Connie Lehman — Professor, Radiology, Harvard Medical School; Chief of Breast Imaging, radiology, Massachusetts General Hospital; Co-director of AVON Breast Center, Radiology, Massachusetts General Hospital; and Director, Breast Imaging Research Center, Radiology, Massachusetts General Hospital spoke at ApplySci’s recent conference at Harvard Medical School. Click to listen to her talk on using AI to discover breast cancer 5 years […]
Browsing Category: AI
AI/EMG system improves prosthetic hand control
UT Dallas researchers Mohsen Jafarzadeh, Yonas Tadesse, and colleagues are using AI to control prosthetic hands with raw EMG signals. The real-time convolutional neural network, which does not require preprocessing, results in faster and more accurate data classification and faster hand movements. User data re-trains the system to personalize actions. Join ApplySci at the 12th Wearable Tech […]
AI detects CHF through analysis of one heartbeat
Sebastiano Massaro at the University of Surrey, Mihaela Porumb and Leandro Pecchia at the University of Warwick, and Ernesto Iadanza at the University of Florence have developed an advanced signal processing and machine learning method to identify congestive heart failure with 100% accuracy through analysis of one raw ECG heartbeat. The CNN model was trained and […]
AI detects brain aneurysms, predicts rupture risk in surgery
Fujitsu, GE Healthcare, Macquarie University and Macquarie Medical Imaging are using AI to detect and monitor brain aneurysms on scans faster and more efficiently. Fujitsu will use AI to analyze brain images generated by GE’s Revolution C scanner and an algorithm that detect abnormalities and aneurysms. The algorithm will be capable of highlighting an arterial ring […]
AIgorithm detects cancer potential of pancreatic cysts
CompCyst is a proof-of-concept study, led by Anne Marie Lennon at Johns Hopkins, which uses AI to more accurately determine which pancreatic cysts will become cancerous. The test evaluates molecular and clinical markers in cyst fluids, and could significantly improve detection rates vs. current clinical and imaging tests. In the study, the researchers evaluated molecular profiles, […]
Deep learning mammography model detects breast cancer up to five years in advance
MIT CSAIL professor Regina Barzilay and Harvard/MGH professor Constance Lehman have developed a deep learning model that can predict breast cancer, from a mammogram, up to five years in the future. The model learned subtle breast tissue patterns that lead to malignant tumors from mammograms and known outcomes of 90,000 MGH patients. The goal is […]
Study: AI accurately predicts childhood disease from health records
Xia Huimin and Guangzhou Women and Children’s Medical Center researchers used AI to read 1.36 million pediatric health records, and diagnosed disease as accurately as doctors, according to a recent study. Common childhood diseases were detected after processing symptoms, medical history and other clinical data from this massive sample. The goal is the diagnosis of complex […]
Alzheimer’s detected by AI 6 years before diagnosis
In a recent study, Jae Ho Sohn and UCSD colleagues used an AI to analyze glucose-monitoring PET scans to detect early-stage Alzheimer’s disease six years before diagnosis. The algorithm was trained on PET scans from patients who were eventually diagnosed with Alzheimer’s disease, MCI, or no disorder. It was able to identify 92% of patients who […]
AI predicts response to antipsychotic drugs, could distinguish between disorders
Lawson Health Research Institute, Mind Research Network and Brainnetome Center researchers have developed an algorithm that analyzes brain scans to classify illness in patients with complex mood disorders and help predict their response to medication. A recent study analyzed and compared fMRI scans of those with MDD, bipolar I, and no history of mental illness, and […]
AI speeds MRI scans
Facebook and NYU’s fastMRI project, led by Larry Zitnick, uses AI in an attempt to make MRI imaging 10 times faster. Neural networks will be trained to fill in missing or degraded parts of scans, turning them from low resolution into high. The goal is to significantly reduce the time patients must lie motionless inside an […]