Deep learning in the detection of high-grade glioma recurrence using multiple MRI sequences: A pilot study.

The identification of high-grade glioma (HGG) progression may pose a diagnostic dilemma due to similar appearances of treatment-related changes (TRC) (e.g. pseudoprogression or radionecrosis). Deep learning (DL) may be able to assist with this task. MRI scans from consecutive patients with histologically confirmed HGG (grade 3 or 4) were reviewed. Scans for which recurrence or TRC was queried were followed up to determine whether the cases indicated recurrence/progression or TRC. Identified cases were randomly split into training and testing sets (80%/20%). Following development on the training set, classification experiments using convolutional neural networks (CNN) were then conducted using models based on each of diffusion weighted imaging (DWI - isotropic diffusion map), apparent diffusion coefficient (ADC), FLAIR and post-contrast T1 sequences. The sequence that achieved the highest accuracy on the test set was then used to develop DL models in which multiple sequences were combined. MRI scans from 55 patients were included in the study (70.1% progression/recurrence). 54.5% of the randomly allocated test set had progression/recurrence. Based upon DWI sequences the CNN achieved an accuracy of 0.73 (F1 score = 0.67). The model based on the DWI+FLAIR sequences in combination achieved an accuracy of 0.82 (F1 score = 0.86). The results of this study support similar studies that have shown that machine learning, in particular DL, may be useful in distinguishing progression/recurrence from TRC. Further studies examining the accuracy of DL models, including magnetic resonance perfusion (MRP) and magnetic resonance spectroscopy (MRS), with larger sample sizes may be beneficial.

Effect of medical student debt on mental health, academic performance and specialty choice: a systematic review.

OBJECTIVES: With the high and rising total cost of medical school, medical student debt is an increasing concern for medical students and graduates, with significant potential to impact the well-being of physicians and their patients. We hypothesised that medical student debt levels would be negatively correlated with mental health and academic performance, and would influence career direction (ie, medical specialty choice). DESIGN: We performed a systematic literature review to identify articles that assessed associations between medical student mental health, academic performance, specialty choice and debt. The databases PubMed, Medline, Embase, Scopus and PsycINFO were searched on 12 April 2017, for combinations of the medical subject headings Medical Student and Debt as search terms. Updates were incorporated on 24 April 2019. RESULTS: 678 articles were identified, of which 52 met the inclusion criteria after being reviewed in full text. The majority of studies were conducted in the USA with some from Canada, New Zealand, Scotland and Australia. The most heavily researched aspect was the association between medical student debt and specialty choice, with the majority of studies finding that medical student debt was associated with pursuit of higher paying specialties. In addition, reported levels of financial stress were high among medical students, and correlated with debt. Finally, debt was also shown to be associated with poorer academic performance. CONCLUSIONS: Medical student debt levels are negatively associated with mental well-being and academic outcomes, and high debt is likely to drive students towards choosing higher paying specialties. Additional prospective studies may be warranted, to better understand how educational debt loads are affecting the well-being, career preparation and career choices of physicians-in-training, which may in turn impact the quality of care provided to their current and future patients.