Search

Abstract Background Angiosarcoma is an extremely rare malignant tumor. So far, only about 42 cases of angiosarcoma involving the eyelids have been reported. Eyelid angiosarcoma occurs more frequently in elderly Caucasian males and is prone to misdiagnosis. We present a case report in a young Asian male patient with eyelid angiosarcoma that was misdiagnosed as a chalazion. Case presentation A 46-year-old South Korean male with no underlying disease had a right lower lid mass. The lesion was initially misdiagnosed as a chalazion at a local clinic, but a diagnosis of eyelid angiosarcoma was made after the first biopsy trial. PET-CT was performed to ensure that there was no metastasis in the whole body. Surgical excision with enough surgical margin was used alone for treatment and reconstruction was performed with a tarsoconjunctival advancement flap (modified Hughes procedure), which helped ensure good cosmesis. No recurrence was observed 4 years and 5 months after the surgery. Conclusions The current study presents the first case of chalazion-mimicked eyelid angiosarcoma in a young Asian male aged under 50 years. This case shows that even if a benign eyelid disease is suspected in a young patient, an incisional biopsy must be performed to confirm whether the lesion is malignant. Since the prognosis is good for the case of eyelid angiosarcoma, if there is no clear evidence of distal metastasis, surgical resection should be performed with an enough safety margin.

Low-light images often lack visibility and information, and traditional methods of adjusting camera sensitivity and exposure time can result in visual quality degradation. In this paper, we propose a low-light enhancement method that utilizes two novel approaches to address these issues. The first approach involves using multi-band NIR (Near Infra-red) to preserve structural components, while a transformer-based cross-attention module efficiently calculates the correlation between NIR and RGB for effective fusion. The second approach involves implementing dual-teacher knowledge distillation, where normal- and mid-light teacher networks transfer low-light enhancement knowledge to the student. Our proposed method produces better color and detail restoration results than existing methods, particularly in ultra low-light environments. We also provide our own datasets for two different low-light conditions, enabling wide evaluations and ablation studies.

This paper proposes to utilize deep spatio-spectral features for color constancy, while most conventional methods focus on only spatial information of RGB images. We propose a novel color constancy method that exploits multi-band near-infrared (NIR). The proposed illuminant estimation network comprises two subnetworks, each tasked with learning different aspects: one focuses on capturing the local illuminant based on the input RGB and NIR images, while the other is dedicated to estimating confidence levels using both RGB and NIR inputs. We leverage a cross-attention mechanism to effectively capture the correlation between RGB and NIR modalities. Additionally, our method capitalizes on the relationship between RGB and NIR by incorporating a NIR colorization network into the primary illuminant estimation framework. Due to the absence of a public dataset for color constancy with multi-band NIR, we constructed a dataset comprising 604 images using a hyperspectral camera. The experimental results demonstrate superior performance in illuminant estimation when utilizing multi-band NIR compared to conventional RGB and single-band NIR approaches. Furthermore, employing a cross-attention mechanism to consider the correlation between RGB and NIR reveals the estimation of a sophisticated confidence map that aids in illuminant estimation, surpassing other existing fusion methods. The feature transfer from an additional task network can further enhance the performance of illuminant estimation.

We aim to contribute to deep learning based smart agriculture through semantic segmentation on crop images from real field environment. The key objective is the precise detection of diseases to facilitate the automation of agricultural management. The most significant issue is that the disease regions, serving as Regions of Interest (RoI), are small, making accurate prediction challenging. To address this issue, we propose a new framework of RoI-Attention Network (RA-Net) which additionally utilizes an RoI-attentive image that includes only regions predicted as disease and their surroundings from the input image. Using the RoI-attentive image, RA-Net enhances the representation power for disease regions by guiding the network to re-focus on RoI-associated context based on the initial prediction from the input. Using the proposed RoI-Attention stage, the coarse predictions of disease regions in crop images can be enhanced by incorporating additional sequential RoI-Attention and fusion stages. We have experimentally demonstrated the effectiveness of the proposed RA-Net in predicting small disease regions.

Abstract Background Light control technology has been developed and studied for decades in controlled environment agriculture (CEA) for successful crop production. The effects of the light spectrum on plant growth can vary because plants have spectral specific responses, and mixed light elicits interactive combination effects. Response surface methodology (RSM) can be utilized with the design of experiments to optimize a response influenced by multiple inputs with limited data. In this study, we aimed to identify the optimal photon ratio in combination of red (R), green (G), and blue (B) light-emitting diodes (LEDs) for growing lettuce seedlings using RSM and a seedling-indicating parameter by performing a similarity analysis of response surfaces that elucidated the response tendency of different factors, such as light quality. Results The highest shoot fresh weight was obtained from the R treatment (red LED 100%) at the end of the seedling stage. However, the RGB141 (photon ratio of R:G:B = 1:4:1) treatment during the seedling stage resulted in the highest shoot fresh weight at the final harvest. The value of the leaf area multiplied by the leaf chlorophyll concentration (SPAD) was selected as the seedling-indicating parameter. The optimal RGB photon ratio that maximized this parameter was R:G:B = 30.6:44.0:25.4, and this ratio was verified by conducting identical cultivation experiments. During the first 6 days after transplanting, SPAD gradually increased in R-treated seedlings, while the optimal treatment maintained the value at a higher constant level, which supported our result of shoot fresh weight at harvest. Conclusions Thus, we confirmed that the mixture design method allowed us to optimize the combined RGB photon ratios for the seedling stage in order to maximize the growth index of mature lettuce plants and to select an appropriate seedling-indicating parameter that represents the final harvest results to benefit crop production in CEA.

Artificial lights, which are powered by alternating current (AC), are ubiquitous nowadays. The intensity of these lights fluctuates dynamically depending on the AC power. In contrast to previous color constancy methods that exploited the spatial color information, we propose a novel deep learning-based color constancy method that exploits the temporal variations exhibited by AC-powered lights. Using a high-speed camera, we capture the intensity variations of AC lights. Then, we use these variations as an important cue for illuminant learning. We propose a network composed of spatial and temporal branches to train the model with both spatial and temporal features. The spatial branch learns the conventional spatial features from a single image, whereas the temporal branch learns the temporal features of AC-induced light intensity variations in a high-speed video. The proposed method calculates the temporal correlation between the high-speed frames to extract the effective temporal features. The calculations are done at a low computational cost and the output is fed into the temporal branch to help the model concentrate on illuminant-attentive regions. By learning both spatial and temporal features, the proposed method performs remarkably under a complex illuminant environment in a real world scenario in which color constancy is difficult to investigate. The experimental results demonstrate that the proposed method produces lower angular error than the previous state-of-the-art by 30%, and works exceptionally well under various illuminants, including complex ambient light environments.