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

Abstract

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.

Blind validation of MSIntuit, an AI-based pre-screening tool for MSI detection from histology slides of colorectal cancer

“…For a subset of 200 patients out of the 600 patients of MPATH-DP200 dataset, 1 to 4 other tumour slides coming from different blocks of the same patient were digitised, resulting in a total of 398 additional slides. We characterise the tumour morphology of these slides (figures 4A, 4C) using a ResNet18 model trained on NCT-CRC-HE-100K dataset [16] from the TIAToolbox library [16,17]. This classifier takes as input a tile of 112 × 112 μm and outputs a probability for each of the following classes : adipose (ADI), debris (DEB), lymphocytes (LYM), mucus (MUC), smooth muscle (MUS), normal colon mucosa (NORM), cancer-associated stroma (STR), colorectal adenocarcinoma epithelium (TUM).…”

Screening of normal endoscopic large bowel biopsies with artificial intelligence: a retrospective study

“…It should be noted, that despite using a GPU with 32GB RAM, our GNN framework incurred a low memory utilisation and therefore different specification GPUs may also be used. The interactive demo was developed using the tile server from TIAToolbox 42 and Bokeh 2.4.3. No changes were made to the AI system or the hardware over the course of the study.…”

Application of 3D, 4D, 5D, and 6D bioprinting in cancer research: what does the future look like?

“…181 Quantitative image analysis (QIA) tools allow for the detailed examination of specific cell types, quantification of histological features, and assessment of biologically relevant regions (e.g., tumoral or peritumoral areas, different immune cell populations). 182,183 These tools can capture data from tissue slides that might be overlooked during manual microscopy. Moreover, QIA enables high-content data generation through multiplexing, allowing for the analysis of co-expression and co-localization of multiple markers within the complex spatial context of tissue regions, including the stroma, tumor parenchyma, and invasive margins.…”