Effects of different preprocessing algorithms on the prognostic value of breast tumour microscopic images

Bridging Histopathology and Radiomics Toward Prognosis of Metastasis in Early Breast Cancer

Tumor histomorphology is crucial for the prognostication of breast cancer outcomes because it contains histological, cellular, and molecular tumor heterogeneity related to metastatic potential. To enhance breast cancer prognosis, we aimed to apply radiomics analysis-traditionally used in 3D scans-to 2D histopathology slides. This study tested radiomics analysis in a cohort of 92 breast tumor specimens for outcome prognosis, addressing -omics dimensionality by comparing models with moderate and high feature counts, using least absolute shrinkage and selection operator for feature selection and machine learning for prognostic modeling. In the test folds, models with radiomics features [area under the curves (AUCs) range 0.799-0.823] significantly outperformed the benchmark model, which only included clinicopathological (CP) parameters (AUC = 0.584). The moderate-dimensionality model with 11 CP + 93 radiomics features matched the performance of the highly dimensional models with 1,208 radiomics or 11 CP + 1,208 radiomics features, showing average AUCs of 0.823, 0.799, and 0.807 and accuracies of 79.8, 79.3, and 76.6%, respectively. In conclusion, our application of deep texture radiomics analysis to 2D histopathology showed strong prognostic performance with a moderate-dimensionality model, surpassing a benchmark based on standard CP parameters, indicating that this deep texture histomics approach could potentially become a valuable prognostic tool.

Preparing Data for Artificial Intelligence in Pathology with Clinical-Grade Performance

The pathology is decisive for disease diagnosis but relies heavily on experienced pathologists. In recent years, there has been growing interest in the use of artificial intelligence in pathology (AIP) to enhance diagnostic accuracy and efficiency. However, the impressive performance of deep learning-based AIP in laboratory settings often proves challenging to replicate in clinical practice. As the data preparation is important for AIP, the paper has reviewed AIP-related studies in the PubMed database published from January 2017 to February 2022, and 118 studies were included. An in-depth analysis of data preparation methods is conducted, encompassing the acquisition of pathological tissue slides, data cleaning, screening, and subsequent digitization. Expert review, image annotation, dataset division for model training and validation are also discussed. Furthermore, we delve into the reasons behind the challenges in reproducing the high performance of AIP in clinical settings and present effective strategies to enhance AIP's clinical performance. The robustness of AIP depends on a randomized collection of representative disease slides, incorporating rigorous quality control and screening, correction of digital discrepancies, reasonable annotation, and sufficient data volume. Digital pathology is fundamental in clinical-grade AIP, and the techniques of data standardization and weakly supervised learning methods based on whole slide image (WSI) are effective ways to overcome obstacles of performance reproduction. The key to performance reproducibility lies in having representative data, an adequate amount of labeling, and ensuring consistency across multiple centers. Digital pathology for clinical diagnosis, data standardization and the technique of WSI-based weakly supervised learning will hopefully build clinical-grade AIP.

Computational approaches for evaluating morphological changes in the corneal stroma associated with decellularization

Decellularized corneas offer a promising and sustainable source of replacement grafts, mimicking native tissue and reducing the risk of immune rejection post-transplantation. Despite great success in achieving acellular scaffolds, little consensus exists regarding the quality of the decellularized extracellular matrix. Metrics used to evaluate extracellular matrix performance are study-specific, subjective, and semi-quantitative. Thus, this work focused on developing a computational method to examine the effectiveness of corneal decellularization. We combined conventional semi-quantitative histological assessments and automated scaffold evaluations based on textual image analyses to assess decellularization efficiency. Our study highlights that it is possible to develop contemporary machine learning (ML) models based on random forests and support vector machine algorithms, which can identify regions of interest in acellularized corneal stromal tissue with relatively high accuracy. These results provide a platform for developing machine learning biosensing systems for evaluating subtle morphological changes in decellularized scaffolds, which are crucial for assessing their functionality.

Gray-Level Co-Occurrence Matrix Analysis of Granule Neurons of the Hippocampal Dentate Gyrus Following Cortical Injury

Traumatic brain injury (TBI) is a main cause of death and disabilities in young adults. Although learning and memory impairments are a major clinical manifestation of TBI, the consequences of TBI on the hippocampus are still not well understood. In particular, how lesions to the sensorimotor cortex damage the hippocampus, to which it is not directly connected, is still elusive. Here, we study the effects of sensorimotor cortex ablation (SCA) on the hippocampal dentate gyrus, by applying a highly sensitive gray-level co-occurrence matrix (GLCM) analysis. Using GLCM analysis of granule neurons, we discovered, in our TBI paradigm, subtle changes in granule cell (GC) morphology, including textual uniformity, contrast, and variance, which is not detected by conventional microscopy. We conclude that sensorimotor cortex trauma leads to specific changes in the hippocampus that advance our understanding of the cellular underpinnings of cognitive impairments in TBI. Moreover, we identified GLCM analysis as a highly sensitive method to detect subtle changes in the GC layers that is expected to significantly improve further studies investigating the impact of TBI on hippocampal neuropathology.