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.
An illustration of the 28 OARs to be delineated in the head and neck area. [Nature]
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.
RSSOwl is a powerful open-source application to organize, search, and read feeds. It extremely has powerful search features and offers synchronization with Google reader and more.
RSS Owl is a powerful application to organize, search and read your RSS, RDF & Atom news feeds in a comfortable way. Highlights are saved
RSS Guard is a simple RSS/ATOM feed reader for Windows, Linux, BSD, OS/2 or macOS which can work with RSS/ATOM/JSON feeds as well as many online feed services:
* Feedly
* Gmail
* Google Reader API (Bazqux, FreshRSS, Inoreader, Miniflux, Reedah, The Old Reader and more)
* Nextcloud News
* Tiny
Raven is a open source desktop news reader with flexible settings to optimize your experience. No login is required, and no personal data is collected.
If you want to add your articles in one place Raven is the best choice. Raven is an open-source desktop newsreader, built on top of
Fluent Reader is one of the most popular Modern desktop RSS readers. It is open-source, and has some special features such as it can export service configs to it through QR code, it has a keyboard shortcut to hide an app on macOS, it also supports Chinese, and Turkish language,
Feed Compass is an open-source application that enables you to find and subscribe to RSS Feeds in your favorite RSS Reader and is built with Swift. It also has numerous default feeds, it supports drag-and-drop feeds to native RSS readers.
Features
* A large number of default feeds (especially Apple developer
Tiny Tiny RSS is a tiny open source project which is an advanced RSS reader/news aggregator. It is a self-hosted RSS aggregator, which can also be used to read from remote sources. With an intuitive UI and great performance, it is fast and easy to install on any hosting
The choice is simple
You either support Rishi Sunak and Steve Barclay or you support the nurses on strike#FairPayforNursing #NursesStrike pic.twitter.com/DepdKUoCw3
— NHS Nurses (@SocialistNHS) January 10, 2023
Day 2 of the NYC nurses strike. This is in front of Montefiore in the Bronx. @NBCNewYork pic.twitter.
NetNewsWire os a free open-source RSS feed reader and organizer for macOS and iOS. It comes without ads, user tracking scripts, or any script that shares your information.
With NetNewsWire, you can organize your feeds in folders, mark them as read/ unread, and sync your data to iCloud, Feedly and
Technology is ever-evolving regardless of the current market conditions. New technologies are emerging with groundbreaking innovations to tackle world issues.
It must be strange that predictions are being made about the future of technology in these uncertain times these innovations are what make life easier in the coming years from
The internet has problems, let's say there are 50 million weblogs, and it's going up, our focus here is on a new and efficient way to keep up with all the cool stuff that's happening on the Internet.
What we are talking about is using a single website that becomes