Using Deep Neural Network to Diagnose Thyroid Nodules on Ultrasound in Patients With Hashimoto's Thyroiditis.

OBJECTIVE: The aim of this study is to develop a model using Deep Neural Network (DNN) to diagnose thyroid nodules in patients with Hashimoto's Thyroiditis. METHODS: In this retrospective study, we included 2,932 patients with thyroid nodules who underwent thyroid ultrasonogram in our hospital from January 2017 to August 2019. 80% of them were included as training set and 20% as test set. Nodules suspected for malignancy underwent FNA or surgery for pathological results. Two DNN models were trained to diagnose thyroid nodules, and we chose the one with better performance. The features of nodules as well as parenchyma around nodules will be learned by the model to achieve better performance under diffused parenchyma. 10-fold cross-validation and an independent test set were used to evaluate the performance of the algorithm. The performance of the model was compared with that of the three groups of radiologists with clinical experience of <5 years, 5-10 years, >10 years respectively. RESULTS: In total, 9,127 images were collected from 2,932 patients with 7,301 images for the training set and 1,806 for the test set. 56% of the patients enrolled had Hashimoto's Thyroiditis. The model achieved an AUC of 0.924 for distinguishing malignant and benign nodules in the test set. It showed similar performance under diffused thyroid parenchyma and normal parenchyma with sensitivity of 0.881 versus 0.871 (p = 0.938) and specificity of 0.846 versus 0.822 (p = 0.178). In patients with HT, the model achieved an AUC of 0.924 to differentiate malignant and benign nodules which was significantly higher than that of the three groups of radiologists (AUC = 0.824, 0.857, 0.863 respectively, p < 0.05). CONCLUSION: The model showed high performance in diagnosing thyroid nodules under both normal and diffused parenchyma. In patients with Hashimoto's Thyroiditis, the model showed a better performance compared to radiologists with various years of experience.

Using BI-RADS Stratifications as Auxiliary Information for Breast Masses Classification in Ultrasound Images.

Breast Ultrasound (BUS) imaging has been recognized as an essential imaging modality for breast masses classification in China. Current deep learning (DL) based solutions for BUS classification seek to feed ultrasound (US) images into deep convolutional neural networks (CNNs), to learn a hierarchical combination of features for discriminating malignant and benign masses. One existing problem in current DL-based BUS classification was the lack of spatial and channel-wise features weighting, which inevitably allow interference from redundant features and low sensitivity. In this study, we aim to incorporate the instructive information provided by breast imaging reporting and data system (BI-RADS) within DL-based classification. A novel DL-based BI-RADS Vector-Attention Network (BVA Net) that trains with both texture information and decoded information from BI-RADS stratifications was proposed for the task. Three baseline models, pre-trained DenseNet-121, ResNet-50 and Residual-Attention Network (RA Net) were included for comparison. Experiments were conducted on a large scale private main dataset and two public datasets, UDIAT and BUSI. On the main dataset, BVA Net outperformed other models, in terms of AUC (area under the receiver operating curve, 0.908), ACC (accuracy, 0.865), sensitivity (0.812) and precision (0.795). BVA Net also achieved the high AUC (0.87 and 0.882) and ACC (0.859 and 0.843), on UDIAT and BUSI. Moreover, we proposed a method that integrates both BVA Net binary classification and BI-RADS stratification estimation, called integrated classification. The introduction of integrated classification helped improving the overall sensitivity while maintaining a high specificity.

Attenuated total reflection Fourier transform infrared spectroscopic investigation of the postmortem metabolic process in rat and human kidney cortex.

Attenuated total reflection (ATR) Fourier transform infrared (FT-IR) spectroscopy has been applied to study the short and long term postmortem metabolic processes in rat and human kidney cortexes. The goals of this project were as follows: (1) to investigate the changes of ATR spectra in different rat and human tissues after death, (2) to explore the best mathematical model with different band absorption ratio changes to determine the postmortem interval (PMI), and (3) to establish a preliminary human postmortem ATR spectra database. There were three different types of metabolic changes after death based on the spectral results: (1) the intensities of some bands increased continuously (e.g., C-H stretching region), (2) the intensities of other bands decreased continuously (e.g., PO(2)(-) symmetric stretching), and (3) other bands remained relatively stable (e.g., C-OH bending, CO-O-C antisymmetric stretching). The band absorbance ratios for rats were found to display either a significant increase or decrease with increasing time after death. Of the absorbance ratios of the various bands investigated to find the best fit with the cubic model function in rats, the A(1652)/A(1396) ratio showed the strongest correlation (R(2) = 0.937). Comparison of the rat kidney cortex spectra with selected human postmortem cases showed similar postmortem metabolic changes. In conclusion, ATR FT-IR spectroscopy was shown to be a convenient and reliable method of determining short and long term postmortem intervals by simultaneously monitoring several specific parameters, although these observations have yet to be applied at forensic scenes by further field studies.