Radiation Therapy is a widely used treatment modality for many types of cancer, but it has potential adverse effects to healthy surrounding organs. So, accurately identifying all Organs at Risk (OARs) is a very important step in Radiation Therapy Planning. However, manually doing so is time consuming and error-prone.
A group of researchers presented a deep learning model to automatically delineate OARs in head and neck, trained on a dataset of 215 CT scans with 28 OARs manually delineated by experienced radiation oncologists.
They chose head and neck due to the complex anatomical structures and dense distribution of important organs in this area. Damaging normal organs in the head and neck can result in a series of complications, such as xerostomia, oral mucosal damage, laryngeal oedema, dysphagia, difficulty in opening the mouth, visual deterioration, hearing loss and cognitive impairment.
This model is named Ua-Net (attention-modulated U-Net) and consists of two submodules, one for OAR detection and the other for OAR segmentation. The goal of the OAR detection module is to identify the location and size of each OAR from the CT images, while the goal of the OAR segmentation module is to further segment OARs within each detected OAR region.
Ua-Net only upsamples feature maps containing OARs, and thus is able to drastically cut down GPU memory consumption. With this model, it becomes feasible to delineate all 28 OARs from whole-volume CT images using only commodity GPUs (for example, with 11 Gb memory), which is important for the method to be able to be deployed in actual clinics.
Ua-Net can complete the entire delineation process of a case within a couple of seconds. By contrast, the human expert took, on average, 34 minutes to complete one case.
On a hold-out dataset of 100 computed tomography scans, Ua-Net achieves an average Dice similarity coefficient of 78.34% across the 28 OARs, significantly outperforming human experts and the previous state-of-the-art method by 10.05% and 5.18%, respectively.
The Code is freely available for non-commercial research purposes.
If you often find yourself overwhelmed with the amount of content available on the internet and struggle to keep up, take a look at Wallabag. This exceptional web application provides a solution to your content overload by allowing you to save web pages for reading at a later time.
With
What is Huntly?
Huntly is an all-in-one, self-hosted information management tool that provides a plethora of features designed to streamline and simplify your data management needs. It includes the ability to subscribe to and read RSS feeds, thereby keeping you updated with the latest news and articles from your favorite
What is Hacker News?
Hacker News is a social news website focusing on computer science and entrepreneurship. It is run by Y Combinator, a seed accelerator. Users can submit stories (links to articles), and other users can upvote these stories, similar to "liking" a post on other social
Z Combinator is a free Hacker News client made with SwiftUI that allows users to log in with their Hacker News account, reply to stories and comments, vote on stories and comments, and add stories and comments to their pins or HN.
Features
* Log in with Hacker News account
* Reply
Hacki is a Hacker News client built with Flutter. It allows users to log in with their Hacker News account, browse stories from various categories, search for stories, submit stories, and pin stories.
Features
* Fast and lightweight app
* Log in using your Hacker News account.
* Browse stories from various categories.
HNClient is a free and open-source desktop client for Hacker News that allows users to read articles and comments without opening multiple tabs.
It features a sidebar for article selection and supports split-screen viewing of articles and their comments. The app is compatible with Mac, Linux, and Windows.
Features
* Sidebar
What is a News Aggregator
A news aggregator is a tool or platform that collects news from various sources and presents them in one location. It is used for conveniently accessing and reading news from multiple sources without having to visit each source individually.
In this list, we collected the
Hacker News Summary is an open-source project that uses AI technology, primarily the ChatGPT gpt-3.5-turbo model, to extract summaries and illustrations from Hacker News articles.
If ChatGPT is unavailable, the local GoogleT5 model is used. The service provides clear and easily understandable summaries.
Features
* Clear and easily understandable summaries
Germany's Federal Ministry for Digital and Transport Affairs has drafted a bill requiring mandatory end-to-end encryption for messengers and cloud services, a move celebrated by cryptography experts and privacy enthusiasts for protecting digital correspondence.
The "right to encryption" law, proposed by the German government, refers to
news-please is an open-source news crawler that extracts structured information from news websites. It uses libraries like scrapy, Newspaper, and readability, and can follow internal hyperlinks and read RSS feeds to fetch both recent and archived articles.
It also features a library mode for Python developers and can extract articles