Dissecting AI-based mutation prediction in lung adenocarcinoma: A comprehensive real-world study.

INTRODUCTION: Molecular profiling of lung cancer is essential to identify genetic alterations that predict response to targeted therapy. While deep learning shows promise for predicting oncogenic mutations from whole tissue images, existing studies often face challenges such as limited sample sizes, a focus on earlier stage patients, and insufficient analysis of robustness and generalizability. METHODS: This retrospective study evaluates factors influencing mutation prediction accuracy using the large Heidelberg Lung Adenocarcinoma Cohort (HLCC), a cohort of 2356 late-stage FFPE samples. Validation is performed in the publicly available TCGA-LUAD cohort. RESULTS: Models trained on the larger HLCC cohort generalized well to the TCGA dataset for mutations in EGFR (AUC 0.76), STK11 (AUC 0.71) and TP53 (AUC 0.75), in line with the hypothesis that larger cohort sizes improve model robustness. Variation in performance due to pre-processing and modeling choices, such as mutation variant calling, affected EGFR prediction accuracy by up to 7 %. DISCUSSION: Model explanations suggest that acinar and papillary growth patterns are critical for the detection of EGFR mutations, whereas solid growth patterns and large nuclei are indicative of TP53 mutations. These findings highlight the importance of specific morphological features in mutation detection and the potential of deep learning models to improve mutation prediction accuracy. CONCLUSION: Although deep learning models trained on larger cohorts show improved robustness and generalizability in predicting oncogenic mutations, they cannot replace comprehensive molecular profiling. However, they may support patient pre-selection for clinical trials and deepen the insight in genotype-phenotype relationships.

[Explainable artificial intelligence in pathology]. / Erklärbare Künstliche Intelligenz in der Pathologie.

With the advancements in precision medicine, the demands on pathological diagnostics have increased, requiring standardized, quantitative, and integrated assessments of histomorphological and molecular pathological data. Great hopes are placed in artificial intelligence (AI) methods, which have demonstrated the ability to analyze complex clinical, histological, and molecular data for disease classification, biomarker quantification, and prognosis estimation. This paper provides an overview of the latest developments in pathology AI, discusses the limitations, particularly concerning the black box character of AI, and describes solutions to make decision processes more transparent using methods of so-called explainable AI (XAI).

Toward Explainable Artificial Intelligence for Precision Pathology.

The rapid development of precision medicine in recent years has started to challenge diagnostic pathology with respect to its ability to analyze histological images and increasingly large molecular profiling data in a quantitative, integrative, and standardized way. Artificial intelligence (AI) and, more precisely, deep learning technologies have recently demonstrated the potential to facilitate complex data analysis tasks, including clinical, histological, and molecular data for disease classification; tissue biomarker quantification; and clinical outcome prediction. This review provides a general introduction to AI and describes recent developments with a focus on applications in diagnostic pathology and beyond. We explain limitations including the black-box character of conventional AI and describe solutions to make machine learning decisions more transparent with so-called explainable AI. The purpose of the review is to foster a mutual understanding of both the biomedical and the AI side. To that end, in addition to providing an overview of the relevant foundations in pathology and machine learning, we present worked-through examples for a better practical understanding of what AI can achieve and how it should be done.

TTF-1 status in early-stage lung adenocarcinoma is an independent predictor of relapse and survival superior to tumor grading.

OBJECTIVES: Thyroid transcription factor 1 (TTF-1) is a well-established independent prognostic factor in lung adenocarcinoma (LUAD), irrespective of stage. This study aims to determine if TTF-1's prognostic impact is solely based on histomorphological differentiation (tumor grading) or if it independently relates to a biologically more aggressive phenotype. We analyzed a large bi-centric LUAD cohort to accurately assess TTF-1's prognostic value in relation to tumor grade. PATIENTS AND METHODS: We studied 447 patients with resected LUAD from major German lung cancer centers (Berlin and Cologne), correlating TTF-1 status and grading with clinical, pathologic, and molecular data, alongside patient outcomes. TTF-1's impact was evaluated through univariate and multivariate Cox regression. Causal graph analysis was used to identify and account for potential confounders, improving the statistical estimation of TTF-1's predictive power for clinical outcomes. RESULTS: Univariate analysis revealed TTF-1 positivity associated with significantly longer disease-free survival (DFS) (median log HR -0.83; p = 0.018). Higher tumor grade showed a non-significant association with shorter DFS (median log HR 0.30; p = 0,62 for G1 to G2 and 0.68; p = 0,34 for G2 to G3). In multivariate analysis, TTF-1 positivity resulted in a significantly longer DFS (median log HR -0.65; p = 0.05) independent of all other parameters, including grading. Adjusting for potential confounders as indicated by the causal graph confirmed the superiority of TTF-1 over tumor grading in prognostics power. CONCLUSIONS: TTF-1 status predicts relapse and survival in LUAD independently of tumor grading. The prognostic power of tumor grading is limited to TTF-1-positive patients, and the effect size of TTF-1 surpasses that of tumor grading. We recommend including TTF1 status as a prognostic factor in the diagnostic guidelines of LUAD.

From Clustering to Cluster Explanations via Neural Networks.

A recent trend in machine learning has been to enrich learned models with the ability to explain their own predictions. The emerging field of explainable AI (XAI) has so far mainly focused on supervised learning, in particular, deep neural network classifiers. In many practical problems, however, the label information is not given and the goal is instead to discover the underlying structure of the data, for example, its clusters. While powerful methods exist for extracting the cluster structure in data, they typically do not answer the question why a certain data point has been assigned to a given cluster. We propose a new framework that can, for the first time, explain cluster assignments in terms of input features in an efficient and reliable manner. It is based on the novel insight that clustering models can be rewritten as neural networks-or "neuralized." Cluster predictions of the obtained networks can then be quickly and accurately attributed to the input features. Several showcases demonstrate the ability of our method to assess the quality of learned clusters and to extract novel insights from the analyzed data and representations.