More Gemini Features Coming to Google TV
Google TV integrates Gemini AI for image/video generation, enhances Google Photos, and adds a dedicated YouTube Shorts feed to the homepage.
Read moreColorectal cancer is the second most common cancer worldwide, with approximately 90% of cases occurring in individuals over 50 years old. Cancer cells originate from the inner surface or mucosal layer of the colon and can penetrate deeper layers and spread to other organs. If left untreated, this disease can be fatal.
The current screening method for colorectal cancer is performed using flexible colonoscopy. This process involves visually inspecting the mucosal lining of the colon and rectum using a camera attached to an endoscope. Abnormal areas are then biopsied for analysis. Although this is the current standard diagnostic method, it does have its drawbacks. Firstly, this technique relies on visual detection, but small lesions are difficult to detect with the naked eye and early-stage malignancies are often missed. Secondly, visual endoscopic examination can only detect surface changes in the intestinal wall and cannot assess deeper layers.
Professor Kuijing Zhu and doctoral student Yifeng Zeng from the McKelvey School of Engineering at Washington University in St. Louis are developing a new imaging technology that can provide accurate, real-time computer-aided diagnosis of colorectal cancer.By utilizing deep learning techniques, the researchers applied this technology to over 26,000 individual imaging frames from colorectal tissue samples to determine the accuracy of this method. In this preliminary study, they were able to identify tumors with 100% accuracy compared to pathological reports.
The research technology is based on optical coherence tomography (OCT), an optical imaging technique that has been used in ophthalmology for 20 years to capture retinal images. However, engineers from the McKelvey School and other institutions have been applying this technology to other purposes because it provides high spatial and depth resolution with imaging depths of up to 1 to 2 millimeters. OCT detects differences in the way refracted light interacts with healthy and diseased tissues and is highly sensitive to morphological changes in precancerous and early-stage cancers. With further development, this technology could be used as a real-time, non-invasive imaging tool alongside traditional colonoscopy to assist in screening for deeper precancerous polyps and early-stage colorectal cancer.
"We believe that combining this technology with colonoscopy will greatly assist surgeons in diagnosing colorectal cancer. More research is needed, but the idea is that when surgeons use colonoscopy to examine the surface of the colon, this technology can be zoomed in locally to aid in more accurate diagnosis of deeper precancerous polyps and early-stage cancers relative to normal tissue," said senior author Zhu, a professor of radiology at the Mallinckrodt Institute of Radiology at Washington University School of Medicine.Two years ago, primary author Fanzhi Zeng began using OCT as a research tool to image extracted colorectal tissue samples from the medical school. He observed that healthy colorectal tissue exhibited a pattern similar to that of teeth. However, precancerous and cancerous tissues rarely displayed this pattern. The tooth-like pattern is caused by the light attenuation of the healthy mucosal microstructure of the colorectal tissue.
Zeng started collaborating with another graduate student, Shiqi Xu, to process the data and identify patterns in the tissue samples. They trained and tested the network using approximately 26,000 OCT images obtained from 20 tumor areas, 16 benign areas, and six other abnormal areas from patient tissue samples. The system's predicted diagnoses were compared to the histopathological evaluation of the tissue specimens. Pathologists Zahra Alipour and Heba Abdelal assisted in the comparison. The research team found a sensitivity of 100% and a specificity of 99.7%.
Zeng stated, "What sets our system apart is that we can detect structural patterns in the images. With OCT, I can find a pattern in all normal tissues. Then, we can use this pattern to classify abnormal and cancerous tissues for accurate diagnosis."
Google TV integrates Gemini AI for image/video generation, enhances Google Photos, and adds a dedicated YouTube Shorts feed to the homepage.
Read moreAlphabet Q1 paid subscribers reached 350M, fueled by YouTube & Google One. YouTube ad revenue slightly missed at $9.88B amid Premium growth. Total Q1 revenue hit $109.9B, beating forecasts.
Read moreAnthropic releases Claude connectors for Adobe, Blender, and Ableton, enabling AI workflow automation and app control. It also sponsors the Blender Development Foundation.
Read moreApple introduces an App Store model splitting 12-month plans into monthly installments. On iOS 26.4+, it lowers upfront costs without reducing total price, adding billing tracking.
Read moreGoogle launches Aadhaar digital IDs in Wallet for India, enabling secure QR/NFC verification. A phased partner rollout targets key sectors, while passport-based credentials expand globally.
Read moreYouTube tests "Ask YouTube," an AI tool blending text and video for complex queries. Initially for US Premium users, it supports interactive follow-ups, expanding Google's AI search.
Read moreGoogle grants US DoD classified AI access, joining OpenAI and xAI in defense deals amid Anthropic's dispute. Contractual safeguards against surveillance and lethal weapons remain unenforceable.
Read moreMistral AI launches Workflows, a Temporal-powered orchestration platform for secure, Python-driven enterprise AI automation featuring human-in-the-loop approvals.
Read moreCustom subliminal audio maker

AI Social Media Manager

AI Search Visibility

Workout and Calorie Tracker
Stock research platform

AI interview assistant

Scientific figure generator

AI courses with real code