Collaborating Authors

Nuclear Medicine

AI Tool Helps Reduce Re-Take Knee X-rays


Re-takes for knee X-rays are common, leading to unnecessary radiation exposures and over-use of radiology personnel. But, until now, little has been done to help alleviate this situation. That's where investigators from Osaka University in Japan have stepped in. Using a deep convolutional neural network they developed, they can potentially help technologists identify and classify tilt direction errors and guide them to the correct positioning for lateral knee X-rays. The team, led by T. Ishida, from the medical physics and engineering department at Osaka University, published their findings recently in Radiography.

3D images and artificial intelligence are combined to diagnose degrees of Parkinson's


A new tool developed by the University of Cordoba, in collaboration with the Nuclear Medicine Unit at the Hospital Reina Sofía, could allow healthcare personnel to diagnose different degrees of Parkinson's, a disease that, according to World Health Organization (WHO) data, affects 7 million people worldwide. To date, according to AYRNA group researcher Javier Barbero, "most diagnoses only determine whether or not the patient suffers from this disease." The research team has developed a system that makes it possible to specify the phase it is in, distinguishing between four different ones, based on severity. Specifically, this new methodology combines Artificial Intelligence and the use of three-dimensional images of the area of the brain in which the neuronal degeneration is occurring. To do this, the research team has analysed, voxel by voxel (the equivalent of a 3D pixel), more than 500 photographs of the brains of people with symptoms compatible with the disease.

Automatic Scan Range Delimitation in Chest CT Using Deep Learning


To develop and evaluate fully automatic scan range delimitation for chest CT by using deep learning. For this retrospective study, scan ranges were annotated by two expert radiologists in consensus in 1149 (mean age, 65 years 16 [standard deviation]; 595 male patients) chest CT topograms acquired between March 2002 and February 2019 (350 with pleural effusion, 376 with atelectasis, 409 with neither, 14 with both). A conditional generative adversarial neural network was trained on 1000 randomly selected topograms to generate virtual scan range delimitations. On the remaining 149 topograms the software-based scan delimitations, scan lengths, and estimated radiation exposure were compared with those from clinical routine. For statistical analysis an equivalence test (two one-sided t tests) was used, with equivalence limits of 10 mm.

AI has a long way to go before doctors can trust it with your life


Geoffrey Hinton is a legendary computer scientist. When Hinton, Yann LeCun, and Yoshua Bengio were given the 2018 Turing Award, considered the Nobel prize of computing, they were described as the "Godfathers of artificial intelligence" and the "Godfathers of Deep Learning." Naturally, people paid attention when Hinton declared in 2016, "We should stop training radiologists now, it's just completely obvious within five years deep learning is going to do better than radiologists." The US Food and Drug Administration (FDA) approved the first AI algorithm for medical imaging that year and there are now more than 80 approved algorithms in the US and a similar number in Europe. Yet, the number of radiologists working in the US has gone up, not down, increasing by about 7% between 2015 and 2019.

Radiology: Artificial Intelligence


The ability to interpret and build on scientific advances depends on our ability to discover those works. If you can't find the information, you won't be able to learn about it or act on it. That's why we're very excited to announce that Radiology: Artificial Intelligence has been included in two important indexing schemes. First, our articles are now searchable in PubMed. The PubMed database contains more than 32 million citations and abstracts of biomedical literature.

Transpara with Fusion AI helps reduce breast screening workload - RAD Magazine


Developer of AI systems for breast care ScreenPoint Medical BV announced the introduction of Transpara powered by FusionAI, an improved and enhanced version of Transpara 1.6, at the European Congress of Radiology virtual meeting in March. Transpara has been in use in more than 20 countries and ScreenPoint says that the latest clinical studies reveal major benefits for radiologists and patients: "Up to 35 per cent of examinations with interval cancers found on earlier mammograms and, to help reduce workload for increasingly pressured radiologists, up to 70 per cent of examinations can now be confidently labelled as normal. Overall Transpara has been shown to match the performance of specialist breast radiologists in both 2D and 3D studies." Transpara with FusionAI is up to 28 per cent more accurate than previous versions, helping to detect more cancers and earlier, the company added. See the full report on page 26 of the April 2021 issue of RAD Magazine.

Episode 43: How artificial intelligence can expand your range and depth of veterinary care


Upon his retirement from veterinary practice--the last 2 decades of which he spent in specialty care where he helped to establish the model of a referral hospital--Neil Shaw, DVM, DACVIM, started thinking about how treatment protocols in general practices could be improved. His primary concern: how to scale what is done in specialty practices for use in general practices. Preventive care protocols are well established in general practice, Shaw says, but "models for treating common illnesses and injuries in primary care practice really have not been well established." "Not all cases need to be referred," he tells Adam Christman, DVM, MBA, in this episode of the Vet Blast Podcast. And he saw technology as the only way to accomplish that goal.



Our April blog is from Dr. Tracy O'Regan. Tracy is a diagnostic radiographer who works at the Society & College of Radiographers (SCoR) as officer for clinical imaging and research. She sits on the steering committee for UK Research & Innovation (UKRI) Science & Technology Facilities Council (STFC) Cancer Diagnosis Network, she is a member of NHSx AI Imaging Advisory Board, and she provides officer support for a SCoR AI & Emerging Technologies Working Party who are currently consulting on a guidance document with recommendations and priorities for AI for UK professionals. In 2011 Nilsson wrote a book that explored 50 years of the development of Artificial Intelligence (AI) (1). Nilsson described AI winters and a series of false dawns; each progressed the path to our current stage of AI with the promise of machine learning, neural networks and deep learning. Despite that development, in the main, clinical imaging and radiotherapy professionals are still discussing AI as if it is a new fashion or perhaps even the emperor's new clothes.

Why these doctors are embracing AI to make triage decisions


There's been a tremendous amount of development around automation in healthcare, thrusting physicians and medical personnel toward a collision with automation that's long been familiar in industrial settings. Radiologists in particular are being confronted with a massive transformation as AI becomes more capable of interpreting scans. Is this a threat to radiologists? Discussions around the use of artificial intelligence to review CT scans are often framed as robots replacing humans. But instead of running scared of AI, Radiology Partners, the largest physician-owned practice in the US servicing 3,000 hospitals, is running to embrace it.

Quantifying Pulmonary Edema on Chest Radiographs


See article by Horng et al in this issue. William F. Auffermann, MD, PhD, is an associate professor of radiology and imaging sciences at the University of Utah School of Medicine. Dr Auffermann is a cardiothoracic radiologist and is ABPM board certified in clinical informatics. His research interests include imaging informatics, clinical informatics, applications of AI in radiology, medical image perception, and perceptual training. Recent research projects include image annotation for AI using eye tracking, human factors engineering, and developing simulation-based perceptual training methods to facilitate radiology education.