{
  "abstract": "Background/Objectives: Deep learning may support the prediction of meningioma response after Gamma Knife radiosurgery (GKRS), but small clinical cohorts increase the risk of overfitting and unstable performance. We developed leakage-controlled code adjusted for small clinical datasets. Methods: Pretreatment contrast-enhanced T1 MRI from 190 patients was analysed using one tumour-centred axial slice per patient. Response was defined as a tumour volume decrease ≥ 30% per log10 (months). ResNet-10t, ResNet-18, ResNet-50 and DenseNet-121 with ImageNet or RadImageNet pretraining were evaluated in three workflows: (1) frozen backbone CNN, head-only training; (2) logistic regression or naive Bayes classification of features extracted from frozen CNNs; and (3) restricted CNN fine-tuning. Five partially overlapping chronological development/test splits were assessed, with all data-dependent fitting, feature selection and model optimisation restricted to development data. Results: The smallest RadImageNet ResNet-10t CNN performed best when fine-tuned (peak AUCs 0.953 and 1.000) but showed the widest split-to-split variation (range 0.738–1.000). When RadImageNet features extracted from ResNet-10t were classified by naive Bayes and logistic regression, they reached lower median and peak AUCs but within narrower ranges. Predictive performance did not consistently depend on CNN size. Conclusions: To our knowledge, this is the first deep learning study predicting volumetric meningioma response after GKRS. We provide openly available, ready-to-use code for three major workflows in small clinical datasets, with safeguards against information leakage. The benefit of fine-tuning and of RadImageNet pretraining depended on architecture. Robust small-cohort modelling requires attention to performance consistency across chronological splits, not only to the highest AUC in a single split.",
  "abstract_shown": true,
  "affiliations": [
    "Centro Gamma Knife Dominicano, Centro de Diagnóstico y Medicina Avanzada y de Conferencias Médicas y Telemedicina, Plaza de la Salud, Santo Domingo 10514, Dominican Republic",
    "Department of Radiology, CEDIMAT, Plaza de la Salud, Santo Domingo 10511, Dominican Republic",
    "Department of Basic and Environmental Science, Instituto Tecnológico de Santo Domingo (INTEC), Santo Domingo 10602, Dominican Republic",
    "Department of Experimental Oncology, Institute for Oncology & Radiology of Serbia, 11000 Belgrade, Serbia"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 14,
  "authors": [
    {
      "affs": [
        0,
        1,
        2
      ],
      "name": "Herwin Speckter",
      "orcid": "0000-0002-9904-2395"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Marko Radulovic",
      "orcid": "0000-0002-2314-7457"
    },
    {
      "affs": [
        0
      ],
      "name": "Ivan Gonzalez",
      "orcid": "0009-0008-6043-6718"
    },
    {
      "affs": [
        0
      ],
      "name": "Giancarlo Hernandez"
    },
    {
      "affs": [
        0
      ],
      "name": "Jose Bido"
    },
    {
      "affs": [
        0
      ],
      "name": "Diones Rivera",
      "orcid": "0000-0001-5935-8005"
    },
    {
      "affs": [
        0
      ],
      "name": "Luis Suazo"
    },
    {
      "affs": [
        0
      ],
      "name": "Santiago Valenzuela"
    },
    {
      "affs": [
        0
      ],
      "name": "Ismael Peralta",
      "orcid": "0000-0002-1162-1318"
    },
    {
      "affs": [
        0
      ],
      "name": "Jeffrey Paulino"
    },
    {
      "affs": [
        0
      ],
      "name": "Teuddis Bernard"
    },
    {
      "affs": [
        0
      ],
      "name": "Issael Ramirez",
      "orcid": "0000-0002-1266-9460"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Peter Stoeter"
    },
    {
      "affs": [
        2
      ],
      "name": "Velicko Vranes",
      "orcid": "0000-0001-8907-7781"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5wzaayzhc4mjp.bib",
  "cited_by": 0,
  "doi": "10.3390/cancers18213590",
  "fulltext_url": null,
  "id": "5wzaayzhc4mjp",
  "issns": [
    "2072-6694"
  ],
  "landing_url": "https://www.mdpi.com/2072-6694/18/21/3590",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [],
  "openalex": null,
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-09",
  "publisher": "MDPI AG",
  "ris": "https://research.draconitic.com/paper/5wzaayzhc4mjp.ris",
  "sources": [
    {
      "first_seen": "2026-11-10T00:21:40Z",
      "native_id": "10.3390/cancers18213590",
      "source": "crossref",
      "url": "https://www.mdpi.com/2072-6694/18/21/3590"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "issn:2072-6694",
      "subfield": "oncology"
    }
  ],
  "title": "Realistic Performance Estimation in Small-Cohort Deep Learning and Machine Learning: A Leakage-Controlled Codebase Applied to Meningioma Response Prediction After Gamma Knife Radiosurgery",
  "title_text": "Realistic Performance Estimation in Small-Cohort Deep Learning and Machine Learning: A Leakage-Controlled Codebase Applied to Meningioma Response Prediction After Gamma Knife Radiosurgery",
  "type": "peer-reviewed",
  "updated_at": "2026-11-10T00:21:40Z",
  "url": "https://research.draconitic.com/paper/5wzaayzhc4mjp",
  "venue": "Cancers",
  "versions": []
}