{
  "abstract": "Background and ObjectiveMicro-ultrasound (MicroUS) is an emerging high-resolution imaging modality for prostate cancer diagnosis and real-time biopsy guidance, but its automated analysis is limited by labor-intensive expert annotation. We aimed to develop and evaluate a foundation model for data-efficient MicroUS image analysis.\n\nMethodsWe developed {micro}FM, a MicroUS-specific foundation model pretrained using DINOv2-style self-supervised learning on 1,736,391 unlabeled images from 780 patients. The model was fine-tuned and evaluated in three downstream cohorts for prostate capsule segmentation (public, 75 patients), urethra segmentation (institutional, 105 patients), and prostate cancer lesion localization (institutional, 190 patients). Under limited annotation, {micro}FM was compared with randomly initialized models and foundation models pretrained on natural, medical, and ultrasound images. Evaluation used the Dice scores and 95th-percentile Hausdorff distance (HD95) for segmentation and free-response receiver operating characteristic analysis for lesion localization.\n\nKey Findings and Limitations{micro}FM improved performance across all three tasks, with the largest gains under limited annotation. With 10% of training scans, {micro}FM achieved Dice scores of 93.8% for prostate capsule segmentation and 58.4% for urethra segmentation, versus 87.9% and 47.0% for the strongest comparators. Corresponding HD95 values were 2.0 and 4.3 mm. For lesion localization, {micro}FM outperformed other models with approximately 0.75 sensitivity at two false-positive detections per 3D volume. Limitations include retrospective single-institution pretraining and lack of explicit 3D modeling.\n\nConclusions and Clinical ImplicationsMicroUS-specific self-supervised pretraining improved data-efficient image analysis across prostate and urethra segmentation, and lesion localization. This approach may reduce annotation requirements for developing automated tools in MicroUS image analysis.\n\nAdvancing PracticeO_ST_ABSWhat does the study add?C_ST_ABSThis study evaluates a deep learning model pretrained on a large-scale dataset of unlabeled prostate MicroUS images. The pretrained model was adapted to three clinically relevant image-analysis tasks: prostate capsule segmentation, urethra segmentation, and prostate cancer lesion localization. Substantial performance gains over other models were observed despite limited training data, suggesting that MicroUS-specific self-supervised pretraining may reduce expert annotation requirements for developing automated image-analysis tools.\n\nPatient SummaryWe developed a foundation model that learns from unlabeled prostate MicroUS images. It performed better with limited labeled data but requires independent validation before clinical use.",
  "abstract_shown": true,
  "affiliations": [
    "UCLA"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 10,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "K. Pang"
    },
    {
      "name": "J. Fan"
    },
    {
      "name": "A. L. Y. Hung"
    },
    {
      "name": "Q. Miao"
    },
    {
      "name": "C. Oh"
    },
    {
      "name": "Q. He"
    },
    {
      "name": "B. Wodlinger"
    },
    {
      "name": "A. Kinnaird"
    },
    {
      "name": "W. Brisbane"
    },
    {
      "name": "K. Sung"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/6d3fccms56bzh.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.29.26364330",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.09.29.26364330v1.full",
  "id": "6d3fccms56bzh",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.09.29.26364330v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "radiology and imaging"
    ],
    [
      "openalex",
      "1707|Medical Image Segmentation Techniques"
    ]
  ],
  "openalex": "W7220448244",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.09.29.26364330v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-29",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/6d3fccms56bzh.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:10Z",
      "native_id": "10.64898/2026.09.29.26364330",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.09.29.26364330v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:radiology and imaging",
      "subfield": "imaging"
    }
  ],
  "title": "Data-Efficient Prostate Micro-Ultrasound Image Analysis using a Modality-specific Foundation Model",
  "title_text": "Data-Efficient Prostate Micro-Ultrasound Image Analysis using a Modality-specific Foundation Model",
  "type": "preprint",
  "updated_at": "2026-10-30T12:20:10Z",
  "url": "https://research.draconitic.com/paper/6d3fccms56bzh",
  "venue": "medRxiv",
  "versions": []
}