Deep Learning Methods in Medical Image-Based Hepatocellular Carcinoma Diagnosis: A Systematic Review and Meta-Analysis

Cancers, Journal Year: 2023, Volume and Issue: 15(23), P. 5701 - 5701

Published: Dec. 3, 2023

(1) Background: The aim of our research was to systematically review papers specifically focused on the hepatocellular carcinoma (HCC) diagnostic performance DL methods based medical images. (2) Materials: To identify related studies, a comprehensive search conducted in prominent databases, including Embase, IEEE, PubMed, Web Science, and Cochrane Library. limited studies published before 3 July 2023. inclusion criteria consisted that either developed or utilized diagnose HCC using extract data, binary information accuracy collected determine outcomes interest, namely, sensitivity, specificity, area under curve (AUC). (3) Results: Among forty-eight initially identified eligible thirty were included meta-analysis. pooled sensitivity 89% (95% CI: 87–91), specificity 90% 87–92), AUC 0.95 0.93–0.97). Analyses subgroups image (contrast-enhanced non-contrast-enhanced images), imaging modalities (ultrasound, magnetic resonance imaging, computed tomography), comparisons between clinicians consistently showed acceptable models. publication bias high heterogeneity observed can potentially result an overestimation imaging. (4) Conclusions: improve future it would be advantageous establish more rigorous reporting standards address challenges associated with this particular field.

Language: Английский

---

Deep Learning Based Classification of Focal Liver Lesions with 3 and 4 Phase Contrast-Enhanced CT Protocols

مجلة کلية دار العلوم, Journal Year: 2024, Volume and Issue: 49(3)

Published: Jan. 1, 2024

It had been noticed that 3-phase and 4-phase computed tomography protocols with contrast serve as standard examinations for diagnosing liver tumors. Additionally, many patients require periodic follow-up, which entails significant radiation exposure them. Advancements in image processing facilitate automated lesion segmentation. However, the challenge remains classifying these small lesions by doctors, especially when has different types of very little intensity difference. Therefore, deep learning can be utilized classification lesions. The present work introduces a CNN-based module consists four stages: data acquisition, preprocessing, modelling, evaluating. proposed system achieved an accuracy 96% 97% protocols, respectively. Moreover, it shown protocol outperforms protocol, according to dose report, only 1% loss accuracy. this not altered multi-classification process. Thus, three-phase is recommended diagnostic tool detecting focal

Language: Английский

---

Application of a Deep Learning Algorithm for the Diagnosis of HCC

JHEP Reports, Journal Year: 2024, Volume and Issue: 7(1), P. 101219 - 101219

Published: Sept. 16, 2024

Language: Английский

---

Artificial intelligence for detection and characterization of focal hepatic lesions: a review

Abdominal Radiology, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 5, 2024

Language: Английский

---