GenU-Net++: An Automatic Intracranial Brain Tumors Segmentation Algorithm on 3D Image Series with High Performance

Automatic segmentation of intracranial brain tumors in three-dimensional (3D) image series is critical in screening and diagnosing related diseases. However, there are various challenges in intracranial brain tumor images: (1) Multiple brain tumor categories hold particular pathological features. (2) It is a thorny issue to locate and discern brain tumors from other non-brain regions due to their complicated structure. (3) Traditional segmentation requires a noticeable difference in the brightness of the interest target relative to the background. (4) Brain tumor magnetic resonance images (MRI) have blurred boundaries, similar gray values, and low image contrast. (5) Image information details would be dropped while suppressing noise. Existing methods and algorithms do not perform satisfactorily in overcoming these obstacles mentioned above. Most of them share an inadequate accuracy in brain tumor segmentation. Considering that the image segmentation task is a symmetric process in which downsampling and upsampling are performed sequentially, this paper proposes a segmentation algorithm based on U-Net++, aiming to address the aforementioned problems. This paper uses the BraTS 2018 dataset, which contains MR images of 245 patients. We suggest the generative mask sub-network, which can generate feature maps. This paper also uses the BiCubic interpolation method for upsampling to obtain segmentation results different from U-Net++. Subsequently, pixel-weighted fusion is adopted to fuse the two segmentation results, thereby, improving the robustness and segmentation performance of the model. At the same time, we propose an auto pruning mechanism in terms of the architectural features of U-Net++ itself. This mechanism deactivates the sub-network by zeroing the input. It also automatically prunes GenU-Net++ during the inference process, increasing the inference speed and improving the network performance by preventing overfitting. Our algorithm’s PA, MIoU, P, and R are tested on the validation dataset, reaching 0.9737, 0.9745, 0.9646, and 0.9527, respectively. The experimental results demonstrate that the proposed model outperformed the contrast models. Additionally, we encapsulate the model and develop a corresponding application based on the MacOS platform to make the model further applicable.

VALIS: Virtual Alignment of pathoLogy Image Series

Spatial analyses can reveal important interactions between and among cells and their microenvironment. However, most existing staining methods are limited to a handful of markers per slice, thereby limiting the number of interactions that can be studied. This limitation is frequently overcome by registering multiple images to create a single composite image containing many markers. While there are several existing image registration methods for whole slide images (WSI), most have specific use cases. Here, we present the Virtual Alignment of pathoLogy Image Series (VALIS), a fully automated pipeline that opens, registers (rigid and/or non-rigid), and saves aligned slides in the ome.tiff format. VALIS has been tested with 273 immunohistochemistry (IHC) samples and 340 immunofluorescence (IF) samples, each of which contained between 2-69 images per sample. The registered WSI tend to have low error and are completed within a matter of minutes. In addition to registering slides, VALIS can also using the registration parameters to warp point data, such as cell centroids previously determined via cell segmentation and phenotyping. VALIS is written in Python and requires only few lines of code for execution. VALIS therefore provides a free, opensource, flexible, and simple pipeline for rigid and non-rigid registration of IF and/or IHC that can facilitate spatial analyses of WSI from novel and existing datasets.

Deep learning for automated river-level monitoring through river-camera images: an approach based on water segmentation and transfer learning

River-level estimation is a critical task required for the understanding of flood events and is often complicated by the scarcity of available data. Recent studies have proposed to take advantage of large networks of river-camera images to estimate river levels but, currently, the utility of this approach remains limited as it requires a large amount of manual intervention (ground topographic surveys and water image annotation). We have developed an approach using an automated water semantic segmentation method to ease the process of river-level estimation from river-camera images. Our method is based on the application of a transfer learning methodology to deep semantic neural networks designed for water segmentation. Using datasets of image series extracted from four river cameras and manually annotated for the observation of a flood event on the rivers Severn and Avon, UK (21 November–5 December 2012), we show that this algorithm is able to automate the annotation process with an accuracy greater than 91 %. Then, we apply our approach to year-long image series from the same cameras observing the rivers Severn and Avon (from 1 June 2019 to 31 May 2020) and compare the results with nearby river-gauge measurements. Given the high correlation (Pearson's correlation coefficient >0.94) between these results and the river-gauge measurements, it is clear that our approach to automation of the water segmentation on river-camera images could allow for straightforward, inexpensive observation of flood events, especially at ungauged locations.

MO1045DEVELOPMENT OF A HOME CARE SUPPORT SYSTEM FOR PERITONEAL DIALYSIS PATIENTS I - USING DIGITAL WATERMARKING AND STEGANOGRAPHY*

Background and Aims As it is necessary to refrain from going out due to the COVID-19 pandemic, a system that allows dialysis patients to be treated at a remote location or at home, i.e., a home care support system, is required. Information and communications technology (ICT) used for these purposes is widely applied in various medical fields. Using ICT has the advantage of allowing the sharing of patients’ electronic patient records (EPR) among medical staff, but increases the risk of copyright infringement and privacy leaks during archiving and transmission. We have developed a home care support system for peritoneal dialysis patients using information hiding technology consisting of both digital watermarking technology for copyright protection and steganography technology for communication security when treating patients at home using ICT. In addition, we evaluated the developed system. Method The system for sharing medical information was developed in the PHP programming language on a personal computer system using Microsoft Azure cloud services. Figure 1 shows an explanation of the digital watermarking technology and steganography technology used in the developed system. 1. Digital watermarking technology The patient’s data, such as EPR data, facility name, etc., were hidden in the region of non-interest (RONI) of the patient’s chest CT image series and stored in a database. 2. Steganography technology We call scene photos “cover pictures.” Medical information (CT images, etc.) was hidden in the cover picture. In this study, the cover picture containing the medical information was designated as a Stego image. A body CT image series (16-bit, 512 × 512, 100 slices) was used to verify the steganography technique. These CT images were compressed using 7-Zip and then saved in a folder, which was then embedded in the cover photo. The Stego image was then sent from the patient’s home to the medical institution via the home care support system. Results We investigated the hash value, peak signal-to-noise ratio (PSNR), and structural similarity (SSIM) of the image series (Fig. 2). If the structure of the image or photograph was exactly the same, the SSIM shows a value of 1. If the PSNR is ≥ 40 dB, the image quality can be maintained without affecting diagnosis. If part of the ROI is changed during transmission, the hash value decoded from the received Stego image will be different from that before transmission. For Stego images containing watermarked or hidden CT images with 4000 words embedded, SSIM and PSNR were ≥ 0.99 dB and 65.3 dB, respectively. If the medical information was embedded in a low bit plane, such as a 1-bit or 2-bit plane, the radiologist could not identify the embedded information. When our technology was applied, there were no changes in the capacity of CT images or Stego images before and after embedding. Therefore, it was not possible to tell that medical information was embedded due to changes in capacity. Conclusion Using ICT, we have built a home care support system that can conceal medical information by combining digital watermarking technology and steganography technology to ensure the copyright of images and to ensure privacy and secure transmission of EPR and CT images. Using the developed system, daily medical information of dialysis patients could be transmitted safely to the institute, and the medical staff could share the information safely. Both techniques can be applied to all digital image information, and is not just limited to CT images.