Download Mobile App

New Solution Enhances AI-Based Quality Control and Diagnosis in Medical Imaging

By MedImaging International staff writers
Posted on 24 Sep 2024

Image: Huawei and its partners have launched the Medical Technology Digitalization 2.0 Solution (Photo courtesy of Huawei)

Medical image data makes up 80% of clinical data, and artificial intelligence (AI) offers significant potential to unlock its full value, which is crucial for clinical diagnosis, decision-making, and disease prevention. Now, a new solution integrates AI-assisted diagnosis and intelligent quality control, paving the way for precision healthcare and optimized diagnosis and treatment processes.

Huawei (Shenzhen, China), in collaboration with its partners, has introduced the Medical Technology Digitalization 2.0 Solution, incorporating AI, computing, storage, and networking capabilities. This solution integrates innovative applications to implement AI-based quality control and diagnosis, greatly enhancing healthcare service quality and efficiency. In the field of medical imaging, the solution can automatically identify and score image quality, with AI quality control achieving 98% accuracy, resulting in improved image quality. Moreover, the solution supports intelligent segmentation, detection, and quantitative analysis of image data, enabling automatic AI analysis and aiding diagnosis, which significantly reduces the rate of missed diagnoses.

The solution also reduces diagnosis time by 40%, leading to a considerable boost in diagnosis and treatment efficiency. In ultrasound, digital and intelligent imaging devices powered by the OpenHarmony operating system are employed. Using AI device-edge synergy, the solution delivers AI-powered real-time diagnosis and centralized quality control across regions, with low-latency video transmission. This enables full coverage of ultrasound quality control, rather than relying on spot checks. The end-to-end delay for AI-assisted diagnosis is less than 150 milliseconds, continuously enhancing the quality and efficiency of ultrasound diagnostics across regions.

Related Links:
Huawei

Visit expo >

Floor‑Mounted Digital X‑Ray System

MasteRad MX30+

Computed Tomography System

Aquilion ONE / INSIGHT Edition

Ultrasonic Pocket Doppler

SD1

Pocket Fetal Doppler

CONTEC10C/CL

Latest General/Advanced Imaging News

Channels

Radiography

view channel

Images in a 75-year-old woman who underwent routine screening mammography in 2022. Left mediolateral oblique views shown from prior screening mammograms: (A) 2015, (B) 2018, (C) 2019, and (D) 2021. In (E) 2022, a new mass developed in the left breast at the 6-o’clock position (arrow), with a (F) corresponding irregular mass at US (arrow). Subsequent US-guided core needle biopsy yielded invasive ductal carcinoma, grade 2. The deep learning 5-year risk scores gradually increased from 2.0 (2015) to 2.1 (2018), 3.4 (2019), 3.6 (2021), and 15.3 (2022). CMFN = centimeters from nipple, LT = left, TRANS = transverse (Photo courtesy of Radiological Society of North America)

AI Tool Predicts Five-Year Breast Cancer Risk from Mammograms

Breast cancer risk assessment during routine screening is difficult because many women who develop the disease have no known genetic mutations or family history. Static risk tools provide limited discrimination... Read more

Image: Screening mammograms and artificial intelligence (AI) score changes over time in two individuals with screen-detected cancer. Full-field digital mammograms show craniocaudal (top) and mediolateral (bottom) views of the left and right breast (Photo courtesy of Radiological Society of North America)

AI Mammography Tools Detect Early Breast Cancer Signs Years Before Diagnosis

Breast cancer screening aims to detect tumors before symptoms develop, but subtle mammographic changes can appear years before diagnosis and may be missed during routine reads. Delayed detection can lead... Read more

$Image: Kyushu University researchers use Dynamic Chest Radiography (DCR) to evaluate the severity of Pulmonary Regurgitation (PR), a common complication after treatment of the congenital heart disease Tetralogy of Fallot. The analysis only requires the patient to hold their breath for seven seconds for a sequence of images of their heart to be taken. The images are then analyzed and extracted into a waveform that can show the severity of PR. The new technique\\\'s detection accuracy of severe PR is 93%, with a sensitivity of 93% and a specificity of 94%. (Photo courtesty of Kyushu University/Yuzo Yamasaki)$

Rapid X-Ray Test Quantifies Pulmonary Regurgitation After Tetralogy of Fallot Repair

Tetralogy of Fallot is the most common cyanotic congenital heart defect and can leave patients with pulmonary valve regurgitation, a backward flow of blood into the right ventricle after repair.... Read more

Image credit: Shu-Han Chen / St. Paul’s Hospital / National Taiwan University

AI Tool Flags Osteoporosis Risk from Routine Chest X-Rays

Osteoporosis is a progressive loss of bone density that is often silent until a fracture occurs. Current screening frameworks concentrate on older women and select high-risk groups. Many men, younger adults,... Read more

MRI

view channel

Image: Video and scientific image caption: Demonstration of ELITE results in two patients — a technology that provides high temporal and spatial resolution, reduces noise, and enhances the visualization of breast tumor (marked in yellow) and blood vessels morphology (Photo courtesy of Dr. Eddy Solomon/Technion - Israel Institute of Technology)

AI Reconstruction Tool Speeds Dynamic Breast MRI and Improves Cancer Detection

Breast cancer affects about 2.3 million people each year, creating sustained demand for precise imaging. Dynamic magnetic resonance imaging (MRI) is highly sensitive, yet slow acquisitions hinder real-time... Read more

International Study Assesses AI for Prostate Cancer MRI Interpretation

Prostate cancer is a leading cause of cancer morbidity in men, and accurate early diagnosis hinges on expert interpretation of prostate magnetic resonance imaging (MRI). Rapid adoption of MRI-first pathways... Read more

$Image: By training the AI with simulations, researchers can reconstruct brain images with high precision using only one-tenth of the data typically required in magnetic resonance imaging. The image shows a metric known as “fractional anisotropy”—an index of myelination—obtained using conventional methods and with the new approach (Photo courtesy of Instituto de Neurociencias UMH CSIC)$