AI-based hip prosthesis failure prediction through evolutional radiological indices.

INTRODUCTION: This study aimed to develop artificial intelligence models for predicting hip implant failure from radiological features. Analyzing the evolution of the periprosthetic bone and implant's position throughout the entire follow-up period has shown the potential to be more relevant in outcome prediction than simply considering the latest radiographic images. Thus, we investigated an AI-based model employing a small set of evolutional parameters derived from conventional radiological features to predict hip prosthesis failure. MATERIALS AND METHODS: One hundred sixty-nine radiological features were annotated from historical anteroposterior and lateral radiographs for 162 total hip arthroplasty patients, 32 of which later underwent implant failure. Linear regression on each patient's chronologically sorted radiological features was employed to derive 169 corresponding evolutional parameters per image. Three sets of machine learning predictors were developed: one employing the original features (standard model), one the evolutional ones (evolutional model), and the last their union (hybrid model). Each set included a model employing all the available features (full model) and a model employing the few most predictive ones according to Gini importance (minimal model). RESULTS: The evolutional and hybrid predictors resulted highly effective (area under the ROC curve (AUC) of full models = 0.94), outperforming the standard one, whose AUC was only 0.82. The minimal hybrid model, employing just four features, three of which evolutional, scored an AUC of 0.95, proving even more accurate than the full one, exploiting 173 features. This tool could be shaped to be either highly specific (sensitivity: 80%, specificity: 98.6%) or highly sensitive (sensitivity: 90%, specificity: 92.4%). CONCLUSION: The proposed predictor may represent a highly sensitive screening tool for clinicians, capable to predict THA failure with an advance between a few months and more than a year through only four radiological parameters, considering either their value at the latest visit or their evolution through time.

Lack of imbalance between the master regulators TTF1/NKX2-1 and ΔNp63/p40 implies adverse prognosis in non-small cell lung cancer.

The transcription factors TTF1/NKX2-1 and ΔNp63/p40 are the counterposed molecular markers associated with the main Non-Small Cell Lung Cancer subtypes: TTF1 for adenocarcinoma, p40 for squamous cell carcinoma. Although they generally display a mutually exclusive expression, some exceptions exist simultaneously lacking or (very rarely) expressing both markers, either pattern being associated to poor prognosis. Hence, we quantitatively analyzed the relationship between their coordinated activity and prognosis. By analyzing the respective downstream transcriptional programs of the two genes, we defined a simple quantitative index summarizing the amount of mutual exclusivity between their activities, called Mean Absolute Activity (MAA). Systematic analysis of the MAA index in a dataset of 1018 NSCLC samples replicated on a validation dataset of 275 showed that the loss of imbalance between TTF-1 and p40 corresponds to a steady, progressive reduction in both overall and recurrence-free survival. Coherently, samples correspondent to more balanced activities were enriched for pathways related to increased malignancy and invasiveness. Importantly, multivariate analysis showed that the prognostic significance of the proposed index MAA is independent of other clinical variables including stage, sex, age and smoke exposure. These results hold irrespectively of tumor morphology across NSCLC subtypes, providing a unifying description of different expression patterns.

Coexpression of ΔNp63/p40 and TTF1 Within Most of the Same Individual Cells Identifies Life-Threatening NSCLC Featuring Squamous and Glandular Biphenotypic Differentiation: Clinicopathologic Correlations.

Introduction: Double occurrence of TTF1 and ΔNp63/p40 (henceforth, p40) within the same individual cells is exceedingly rare in lung cancer. Little is known on their biological and clinical implications. Methods: Two index cases immunoreactive for both p40 and TTF1 and nine tumors selected from The Cancer Genome Atlas (TCGA) according to the mRNA levels of the two relevant genes entered the study. Results: The two index cases were peripherally located, poorly differentiated, and behaviorally unfavorable carcinomas, which shared widespread p40 and TTF1 decoration within the same individual tumor cells. They also retained SMARCA2 and SMARCA4 expression, while variably stained for p53, cytokeratin 5, and programmed death-ligand 1. A subset of basal cells p40+/TTF1+ could be found in normal distal airways. Biphenotypic glandular and squamous differentiation was unveiled by electron microscopy, along with EGFR, RAD51B, CCND3, or NF1 mutations and IGF1R, MYC, CCND1, or CDK2 copy number variations on next-generation sequencing analysis. The nine tumors from TCGA (0.88% of 1018 tumors) shared the same poor prognosis, clinical presentation, and challenging histology and had activated pathways of enhanced angiogenesis and epithelial-mesenchymal transition. Mutation and copy number variation profiles did not differ from the other TCGA tumors. Conclusions: Double p40+/TTF1+ lung carcinomas are aggressive and likely underrecognized non-small cell carcinomas, whose origin could reside in double-positive distal airway stem-like basal cells through either de novo-basal-like or differentiating cell mechanisms according to a model of epithelial renewal.

Automated Analysis of Proliferating Cells Spatial Organisation Predicts Prognosis in Lung Neuroendocrine Neoplasms.

Lung neuroendocrine neoplasms (lung NENs) are categorised by morphology, defining a classification sometimes unable to reflect ultimate clinical outcome. Subjectivity and poor reproducibility characterise diagnosis and prognosis assessment of all NENs. Here, we propose a machine learning framework for tumour prognosis assessment based on a quantitative, automated and repeatable evaluation of the spatial distribution of cells immunohistochemically positive for the proliferation marker Ki-67, performed on the entire extent of high-resolution whole slide images. Combining features from the fields of graph theory, fractality analysis, stochastic geometry and information theory, we describe the topology of replicating cells and predict prognosis in a histology-independent way. We demonstrate how our approach outperforms the well-recognised prognostic role of Ki-67 Labelling Index on a multi-centre dataset comprising the most controversial lung NENs. Moreover, we show that our system identifies arrangement patterns in the cells positive for Ki-67 that appear independently of tumour subtyping. Strikingly, the subset of these features whose presence is also independent of the value of the Labelling Index and the density of Ki-67-positive cells prove to be especially relevant in discerning prognostic classes. These findings disclose a possible path for the future of grading and classification of NENs.