Deep learning-based high-resolution united compressed sensing for gadoxetic acid-enhanced liver magnetic…

AI / informaticsQuantitative imaging in medicine and surgery· Jul 2026

Deep learning-based high-resolution united compressed sensing for gadoxetic acid-enhanced liver magnetic resonance imaging in the detection of colorectal liver metastases.

Dongqiu Shan, Yuedi Ma, Junhui Yuan … Xuejun Chen

Abdominal & Body ImagingAI / informaticsQ2IF 2.5

DR-HR-uCS magnetic resonance imaging raised sensitivity for detecting sub-centimeter colorectal liver metastases

Deep learning-based high-resolution united compressed sensing for gadoxetic acid-enhanced liver magnetic resonance imaging in the detection of colorectal liver metastases.

Dongqiu Shan … Xuejun Chen

Quantitative imaging in medicine and surgery · Jul 2026 · Q2 in Radiology

Background

The hepatobiliary phase (hepatobiliary phase) of gadoxetic acid-enhanced liver magnetic resonance imaging (magnetic resonance imaging) is important for detecting colorectal liver metastasis (colorectal liver metastasis), but image quality may be limited.

Purpose

This study evaluated whether deep learning-based reconstruction united compressed sensing (DR-uCS) and deep learning-based reconstruction high-resolution united compressed sensing (DR-HR-uCS) improve image quality and lesion detection in colorectal liver metastasis.

Methods

This retrospective study included 86 patients with 116 colorectal liver metastasis lesions (71 lesions ≥1 cm and 45 lesions <1 cm) who underwent 3.0-T gadoxetic acid-enhanced liver magnetic resonance imaging.

n = 86 patients

Results

Sensitivity for small liver metastases rose to 87.1%, above older reconstruction methods.

72.4%

uCS

78.6%

DR-uCS

87.1%

DR-HR-uCS

More results

DR-uCS achieved the highest liver signal-to-noise ratio and contrast-to-noise ratio, while the lesion signal-to-noise ratio was comparable across methods (P=0.03 and P=0.001, respectively).

For lesions ≥1 cm, conspicuity and diagnostic performance were similar (all P>0.05).

More results

Diagnostic time for sub-centimeter lesions was significantly shorter with DR-HR-uCS (P<0.001), and differences among readers were reduced.

“

Conclusion · 1 of 2

DR-uCS improves hepatobiliary phase image quality, while DR-HR-uCS further enhances the detection efficiency and conspicuity of sub-centimeter CRLMs.

Conclusion · 2 of 2

Its advantage likely reflects the combined effects of high-resolution acquisition and deep learning-based reconstruction.

Deep learning-based high-resolution united compressed sensing for gadoxetic acid-enhanced liver magnetic resonance imaging in the detection of colorectal liver metastases.

Deep learning-based high-resolution united compressed sensing for gadoxetic acid-enhanced liver magnetic resonance imaging in the detection of colorectal liver metastases.

Related papers