Biology subjects

Aits, S.

Publications and source records attributed to Aits, S..

3 recordsLinked to original sources

bioRxiv2026

Improving Data Quality, Model Transparency and Performance in Lung Histopathology with Explainable AI

Convolutional neural networks (CNNs) have shown strong capabilities for image analysis. However, deploying these models in medical settings is complicated by their limited transparency. Over recent years, many approaches have been developed to overcome the so-called "black box" problem of deep neural networks. Here, we show how such explainable AI (XAI) approaches can be applied to not only improve transparency but also training data quality and model performance, with classification of lung damage in histopathology images as use case. First, we conducted a thorough exploratory data analysis and visually compared the compressed multi-dimensional representations of the histology images from the last CNN layers with labels given by pathologists to reveal flaws in the training data. Second, we used Gradient-based Class Activation Mapping (Grad-CAM) as well as SHapley Additive exPlanations (SHAP) values to identify image regions that significantly contributed to the model decisions. To overcome identified shortcomings, we then finetuned additional top layers of the CNNs and introduced model architectures with attention which improved model performance. In summary, we developed a practical workflow that uses interpretability analyses to examine model perception, assess label consistency, and guide model refinement on the example of lung histopathology scoring, demonstrating how XAI approaches can increase both transparency and model performance. The code for this paper is shared at https://github.com/Aitslab/Histology_XAI.git.

pathology↗

bioRxiv2024

The Cell Death Census 2024

Cell death plays a pivotal role in many physiological processes, such as cell homeostasis, embryonic development, immune defence and in the pathophysiology of numerous diseases, such as cancer, infections and degenerative diseases. However, the lack of a comprehensive and up-to-date resource on cell death regulators poses a signi[fi]cant challenge to researchers in the [fi]eld. Existing databases are often limited in scope, differ in content and are updated irregularly. This de[fi]ciency impedes progress in understanding the intricate molecular mechanisms governing cell death and hampers the development of targeted therapies. To address this, we have performed a census of the existing cell death databases as well as the cell death-associated entries in the UniProt and Gene Ontology databases. To ensure high quality, we have focused on manually curated entries rather than those created from automatic prediction tools. The results have been consolidated into a joint database of the known cell death regulators, including both proteins and non-coding RNAs. The Cell Death Census 2024 results and the associated python code for database parsing, cleaning and merging is publicly available at https://github.com/Aitslab/CellDeathCensus/.

bioinformatics↗

bioRxiv2023

Deep learning for rapid and reproducible histology scoring of lung injury in a porcine model

Acute respiratory distress syndrome (ARDS) is a life-threatening condition with mortality rates between 30-50%. Although in vitro models replicate some aspects of ARDS, small and large animal models remain the primary research tools due to the multifactorial nature of the disease. When using these animal models, histology serves as the gold standard method to confirm lung injury and exclude other diagnoses as high-resolution chest images are often not feasible. Semi-quantitative scoring performed by independent observers is the most common form of histologic analysis in pre-clinical animal models of ARDS. Despite progress in standardizing analysis procedures, objectively comparing histological injuries remains challenging, even for highly-trained pathologists. Standardized scoring simplifies the task and allows better comparisons between research groups and across different injury models, but it is time-consuming, and interobserver variability remains a significant concern. Convolutional neural networks (CNNs), which have emerged as a key tool in image analysis, could automate this process, potentially enabling faster and more reproducible analysis. Here we explored the reproducibility of human standardized scoring for an animal model of ARDS and its suitability for training CNNs for automated scoring at the whole slide level. We found large variations between human scorers, even for pre-clinical experts and board-certified pathologies in evaluating ARDS animal models. We demonstrate that CNNs (VGG16, EfficientNetB4) are suitable for automated scoring and achieve up to 83% F1-score and 78% accuracy. Thus, CNNs for histopathological classification of acute lung injury could help reduce human variability and eliminate a time-consuming manual research task with acceptable performance.

bioinformatics↗