Performance and limitations of a supervised deep learning approach for the histopathological Oxford Classification of glomeruli with IgA nephropathy.

BACKGROUND AND OBJECTIVE: The Oxford Classification for IgA nephropathy is the most successful example of an evidence-based nephropathology classification system. The aim of our study was to replicate the glomerular components of Oxford scoring with an end-to-end deep learning pipeline that involves automatic glomerular segmentation followed by classification for mesangial hypercellularity (M), endocapillary hypercellularity (E), segmental sclerosis (S) and active crescents (C). METHODS: A total number of 1056 periodic acid-Schiff (PAS) whole slide images (WSIs), coming from 386 kidney biopsies, were annotated. Several detection models for glomeruli, based on the Mask R-CNN architecture, were trained on 587 WSIs, validated on 161 WSIs, and tested on 127 WSIs. For the development of segmentation models, 20,529 glomeruli were annotated, of which 16,571 as training and 3958 as validation set. The test set of the segmentation module comprised of 2948 glomeruli. For the Oxford classification, 6206 expert-annotated glomeruli from 308 PAS WSIs were labelled for M, E, S, C and split into a training set of 4298 glomeruli from 207 WSIs, and a test set of 1908 glomeruli. We chose the best-performing models to construct an end-to-end pipeline, which we named MESCnn (MESC classification by neural network), for the glomerular Oxford classification of WSIs. RESULTS: Instance segmentation yielded excellent results with an AP50 ranging between 78.2-80.1 % (79.4 ± 0.7 %) on the validation and 75.1-77.7 % (76.5 ± 0.9 %) on the test set. The aggregated Jaccard Index was between 73.4-75.9 % (75.0 ± 0.8 %) on the validation and 69.1-73.4 % (72.2 ± 1.4 %) on the test set. At granular glomerular level, Oxford Classification was best replicated for M with EfficientNetV2-L with a mean ROC-AUC of 90.2 % and a mean precision/recall area under the curve (PR-AUC) of 81.8 %, best for E with MobileNetV2 (ROC-AUC 94.7 %) and ResNet50 (PR-AUC 75.8 %), best for S with EfficientNetV2-M (mean ROC-AUC 92.7 %, mean PR-AUC 87.7 %), best for C with EfficientNetV2-L (ROC-AUC 92.3 %) and EfficientNetV2-S (PR-AUC 54.7 %). At biopsy-level, correlation between expert and deep learning labels fulfilled the demands of the Oxford Classification. CONCLUSION: We designed an end-to-end pipeline for glomerular Oxford Classification on both a granular glomerular and an entire biopsy level. Both the glomerular segmentation and the classification modules are freely available for further development to the renal medicine community.

The Perceptions of People with Dementia and Key Stakeholders Regarding the Use and Impact of the Social Robot MARIO.

People with dementia often experience loneliness and social isolation. This can result in increased cognitive decline which, in turn, has a negative impact on quality of life. This paper explores the use of the social robot, MARIO, with older people living with dementia as a way of addressing these issues. A descriptive qualitative study was conducted to explore the perceptions and experiences of the use and impact of MARIO. The research took place in the UK, Italy and Ireland. Semi-structured interviews were held in each location with people with dementia (n = 38), relatives/carers (n = 28), formal carers (n = 28) and managers (n = 13). The data was analyzed using qualitative content analysis. The findings revealed that despite challenges in relation to voice recognition and the practicalities of conducting research involving robots in real-life settings, most participants were positive about MARIO. Through the robot's user-led design and personalized applications, MARIO provided a point of interest, social activities, and cognitive engagement increased. However, some formal carers and managers voiced concern that robots might replace care staff.

Interacting with Dementia: The MARIO Approach.

MARIO is a companion robot that aims to help people with dementia (PWD) to battle isolation and loneliness by enabling them to stay socially active by providing a number of applications focused on hobbies (music, movies, etc), staying engaged with communities (reading headlines, reading local twitter feeds etc.) and staying connected with family and friends (telephoning them, reading their news from twitter, etc.). This paper presents the results from the initial trials of MARIO interacting with PWD involving a limited set of applications. It confirms some of the challenges hypothesized at the outset of the study and provides guidelines for future development work.