{
  "abstract": "Introduction Recurrence after thermal ablation in early-stage hepatocellular carcinoma (HCC) is high with a lack of clinical predictors. This study used pretreatment multiphase MRI-derived radiomic features to predict recurrence after ablation. Targeted RNA sequencing was used to determine drivers of radiomic signatures.Methods 156 HCC patients undergoing ablation from the SORAMIC ( NCT01126645) and Lausanne (NCT02859753) prospective phase 2 randomised control trials were reviewed. Radiomic features from pretreatment T1-weighted arterial, portal venous and delayed phase lesions were extracted. Radiomic models predicting 12-month recurrence for each phase were trained in the SORAMIC cohort using eight supervised machine learning models, including the state-of-the-art generative foundation model, TabPFN, and thirteen feature selection techniques. The best performing radiomic models were combined and integrated with clinical variables using ensemble learning. Patients were stratified using optimal threshold tuning. Model performance was externally validated in the independent Lausanne cohort. RNA sequencing was performed for radiomic risk-groups.Results The ensemble machine learning-based arterial phase radiomic model outperformed all clinical benchmarks and TabPFN in predicting recurrence in training (AUC 0.90, 95% CI 0.80-0.98) and external validation (AUC 0.74, 95% CI 0.61-0.87) cohorts. Arterial-portal venous and integrated radiomic-clinical models had comparable performance to the standalone arterial phase radiomic model. The arterial phase radiomic model stratified high-risk group had a significantly shorter median time-to-recurrence compared to the low-risk group in training (4.2 months, 95% CI 1.9-9.9 vs. 29.0 months, 95% CI 15.8-34.4; p<0.001) and external validation (4.5 months, 95% CI 1.2-9.4 vs. 12.5 months, 95% CI 9.6-22.9; p=0.007) (figure 1). Radiomic risk group was the only significant predictor of recurrence in multivariable Cox regression. Telomerase reverse transcriptase (TERT) expression was significantly enriched in the high-risk radiomic group.Conclusions Arterial phase radiomic-based models can predict recurrence after curative HCC ablation. Pretreatment MRI can identify patients at high-risk of recurrence for precision surveillance and adjuvant strategies.Abstract O13 Figure 1",
  "authors": [
    {
      "affiliations": [
        "Department of Surgery and Cancer, Imperial College London, London, United Kingdom"
      ],
      "name": "Mathew Vithayathil"
    },
    {
      "affiliations": [
        "Department of Surgery and Cancer, Imperial College London, London, United Kingdom"
      ],
      "name": "Paul Tait"
    },
    {
      "affiliations": [
        "Department of Surgery and Cancer, Imperial College London, London, United Kingdom"
      ],
      "name": "Yuki Agarwala"
    },
    {
      "affiliations": [
        "Department of Surgery and Cancer, Imperial College London, London, United Kingdom",
        "Laboratory of Translational Cancer Genomics, Biomedical Center, Faculty of Medicine, Charles University, Pilsen, Czech Republic"
      ],
      "name": "Venkata Ramana Mallela"
    },
    {
      "affiliations": [
        "Department of Surgery and Cancer, Imperial College London, London, United Kingdom",
        "Applied Genomic Technologies Institute, King Abdulaziz City for Science and Technology (KACST), Riyadh, Saudi Arabia"
      ],
      "name": "Sultan Alharbi"
    },
    {
      "affiliations": [
        "Department of Surgery and Cancer, Imperial College London, London, United Kingdom"
      ],
      "name": "Samir Tariq"
    },
    {
      "affiliations": [
        "Department of Surgery and Cancer, Imperial College London, London, United Kingdom"
      ],
      "name": "Amar Rai"
    },
    {
      "affiliations": [
        "Department of Surgery and Cancer, Imperial College London, London, United Kingdom"
      ],
      "name": "Tim Hoogenboom"
    },
    {
      "affiliations": [
        "Department of Diagnostic and Interventional Radiology, University Hospital of Heidelberg, Heidelberg, Germany"
      ],
      "name": "Oscan Ocal"
    },
    {
      "affiliations": [
        "Department of Radiology, LMU University Hospital, Munich, Germany"
      ],
      "name": "Matthias P Fabritius"
    },
    {
      "affiliations": [
        "Otto-von-Guericke University Magdeburg, Department of Radiology and Nuclear Medicine, Magdeburg, Germany"
      ],
      "name": "Maciej Pech"
    },
    {
      "affiliations": [
        "Universitätsklinikum Leipzig, Klinik und Poliklinik für Gastroenterologie, Sektion Hepatologie, Germany"
      ],
      "name": "Thomas Berg"
    },
    {
      "affiliations": [
        "Medical University of Vienna, Division of Cardiovascular and Interventional Radiology, Department of Bioimaging and Image-Guided Therapy, Wien, Austria"
      ],
      "name": "Christian Loewe"
    },
    {
      "affiliations": [
        "University of Amsterdam, Department of Medical Oncology, Amsterdam University Medical Centers, Amsterdam, Netherlands"
      ],
      "name": "Heinz-Josef Klümpen"
    },
    {
      "affiliations": [
        "Department of Radiology and Interventional Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland"
      ],
      "name": "Rafael Duran"
    },
    {
      "affiliations": [
        "Department of Oncology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland"
      ],
      "name": "Antonia Digklia"
    },
    {
      "affiliations": [
        "Department of Radiology and Interventional Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland"
      ],
      "name": "Alban Denys"
    },
    {
      "affiliations": [
        "Eastman Dental School, University College London, London, United Kingdom"
      ],
      "name": "Rishi Patel"
    },
    {
      "affiliations": [
        "Department of Surgery and Cancer, Imperial College London, London, United Kingdom"
      ],
      "name": "Xingfeng Li"
    },
    {
      "affiliations": [
        "Department of Surgery and Cancer, Imperial College London, London, United Kingdom"
      ],
      "name": "Kristofer Linton-Reid"
    },
    {
      "affiliations": [
        "Department of Surgery and Cancer, Imperial College London, London, United Kingdom"
      ],
      "name": "Mitchell Chen"
    },
    {
      "affiliations": [
        "Department of Computing, Department of Brain Sciences, Imperial College London, London, United Kingdom"
      ],
      "name": "Wenjia Bai"
    },
    {
      "affiliations": [
        "Department of Radiology, LMU University Hospital, Munich, Germany"
      ],
      "name": "Jens Ricke"
    },
    {
      "affiliations": [
        "Department of Radiology and Interventional Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland"
      ],
      "name": "Naik Vietti Violi"
    },
    {
      "affiliations": [
        "Department of Surgery and Cancer, Imperial College London, London, United Kingdom"
      ],
      "name": "Andrea Rockall"
    },
    {
      "affiliations": [
        "Department of Surgery and Cancer, Imperial College London, London, United Kingdom"
      ],
      "name": "Eric O Aboagye"
    },
    {
      "affiliations": [
        "Department of Radiology, LMU University Hospital, Munich, Germany"
      ],
      "name": "Max Seidensticker"
    },
    {
      "affiliations": [
        "Department of Surgery and Cancer, Imperial College London, London, United Kingdom"
      ],
      "name": "Rohini Sharma"
    }
  ],
  "title": "O13 Development and validation of a novel pretreatment MRI-based radiomic model to predict recurrence after thermal ablation of hepatocellular carcinoma",
  "uid": "85e445a5-0a4b-5c5c-90bb-abaf72a3ba97"
}