Posted tagged ‘radiology’

Artificial intelligence could help diagnose tuberculosis in remote regions, study finds

May 3, 2017

Image courtesy of Paras Laknani

Tuberculosis is an infectious disease that kills almost two million people worldwide each year, even though the disease can be identified on a simple chest X-ray and treated with antibiotics. One major challenge is that TB-prevalent areas typically lack the radiologists needed to screen and diagnose the disease.

New artificial intelligence models may help. Researchers from the Thomas Jefferson University Hospital in Pennsylvania have developed and tested an artificial intelligence model to accurately identify tuberculosis from chest X-rays, such as the TB-positive scan shown at right.

The model could provide a cost-effective way to expand TB diagnosis and treatment in developing nations, said Paras Lakhani, MD, study co-author and TJUH radiologist, in a recent news release.

Lakhani performed the retrospective study with his colleague Baskaran Sundaram, MD, a TJUH cardiothoracic radiologist. They obtained 1007 chest X-rays of patients with and without active TB from publically available datasets. The data were split into three categories: training (685 patients), validation (172 patients) and test (150 patients).

The training dataset was used to teach two artificial intelligence models — AlexNet and GoogLeNet — to analyze the chest X-ray data and classify the patients as having TB or being healthy. These existing deep learning models had already been pre-trained with everyday nonmedical images on ImageNet. Once the models were trained, the validation dataset was used to select the best-performing model and then the test dataset was used to assess its accuracy.

The researchers got the best performance using an ensemble of AlexNet and GoogLeNet that statistically combined the probability scores for both artificial intelligence models — with a net accuracy of 96 percent.

The authors explain that the workflow of combining artificial intelligence and human diagnosis could work well in TB-prevalent regions, where an automated method could interpret most cases and only the ambiguous cases would be sent to a radiologist.

The researchers plan to further improve their artificial intelligence models with more training cases and other artificial intelligence algorithms, and then they hope to apply it in community

“The relatively high accuracy of the deep learning models is exciting,” Lakhani said in the release. “The applicability for TB is important because it’s a condition for which we have treatment options. It’s a problem that we can solve.”

This is a reposting of my Scope blog story, courtesy of Stanford School of Medicine.

Enlisting artificial intelligence to assist radiologists

June 24, 2016
Photo by Gerd Leonhard

Photo by Gerd Leonhard

Specialized electronic circuits called graphic processing units, or GPUs, are at the heart of modern mobile phones, personal computers and gaming consoles. By combining multiple GPUs in concert, researchers can now solve previously elusive image processing problems. For example, Google and Facebook have both developed extremely accurate facial recognition software using these new techniques.

GPUs are also crucial to radiologists, because they can rapidly process large medical imaging datasets from CT, MRI, ultrasound and even conventional x-rays.

Now some radiology groups and technology companies are combining multiple GPUs with artificial intelligence (AI) algorithms to help improve radiology care. Simply put, an AI computer program can do tasks normally performed by intelligent people. In this case, AI algorithms can be trained to recognize and interpret subtle differences in medical images.

Stanford researchers have used machine learning for many years to look at medical images and computationally extract the features used to predict something about the patient, much as a radiologist would. However, the use of artificial intelligence, or deep learning algorithms, is new. Sandy Napel, PhD, a professor of radiology, explained:

“These deep learning paradigms are a deeply layered set of connections, not unlike the human brain, that are trained by giving them a massive amount of data with known truth. They basically iterate on the strength of the connections until they are able to predict the known truth very accurately.”

“You can give it 10,000 images of colon cancer. It will find the common features across those images automatically,” said Garry Choy, MD, a staff radiologist and assistant chief medical information officer at Massachusetts General Hospital, in a recent Diagnostic Imaging article. “If there are large data sets, it can teach itself what to look for.”

A major challenge is that these AI algorithms may require thousands of annotated radiology images to train them. So Stanford researchers are creating a database containing millions of de-identified radiology studies, including billions of images, totaling about a half million gigabytes. Each study in the database is associated with the de‐identified report that was created by the radiologist when the images were originally used for patient care.

“To enable our deep learning research, we are also applying machine learning methods to our large database of narrative radiology reports,” said Curtis Langlotz, MD, PhD, a Stanford professor of radiology and biomedical informatics. “We use natural language processing methods to extract discrete concepts, such as anatomy and pathology, from the radiology reports. This discrete data can then be used to train AI systems to recognize the abnormalities shown on the images themselves.”

Potential applications include using AI systems to help radiologists more quickly identify intracranial hemorrhages or more effectively detect malignant lung nodules. Deep learning systems are also being developed to perform triage — looking through all incoming cases and prioritizing the most critical ones to the top of the radiologist’s work queue.

However, the potential clinical applications have not been validated yet, according to Langlotz:

“We’re cautious about automated detection of abnormalities like lung nodules and colon polyps. Even with high sensitivity, these systems can distract radiologists with numerous false positives. And radiology images are significantly more complex than photos from the web or even other medical images. Few deep learning results of clinical relevance have been published or peer-reviewed yet.”

Researchers say the goal is to improve patient care and workflow, not replace doctors with intelligent computers.

“Reading about these advances in the news, and seeing demonstrations at meetings, some radiologists have become concerned that their jobs are at risk,” said Langlotz. “I disagree. Instead, radiologists will benefit from even more sophisticated electronic tools that focus on assistance with repetitive tasks, rare conditions, or meticulous exhaustive search — things that most humans aren’t very good at anyway.”

Napel concluded:

“At the end of the day, what matters to physicians is whether or not they can trust the information a diagnostic device, whether it be based in AI or something else, gives them. It doesn’t matter whether the opinion comes from a human or a machine. … Some day we may believe in the accuracy of these deep learning algorithms, when given the right kind of data, to create useful information for patient management. We’re just not there yet.”

This is a reposting of my Scope blog story, courtesy of Stanford School of Medicine.

MRI use flushes gadolinium into San Francisco Bay

February 5, 2016

The levels of gadolinium in the San Francisco Bay have been steadily increasing over the past two decades, according to a study recently published in Environmental Science & Technology. Gadolinium is a rare-earth metal and the potential long-term effects of its exposure have not been studied in detail.

Russell Flegal, PhD, and his research team at UC Santa Cruz collected and analyzed water samples throughout the San Francisco Bay from 1993 to 2013, as part of the San Francisco Bay Regional Monitoring Program.

They found the gadolinium levels to be much higher in the southern end of the Bay, which is home to about 5 million people and densely populated with medical and industrial facilities, than in the central and northern regions. They also observed a sevenfold rise in gadolinium concentration in the South Bay over that time period.

The study attributes the rising level of gadolinium contamination largely to the growing number of magnetic resonance imaging (MRI) scans performed with a gadolinium contrast agent. A gadolinium contrast agent is used for about 30 percent of MRI scans to improve the clarity of the images. It is injected into the patient then excreted out of the body in urine within 24 hours.

Lewis Shin, MD, assistant professor of radiology and a MRI radiologist, explained to me the importance of using intravenous gadolinium contrast agents:

“Gadolinium contrast agents allow us to detect abnormalities that would otherwise be hidden from view and to improve our characterization of the abnormalities that we do find. Gadolinium is not always used; for example, if a physician is just concerned about identifying a herniated disk in the spine, an MRI without contrast agent is sufficient.

However, gadolinium is routinely administered to detect and characterize lesions if there is a clinical concern of cancer. Also, if a patient was previously treated for cancer, gadolinium administration is often extremely helpful to detect early recurrences. In summary, MRI with a gadolinium contrast agent greatly improves our ability to make an accurate diagnosis not only for cancer but for many other disease processes as well.”

According to UCSC researchers, gadolinium is not removed by standard wastewater treatment technologies, so it is discharged by wastewater treatment plants into surface waters that reach the Bay.

Shin expressed some surprise when he learned about this study:

“The majority of radiologists probably don’t even think about gadolinium once it’s excreted out of a patient’s body. Of course it’s concerning that there is a rise in gadolinium levels in the environment, but the next questions are how is this impacting the environment and whether there is a safe level or not? Since most of the gadolinium contrast agents used for MRI studies are excreted through the urine within 12 to 24 hours, one strategy to reduce environmental release of gadolinium could be to collect patients’ urine for a brief period of time for proper disposal or even recycling of the gadolinium itself.”

The UCSC researchers assert that the current levels of gadolinium observed in San Francisco Bay are well below the peak concentrations that could pose harmful effects on the aquatic ecosystem. However, they recommend in their paper, “new public policies and the development of more effective treatment technologies may be necessary to control sources and minimize future contamination.”

This is a reposting of my Scope blog story, courtesy of Stanford School of Medicine.


%d bloggers like this: