Oncology Imaging

Medical imaging has become integral to cancer care, assessing the stage and location of cancerous tumors. By utilizing powerful imaging modalities including CT, MRI, MRA and PET/CT, oncology imaging radiologists are able to assist referring physicians in the detection and diagnosis of cancer.

Two examples of PSMA-PET scans showing numerous prostate cancer metastases spread throughout the body. Many of these smaller tumors would not have been dected on previous standard-of-care imaging. Photo on left courtesy of SNMMI, right University of Chicago. #PSMAPET

PSMA-PET is rapidly changing the standard of care for prostate cancer patients

Adoption of PSMA-PET has been swift because it can significantly improve prostate cancer detection and treatment. SNMMI President Munir Ghesani, MD, explains how.

breast cancer mammography mammogram

MR-directed enhanced mammography detects more malignancies than MR-directed ultrasound

MRI-directed contrast enhanced mammography could serve as a useful stand-alone or complimentary tool for biopsy planning when suspicious lesions are detected. 

Fully automated CT body composition analysis predicts survival for CRC patients

A fully automated body composition analysis derived from CT imaging can be a valuable pretreatment tool for patients with colorectal cancer. 

non-small cell lung cancer tumor segmentation

Algorithm reduces NSCLC tumor segmentation times by 65%

In a close collaboration with radiation oncologists, experts trained their model on the CT lung images of 787 patients and tested it on the scans of more than 1,300 patients from external datasets.

Cancer patients who undergo PCI face a higher risk of early mortality

Overall, PCI patients appear to face a higher risk of in-hospital mortality, 30-day mortality and in-hospital cardiovascular mortality if they present with an active or historical cancer diagnosis. The group's analysis included data from nearly 6.6 million patients.

Thumbnail

Machine learning model uses MRI data to identify candidates for liver transplant

When applied to MRI and clinical features, different machine learning models were recently shown to reliably predict post-treatment recurrences of hepatocellular carcinoma. 

Thumbnail

Deep learning system outperforms rads in brain tumor identification and classification

The new findings findings represent “a step toward improved tumor diagnoses," according to authors of a new study published in JAMA.

Thumbnail

EHR tracking system significantly improves diagnostic timelines for liver cancer patients

Implementing an EHR cancer tracking system to review radiology reports for abnormal findings resulted in patients at one Veterans Affairs Hospital receiving their cancer diagnosis and treatment months earlier than those who were imaged before the system was put into place.