Search

Developing AI models for digital pathology has traditionally relied on single-scale analysis of histopathology slides. However, a whole slide image is a rich digital representation of the tissue, captured at various magnification levels. Limiting our analysis to a single scale overlooks critical information, spanning from intricate high-resolution cellular details to broad low-resolution tissue structures. In this study, we propose a model-agnostic multiresolution feature aggregation framework tailored for the analysis of histopathology slides in the context of breast cancer, on a multicohort dataset of 2038 patient samples. We have adapted 9 state-of-the-art multiple instance learning models on our multi-scale methodology and evaluated their performance on grade prediction, TP53 mutation status prediction and survival prediction. The results prove the dominance of the multiresolution methodology, and specifically, concatenating or linearly transforming via a learnable layer the feature vectors of image patches from a high (20x) and low (10x) magnification factors achieve improved performance for all prediction tasks across domain-specific and imagenet-based features. On the contrary, the performance of uniresolution baseline models was not consistent across domain-specific and imagenet-based features. Moreover, we shed light on the inherent inconsistencies observed in models trained on whole-tissue-sections when validated against biopsy-based datasets. Despite these challenges, our findings underscore the superiority of multiresolution analysis over uniresolution methods. Finally, cross-scale analysis also benefits the explainability aspects of attention-based architectures, since one can extract attention maps at the tissue- and cell-levels, improving the interpretation of the model's decision.

Purpose: Colour fundus images are widely used in diagnosis treatment decision of several retinal diseases such as diabetic retinopathy (DR), glaucoma and age-related macular degeneration (AMD). These very common conditions must be detected early and monitored to prevent progression and avoid permanent damage. Fundus images revealed to be useful also for the diagnosis of cataracts. Methods: In this review paper, an overview of traditional, machine learning and modern deep learning techniques for ophthalmic disease diagnosis (i.e. glaucoma, DR, AMD, and cataract) using retinal fundus images is presented. In addition, various publicly available image datasets used for such purposes are described. Results: The current main challenges and findings are identified, as well as common aspects and discrepancies between the various methods developed for the various diseases. Conclusion: The overview of what has been done about all pathologies, rather than only on a specific one, could favour a migration of the best solutions and, hopefully, the development of a more precise and clinically useful automatic analysis of all pathologies. Important critical insights and research trends are also discussed. Graphical abstract:

Eye behaviour provides valuable information revealing one’s higher cognitive functions and state of affect. Although eye tracking is gaining ground in the research community, it is not yet a popular approach for the detection of emotional and cognitive states. In this paper, we present a review of eye and pupil tracking related metrics (such as gaze, fixations, saccades, blinks, pupil size variation, etc.) utilized towards the detection of emotional and cognitive processes, focusing on visual attention, emotional arousal and cognitive workload. Besides, we investigate their involvement as well as the computational recognition methods employed for the reliable emotional and cognitive assessment. The publicly available datasets employed in relevant research efforts were collected and their specifications and other pertinent details are described. The multimodal approaches which combine eye-tracking features with other modalities (e.g. biosignals), along with artificial intelligence and machine learning techniques were also surveyed in terms of their recognition/classification accuracy. The limitations, current open research problems and prospective future research directions were discussed for the usage of eye-tracking as the primary sensor modality. This study aims to comprehensively present the most robust and significant eye/pupil metrics based on available literature towards the development of a robust emotional or cognitive computational model.

Prostate cancer diagnosis and treatment relies on precise MRI lesion segmentation, a challenge notably for small (<15 mm) and intermediate (15–30 mm) lesions. Our study introduces ProLesA-Net, a multi-channel 3D deep-learning architecture with multi-scale squeeze and excitation and attention gate mechanisms. Tested against six models across two datasets, ProLesA-Net significantly outperformed in key metrics: Dice score increased by 2.2%, and Hausdorff distance and average surface distance improved by 0.5 mm, with recall and precision also undergoing enhancements. Specifically, for lesions under 15 mm, our model showed a notable increase in five key metrics. In summary, ProLesA-Net consistently ranked at the top, demonstrating enhanced performance and stability. This advancement addresses crucial challenges in prostate lesion segmentation, enhancing clinical decision making and expediting treatment processes.

ABSTRACTIntroduction: As stem cell treatments reach closer to the clinic, the need for appropriate noninvasive imaging for accurate disease diagnosis, treatment planning, follow-up, and early detection of complications, is constantly rising. Clinical radiology affords an extensive arsenal of advanced imaging techniques, to provide anatomical and functional information on the whole spectrum of stem cell treatments from diagnosis to follow-up.Areas covered: This manuscript aims at providing a critical review of major published studies on the utilization of advanced imaging for stem cell treatments. Uses of magnetic resonance imaging (MRI), computed tomography (CT), ultrasound, and positron emission tomography (PET) are reviewed and interrogated for their applicability to stem cell imaging.Expert opinion: A wide spectrum of imaging methods have been utilized for the evaluation of stem cell therapies. The majority of published techniques are not clinically applicable, using methods exclusively applicable to animals or technology irrelevant to current clinical practice. Harmonization of preclinical methods with clinical reality is necessary for the timely translation of stem cell therapies to the clinic. Methods such as diffusion weighted MRI, hybrid imaging, and contrast-enhanced ultrasound hold great promise and should be routinely incorporated in the evaluation of patients receiving stem cell treatments.

To compare two Gaussian diffusion-weighted MRI (DWI) models including mono-exponential and bi-exponential, with the non-Gaussian kurtosis model in patients with pancreatic ductal adenocarcinoma.

Melorheostosis is a rare, nonhereditary, benign, sclerotic bone dysplasia with no sex predilection, typically occurring in late childhood or early adulthood, which can lead to substantial functional morbidity, depending on the sites of involvement. We report on a patient with extensive melorheostosis in the axial and appendicular skeleton, as well as in the soft tissues, who was evaluated with whole-body 18F-NaF PET/CT scan. All melorheostotic lesions of the skeleton and of the ossified soft-tissue masses demonstrated intensely increased 18F-NaF activity, suggesting the application of this modality in assessing and monitoring the disease activity.

Applying diffusive models for simulating the spatiotemporal change of concentration of tumour cells is a modern application of predictive oncology. Diffusive models are used for modelling glioblastoma, the most aggressive type of glioma. This paper presents the results of applying a linear quadratic model for simulating the effects of radiotherapy on an advanced diffusive glioma model. This diffusive model takes into consideration the heterogeneous velocity of glioma in gray and white matter and the anisotropic migration of tumor cells, which is facilitated along white fibers. This work uses normal brain atlases for extracting the proportions of white and gray matter and the diffusion tensors used for anisotropy. The paper also presents the results of applying this glioma model on real clinical datasets.