State-of-the-art performance of deep learning methods for pre-operative radiologic staging of colorectal cancer lymph node metastasis: a scoping review

Objectives
To assess the current state-of-the-art in deep learning methods applied to pre-operative radiologic staging of colorectal cancer lymph node metastasis. Specifically, by evaluating the data, methodology and validation of existing work, as well as the current use of explainable AI in this fast-moving domain.

Design
Scoping review.

Data sources
Academic databases MEDLINE, Embase, Scopus, IEEE Xplore, Web of Science and Google Scholar were searched with a date range of 1 January 2018 to 1 February 2024.

Eligibility criteria
Includes any English language research articles or conference papers published since 2018 which have applied deep learning methods for feature extraction and classification of colorectal cancer lymph nodes on pre-operative radiologic imaging.

Data extraction and synthesis
Key results and characteristics for each included study were extracted using a shared template. A narrative synthesis was then conducted to qualitatively integrate and interpret these findings.

Results
This scoping review covers 13 studies which met the inclusion criteria. The deep learning methods had an area under the curve score of 0.856 (0.796 to 0.916) for patient-level lymph node diagnosis and 0.904 (0.841 to 0.967) for individual lymph node assessment, given with a 95% confidence interval. Most studies have fundamental limitations including unrepresentative data, inadequate methodology, poor model validation and limited explainability techniques.

Conclusions
Deep learning methods have demonstrated the potential for accurately diagnosing colorectal cancer lymph nodes using pre-operative radiologic imaging. However, several methodological and validation flaws such as selection bias and lack of external validation make it difficult to trust the results. This review has uncovered a research gap for robust, representative and explainable deep learning methods that are end-to-end from automatic lymph node detection to the diagnosis of lymph node metastasis.

Leggi
Dicembre 2024

Predictors of upper limb motor recovery in stroke survivors: a pre-post test study design

Objectives
The study aimed to assess the predictors of upper limb motor recovery in stroke survivors.

Design
Pre–post test study design.

Setting
Conducted in two centres (First Level Hospital and University Teaching Hospital in Lusaka).

Participants
Patients living with stroke accessing physiotherapy services at the two public hospitals. A total of 52 patients were recruited at the start of the study, 6 were lost to follow-up and 46 completed the study.

Intervention
Conventional physiotherapy for 8 weeks (5 September 2022–28 October 2022).

Primary outcome
Motor function measured using a Fugl-Meyer assessment of the upper extremity.

Results
Analysis was conducted on 46 participants. A significant difference was observed between the level of motor function at baseline and after 8 weeks of treatment (p=0.0183). At baseline, 50% of participants had mild motor function, which improved after 8 weeks, with 69.6% having mild motor function. Stroke patients with severe motor function impairment at baseline were associated with 0.01 times likelihood of having mild motor function impairment after 8 weeks of physiotherapy treatment (AOR 0.01; 95 % CI 0.00 to 0.16; p=0.002).

Conclusion
The motor function of stroke patients continues to improve over time. This study demonstrated that initial upper limb motor function impairment could be used as a predictor for upper limb motor function.

Leggi
Novembre 2024

Physical activity promotion intervention improved physical activity knowledge, confidence and behaviour among diverse immigrant women: pre-post multiple methods feasibility study

Objectives
Little prior research investigated how to promote physical activity (PA), which can reduce cancer risk, to immigrant women. The overall aim of the current study was to pilot test education session feasibility. The objectives were to assess participation in, satisfaction with and potential impact of the education session, knowledge needed to refine the education session prior to a future trial.

Design
Pre–post multiple-methods comparative cohort,

Setting
Canadian immigrant settlement agencies recruited intervention and control women.

Participants
Intervention: 60 baseline, 53 education (49 virtual group, 4 video only), 1 month (43 virtual, 4 video), 6 months (38 virtual, 4 video), 37% African black; control: 41, 32% African black.

Results
Among intervention women, PA knowledge increased significantly from baseline at 1 (p

Leggi
Novembre 2024