A deep learning model leveraging SAM improved segmentation speed and matched radiologist performance in classifying ovarian lesions on MRI.
Key Details
- 1Researchers from Johns Hopkins developed an MRI-based, end-to-end DL pipeline incorporating Meta’s Segment Anything Model (SAM) and DenseNet-121.
- 2Integrated model reduced segmentation time by 4 minutes per lesion compared to manual segmentation.
- 3SAM achieved a Dice coefficient of 0.86 to 0.88 for lesion segmentation.
- 4DL model achieved an AUC of 0.85 internally and 0.79 externally, on par with radiologists’ AUC of 0.84 (p > 0.05).
- 5Training data included 534 lesions (internal) and 87 lesions (external) from the US and Taiwan.
Why It Matters
This study demonstrates that foundation AI models can efficiently streamlines lesion segmentation and classification with accuracy rivaling radiologists, suggesting a path toward more automated and collaborative clinical workflows in radiology.
Source
AuntMinnie
Related News
•AuntMinnie
AI for Breast Cancer Screening Not Cost-Effective, Study Finds
AI-assisted breast cancer screening showed minor clinical benefits over DBT alone but was not cost-effective at standard willingness-to-pay thresholds.
•AuntMinnie
AI Device Manufacturers Paid $39.7M for Radiology Between 2017–2023
AI/ML-enabled medical device firms paid $39.7 million for radiology devices from 2017–2023, raising transparency concerns.
•Radiology Business
AI-Generated Reports Cut Radiology Reading Times and Gain Acceptance
AI-generated reporting significantly reduces radiologists' reading times and increases report acceptability over time.