Pathology Machine-Learning Models and Diagnosis of Nonmelanoma Skin Cancers in Resource-Limited Settings - Takeaway - MDSpire
From the Journals

Pathology Machine-Learning Models and Diagnosis of Nonmelanoma Skin Cancers in Resource-Limited Settings

Artificial intelligence (AI) models, which were pretrained on vast data sets, outperformed a standard baseline model in identifying nonmelanoma skin cancers from digital images of tissue samples, base...

Share

  • 1

    AI models pretrained on extensive data showed enhanced capability in identifying nonmelanoma skin cancers.

  • 2

    Evaluation of contemporary pathology foundation models and development of simplified versions.

  • 3

    Potential to aid cancer diagnosis in resource-limited settings.

  • 4

    Study limitations include generalizability and practical deployment considerations.

  • 5

    Supported by the National Institutes of Health.

  • 6

    References: 2025 AACR Annual Meeting, Cancer Epidemiol Biomarkers Prev.

Original Source(s)

Pathology Machine-Learning Models and Diagnosis of Nonmelanoma Skin Cancers in Resource-Limited Settings

  • by Susan Reckling

  • April 6, 2026

Related Content

UVB and Psoriasis: More Than Immunosuppression

UVB's benefits may run deeper than inflammation suppression—cholesterol metabolism could be a key link.

Skin Fluorescent Imaging Shows High Sensitivity, Specificity for Discriminating Melanoma Lesions

Skin fluorescent imaging demonstrated high sensitivity and specificity for the discrimination of low- and high-risk lesions, showing an alternative, noninvasive approach to melanoma biopsies, accordin...

Tanning Bed Exposure and Melanoma Risks

Research has elucidated how radiation from tanning beds increases the mutation burden across a broad area of melanocytes, thereby significantly raising the risk of developing melanoma. Findings publis...