Minimum resolution requirements of digital pathology images for accurate classification.

Digitization of pathology has been proposed as an essential mitigation strategy for the severe staffing crisis facing most pathology departments. Despite its benefits, several barriers have prevented widespread adoption of digital workflows, including cost and pathologist reluctance due to subjective image quality concerns. In this work, we quantitatively determine the minimum image quality requirements for binary classification of histopathology images of breast tissue in terms of spatial and sampling resolution. We train an ensemble of deep learning classifier models on publicly available datasets to obtain a baseline accuracy and computationally degrade these images according to our derived theoretical model to identify the minimum resolution necessary for acceptable diagnostic accuracy. Our results show that images can be degraded significantly below the resolution of most commercial whole-slide imaging systems while maintaining reasonable accuracy, demonstrating that macroscopic features are sufficient for binary classification of stained breast tissue. A rapid low-cost imaging system capable of identifying healthy tissue not requiring human assessment could serve as a triage system for reducing caseloads and alleviating the significant strain on the current workforce.

The effect of baseline cognition and delirium on long-term cognitive impairment and mortality: a prospective population-based study.

Background: There is an unmet public health need to understand better the relationship between baseline cognitive function, the occurrence and severity of delirium, and subsequent cognitive decline. Our aim was to quantify the relationship between baseline cognition and delirium and follow-up cognitive impairment. Methods: We did a prospective longitudinal study in a stable representative community sample of adults aged 70 years or older who were registered with a Camden-based general practitioner in the London Borough of Camden (London, UK). Participants were recruited by invitation letters from general practice lists or by direct recruitment of patients from memory clinics or patients recently discharged from secondary care. We quantified baseline cognitive function with the modified Telephone Interview for Cognitive Status. In patients who were admitted to hospital, we undertook daily assessments of delirium using the Memorial Delirium Assessment Scale (MDAS). We estimated the association of pre-admission baseline cognitive function with delirium prevalence, severity, and duration. We assessed subsequent cognitive function 2 years after baseline recruitment using the Telephone Interview for Cognitive Status. Regression models were adjusted by age, sex, education, illness severity, and frailty. Findings: We recruited 1510 participants (median age 77 [IQR 73-82], 57% women) between March, 2017, and October, 2018. 209 participants were admitted to hospital across 371 episodes (1999 person-days of assessment). Better baseline cognition was associated with a lower risk of delirium (odds ratio 0·63, 95% CI 0·45 to 0·89) and with less severe delirium (-1·6 MDAS point, 95% CI -2·6 to -0·7). Individuals with high baseline cognition (baseline Z score +2·0 SD) had demonstrable decline even without delirium (follow-up Z score +1·2 SD). However, those with a high delirium burden had an even larger absolute decline of 2·2 SD in Z score (follow-up Z score -0·2). Once individuals had more than 2 days of moderate delirium, the rates of death over 2 years were similar regardless of baseline cognition; a better baseline cognition no longer conferred any mortality benefit. Interpretation: A higher baseline cognitive function is associated with a good prognosis with regard to likelihood and severity of delirium. However, those with a high baseline cognition and with delirium had the highest degree of cognitive decline, a change similar to the decline observed in individuals with a high amyloid burden in other cohorts. Older people with a healthy baseline cognitive function who develop delirium stand to lose the most after delirium. This group could benefit from targeted cognitive rehabilitation interventions after delirium.

Fast catheter segmentation from echocardiographic sequences based on segmentation from corresponding X-ray fluoroscopy for cardiac catheterization interventions.

Echocardiography is a potential alternative to X-ray fluoroscopy in cardiac catheterization given its richness in soft tissue information and its lack of ionizing radiation. However, its small field of view and acoustic artifacts make direct automatic segmentation of the catheters very challenging. In this study, a fast catheter segmentation framework for echocardiographic imaging guided by the segmentation of corresponding X-ray fluoroscopic imaging is proposed. The complete framework consists of: 1) catheter initialization in the first X-ray frame; 2) catheter tracking in the rest of the X-ray sequence; 3) fast registration of corresponding X-ray and ultrasound frames; and 4) catheter segmentation in ultrasound images guided by the results of both X-ray tracking and fast registration. The main contributions include: 1) a Kalman filter-based growing strategy with more clinical data evalution; 2) a SURF detector applied in a constrained search space for catheter segmentation in ultrasound images; 3) a two layer hierarchical graph model to integrate and smooth catheter fragments into a complete catheter; and 4) the integration of these components into a system for clinical applications. This framework is evaluated on five sequences of porcine data and four sequences of patient data comprising more than 3000 X-ray frames and more than 1000 ultrasound frames. The results show that our algorithm is able to track the catheter in ultrasound images at 1.3 s per frame, with an error of less than 2 mm. However, although this may satisfy the accuracy for visualization purposes and is also fast, the algorithm still needs to be further accelerated for real-time clinical applications.