Background Artificial intelligence (AI)-based mobile phone apps (mHealth) have the potential to streamline care for suspicious skin lesions in primary care. This study aims to investigate the... Show moreBackground Artificial intelligence (AI)-based mobile phone apps (mHealth) have the potential to streamline care for suspicious skin lesions in primary care. This study aims to investigate the conditions and feasibility of a study that incorporates an AI-based app in primary care and evaluates its potential impact. Methods We conducted a pilot feasibility study from November 22nd, 2021 to June 9th, 2022 with a mixed-methods design on implementation of an AI-based mHealth app for skin cancer detection in three primary care practices in the Netherlands (Rotterdam, Leiden and Katwijk). The primary outcome was the inclusion and successful participation rate of patients and general practitioners (GPs). Secondary outcomes were the reasons, facilitators and barriers for successful participation and the potential impact in both pathways for future sample size calculations. Patients were offered use of an AI-based mHealth app before consulting their GP. GPs assessed the patients blinded and then unblinded to the app. Qualitative data included observations and audio-diaries from patients and GPs and focus-groups and interviews with GPs and GP assistants. Findings Fifty patients were included with a median age of 52 years (IQR 33.5-60.3), 64% were female, and 90% had a light skin type. The average patient inclusion rate was 4-6 per GP practice per month and 84% (n = 42) successfully participated. Similarly, in 90% (n = 45 patients) the GPs also successfully completed the study. GPs never changed their working diagnosis, but did change their treatment plan (n = 5) based on the app's assessments. Notably, 54% of patients with a benign skin lesion and low risk rating, indicated that they would be reassured and cancel their GP visit with these results (p < 0.001). Interpretation Our findings suggest that studying implementation of an AI-based mHealth app for detection of skin cancer in the hands of patients or as a diagnostic tool used by GPs in primary care appears feasible. Preliminary results indicate potential to further investigate both intended use settings. Show less
Outeiral, R.R.; Bos, P.; Hulst, H.J. van der; Al-Mamgani, A.; Jasperse, B.; Simoes, R.; Heide, U.A. van der 2022
Background and purpose: Contouring oropharyngeal primary tumors in radiotherapy is currently done manually which is time-consuming. Autocontouring techniques based on deep learning methods are a... Show moreBackground and purpose: Contouring oropharyngeal primary tumors in radiotherapy is currently done manually which is time-consuming. Autocontouring techniques based on deep learning methods are a desirable alternative, but these methods can render suboptimal results when the structure to segment is considerably smaller than the rest of the image. The purpose of this work was to investigate different strategies to tackle the class imbalance problem in this tumor site.Materials and methods: A cohort of 230 oropharyngeal cancer patients treated between 2010 and 2018 was retrospectively collected. The following magnetic resonance imaging (MRI) sequences were available: T1 -weighted, T2-weighted, 3D T1-weighted after gadolinium injection. Two strategies to tackle the class imbal-ance problem were studied: training with different loss functions (namely: Dice loss, Generalized Dice loss, Focal Tversky loss and Unified Focal loss) and implementing a two-stage approach (i.e. splitting the task in detection and segmentation). Segmentation performance was measured with Sorensen-Dice coefficient (Dice), 95th Hausdorff distance (HD) and Mean Surface Distance (MSD). Results: The network trained with the Generalized Dice Loss yielded a median Dice of 0.54, median 95th HD of 10.6 mm and median MSD of 2.4 mm but no significant differences were observed among the different loss functions (p-value > 0.7). The two-stage approach resulted in a median Dice of 0.64, median HD of 8.7 mm and median MSD of 2.1 mm, significantly outperforming the end-to-end 3D U-Net (p-value < 0.05).Conclusion: No significant differences were observed when training with different loss functions. The two-stage approach outperformed the end-to-end 3D U-Net. Show less
Optical projection tomography (OPT) is a tomographic 3D imaging technique used for specimens in the millimetre scale. 3D images are computed from a tomogram and therefore OPT is considered as... Show moreOptical projection tomography (OPT) is a tomographic 3D imaging technique used for specimens in the millimetre scale. 3D images are computed from a tomogram and therefore OPT is considered as computational imaging. In order to provide imaging and image analysis solutions for large scale biomedical research, optimisation of the OPT reconstruction is required. The aim of the optimisation presented in this thesis includes: (1) accelerate the reconstruction process; (2) reduce the reconstruction artefacts; (3) improve the image quality of 3D image; (4) Find optimal parameters for the iterative reconstruction.Starting from the optimisations that we have elaborated and implemented in the OPT imaging workflow, we have worked on case studies in zebrafish imaging. In this thesis we present one such particular case study (5) as it falls nicely in the order of magnitude for specimens in OPT imaging. The case study is on quantification of tumours in zebrafish and it is explored with image segmentation and object detection using artificial intelligence (AI) techniques. Show less
With the ever-growing amount of image data on the web, much attention has been devoted to large scale image search. It is one of the most challenging problems in computer vision for several... Show moreWith the ever-growing amount of image data on the web, much attention has been devoted to large scale image search. It is one of the most challenging problems in computer vision for several reasons. First, it must address various appearance transformations such as changes in perspective, rotation and scale existing in the huge amount of image data. Second, it needs to minimize memory requirements and computational cost when generating image representations. Finally, it needs to construct an efficient index space and a suitable similarity measure to reduce the response time to the users. This thesis aims to provide robust image representations that are less sensitive to above mentioned appearance transformations and are suitable for large scale image retrieval. Although this thesis makes a substantial number of contributions to large scale image retrieval, we also presented additional challenges and future research based on the contributions in this thesis. Show less