TY - JOUR
T1 - Artificial Intelligence and radiomics models for the diagnosis and prognosis of peritoneal metastases on imaging
T2 - a systematic review and meta-analysis
AU - Fleurkens-Ewals, Lotte J.S.
AU - Tops-Welten, Marion
AU - Claessens, Cris H.B.
AU - Piek, Jurgen M.J.
AU - van Hellemond, Irene E.G.
AU - van der Sommen, Fons
AU - Lahaye, Max J.
AU - de Hingh, Ignace H.J.T.
AU - Luyer, Misha D.P.
AU - Nederend, Joost
N1 - Publisher Copyright:
© 2025 Elsevier Ltd.
PY - 2025/11/1
Y1 - 2025/11/1
N2 - Purpose Peritoneal metastases (PM) significantly impact treatment options and prognosis of patients with cancer. Early detection and accurate evaluation are essential for guiding clinical decisions. This systematic review and meta-analysis aimed to provide a comprehensive overview and evaluate the performance of Artificial Intelligence (AI) and radiomics models for diagnosis and prognosis of PM on imaging. Methods A systematic search of PubMed, Embase, and the Cochrane Library was conducted for studies published up to July 2024 that evaluated AI or radiomics models analyzing imaging data for diagnosing or predicting prognosis in PM. Data were extracted, and if more than 3 studies evaluated the same endpoint and reported true/false positive and negative values, a meta-analysis was conducted to obtain pooled area under the curve (AUC), sensitivity, and specificity. Bias was assessed using the PROBAST + AI tool. Results This review included 24 studies, of which 18 evaluated PM presence, 2 assessed PM severity (low versus high Peritoneal Cancer Index (PCI)), and 4 focused on prognosis or treatment efficacy. Meta-analysis of 13 studies evaluating PM presence revealed a pooled AUC of 0.84, sensitivity of 0.75, and specificity of 0.80. Subgroup analysis indicated comparable performance for 2D and 3D imaging data, and lower performance for models detecting occult PM compared to all PM presentations. Incorporating clinical factors into AI and radiomics models improved performance. Conclusion AI and radiomics models demonstrated promising performance outcomes for PM evaluation on imaging, showing potential to aid in diagnosis and prognosis prediction. However, large validation studies are needed to evaluate their effects in clinical practice.
AB - Purpose Peritoneal metastases (PM) significantly impact treatment options and prognosis of patients with cancer. Early detection and accurate evaluation are essential for guiding clinical decisions. This systematic review and meta-analysis aimed to provide a comprehensive overview and evaluate the performance of Artificial Intelligence (AI) and radiomics models for diagnosis and prognosis of PM on imaging. Methods A systematic search of PubMed, Embase, and the Cochrane Library was conducted for studies published up to July 2024 that evaluated AI or radiomics models analyzing imaging data for diagnosing or predicting prognosis in PM. Data were extracted, and if more than 3 studies evaluated the same endpoint and reported true/false positive and negative values, a meta-analysis was conducted to obtain pooled area under the curve (AUC), sensitivity, and specificity. Bias was assessed using the PROBAST + AI tool. Results This review included 24 studies, of which 18 evaluated PM presence, 2 assessed PM severity (low versus high Peritoneal Cancer Index (PCI)), and 4 focused on prognosis or treatment efficacy. Meta-analysis of 13 studies evaluating PM presence revealed a pooled AUC of 0.84, sensitivity of 0.75, and specificity of 0.80. Subgroup analysis indicated comparable performance for 2D and 3D imaging data, and lower performance for models detecting occult PM compared to all PM presentations. Incorporating clinical factors into AI and radiomics models improved performance. Conclusion AI and radiomics models demonstrated promising performance outcomes for PM evaluation on imaging, showing potential to aid in diagnosis and prognosis prediction. However, large validation studies are needed to evaluate their effects in clinical practice.
KW - Artificial intelligence
KW - Computer-assisted
KW - Diagnosis
KW - Diagnostic imaging
KW - Machine learning
KW - Meta-analysis
U2 - 10.1016/j.compbiomed.2025.111188
DO - 10.1016/j.compbiomed.2025.111188
M3 - (Systematic) Review article
SN - 0010-4825
VL - 198
JO - Computers in Biology and Medicine
JF - Computers in Biology and Medicine
M1 - 111188
ER -