Deep Learning-Based Diagnostic System for Velopharyngeal Insufficiency Based on Videofluoroscopy in Patients With Repaired Cleft Palates.

Velopharyngeal insufficiency (VPI), which is the incomplete closure of the velopharyngeal valve during speech, is a typical poor outcome that should be evaluated after cleft palate repair. The interpretation of VPI considering both imaging analysis and perceptual evaluation is essential for further management. The authors retrospectively reviewed patients with repaired cleft palates who underwent assessment for velopharyngeal function, including both videofluoroscopic imaging and perceptual speech evaluation. The final diagnosis of VPI was made by plastic surgeons based on both assessment modalities. Deep learning techniques were applied for the diagnosis of VPI and compared with the human experts' diagnostic results of videofluoroscopic imaging. In addition, the results of the deep learning techniques were compared with a speech pathologist's diagnosis of perceptual evaluation to assess consistency with clinical symptoms. A total of 714 cases from January 2010 to June 2019 were reviewed. Six deep learning algorithms (VGGNet, ResNet, Xception, ResNext, DenseNet, and SENet) were trained using the obtained dataset. The area under the receiver operating characteristic curve of the algorithms ranged between 0.8758 and 0.9468 in the hold-out method and between 0.7992 and 0.8574 in the 5-fold cross-validation. Our findings demonstrated the deep learning algorithms performed comparable to experienced plastic surgeons in the diagnosis of VPI based on videofluoroscopic velopharyngeal imaging.

Speckle Reduction via Deep Content-Aware Image Prior for Precise Breast Tumor Segmentation in an Ultrasound Image.

The performance of computer-aided diagnosis (CAD) systems that are based on ultrasound imaging has been enhanced owing to the advancement in deep learning. However, because of the inherent speckle noise in ultrasound images, the ambiguous boundaries of lesions deteriorate and are difficult to distinguish, resulting in the performance degradation of CAD. Although several methods have been proposed to reduce speckle noise over decades, this task remains a challenge that must be improved to enhance the performance of CAD. In this article, we propose a deep content-aware image prior (DCAIP) with a content-aware attention module (CAAM) for superior despeckling of ultrasound images without clean images. For the image prior, we developed a CAAM to deal with the content information in an input image. In this module, super-pixel pooling (SPP) is used to give attention to salient regions in an ultrasound image. Therefore, it can provide more content information regarding the input image when compared to other attention modules. The DCAIP consists of deep learning networks based on this attention module. The DCAIP is validated by applying it as a preprocessing step for breast tumor segmentation in ultrasound images, which is one of the tasks in CAD. Our method improved the segmentation performance by 15.89% in terms of the area under the precision-recall (PR) curve (AUPRC). The results demonstrate that our method enhances the quality of ultrasound images by effectively reducing speckle noise while preserving important information in the image, promising for the design of superior CAD systems.

Explainable deep learning algorithm for distinguishing incomplete Kawasaki disease by coronary artery lesions on echocardiographic imaging.

BACKGROUND AND OBJECTIVE: Incomplete Kawasaki disease (KD) has often been misdiagnosed due to a lack of the clinical manifestations of classic KD. However, it is associated with a markedly higher prevalence of coronary artery lesions. Identifying coronary artery lesions by echocardiography is important for the timely diagnosis of and favorable outcomes in KD. Moreover, similar to KD, coronavirus disease 2019, currently causing a worldwide pandemic, also manifests with fever; therefore, it is crucial at this moment that KD should be distinguished clearly among the febrile diseases in children. In this study, we aimed to validate a deep learning algorithm for classification of KD and other acute febrile diseases. METHODS: We obtained coronary artery images by echocardiography of children (n = 138 for KD; n = 65 for pneumonia). We trained six deep learning networks (VGG19, Xception, ResNet50, ResNext50, SE-ResNet50, and SE-ResNext50) using the collected data. RESULTS: SE-ResNext50 showed the best performance in terms of accuracy, specificity, and precision in the classification. SE-ResNext50 offered a precision of 81.12%, a sensitivity of 84.06%, and a specificity of 58.46%. CONCLUSIONS: The results of our study suggested that deep learning algorithms have similar performance to an experienced cardiologist in detecting coronary artery lesions to facilitate the diagnosis of KD.

Federated Learning for Thyroid Ultrasound Image Analysis to Protect Personal Information: Validation Study in a Real Health Care Environment.

BACKGROUND: Federated learning is a decentralized approach to machine learning; it is a training strategy that overcomes medical data privacy regulations and generalizes deep learning algorithms. Federated learning mitigates many systemic privacy risks by sharing only the model and parameters for training, without the need to export existing medical data sets. In this study, we performed ultrasound image analysis using federated learning to predict whether thyroid nodules were benign or malignant. OBJECTIVE: The goal of this study was to evaluate whether the performance of federated learning was comparable with that of conventional deep learning. METHODS: A total of 8457 (5375 malignant, 3082 benign) ultrasound images were collected from 6 institutions and used for federated learning and conventional deep learning. Five deep learning networks (VGG19, ResNet50, ResNext50, SE-ResNet50, and SE-ResNext50) were used. Using stratified random sampling, we selected 20% (1075 malignant, 616 benign) of the total images for internal validation. For external validation, we used 100 ultrasound images (50 malignant, 50 benign) from another institution. RESULTS: For internal validation, the area under the receiver operating characteristic (AUROC) curve for federated learning was between 78.88% and 87.56%, and the AUROC for conventional deep learning was between 82.61% and 91.57%. For external validation, the AUROC for federated learning was between 75.20% and 86.72%, and the AUROC curve for conventional deep learning was between 73.04% and 91.04%. CONCLUSIONS: We demonstrated that the performance of federated learning using decentralized data was comparable to that of conventional deep learning using pooled data. Federated learning might be potentially useful for analyzing medical images while protecting patients' personal information.

Channel Attention Module With Multiscale Grid Average Pooling for Breast Cancer Segmentation in an Ultrasound Image.

Breast cancer accounts for the second-largest number of deaths in women around the world, and more than 8% of women will suffer from the disease in their lifetime. Mortality due to breast cancer can be reduced by its early and precise diagnosis. Many studies have investigated methods for segmentation, and computer-aided diagnosis based on deep learning techniques, in particular, has recently gained attention. However, recently proposed methods such as fully convolutional network (FCN), SegNet, and U-Net still need to be further improved to provide better semantic segmentation when diagnosing breast cancer by ultrasound imaging, because of their low performance. In this article, we propose a channel attention module with multiscale grid average pooling (MSGRAP) for the precise segmentation of breast cancer regions in ultrasound images. We demonstrate the effectiveness of the channel attention module with MSGRAP for semantic segmentation and develop a novel semantic segmentation network with the proposed attention module for the precise segmentation of breast cancer regions in ultrasound images. While a conventional convolutional operation cannot use global spatial information on input images and only use the small local information in a kernel of a convolution filter, the proposed attention module allows using both global and local spatial information. In addition, through ablation studies, we come up with a network architecture for precise breast cancer segmentation in an ultrasound image. The proposed network was constructed with an open-source breast cancer ultrasound image data set, and its performance was compared with those of other state-of-the-art deep-learning models for the segmentation of breast cancer. The experimental results showed that our network outperformed other segmentation methods, and the proposed channel attention module improved the performance of the network for breast cancer segmentation in ultrasound images.

Diethyldithiocarbamate inhibition of galactosamine-induced hepatitis in rats.

Free-radical-mediated oxidant damage can contribute to acute hepatitis. Vitamin E, a classic antioxidant, has been tested as a therapy for rodent acute hepatitis, but the protection achieved has not been complete. This study demonstrated that in rats, sodium diethyldithiocarbamate (DDC), a potent antioxidant, strongly depressed galactosamine-induced hepatitis in terms of serum alanine amino transferase activities and bile acids, though not in terms of serum beta-glucuronidase activities. A potential limitation for DDC use in humans, inhibition of copper metalloenzyme activities, did occur at the DDC dose used here. However, these effects were not severe. Thus, DDC could make a useful short term therapeutic drug for acute hepatitis.