MIDRC CRP10 AI interface-an integrated tool for exploring, testing and visualization of AI models.

Objective. Developing Machine Learning models (N Gorre et al 2023) for clinical applications from scratch can be a cumbersome task requiring varying levels of expertise. Seasoned developers and researchers may also often face incompatible frameworks and data preparation issues. This is further complicated in the context of diagnostic radiology and oncology applications, given the heterogenous nature of the input data and the specialized task requirements. Our goal is to provide clinicians, researchers, and early AI developers with a modular, flexible, and user-friendly software tool that can effectively meet their needs to explore, train, and test AI algorithms by allowing users to interpret their model results. This latter step involves the incorporation of interpretability and explainability methods that would allow visualizing performance as well as interpreting predictions across the different neural network layers of a deep learning algorithm.Approach. To demonstrate our proposed tool, we have developed the CRP10 AI Application Interface (CRP10AII) as part of the MIDRC consortium. CRP10AII is based on the web service Django framework in Python. CRP10AII/Django/Python in combination with another data manager tool/platform, data commons such as Gen3 can provide a comprehensive while easy to use machine/deep learning analytics tool. The tool allows to test, visualize, interpret how and why the deep learning model is performing. The major highlight of CRP10AII is its capability of visualization and interpretability of otherwise Blackbox AI algorithms.Results. CRP10AII provides many convenient features for model building and evaluation, including: (1) query and acquire data according to the specific application (e.g. classification, segmentation) from the data common platform (Gen3 here); (2) train the AI models from scratch or use pre-trained models (e.g. VGGNet, AlexNet, BERT) for transfer learning and test the model predictions, performance assessment, receiver operating characteristics curve evaluation; (3) interpret the AI model predictions using methods like SHAPLEY, LIME values; and (4) visualize the model learning through heatmaps and activation maps of individual layers of the neural network.Significance. Unexperienced users may have more time to swiftly pre-process, build/train their AI models on their own use-cases, and further visualize and explore these AI models as part of this pipeline, all in an end-to-end manner. CRP10AII will be provided as an open-source tool, and we expect to continue developing it based on users' feedback.

Development of Low-Cost Point-of-Care Technologies for Cervical Cancer Prevention Based on a Single-Board Computer.

Cervical cancer disproportionally affects women in low- and middle-income countries, in part due to the difficulty of implementing existing cervical cancer screening and diagnostic technologies in low-resource settings. Single-board computers offer a low-cost alternative to provide computational support for automated point-of-care technologies. Here we demonstrate two new devices for cervical cancer prevention that use a single-board computer: 1) a low-cost imaging system for real-time detection of cervical precancer and 2) a low-cost reader for real-time interpretation of lateral flow-based molecular tests to detect cervical cancer biomarkers. Using a Raspberry Pi computer to provide real-time image collection and processing, we developed: 1) a low-cost, portable high-resolution microendoscope system (PiHRME); and 2) a low-cost automatic lateral flow test reader (PiReader). The PiHRME acquired high-resolution ([Formula: see text]) images of the cervix at half the cost of existing high-resolution microendoscope systems; image analysis algorithms based on convolutional neural networks were implemented to provide real-time image interpretation. The PiReader acquired and analyzed images of a point-of-care human papillomavirus (HPV) serology test with the same contrast and accuracy as a standard flatbed high-resolution scanner coupled to a laptop computer, for less than one-fifth of the cost. Raspberry Pi single-board computers provide a low-cost means to implement point-of-care tools with automatic image analysis. This work demonstrates the promise of single-board computers to develop and translate low-cost, point-of-care technologies for use in low-resource settings.