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.

Development and validation of a multivariable model for prediction of malignant transformation and recurrence of oral epithelial dysplasia.

BACKGROUND: Oral epithelial dysplasia (OED) is the precursor to oral squamous cell carcinoma which is amongst the top ten cancers worldwide. Prognostic significance of conventional histological features in OED is not well established. Many additional histological abnormalities are seen in OED, but are insufficiently investigated, and have not been correlated to clinical outcomes. METHODS: A digital quantitative analysis of epithelial cellularity, nuclear geometry, cytoplasm staining intensity and epithelial architecture/thickness is conducted on 75 OED whole-slide images (252 regions of interest) with feature-specific comparisons between grades and against non-dysplastic/control cases. Multivariable models were developed to evaluate prediction of OED recurrence and malignant transformation. The best performing models were externally validated on unseen cases pooled from four different centres (n = 121), of which 32% progressed to cancer, with an average transformation time of 45 months. RESULTS: Grade-based differences were seen for cytoplasmic eosin, nuclear eccentricity, and circularity in basal epithelial cells of OED (p < 0.05). Nucleus circularity was associated with OED recurrence (p = 0.018) and epithelial perimeter associated with malignant transformation (p = 0.03). The developed model demonstrated superior predictive potential for malignant transformation (AUROC 0.77) and OED recurrence (AUROC 0.74) as compared with conventional WHO grading (AUROC 0.68 and 0.71, respectively). External validation supported the prognostic strength of this model. CONCLUSIONS: This study supports a novel prognostic model which outperforms existing grading systems. Further studies are warranted to evaluate its significance for OED prognostication.

Mitosis detection, fast and slow: Robust and efficient detection of mitotic figures.

Counting of mitotic figures is a fundamental step in grading and prognostication of several cancers. However, manual mitosis counting is tedious and time-consuming. In addition, variation in the appearance of mitotic figures causes a high degree of discordance among pathologists. With advances in deep learning models, several automatic mitosis detection algorithms have been proposed but they are sensitive to domain shift often seen in histology images. We propose a robust and efficient two-stage mitosis detection framework, which comprises mitosis candidate segmentation (Detecting Fast) and candidate refinement (Detecting Slow) stages. The proposed candidate segmentation model, termed EUNet, is fast and accurate due to its architectural design. EUNet can precisely segment candidates at a lower resolution to considerably speed up candidate detection. Candidates are then refined using a deeper classifier network, EfficientNet-B7, in the second stage. We make sure both stages are robust against domain shift by incorporating domain generalization methods. We demonstrate state-of-the-art performance and generalizability of the proposed model on the three largest publicly available mitosis datasets, winning the two mitosis domain generalization challenge contests (MIDOG21 and MIDOG22). Finally, we showcase the utility of the proposed algorithm by processing the TCGA breast cancer cohort (1,124 whole-slide images) to generate and release a repository of more than 620K potential mitotic figures (not exhaustively validated).

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.

Domain generalization across tumor types, laboratories, and species - Insights from the 2022 edition of the Mitosis Domain Generalization Challenge.

Recognition of mitotic figures in histologic tumor specimens is highly relevant to patient outcome assessment. This task is challenging for algorithms and human experts alike, with deterioration of algorithmic performance under shifts in image representations. Considerable covariate shifts occur when assessment is performed on different tumor types, images are acquired using different digitization devices, or specimens are produced in different laboratories. This observation motivated the inception of the 2022 challenge on MItosis Domain Generalization (MIDOG 2022). The challenge provided annotated histologic tumor images from six different domains and evaluated the algorithmic approaches for mitotic figure detection provided by nine challenge participants on ten independent domains. Ground truth for mitotic figure detection was established in two ways: a three-expert majority vote and an independent, immunohistochemistry-assisted set of labels. This work represents an overview of the challenge tasks, the algorithmic strategies employed by the participants, and potential factors contributing to their success. With an F1 score of 0.764 for the top-performing team, we summarize that domain generalization across various tumor domains is possible with today's deep learning-based recognition pipelines. However, we also found that domain characteristics not present in the training set (feline as new species, spindle cell shape as new morphology and a new scanner) led to small but significant decreases in performance. When assessed against the immunohistochemistry-assisted reference standard, all methods resulted in reduced recall scores, with only minor changes in the order of participants in the ranking.

Mitosis domain generalization in histopathology images - The MIDOG challenge.

The density of mitotic figures (MF) within tumor tissue is known to be highly correlated with tumor proliferation and thus is an important marker in tumor grading. Recognition of MF by pathologists is subject to a strong inter-rater bias, limiting its prognostic value. State-of-the-art deep learning methods can support experts but have been observed to strongly deteriorate when applied in a different clinical environment. The variability caused by using different whole slide scanners has been identified as one decisive component in the underlying domain shift. The goal of the MICCAI MIDOG 2021 challenge was the creation of scanner-agnostic MF detection algorithms. The challenge used a training set of 200 cases, split across four scanning systems. As test set, an additional 100 cases split across four scanning systems, including two previously unseen scanners, were provided. In this paper, we evaluate and compare the approaches that were submitted to the challenge and identify methodological factors contributing to better performance. The winning algorithm yielded an F1 score of 0.748 (CI95: 0.704-0.781), exceeding the performance of six experts on the same task.

TIAToolbox as an end-to-end library for advanced tissue image analytics.

Background: Computational pathology has seen rapid growth in recent years, driven by advanced deep-learning algorithms. Due to the sheer size and complexity of multi-gigapixel whole-slide images, to the best of our knowledge, there is no open-source software library providing a generic end-to-end API for pathology image analysis using best practices. Most researchers have designed custom pipelines from the bottom up, restricting the development of advanced algorithms to specialist users. To help overcome this bottleneck, we present TIAToolbox, a Python toolbox designed to make computational pathology accessible to computational, biomedical, and clinical researchers. Methods: By creating modular and configurable components, we enable the implementation of computational pathology algorithms in a way that is easy to use, flexible and extensible. We consider common sub-tasks including reading whole slide image data, patch extraction, stain normalization and augmentation, model inference, and visualization. For each of these steps, we provide a user-friendly application programming interface for commonly used methods and models. Results: We demonstrate the use of the interface to construct a full computational pathology deep-learning pipeline. We show, with the help of examples, how state-of-the-art deep-learning algorithms can be reimplemented in a streamlined manner using our library with minimal effort. Conclusions: We provide a usable and adaptable library with efficient, cutting-edge, and unit-tested tools for data loading, pre-processing, model inference, post-processing, and visualization. This enables a range of users to easily build upon recent deep-learning developments in the computational pathology literature.

Fate and adaptive plasticity of heterogeneous resistant population of Echinochloa colona in response to glyphosate.

Understanding the fate of heterogenous herbicide resistant weed populations in response to management practices can help towards overcoming the resistance issues. We selected one pair of susceptible (S) and resistant (R) phenotypes (2B21-R vs 2B21-S and 2B37-R vs 2B37-S) separately from two glyphosate resistant heterogeneous populations (2B21 and 2B37) of Echinochloa colona and their fate and adaptive plasticity were evaluated after glyphosate application. Our study revealed the glyphosate concentration required to cause a 50% plant mortality (LD50) was 1187, 200, 3064, and 192 g a. e. ha-1 for the four phenotypes 2B21-R, 2B21-S, 2B37-R, and 2B37-S respectively. Both S phenotypes accumulated more biomass than the R phenotypes at the lower application rates (34 and 67.5 g a. e. ha-1) of glyphosate. However, the R phenotypes generally produced more biomass at rates of glyphosate higher than 100 g a. e. ha-1 throughout the growth period. Plants from the R phenotypes of 2B21 and 2B37 generated 32% and 38% fewer spikesplant-1 than their respective S counterparts in the absence of glyphosate respectively. The spike and seed numbersplant-1 significantly higher in R than S phenotypes at increased rates of glyphosate and these relationships were significant. Our research suggests that glyphosate-resistant E. colona plants will be less fit than susceptible plants (from the same population) in the absence of glyphosate. But in the presence of glyphosate, the R plants may eventually dominate in the field. The use of glyphosate is widespread in field, would favour the selection towards resistant individuals.

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.