Deep learning is one of the most effective approaches to medical image processing applications. Network models are being studied more and more for medical image segmentation challenges. The encoder–decoder structure is achieving great success, in particular the Unet architecture, which is used as a baseline architecture for the medical image segmentation networks. Traditional Unet and Unet-based networks still have a limitation that is not able to fully exploit the output features of the convolutional units in the node. In this study, we proposed a new network model named TMD-Unet, which had three main enhancements in comparison with Unet: (1) modifying the interconnection of the network node, (2) using dilated convolution instead of the standard convolution, and (3) integrating the multi-scale input features on the input side of the model and applying a dense skip connection instead of a regular skip connection. Our experiments were performed on seven datasets, including many different medical image modalities such as colonoscopy, electron microscopy (EM), dermoscopy, computed tomography (CT), and magnetic resonance imaging (MRI). The segmentation applications implemented in the paper include EM, nuclei, polyp, skin lesion, left atrium, spleen, and liver segmentation. The dice score of our proposed models achieved 96.43% for liver segmentation, 95.51% for spleen segmentation, 92.65% for polyp segmentation, 94.11% for EM segmentation, 92.49% for nuclei segmentation, 91.81% for left atrium segmentation, and 87.27% for skin lesion segmentation. The experimental results showed that the proposed model was superior to the popular models for all seven applications, which demonstrates the high generality of the proposed model.

Light Detection and Ranging (LiDAR) is a critical sensor for autonomous vehicle systems, providing high-resolution distance measurements in real-time. However, adverse weather conditions such as snow, rain, fog, and sun glare can affect LiDAR performance, requiring data preprocessing. This paper proposes a novel approach, the Adaptive Outlier Removal filter on range Image (AORI), which combines a projection image from LiDAR point clouds with an adaptive outlier removal filter to remove snow particles. Our research aims to analyze the characteristics of LiDAR and propose an image-based approach derived from LiDAR data that addresses the limitations of previous studies, particularly in improving the efficiency of nearest neighbor point search. Our proposed method achieves outstanding performance in both accuracy (>96%) and processing speed (0.26 s per frame) for autonomous driving systems under harsh weather from raw LiDAR point clouds in the Winter Adverse Driving dataset (WADS). Notably, AORI outperforms state-of-the-art filters by achieving a 6.6% higher F1 score and 0.7% higher accuracy. Although our method has a lower recall than state-of-the-art methods, it achieves a good balance between retaining object points and filter noise points from LiDAR, indicating its promise for snow removal in adverse weather conditions.

Purpose: The minimally invasive surgery (MIS) has shown advantages when compared to traditional surgery. However, there are two major challenges in the MIS technique: the limited field of view (FOV) and the lack of depth perception provided by the standard monocular endoscope. Therefore, in this study, we proposed a New Endoscope for Panoramic-View with Focus-Area 3D-Vision (3DMISPE) in order to provide surgeons with a broad view field and 3D images in the surgical area for real-time display.Method: The proposed system consisted of two endoscopic cameras fixed to each other. Compared to our previous study, the proposed algorithm for the stitching videos was novel. This proposed stitching algorithm was based on the stereo vision synthesis theory. Thus, this new method can support 3D reconstruction and image stitching at the same time. Moreover, our approach employed the same functions on reconstructing 3D surface images by calculating the overlap region’s disparity and performing image stitching with the two-view images from both the cameras.Results: The experimental results demonstrated that the proposed method can combine two endoscope’s FOV into one wider FOV. In addition, the part in the overlap region could also be synthesized for a 3D display to provide more information about depth and distance, with an error of about 1 mm. In the proposed system, the performance could achieve a frame rate of up to 11.3 fps on a single Intel i5-4590 CPU computer and 17.6 fps on a computer with an additional GTX1060 Nvidia GeForce GPU. Furthermore, the proposed stitching method in this study could be made 1.4 times after when compared to that in our previous report. Besides, our method also improved stitched image quality by significantly reducing the alignment errors or “ghosting” when compared to the SURF-based stitching method employed in our previous study.Conclusion: The proposed system can provide a more efficient way for the doctors with a broad area of view while still providing a 3D surface image in real-time applications. Our system give promises to improve existing limitations in laparoscopic surgery such as the limited FOV and the lack of depth perception.

Light Detection And Ranging (LiDAR) is an important technology integrated into self-driving cars to enhance the reliability of these systems. Even with some advantages over cameras, it is still limited under extreme weather conditions such as heavy rain, fog, or snow. Traditional methods such as Radius Outlier Removal (ROR) and Statistical Outlier Removal (SOR) are limited in their ability to detect snow points in LiDAR point clouds. This paper proposes an Adaptive Group of Density Outlier Removal (AGDOR) filter that can remove snow particles more effectively in raw LiDAR point clouds, with verification on the Winter Adverse Driving Dataset (WADS). In our proposed method, an intensity threshold combined with a proposed outlier removal filter was employed. Outstanding performance was obtained, with higher accuracy up to 96% and processing speed of 0.51 s per frame in our result. In particular, our filter outperforms the state-of-the-art filter by achieving a 16.32% higher Precision at the same accuracy. However, our method archive is lower in recall than the state-of-the-art method. This clearly indicates that AGDOR retains a significant amount of object points from LiDAR. The results suggest that our filter would be useful for snow removal under harsh weathers for autonomous driving systems.

Background light noise is one of the major challenges in the design of Light Detection and Ranging (LiDAR) systems. In this paper, we build a single-beam LiDAR module to investigate the effect of light intensity on the accuracy/precision and success rate of measurements in environments with strong background noises. The proposed LiDAR system includes the laser signal emitter and receiver system, the signal processing embedded platform, and the computer for remote control. In this study, two well-known time-of-flight (ToF) estimation methods, which are peak detection and cross-correlation (CC), were applied and compared. In the meanwhile, we exploited the cross-correlation technique combined with the reduced parabolic interpolation (CCP) algorithm to improve the accuracy and precision of the LiDAR system, with the analog-to-digital converter (ADC) having a limited resolution of 125 mega samples per second (Msps). The results show that the CC and CCP methods achieved a higher success rate than the peak method, which is 12.3% in the case of applying emitted pulses 10 µs/frame and 8.6% with 20 µs/frame. In addition, the CCP method has the highest accuracy/precision in the three methods reaching 7.4 cm/10 cm and has a significant improvement over the ADC’s resolution of 1.2 m. This work shows our contribution in building a LiDAR system with low cost and high performance, accuracy, and precision.

Processing speed and accuracy of measurements are important factors reflecting the performance quality of light detection and ranging (LiDAR) systems. This study proposed a fast cross-correlation (fCC) algorithm to improve the computation loading in the LiDAR system operating in high background noise environments. To reduce the calculation time, we accumulated cycles of the receiver waveform to increase the signal-to-noise ratio. In this way, the stop pulse can be easily distinguished from the background noise by applying the cross-correlation (CC) on the accumulated receiver waveform with the first start pulse. In addition, the proposed fCC combined with variant interpolation techniques: the parabolic (fCCP), gaussian (fCCG), cosine (fCCC), and cubic spline (fCCS) to increase the measurement accuracy were also investigated and compared. The experiments were performed on the real-time LiDAR system under high background light intensity. The tested results showed that the proposed method fCCP achieved 879 ns per measurement, 38 times faster than the original CC method combined with the same parabolic interpolation algorithm (CCP) 33.5 μs. Meanwhile, the fCCS method resulted in the highest accuracy/precision, reaching 5.193 cm/8.588 cm, respectively. These results demonstrated that our proposed method significantly improves the measurements speed in the LiDAR system operating under strong background light.