Head computed tomography (CT) imaging is a widely-used imaging modality with multitudes of medical indications, particularly in assessing pathology of the brain, skull, and cerebrovascular system. It is commonly the first-line imaging in neurologic emergencies given its rapidity of image acquisition, safety, cost, and ubiquity. Deep learning models may facilitate detection of a wide range of diseases. However, the scarcity of high-quality labels and annotations, particularly among less common conditions, significantly hinders the development of powerful models. To address this challenge, we introduce FM-CT: a Foundation Model for Head CT for generalizable disease detection, trained using self-supervised learning. Our approach pre-trains a deep learning model on a large, diverse dataset of 361,663 non-contrast 3D head CT scans without the need for manual annotations, enabling the model to learn robust, generalizable features. To investigate the potential of self-supervised learning in head CT, we employed both discrimination with self-distillation and masked image modeling, and we construct our model in 3D rather than at the slice level (2D) to exploit the structure of head CT scans more comprehensively and efficiently. The model's downstream classification performance is evaluated using internal and three external datasets, encompassing both in-distribution (ID) and out-of-distribution (OOD) data. Our results demonstrate that the self-supervised foundation model significantly improves performance on downstream diagnostic tasks compared to models trained from scratch and previous 3D CT foundation models on scarce annotated datasets. This work highlights the effectiveness of self-supervised learning in medical imaging and sets a new benchmark for head CT image analysis in 3D, enabling broader use of artificial intelligence for head CT-based diagnosis.

Since its invention in the 1970s, magnetic resonance imaging (MRI) has opened up a window onto the world beneath our skin. By exploiting the way the nuclei of hydrogen atoms in water and fat molecules resonate in a strong magnetic field, MRI can generate high-contrast three-dimensional images of soft body tissues, joints, and bones. MRI allows clinicians to see evidence of injury and disease within the body, ranging from torn muscle to damaged cartilage, ligaments, and tendons, as well as tumors or other disease lesions within major organs, and blood-flow blockages in the brain, all without the ionizing radiation of the X-rays used in computed tomography (CT) scans. There is, however, a considerable usability problem with the MRI scanner as we currently know it: the technology takes far too long to acquire images, forcing patients to lie still in the confined maw of a massive magnet for up to an hour. With the observable world reduced to a halo of grayish plastic just inches from one's nose, it is a particularly tough experience for those suffering from claustrophobia.

An AI neural network can accurately predict the prognosis of melanoma patients based on pre-treatment histology imaging data, shows research led by the NYU Grossman School of Medicine. Immune checkpoint inhibitors have revolutionized melanoma treatment, but only some tumors respond well to them and they can be quite toxic to patients. Having a more reliable way to predict who is most likely to respond to these therapies is therefore crucial. "An unmet need is the ability to accurately predict which tumors will respond to which therapy," says Iman Osman, M.D., a medical oncologist based at New York University (NYU) Grossman School of Medicine and NYU Langone's Perlmutter Cancer Center, who co-led the work. "This would enable personalized treatment strategies that maximize the potential for clinical benefit and minimize exposure to unnecessary toxicity." In collaboration with Aristotelis Tsirigos, Ph.D., professor in the Institute for Computational Medicine at NYU Grossman School of Medicine and member of NYU Langone's Perlmutter Cancer Center, Osman and team first trained an artificial neural network using pre-treatment histology images from 121 patients with metastatic melanoma.

Experts trained a computer to tell which patients with skin cancer may benefit from drugs that keep tumors from shutting down the immune system's attack on them, a new study finds. Led by researchers from NYU Grossman School of Medicine and Perlmutter Cancer Center, the study showed that an artificial intelligence (AI) tool can predict which patients with a specific type of skin cancer would respond well to such immunotherapies in four out of five cases. Specifically, the study examined patients with metastatic melanoma, skin cancer that has the capacity to spread to other organs and kills 6,800 Americans each year. The results are important, say the study investigators, because while the drug class studied, immune checkpoint inhibitors, has been more effective for many patients than traditional chemotherapies, half of patients do not respond to them. Adding to the urgency of efforts to determine which patients will respond, researchers say the drugs may cause side effects in many of them and are also expensive.

Using data from China and New York, the new mobile app, which has been developed by researchers NYU College of Dentistry, works to help clinicians identify which COVID-19 patients are most at risk of suffering a high severity of the disease. The Artificial Intelligence (AI) is used to help the clinicians assess the risk factors and identify biomarkers from blood tests. The findings have been published Royal Society of Chemistry journal Lab on a Chip. This new mobile app could be a vital tool in the fight against COVID-19 as current tests only test whether someone does or does not have the virus, not how sick they may become. Lead researcher John McDevitt, professor of biomaterials at NYU College of Dentistry, said: "Identifying and monitoring those at risk for severe cases could help hospitals prioritise care and allocate resources like ICU beds and ventilators. Likewise, knowing who is at low risk for complications could help reduce hospital admissions while these patients are safely managed at home. "We want doctors to have both the information they need, and the infrastructure required to save lives.

A novel method of combining advanced optical imaging with an artificial intelligence algorithm produces accurate, real-time intraoperative diagnosis of brain tumors, a new study finds. Published in Nature Medicine on January 6, the study examined the diagnostic accuracy of brain tumor image classification through machine learning, compared with the accuracy of pathologist interpretation of conventional histologic images. The results for both methods were comparable: the AI-based diagnosis was 94.6% accurate, compared with 93.9% for the pathologist-based interpretation. The imaging technique, stimulated Raman histology (SRH), reveals tumor infiltration in human tissue by collecting scattered laser light, illuminating essential features not typically seen in standard histologic images. The microscopic images are then processed and analyzed with artificial intelligence, and in under two and a half minutes, surgeons are able to see a predicted brain tumor diagnosis.

Published in Nature Medicine on January 6, the study examined the diagnostic accuracy of brain tumor image classification through machine learning, compared with the accuracy of pathologist interpretation of conventional histologic images. The results for both methods were comparable: the AI-based diagnosis was 94.6% accurate, compared with 93.9% for the pathologist-based interpretation. The imaging technique, stimulated Raman histology (SRH), reveals tumor infiltration in human tissue by collecting scattered laser light, illuminating essential features not typically seen in standard histologic images. The microscopic images are then processed and analyzed with artificial intelligence, and in under two and a half minutes, surgeons are able to see a predicted brain tumor diagnosis. Using the same technology, after the resection, they are able to accurately detect and remove otherwise undetectable tumor.

Eventually, many conversations about artificial intelligence (AI) include HAL. An acronym for Heuristically programmed ALgorithmic computer, HAL played a prominent and disconcerting role in Stanley Kubrick's mind-bending 1968 film 2001: A Space Odyssey. In the film, sentient computer HAL learns that the humans suspect it of being in error and will disconnect it should that error be confirmed. Of course, HAL is having none of that, and terror ensues. So influential was Kubrick's adaptation of an Arthur C. Clarke short story that HAL is now a part of the ways in which AI is often conceived.