Reproducible SERS substrates manipulated by interparticle spacing and particle diameter of gold nano-island array using in-situ thermal evaporation.

Gold (Au) nano-island arrays were deposited on the glass substrate to fabricate surface-enhanced Raman scattering (SERS) substrates by in-situ thermal evaporation (deposited and annealed samples at the same time). The optimal SERS intensity deposited by various thicknesses and in-situ annealing temperatures of Au nano-island arrays would be investigated. The biomolecules (adenine) were dropped on the well-designed SERS substrate for precise and quantitative SERS detection. The characterization of Au nano-island arrays SERS substrate would be evaluated by scanning electron microscope (SEM) and Raman spectroscopy. The results showed that the optimal deposition thickness and annealing temperature of Au nano-island arrays SERS substrate is about 14 nm and 200 °C respectively, which can construct the smallest interparticle spacing (W)/ particle diameter (D) ratio and the lowest reflection (%) and transmittance (%) to form the strongest SERS intensity. Moreover, finite-difference time-domain (FDTD) simulation of the electromagnetic field distributions on Au nano-island arrays displays the similar trend with the experimental results. The 14 nm deposition with 200 °C in-situ annealing temperature would display the highest density of hot-spots by FDTD simulation. The reproducible Au nano-island arrays SERS substrates with tunable surface roughness, W/D ratio, and lower reflection and transmittance show promising potential for SERS detection of biomolecules, bacteria, and viruses.

3-D Res-CapsNet convolutional neural network on automated breast ultrasound tumor diagnosis.

PURPOSE: We propose a 3-D tumor computer-aided diagnosis (CADx) system with U-net and a residual-capsule neural network (Res-CapsNet) for ABUS images and provide a reference for early tumor diagnosis, especially non-mass lesions. METHODS: A total of 396 patients with 444 tumors (226 malignant and 218 benign) were retrospectively enrolled from Sun Yat-sen University Cancer Center. In our CADx, preprocessing was performed first to crop and resize the tumor volumes of interest (VOIs). Then, a 3-D U-net and postprocessing were applied to the VOIs to obtain tumor masks. Finally, a 3-D Res-CapsNet classification model was executed with the VOIs and the corresponding masks to diagnose the tumors. Finally, the diagnostic performance, including accuracy, sensitivity, specificity, and area under the curve (AUC), was compared with other classification models and among three readers with different years of experience in ABUS review. RESULTS: For all tumors, the accuracy, sensitivity, specificity, and AUC of the proposed CADx were 84.9 %, 87.2 %, 82.6 %, and 0.9122, respectively, outperforming other models and junior reader. Next, the tumors were subdivided into mass and non-mass tumors to validate the system performance. For mass tumors, our CADx achieved an accuracy, sensitivity, specificity, and AUC of 85.2 %, 88.2 %, 82.3 %, and 0.9147, respectively, which was higher than that of other models and junior reader. For non-mass tumors, our CADx achieved an accuracy, sensitivity, specificity, and AUC of 81.6 %, 78.3 %, 86.7 %, and 0.8654, respectively, outperforming the two readers. CONCLUSION: The proposed CADx with 3-D U-net and 3-D Res-CapsNet models has the potential to reduce misdiagnosis, especially for non-mass lesions.

Computer-aided tumor detection in automated breast ultrasound using a 3-D convolutional neural network.

BACKGROUND AND OBJECTIVES: Automated breast ultrasound (ABUS) is a widely used screening modality for breast cancer detection and diagnosis. In this study, an effective and fast computer-aided detection (CADe) system based on a 3-D convolutional neural network (CNN) is proposed as the second reader for the physician in order to decrease the reviewing time and misdetection rate. METHODS: Our CADe system uses the sliding window method, a CNN-based determining model, and a candidate aggregation algorithm. First, the sliding window method is performed to split the ABUS volume into volumes of interest (VOIs). Afterward, VOIs are selected as tumor candidates by our determining model. To achieve higher performance, focal loss and ensemble learning are used to solve data imbalance and reduce false positive (FP) and false negative (FN) rates. Because several selected candidates may be part of the same tumor and they may overlap each other, a candidate aggregation method is applied to merge the overlapping candidates into the final detection result. RESULTS: In the experiments, 165 and 81 cases are utilized for training the system and evaluating system performance, respectively. On evaluation with the 81 cases, our system achieves sensitivities of 100% (81/81), 95.3% (77/81), and 90.9% (74/81) with FPs per pass (per case) of 21.6 (126.2), 6.0 (34.8), and 4.6 (27.1) respectively. According to the results, the number of FPs per pass (per case) can be diminished by 56.8% (57.1%) at a sensitivity of 95.3% based on our tumor detection model. CONCLUSIONS: In conclusion, our CADe system using 3-D CNN with the focal loss and ensemble learning may have the capability of being a tumor detection system in ABUS image.