A fully automated and explainable algorithm for predicting malignant transformation in oral epithelial dysplasia.

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 an artificial intelligence (AI) algorithm, that assigns an Oral Malignant Transformation (OMT) risk score based on the Haematoxylin and Eosin (H&E) stained whole slide images (WSIs). Our AI pipeline leverages an in-house segmentation model to detect and segment both nuclei and epithelium. Subsequently, a shallow neural network utilises interpretable morphological and spatial features, emulating histological markers, to predict progression. We conducted internal cross-validation on our development cohort (Sheffield; n = 193 cases) and independent validation on two external cohorts (Birmingham and Belfast; n = 89 cases). On external validation, the proposed OMTscore achieved an AUROC = 0.75 (Recall = 0.92) in predicting OED progression, outperforming other grading systems (Binary: AUROC = 0.72, Recall = 0.85). Survival analyses showed the prognostic value of our OMTscore (C-index = 0.60, p = 0.02), compared to WHO (C-index = 0.64, p = 0.003) and binary grades (C-index = 0.65, p < 0.001). Nuclear analyses elucidated the presence of peri-epithelial and intra-epithelial lymphocytes in highly predictive patches of transforming cases (p < 0.001). This is the first study to propose a completely automated, explainable, and externally validated algorithm for predicting OED transformation. Our algorithm shows comparable-to-human-level performance, offering a promising solution to the challenges of grading OED in routine clinical practice.

A digital score of peri-epithelial lymphocytic activity predicts malignant transformation in oral epithelial dysplasia.

Oral squamous cell carcinoma (OSCC) is amongst the most common cancers, with more than 377,000 new cases worldwide each year. OSCC prognosis remains poor, related to cancer presentation at a late stage, indicating the need for early detection to improve patient prognosis. OSCC is often preceded by a premalignant state known as oral epithelial dysplasia (OED), which is diagnosed and graded using subjective histological criteria leading to variability and prognostic unreliability. In this work, we propose a deep learning approach for the development of prognostic models for malignant transformation and their association with clinical outcomes in histology whole slide images (WSIs) of OED tissue sections. We train a weakly supervised method on OED cases (n = 137) with malignant transformation (n = 50) and mean malignant transformation time of 6.51 years (±5.35 SD). Stratified five-fold cross-validation achieved an average area under the receiver-operator characteristic curve (AUROC) of 0.78 for predicting malignant transformation in OED. Hotspot analysis revealed various features of nuclei in the epithelium and peri-epithelial tissue to be significant prognostic factors for malignant transformation, including the count of peri-epithelial lymphocytes (PELs) (p < 0.05), epithelial layer nuclei count (NC) (p < 0.05), and basal layer NC (p < 0.05). Progression-free survival (PFS) using the epithelial layer NC (p < 0.05, C-index = 0.73), basal layer NC (p < 0.05, C-index = 0.70), and PELs count (p < 0.05, C-index = 0.73) all showed association of these features with a high risk of malignant transformation in our univariate analysis. Our work shows the application of deep learning for the prognostication and prediction of PFS of OED for the first time and offers potential to aid patient management. Further evaluation and testing on multi-centre data is required for validation and translation to clinical practice. © 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Lesion Induced Error on Automated Measures of Brain Volume: Data From a Pediatric Traumatic Brain Injury Cohort.

Structural segmentation of T1-weighted (T1w) MRI has shown morphometric differences, both compared to controls and longitudinally, following a traumatic brain injury (TBI). While many patients with TBI present with abnormalities on structural MRI images, most neuroimaging software packages have not been systematically evaluated for accuracy in the presence of these pathology-related MRI abnormalities. The current study aimed to assess whether acute MRI lesions (MRI acquired 7-71 days post-injury) cause error in the estimates of brain volume produced by the semi-automated segmentation tool, Freesurfer. More specifically, to investigate whether this error was global, the presence of lesion-induced error in the contralesional hemisphere, where no abnormal signal was present, was measured. A dataset of 176 simulated lesion cases was generated using actual lesions from 16 pediatric TBI (pTBI) cases recruited from the emergency department and 11 typically-developing controls. Simulated lesion cases were compared to the "ground truth" of the non-lesion control-case T1w images. Using linear mixed-effects models, results showed that hemispheric measures of cortex volume were significantly lower in the contralesional-hemisphere compared to the ground truth. Interestingly, however, cortex volume (and cerebral white matter volume) were not significantly different in the lesioned hemisphere. However, percent volume difference (PVD) between the simulated lesion and ground truth showed that the magnitude of difference of cortex volume in the contralesional-hemisphere (mean PVD = 0.37%) was significantly smaller than that in the lesioned hemisphere (mean PVD = 0.47%), suggesting a small, but systematic lesion-induced error. Lesion characteristics that could explain variance in the PVD for each hemisphere were investigated. Taken together, these results suggest that the lesion-induced error caused by simulated lesions was not focal, but globally distributed. Previous post-processing approaches to adjust for lesions in structural analyses address the focal region where the lesion was located however, our results suggest that focal correction approaches are insufficient for the global error in morphometric measures of the injured brain.