Deep Learning-Accelerated Non-Contrast Abbreviated Liver MRI for Detecting Malignant Focal Hepatic Lesions: Dual-Center Validation.

in Korean journal of radiology by So Hyun Park, Moon Hyung Choi, Bohyun Kim, Hyun-Soo Lee, Sungjin Yoon, Young Joon Lee, Dominik Nickel, Thomas Benkert

TLDR

  • The study compared a DL-accelerated AMRI protocol with standard AMRI for liver imaging, finding comparable sensitivity for detecting malignant focal lesions while significantly enhancing image quality and reducing scan time by approximately 50%.
  • Key Insights: The study demonstrated the feasibility of DL-accelerated AMRI in liver imaging, achieving comparable sensitivity and improved image quality while reducing scan time.

Abstract

To compare a deep learning (DL)-accelerated non-enhanced abbreviated MRI (AMRI) protocol with standard AMRI (AMRI) of the liver in terms of image quality and malignant focal lesion detection. This retrospective study included 155 consecutive patients (110 male; mean age 62.4 ± 11 years) from two sites who underwent standard liver MRI and additional AMRIsequences, specifically DL-accelerated single-shot fast-spin echo (SSFSE) and DL-accelerated diffusion-weighted imaging (DWI). Additional MRI phantom experiments assessed signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and apparent diffusion coefficient (ADC) values. Three reviewers evaluated AMRIand AMRIprotocols for image quality using a five-point Likert scale and identified malignant hepatic lesions. Image quality scores and per-lesion sensitivities were compared between AMRIand AMRIusing the Wilcoxon signed-rank test and logistic regression with generalized estimating equations, respectively. Phantom experiments demonstrated comparable SNR and higher CNR for SSFSEcompared to SSFSE, with similar ADC values for DWIand DWI. Among the 155 patients, 130 (83.9%) had chronic liver disease or a history of intra- or extrahepatic malignancy. Of 104 malignant focal lesions in 64 patients, 58 (55.8%) were hepatocellular carcinomas (HCCs), 38 (36.5%) were metastases, four (3.8%) were cholangiocarcinomas, and four (3.8%) were lymphomas. The pooled per-lesion sensitivity across three readers was 97.6% for AMRI, comparable to 97.6% for AMRI. Compared with AMRI, AMRIdemonstrated superior image quality regarding structural sharpness, artifacts, and noise (all< 0.001) and reduced the average scan time by approximately 50% (2 min 29 sec vs. 4 min 11 sec). In patients with chronic liver disease, AMRIachieved a 96.6% per-lesion sensitivity for HCC detection, similar to 96.5% for AMRI(> 0.05). The AMRIprotocol offers comparable sensitivity for detecting malignant focal lesions, including HCC while significantly enhancing image quality and reducing scan time by approximately 50% compared to AMRI.

Overview

  • The study compared a deep learning (DL)-accelerated non-enhanced abbreviated MRI (AMRI) protocol with standard AMRI of the liver in terms of image quality and malignant focal lesion detection.
  • The study included 155 patients who underwent standard liver MRI and additional AMRI sequences, specifically DL-accelerated single-shot fast-spin echo (SSFSE) and DL-accelerated diffusion-weighted imaging (DWI).
  • The primary objective was to compare the image quality and malignant focal lesion detection between the two protocols.

Comparative Analysis & Findings

  • Phantom experiments demonstrated comparable signal-to-noise ratio (SNR) and higher contrast-to-noise ratio (CNR) for SSFSE compared to SSFSE, with similar apparent diffusion coefficient (ADC) values for DWI and DWI.
  • The pooled per-lesion sensitivity across three readers was 97.6% for AMRI, comparable to 97.6% for AMRI.
  • AMRI achieved a 96.6% per-lesion sensitivity for HCC detection, similar to 96.5% for AMRI ( > 0.05).

Implications and Future Directions

  • The AMRI protocol offers comparable sensitivity for detecting malignant focal lesions, including HCC, while significantly enhancing image quality and reducing scan time by approximately 50% compared to AMRI.
  • Future studies can explore the use of DL-accelerated AMRI in other organs and pathologies to assess its feasibility and effectiveness.
  • The study's results highlight the potential of DL-accelerated AMRI to improve patient care by reducing scan time and maximizing image quality.
Read Full Article