mlsanityData to 7 Oct 2026

A Fully Automated and Explainable Algorithm for the Prediction of Malignant Transformation in Oral Epithelial Dysplasia

arXiv 2307.03757 ↗First posted 6 Jul 2023q-bio.QM cs.CV eess.IVcited by 3

Not on the map. Why?

Abstract (arXiv)

Oral epithelial dysplasia (OED) is a premalignant histopathological diagnosis given to lesions of the oral cavity. Its grading suffers from significant inter-/intra- observer variability, and does not reliably predict malignancy progression, potentially leading to suboptimal treatment decisions. To address this, we developed a novel artificial intelligence algorithm that can assign an Oral Malignant Transformation (OMT) risk score, based on histological patterns in the in Haematoxylin and Eosin stained whole slide images, to quantify the risk of OED progression. The algorithm is based on the detection and segmentation of nuclei within (and around) the epithelium using an in-house segmentation model. We then employed a shallow neural network fed with interpretable morphological/spatial features, emulating histological markers. We conducted internal cross-validation on our development cohort (Sheffield; n = 193 cases) followed by independent validation on two external cohorts (Birmingham and Belfast; n = 92 cases). The proposed OMTscore yields an AUROC = 0.74 in predicting whether an OED progresses to malignancy or not. Survival analyses showed the prognostic value of our OMTscore for predicting malignancy transformation, when compared to the manually-assigned WHO and binary grades. Analysis of the correctly predicted cases elucidated the presence of peri-epithelial and epithelium-infiltrating lymphocytes in the most predictive patches of cases that transformed (p < 0.0001). This is the first study to propose a completely automated algorithm for predicting OED transformation based on interpretable nuclear features, whilst being validated on external datasets. The algorithm shows better-than-human-level performance for prediction of OED malignant transformation and offers a promising solution to the challenges of grading OED in routine clinical practice.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 20 of its 53 references that are in the map. First posted on arXiv 6 Jul 2023.

Builds on

20 of 53 references.

References · 20

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  3. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,182
  4. 2018Attention-based Deep Multiple Instance Learningcited by 1,077
  5. 2020Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Imagescited by 738
  6. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 499
  7. 2017Deep Learning for Medical Image Analysiscited by 399
  8. 2018HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Imagescited by 387
  9. 2022Mitosis domain generalization in histopathology images -- The MIDOG challengecited by 66
  10. 2019CGC-Net: Cell Graph Convolutional Network for Grading of Colorectal Cancer Histology Imagescited by 57
  11. 2018Micro-Net: A unified model for segmentation of various objects in microscopy imagescited by 56
  12. 2020NuClick: A Deep Learning Framework for Interactive Segmentation of Microscopy Imagescited by 46
8 more
  1. 2022One Model is All You Need: Multi-Task Learning Enables Simultaneous Histology Image Segmentation and Classificationcited by 38
  2. 2021SlideGraph+: Whole Slide Image Level Graphs to Predict HER2Status in Breast Cancercited by 31
  3. 2018Epithelium segmentation using deep learning in H&E-stained prostate specimens with immunohistochemistry as reference standardcited by 25
  4. 2022An Aggregation of Aggregation Methods in Computational Pathologycited by 20
  5. 2021Stain-Robust Mitotic Figure Detection for the Mitosis Domain Generalization Challengecited by 14
  6. 2016Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensitiescited by 13
  7. 2021Simultaneous Nuclear Instance and Layer Segmentation in Oral Epithelial Dysplasiacited by 8
  8. 2019NuClick: From Clicks in the Nuclei to Nuclear Boundariescited by 5

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1.

3 papers.

  1. 2023Domain Generalization in Computational Pathology: Survey and Guidelinescited by 29
  2. 2023An Automated Pipeline for Tumour-Infiltrating Lymphocyte Scoring in Breast Cancercited by 1
  3. 2024An Attention Based Pipeline for Identifying Pre-Cancer Lesions in Head and Neck Clinical Imagescited by 0