During image segmentation tasks in computer vision, achieving high accuracy performance while requiring fewer computations and faster inference is a big challenge. This is especially important in medical imaging tasks but one metric is usually compromised for the other. To address this problem, this paper presents an extremely fast, small and computationally effective deep neural network called Stripped-Down UNet (SD-UNet), designed for the segmentation of biomedical data on devices with limited computational resources. By making use of depthwise separable convolutions in the entire network, we design a lightweight deep convolutional neural network architecture inspired by the widely adapted U-Net model. In order to recover the expected performance degradation in the process, we introduce a weight standardization algorithm with the group normalization method. We demonstrate that SD-UNet has three major advantages including: (i) smaller model size (23x smaller than U-Net); (ii) 8x fewer parameters; and (iii) faster inference time with a computational complexity lower than 8M floating point operations (FLOPs). Experiments on the benchmark dataset of the Internatioanl Symposium on Biomedical Imaging (ISBI) challenge for segmentation of neuronal structures in electron microscopic (EM) stacks and the Medical Segmentation Decathlon (MSD) challenge brain tumor segmentation (BRATs) dataset show that the proposed model achieves comparable and sometimes better results compared to the current state-of-the-art.

PurposeTo construct a sequence diagram based on radiological and clinical factors for the evaluation of extrathyroidal extension (ETE) in patients with papillary thyroid carcinoma (PTC).Materials and MethodsBetween January 2016 and January 2020, 161 patients with PTC who underwent preoperative ultrasound examination in the Affiliated People’s Hospital of Jiangsu University were enrolled in this retrospective study. According to the pathology results, the enrolled patients were divided into a non-ETE group and an ETE group. All patients were randomly divided into a training cohort (n = 97) and a validation cohort (n = 64). A total of 479 image features of lesion areas in ultrasonic images were extracted. The radiomic signature was developed using least absolute shrinkage and selection operator algorithms after feature selection using the minimum redundancy maximum relevance method. The radiomic nomogram model was established by multivariable logistic regression analysis based on the radiomic signature and clinical risk factors. The discrimination, calibration, and clinical usefulness of the nomogram model were evaluated in the training and validation cohorts.ResultsThe radiomic signature consisted of six radiomic features determined in ultrasound images. The radiomic nomogram included the parameters tumor location, radiological ETE diagnosis, and the radiomic signature. Area under the curve (AUC) values confirmed good discrimination of this nomogram in the training cohort [AUC, 0.837; 95% confidence interval (CI), 0.756–0.919] and the validation cohort (AUC, 0.824; 95% CI, 0.723–0.925). The decision curve analysis showed that the radiomic nomogram has good clinical application value.ConclusionThe newly developed radiomic nomogram model is a noninvasive and reliable tool with high accuracy to predict ETE in patients with PTC.

BRAFV600E is the most common mutated gene in thyroid cancer and is most closely related to papillary thyroid carcinoma(PTC). We investigated the value of elasticity and grayscale ultrasonography for predicting BRAFV600E mutations in PTC.Methods138 patients with PTC who underwent preoperative ultrasound between January 2014 and 2021 were retrospectively examined. Patients were divided into BRAFV600E mutation-free group (n=75) and BRAFV600E mutation group (n=63). Patients were randomly divided into training (n=96) and test (n=42) groups. A total of 479 radiomic features were extracted from the grayscale and elasticity ultra-sonograms. Regression analysis was done to select the features that provided the most information. Then, 10-fold cross-validation was used to compare the performance of different classification algorithms. Logistic regression was used to predict BRAFV600E mutations.ResultsEight radiomics features were extracted from the grayscale ultrasonogram, and five radiomics features were extracted from the elasticity ultrasonogram. Three models were developed using these radiomic features. The models were derived from elasticity ultrasound, grayscale ultrasound, and a combination of grayscale and elasticity ultrasound, with areas under the curve (AUC) 0.952 [95% confidence interval (CI), 0.914−0.990], AUC 0.792 [95% CI, 0.703−0.882], and AUC 0.985 [95% CI, 0.965−1.000] in the training dataset, AUC 0.931 [95% CI, 0.841−1.000], AUC 0. 725 [95% CI, 0.569−0.880], and AUC 0.938 [95% CI, 0.851−1.000] in the test dataset, respectively.ConclusionThe radiomic model based on grayscale and elasticity ultrasound had a good predictive value for BRAFV600E gene mutations in patients with PTC.

This study was performed to describe a rare case of granulomatous lobular mastitis (GLM) that was successfully treated with bromocriptine in a male patient with gynecomastia and hyperprolactinemia. A 20-year-old man presented with a 1-year history of breast enlargement and galactorrhea. Physical examination revealed bilateral breast enlargement, porous discharge, and a 3-cm left breast lump in the 10-o’clock quadrant. Magnetic resonance imaging of the brain showed a 1.2-mm pituitary tumor. Laboratory analysis revealed hyperprolactinemia with low serum testosterone and elevated prolactin and estradiol levels. The lump in the left breast was examined by ultrasonography and mammography, and a core needle biopsy revealed chronic inflammation. The patient’s galactorrhea and breast lump disappeared after 3 months of treatment with bromocriptine at 2.5 mg once a day. His serum prolactin level also normalized. Following a review of this case, the patient was diagnosed with gynecomastia with hyperprolactinemia complicated by rare GLM. To the best of our knowledge, this is the first reported case of concurrent gynecomastia and GLM.

Thyroid nodules are commonly encountered in health care practice. They are usually benign in nature, with few cases being malignant, and their detection has increased in the adult population with the help of ultrasonography. Thyroidectomy or surgery is the first-line treatment and traditional method for thyroid nodules; however, thyroidectomy leaves permanent scars and requires long-term use of levothyroxine after surgery, which makes patients more reticent to accept this treatment. Thermal ablation is a minimally-invasive technique that have been employed in the treatment of benign and malignant thyroid nodules nodules, and have been shown to be effective and safe. Several studies, including long-term, retrospective, and prospective studies, have investigated the use of ablation to treat benign thyroid nodules and malignant thyroid nodules, including papillary thyroid carcinoma. Here, we review the recent progress in thermal ablation techniques for treating benign and malignant nodules, including their technicalities, clinical applications, pitfalls and limitations, and factors that could affect treatment outcomes. Special in-depth elaboration on the recent progress of the application of thermal ablation therapy in malignant thyroid nodules.