Dataset Information

A multicenter clinical AI system study for detection and diagnosis of focal liver lesions.

ABSTRACT: Early and accurate diagnosis of focal liver lesions is crucial for effective treatment and prognosis. We developed and validated a fully automated diagnostic system named Liver Artificial Intelligence Diagnosis System (LiAIDS) based on a diverse sample of 12,610 patients from 18 hospitals, both retrospectively and prospectively. In this study, LiAIDS achieved an F1-score of 0.940 for benign and 0.692 for malignant lesions, outperforming junior radiologists (benign: 0.830-0.890, malignant: 0.230-0.360) and being on par with senior radiologists (benign: 0.920-0.950, malignant: 0.550-0.650). Furthermore, with the assistance of LiAIDS, the diagnostic accuracy of all radiologists improved. For benign and malignant lesions, junior radiologists' F1-scores improved to 0.936-0.946 and 0.667-0.680 respectively, while seniors improved to 0.950-0.961 and 0.679-0.753. Additionally, in a triage study of 13,192 consecutive patients, LiAIDS automatically classified 76.46% of patients as low risk with a high NPV of 99.0%. The evidence suggests that LiAIDS can serve as a routine diagnostic tool and enhance the diagnostic capabilities of radiologists for liver lesions.

SUBMITTER: Ying H

PROVIDER: S-EPMC10850133 | biostudies-literature | 2024 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A multicenter clinical AI system study for detection and diagnosis of focal liver lesions.

Ying Hanning H Liu Xiaoqing X Zhang Min M Ren Yiyue Y Zhen Shihui S Wang Xiaojie X Liu Bo B Hu Peng P Duan Lian L Cai Mingzhi M Jiang Ming M Cheng Xiangdong X Gong Xiangyang X Jiang Haitao H Jiang Jianshuai J Zheng Jianjun J Zhu Kelei K Zhou Wei W Lu Baochun B Zhou Hongkun H Shen Yiyu Y Du Jinlin J Ying Mingliang M Hong Qiang Q Mo Jingang J Li Jianfeng J Ye Guanxiong G Zhang Shizheng S Hu Hongjie H Sun Jihong J Liu Hui H Li Yiming Y Xu Xingxin X Bai Huiping H Wang Shuxin S Cheng Xin X Xu Xiaoyin X Jiao Long L Yu Risheng R Lau Wan Yee WY Yu Yizhou Y Cai Xiujun X

Nature communications 20240207 1

Early and accurate diagnosis of focal liver lesions is crucial for effective treatment and prognosis. We developed and validated a fully automated diagnostic system named Liver Artificial Intelligence Diagnosis System (LiAIDS) based on a diverse sample of 12,610 patients from 18 hospitals, both retrospectively and prospectively. In this study, LiAIDS achieved an F1-score of 0.940 for benign and 0.692 for malignant lesions, outperforming junior radiologists (benign: 0.830-0.890, malignant: 0.230- ...[more]

PMID: 38326351

Similar Datasets

Project description:Purpose To assess the performance of computer-aided diagnosis (CAD) systems and to determine the dominant ultrasonographic (US) features when classifying benign versus malignant focal liver lesions (FLLs) by using contrast material-enhanced US cine clips. Materials and Methods One hundred six US data sets in all subjects enrolled by three centers from a multicenter trial that included 54 malignant, 51 benign, and one indeterminate FLL were retrospectively analyzed. The 105 benign or malignant lesions were confirmed at histologic examination, contrast-enhanced computed tomography (CT), dynamic contrast-enhanced magnetic resonance (MR) imaging, and/or 6 or more months of clinical follow-up. Data sets included 3-minute cine clips that were automatically corrected for in-plane motion and automatically filtered out frames acquired off plane. B-mode and contrast-specific features were automatically extracted on a pixel-by-pixel basis and analyzed by using an artificial neural network (ANN) and a support vector machine (SVM). Areas under the receiver operating characteristic curve (AUCs) for CAD were compared with those for one experienced and one inexperienced blinded reader. A third observer graded cine quality to assess its effects on CAD performance. Results CAD, the inexperienced observer, and the experienced observer were able to analyze 95, 100, and 102 cine clips, respectively. The AUCs for the SVM, ANN, and experienced and inexperienced observers were 0.883 (95% confidence interval [CI]: 0.793, 0.940), 0.829 (95% CI: 0.724, 0.901), 0.843 (95% CI: 0.756, 0.903), and 0.702 (95% CI: 0.586, 0.782), respectively; only the difference between SVM and the inexperienced observer was statistically significant. Accuracy improved from 71.3% (67 of 94; 95% CI: 60.6%, 79.8%) to 87.7% (57 of 65; 95% CI: 78.5%, 93.8%) and from 80.9% (76 of 94; 95% CI: 72.3%, 88.3%) to 90.3% (65 of 72; 95% CI: 80.6%, 95.8%) when CAD was in agreement with the inexperienced reader and when it was in agreement with the experienced reader, respectively. B-mode heterogeneity and contrast material washout were the most discriminating features selected by CAD for all iterations. CAD selected time-based time-intensity curve (TIC) features 99.0% (207 of 209) of the time to classify FLLs, versus 1.0% (two of 209) of the time for intensity-based features. None of the 15 video-quality criteria had a statistically significant effect on CAD accuracy-all P values were greater than the Holm-Sidak α-level correction for multiple comparisons. Conclusion CAD systems classified benign and malignant FLLs with an accuracy similar to that of an expert reader. CAD improved the accuracy of both readers. Time-based features of TIC were more discriminating than intensity-based features. © RSNA, 2017 Online supplemental material is available for this article.

Project description:ObjectivesTo compare clinical success, procedure time, and complication rates between MRI-guided and CT-guided real-time biopsies of small focal liver lesions (FLL) < 20 mm.MethodsA comparison of a prospectively collected MRI-guided cohort (n = 30) to a retrospectively collected CT-guided cohort (n = 147) was performed, in which patients underwent real-time biopsies of small FLL < 20 mm in a freehand technique. In both groups, clinical and periprocedural data, including clinical success, procedure time, and complication rates (classified according to CIRSE guidelines), were analyzed. Wilcoxon rank sum test, Pearson's chi-squared test, and Fisher's exact test were used for statistical analysis. Additionally, propensity score matching (PSM) was performed using the following criteria for direct matching: age, gender, presence of liver cirrhosis, liver lobe, lesion diameter, and skin-to-target distance.ResultsThe median FLL diameter in the MRI-guided cohort was significantly smaller compared to CT guidance (p < 0.001; 11.0 mm vs. 16.3 mm), while the skin-to-target distance was significantly longer (p < 0.001; 90.0 mm vs. 74.0 mm). MRI-guided procedures revealed significantly higher clinical success compared to CT guidance (p = 0.021; 97% vs. 79%) as well as lower complication rates (p = 0.047; 0% vs. 13%). Total procedure time was significantly longer in the MRI-guided cohort (p < 0.001; 38 min vs. 28 min). After PSM (n = 24/n = 38), MRI-guided procedures still revealed significantly higher clinical success compared to CT guidance (p = 0.039; 96% vs. 74%).ConclusionDespite the longer procedure time, freehand biopsy of small FLL < 20 mm under MR guidance can be considered superior to CT guidance because of its high clinical success and low complication rates.Clinical relevance statementBiopsy of small liver lesions is challenging due to the size and conspicuity of the lesions on native images. MRI offers higher soft tissue contrast, which translates into a higher success of obtaining enough tissue material with MRI compared to CT-guided biopsies.Key points• Image-guided biopsy of small focal liver lesions (FLL) is challenging due to inadequate visualization, leading to sampling errors and false-negative biopsies. • MRI-guided real-time biopsy of FLL < 20 mm revealed significantly higher clinical success (p = 0.021; 97% vs. 79%) and lower complication rates (p = 0.047; 0% vs. 13%) compared to CT guidance. • Although the procedure time is longer, MRI-guided biopsy can be considered superior for small FLL < 20 mm.

Dataset Information

A multicenter clinical AI system study for detection and diagnosis of focal liver lesions.

Publications

A multicenter clinical AI system study for detection and diagnosis of focal liver lesions.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets