A new study led by researchers at Moffitt Cancer Center shows that asymptomatic brain metastasis is more common in stage 4 breast cancer patients than previously believed. The study, published in Neuro-Oncology, suggests that doctors may need to rethink current screening guidelines for detecting brain metastases in patients without symptoms.
Researchers examined 101 asymptomatic patients diagnosed with stage 4 breast cancer, including triple-negative, HER2-positive, and hormone receptor-positive/HER2-negative breast cancer. These patients underwent MRI scans to check for brain metastasis, with a follow-up MRI six months later, if the initial scan showed no signs of cancer spread.
Of the patients who completed the initial MRI, 14% had brain metastasis. The rates by subtype were:
- 18% in triple-negative breast cancer;
- 15% in HER2-positive breast cancer; and
- 10% in hormone receptor-positive/HER2-negative breast cancer.
After the second MRI, the number of patients with brain metastasis grew to about 25% in each subtype. Following diagnosis, patients went on to receive early treatment for their brain metastases, including changes in systemic therapy and local therapies.
“Our study suggests that asymptomatic brain metastasis is quite common in stage 4 breast cancer,” says Kamran Ahmed, MD, an associate member and section chief for breast radiation oncology at Moffitt and principal investigator of the study. “Although larger studies are needed to confirm our findings, given the improvements in systemic and local therapies for breast cancer brain metastasis, the time may be appropriate to reconsider current guidelines that recommend against routine MRI surveillance in late stage breast cancer.
This study was supported by the Florida Breast Cancer Foundation.
— Moffitt Cancer Center
AI Model Automatically Segments MRI Images
Research scientists in Switzerland have developed and tested a robust AI model that automatically segments major anatomic structures in MRI images, independent of sequence, according to a new study published in Radiology, a journal of the RSNA. In the study, the model outperformed other publicly available tools.
MRI provides detailed images of the human body and is essential for diagnosing various medical conditions, from neurological disorders to musculoskeletal injuries. For in-depth interpretation of MRI images, the organs, muscles, and bones in the images are outlined or marked, which is known as segmenting.
“MRI images have traditionally been manually segmented, which is a time-consuming process that requires intensive effort by radiologists and is subject to interreader variability,” says Jakob Wasserthal, PhD, radiology department research scientist at University Hospital Basel in Basel, Switzerland. “Automated systems can potentially reduce radiologist’s workload, minimize human errors, and provide more consistent and reproducible results.”
Wasserthal and colleagues built an open-source automated segmentation tool called the TotalSegmentator MRI based on nnU-Net, a self-configuring framework that has set new standards in medical image segmentation. It adapts to any new dataset with minimal user intervention, automatically adjusting its architecture, preprocessing, and training strategies to optimize performance. A similar model for CT (TotalSegmentator CT) is being used by over 300,000 users worldwide to process over 100,000 CT images daily.
In the retrospective study, the researchers trained TotalSegmentator MRI to provide sequence-independent segmentations of major anatomic structures using a randomly sampled dataset of 616 MRI and 527 CT exams. The training set included segmentations of 80 anatomic structures typically used for measuring volume, characterizing disease, surgical planning, and opportunistic screening.
“Our innovation was creating a large dataset,” Wasserthal says. “We used a lot more data and segmented many more organs, bones, and muscles than has been previously done. Our model also works across different MRI scanners and image acquisition settings.”
To evaluate the model’s performance, Dice scores—which measure how similar two sets of data are—were calculated between predicted segmentations and radiologist reference standards for segmentations. The model performed well across the 80 structures with a Dice score of 0.839 on an internal MRI test set. It also significantly outperformed two publicly available segmentation models (0.862 vs 0.838 and 0.560) and matched the performance of TotalSegmentator CT.
“To our knowledge, our model is the only one that can automatically segment the highest number of structures on MRIs of any sequence,” Wasserthal says. “It’s a tool that helps improve radiologists’ work, makes measurements more precise, and enables other measurements to be done that would have taken too much time to do manually.”
In addition to research and AI product development, Wasserthal says the model could potentially be used clinically for treatment planning, monitoring disease progression, and opportunistic screening.
— RSNA