Two radiologists independently analyzed axial magnitude images drawing regions of interest (ROIs) encompassing the entire gland while excluding intraparotid lymph nodes and vascular structures. Mean and maximum stiffness values (kPa) were recorded for each gland. Interobserver agreement was assessed using intraclass correlation coefficients (ICCs) and Bland–Altman analysis. Results: Mean stiffness was 1.209 ± 0.240 kPa (Radiologist 1) and 1.146 ± 0.233 kPa (Radiologist 2); maximum stiffness was 1.595 ± 0.532 kPa and 1.563 ± 0.528 kPa, respectively. ICCs were 0.638 for mean stiffness and 0.918 for maximum stiffness, indicating moderate-to-excellent agreement. Conclusions: MRE is a technically feasible and reproducible method for evaluating parotid stiffness using standard imaging infrastructure. This feasibility study in healthy volunteers provides normative stiffness values for the parotid gland and supports MRE as a potential tool for “radiological palpation” to aid in the differentiation of salivary gland lesions and post-treatment assessment in OMFS and otorhinolaryngology practice.

Massive hemoptysis is a serious respiratory emergency. In most cases, the bleeding source is the bronchial circulation, and bronchial artery embolization (