Archive: 24 December 2021

Ultrasound Imaging of Brain with Machine Learning

A proposed machine-learning technique can convert ultrasound signals into a skull profile, which could lead to noninvasive imaging for medical treatments in the human brain.

The current best practice is to create individual skull profiles using CT scans or MRI. The profile provides exact knowledge of how the skull affects ultrasound propagation. Still, requiring an additional scan “defeats the ease of ultrasound,” says Yun Jing from Pennsylvania State University. CT and MRI methods are resource and time-intensive, and CT scans expose the brain to harmful radiation.

The researcher team proposed a new method to extract the skull properties using radio-frequency (rf) ultrasound pulses reflecting off a skull.

Read about the proposal: https://physics.aps.org/articles/v14/182

Should interval chest CT findings affect timing of lung screening?

In lung cancer screening participants, findings on interval diagnostic chest CT can potentially be used to adjust the timing of subsequent lung cancer screening CT follow-up.

Interval diagnostic chest CT could ‘reset the clock’. It could also serve as a potential substitute for annual low-dose CT, especially if it coincides with the next annual screening date.

Read the findings from the study in detail: https://www.auntminnie.com/index.aspx?sec=sup&sub=cto&pag=dis&ItemID=134571

New AI algorithm can quickly detect x-rays that are positive for fractures

A new study has found that artificial intelligence (AI) can help physicians in interpreting x-rays after an injury and suspected fracture.

Fracture interpretation errors represent up to 24 percent of harmful diagnostic errors seen in the emergency department. Furthermore, inconsistencies in radiographic diagnosis of fractures are more common during the evening and overnight hours (5 p.m. to 3 a.m.), likely related to non-expert reading and fatigue.

The AI algorithm (AI BoneView), was trained on a very large number of X-rays from multiple institutions to detect fractures of the limbs, pelvis, torso and lumbar spine and rib cage.

Read more: https://www.news-medical.net/news/20211221/New-AI-algorithm-can-quickly-detect-x-rays-that-are-positive-for-fractures.aspx

 

U.K. releases practical new guidance on spleen imaging

The U.K. Royal College of Radiologists (RCR) has issued guidelines on incidental radiation of the spleen. The 10-page document is free to download from the RCR website.

The guidance applies to all patients who may receive radiotherapy to the spleen. It is a defined organ at risk as a result of being referred for radiotherapy to the upper abdomen or an adjacent anatomical site where the upper abdomen might also be irradiated.

Read more about the guidelines: https://www.auntminnieeurope.com/index.aspx?sec=sup&sub=cto&pag=dis&ItemID=620971

Novel study evaluates ultrasound’s impact on length of hospital stay

Performing focused ultrasound scans on cardiopulmonary patients just admitted to the hospital may not decrease their length of stay compared to standard treatment, according to an Australian research.

Internal medicine physicians usually begin their clinical evaluations based on a patient’s medical history and physical examination findings. However, this alone has shown to be inaccurate in determining the correct diagnosis, the study authors said. This means more investigations are done, such as chest radiographs and blood tests.

Read the full study: https://www.auntminnieeurope.com/index.aspx?sec=sup&sub=ult&pag=dis&ItemID=620978

Researchers achieve 3D imaging through single optical fibre

A team of scientists, led by the University of Glasgow’s Optics Group, has built a 3D imager able to capture video at 5Hz through a single optical fibre.

The prototype system delivers images through a 40cm long optical fibre, each frame containing up to approximately 4,000 independently resolvable features, with a depth resolution of around 5mm.

By using a pulsed laser, the device also measures the time of flight of the light and hence the range of every pixel in the image. These 3D images can be recorded at distances from a few tens of millimetres to several metres away from the fibre end, with millimetric distance resolution and frame rates high enough to perceive motion at close to video quality.

Read more: https://www.imveurope.com/news/researchers-achieve-3d-imaging-through-single-optical-fibre

Ultrasound useful for workup of DBT recalls

Ultrasound should be the first line for diagnostic workup of noncalcified masses recalled from digital breast tomosynthesis (DBT) exams, according to research.

However, for asymmetries, the researchers also found that diagnostic mammography may be best without additional ultrasound, while architectural distortions still warrant mammography and ultrasound.

DBT has seen increased use in the U.S. over the past 10 years following clearance of the first systems. The study authors said this is due to the technology’s increased cancer detection rate and lower recall rate compared with conventional digital mammography.

Read more: https://www.auntminnie.com/index.aspx?sec=ser&sub=def&pag=dis&ItemID=134588

 

Advanced MRI technique significantly improves radiologists’ ability to image the pancreas

Newly developed advanced diffusion-weighted imaging techniques can help radiologists better visualize the pancreas on MRI scans, according to a new research.

Due to its small size, and gastric and respiratory motion, high-quality, artifact-free images of the pancreas can be difficult to achieve on MRI. Current solutions involve giving patients verbal breathing cues, but this time-consuming process doesn’t always work.

Achieving an improved image quality for pancreatic evaluation was the result of combining an approach of optimizing classic image parameters in combination with using advanced post-processing. This study demonstrates the advantages of an advanced sequence for the assessment of the pancreas in clinical patients without pancreatic pathology.

Read more: https://www.healthimaging.com/topics/diagnostic-screening/advanced-dwi-improves-image-quality-pancreas-mri

MRI, hybrid imaging outperform conventional tests for small cell lung cancer staging

FDG PET/CT, whole-body MRI, and coregistered FDG PET/MRI outperformed conventional tests for various staging endpoints in patients with SCLC,” concluded first author Yoshiharu Ohno from the Fujita Health University School of Medicine in Japan. Whole-body MRI and FDG PET/MRI outperformed FDG PET/CT for T category and thus TNM stage, indicating the utility of MRI for assessing extent of local invasion in SCLC. MRI, with or without FDG PET coregistration, can improve the staging of patients with small-cell lung cancer.

These additional observations may relate to a superior role of MRI in assessing the extent of local soft-tissue invasion by tumor, as has been observed in settings other than SCLC.

Read more: https://www.sciencedaily.com/releases/2021/12/211209095634.htm