Large-scale validation study of an improved semiautonomous urine cytology assessment tool: AutoParis-X

BACKGROUND

Adopting a computational approach for the assessment of urine cytology specimens has the potential to improve the efficiency, accuracy, and reliability of bladder cancer screening, which has heretofore relied on semisubjective manual assessment methods. As rigorous, quantitative criteria and guidelines have been introduced for improving screening practices (e.g., The Paris System for Reporting Urinary Cytology), algorithms to emulate semiautonomous diagnostic decision-making have lagged behind, in part because of the complex and nuanced nature of urine cytology reporting.

METHODS

In this study, the authors report on the development and large-scale validation of a deep-learning tool, AutoParis-X, which can facilitate rapid, semiautonomous examination of urine cytology specimens.

RESULTS

The results of this large-scale, retrospective validation study indicate that AutoParis-X can accurately determine urothelial cell atypia and aggregate a wide variety of cell-related and cluster-related information across a slide to yield an atypia burden score, which correlates closely with overall specimen atypia and is predictive of Paris system diagnostic categories. Importantly, this approach accounts for challenges associated with the assessment of overlapping cell cluster borders, which improve the ability to predict specimen atypia and accurately estimate the nuclear-to-cytoplasm ratio for cells in these clusters.

CONCLUSIONS

The authors developed a publicly available, open-source, interactive web application that features a simple, easy-to-use display for examining urine cytology whole-slide images and determining the level of atypia in specific cells, flagging the most abnormal cells for pathologist review. The accuracy of AutoParis-X (and other semiautomated digital pathology systems) indicates that these technologies are approaching clinical readiness and necessitates full evaluation of these algorithms in head-to-head clinical trials.

Examining longitudinal markers of bladder cancer recurrence through a semiautonomous machine learning system for quantifying specimen atypia from urine cytology

BACKGROUND

Urine cytology is generally considered the primary approach for screening for recurrence of bladder cancer. However, it is currently unclear how best to use cytological examinations for assessment and early detection of recurrence, beyond identifying a positive finding that requires more invasive methods to confirm recurrence and decide on therapeutic options. Because screening programs are frequent, and can be burdensome, finding quantitative means to reduce this burden for patients, cytopathologists, and urologists is an important endeavor and can improve both the efficiency and reliability of findings. Additionally, identifying ways to risk-stratify patients is crucial for improving quality of life while reducing the risk of future recurrence or progression of the cancer.

METHODS

In this study, a computational machine learning tool, AutoParis-X, was leveraged to extract imaging features from urine cytology examinations longitudinally to study the predictive potential of urine cytology for assessing recurrence risk. This study examined how the significance of imaging predictors changes over time before and after surgery to determine which predictors and time periods are most relevant for assessing recurrence risk.

RESULTS

Results indicate that imaging predictors extracted using AutoParis-X can predict recurrence as well or better than traditional cytological/histological assessments alone and that the predictiveness of these features is variable across time, with key differences in overall specimen atypia identified immediately before tumor recurrence.

CONCLUSIONS

Further research will clarify how computational methods can be effectively used in high-volume screening programs to improve recurrence detection and complement traditional modes of assessment.

Uncovering additional predictors of urothelial carcinoma from voided urothelial cell clusters through a deep learning-based image preprocessing technique

BACKGROUND

Urine cytology is commonly used as a screening test for high-grade urothelial carcinoma for patients with risk factors or hematuria and is an essential step in longitudinal monitoring of patients with previous bladder cancer history. However, the semisubjective nature of current reporting systems for urine cytology (e.g., The Paris System) can hamper reproducibility. For instance, the incorporation of urothelial cell clusters into the classification schema is still an item of debate and perplexity among expert cytopathologists because several previous works have disputed their diagnostic relevance.

METHODS

In this work, an automated preprocessing tool for urothelial cell cluster assessment was developed that divides urothelial cell clusters into meaningful components for downstream assessment (ie, population-based studies, workflow automation).

RESULTS

In this work, an automated preprocessing tool for urothelial cell cluster assessment was developed that divides urothelial cell clusters into meaningful components for downstream assessment (ie, population-based studies, workflow automation). Results indicate that cell cluster atypia (i.e., defined by whether the cell cluster harbored multiple atypical cells, thresholded by a minimum number of cells), cell border overlap and smoothness, and total number of clusters are important markers of specimen atypia when considering assessment of urothelial cell clusters.

CONCLUSIONS

Markers established through techniques to separate cell clusters may have wider applicability for the design and implementation of machine learning approaches for urine cytology assessment.

Large-scale longitudinal comparison of urine cytological classification systems reveals potential early adoption of The Paris System criteria

INTRODUCTION

Urine cytology is used to screen for urothelial carcinoma in patients with hematuria or risk factors (eg, smoking, industrial dye exposure) and is an essential clinical triage and longitudinal monitoring tool for patients with known bladder cancer. However, urine cytology is semisubjective and thus susceptible to issues including specimen quality, interobserver variability, and "hedging" towards equivocal ("atypical") diagnoses. These factors limit the predictive value of urine cytology and increase reliance on invasive procedures (cystoscopy). The Paris System for Reporting Urine Cytology (TPS) was formulated to provide more quantitative/reproducible endpoints with well-defined criteria for urothelial atypia. TPS is often compared to other assessment techniques to justify its adoption. TPS results in decreased use of the atypical category and better reproducibility. Previous reports comparing diagnoses pre- and post-TPS have not considered temporal differences between diagnoses made under prior systems and TPS. By aggregating across time, studies may underestimate the magnitude of differences between assessment methods.

MATERIALS AND METHODS

We conducted a large-scale longitudinal reassessment of urine cytology using TPS criteria from specimens collected from 2008 to 2018, prior to the mid-2018 adoption of TPS at an academic medical center.

RESULTS

Findings indicate that differences in atypical assignment were largest at the start of the period and these differences progressively decreased towards insignificance just prior to TPS implementation.

CONCLUSIONS

This finding suggests that cytopathologists had begun to utilize the quantitative TPS criteria prior to official adoption, which may more broadly inform adoption strategies, communication, and understanding for evolving classification systems in cytology.

Abuse, Toxicology and the Resurgence of Propylhexedrine: A Case Report and Review of Literature

Propylhexedrine, the active ingredient in over-the-counter nasal decongestants, carries significant abuse potential for users seeking psychostimulant effects. Historically, propylhexedrine was perceived to have a good safety profile resulting in endorsement of it replacing the highly abused amphetamine sulfate as the active ingredient in nasal decongestants in 1949. While much of the published literature concerning its psychoactive potential comes from the 1970s and 1980s, we have encountered several recent cases of toxidrome secondary to its abuse. Awareness of the hazards associated with this pharmaceutical should be of interest to physicians of all specialties who are likely to encounter such cases, as well and legislators interested in exerting regulatory control. Here we review all existing literature concerning this pharmaceutical compound.

Emergence characteristics of sevoflurane compared to halothane in pediatric patients undergoing bilateral pressure equalization tube insertion

STUDY OBJECTIVE

To compare the emergence characteristics of sevoflurane with halothane in pediatric patients having bilateral myringotomy and pressure equalization tube insertion using a highly standardized and common anesthetic technique.

DESIGN

Prospective, randomized, double-blind study.

SETTING

University hospital.

PATIENTS

43 ASA physical status I and II healthy pediatric outpatients scheduled for initial ear tube placement by one surgeon.

INTERVENTIONS

Patients were randomized to receive either halothane or sevoflurane as their sole anesthetic drug for ear tube insertion. All patients as well as the research nurse grading emergence agitation were blinded to group assignment. No premedication was administered, and all patients received a standard dose of rectal acetaminophen for postoperative pain control.

MEASUREMENT AND MAIN RESULTS

The primary outcome was the percentage of patients with emergence agitation, defined as thrashing behavior requiring physical restraint for greater than three minutes. Time to discharge from the postanesthesia care unit (PACU) and from the hospital were also compared. Sevoflurane patients had a greater incidence of emergence delirium: 57% versus 27% [95% CI (1.7%-58.1%) p = 0.047]. Time to discharge from the PACU and the hospital were longer for patients who received sevoflurane: 62 versus 50 min [95% CI (1.4-23.6) p = 0.02] and 102 versus 79 mins [95% CI (9.6-37.1) p = 0.003].

CONCLUSION

In our institution there is a trend toward greater emergence agitation in ear tube placement patients given sevoflurane versus halothane anesthesia. Further, (with our discharge criteria) patients are actually discharged from the PACU and the hospital faster when given halothane as a sole anesthetic when compared to sevoflurane.

Parental presence plus oral midazolam decreases frequency of 5% halothane inductions in children

STUDY OBJECTIVE

To determine the frequency of 5% halothane induction and behavioral distress during inhalation induction with both oral midazolam and parental presence compared with parental presence alone.

DESIGN

Randomized, controlled, double blind study.

SETTING

Same day anesthesia at a university department of anesthesiology.

PATIENTS

72 ASA status I and II children, 3 to 10 years of age, scheduled for first time anesthesia.

INTERVENTIONS

Children were assigned to one of two groups to receive midazolam 0.5 mg/kg orally or placebo. A parent was present during induction. Children were videotaped at baseline, after treatment, and during induction. Tapes were scored for behavioral distress using the revised Observational Scale of Behavioral Distress.

MEASUREMENTS AND MAIN RESULTS

Children who received midazolam in the setting of parental presence had significantly fewer 5% halothane inductions than those who received placebo (p < 0.02). They also had less behavioral distress (p < 0.01).

CONCLUSIONS

The combination of parental presence plus oral midazolam reduces the likelihood of needing a 5% rapid halothane induction when compared with parental presence without premedication.

Repatriation of 150,000 sudanese refugees from ethiopia: the manipulation of civilians in a situation of civil conflict

This paper outlines the dramatic return to Sudan of 150,000 men, women and children from Itang Refugee Camp in Ethiopia in June 1991. These people were pawns in Sudan's civil war, manipulated by governments, military forces and the media - a state of affairs that the international community failed to deal with effectively. At the time of the return to Sudan, ICRC and the United Nations were working to assist the returnees in two different areas and each had a different access agreement and thus a different impact on the survival of the returnees. The paper focuses on the role of political awareness and negotiation in the protection of refugees and in the organisation of relief in the context of a civil war.

Health implications of war in Uganda and Sudan

Civil war disrupted agriculture and trade in Uganda and Sudan. This reduced tax revenues and drained scarce resources away from health budgets to finance increased military expenditures. Hundreds and thousands of people were driven from their homes either as internally displaced people or as refugees. Normal health service delivery systems were broken down forcing doctors, nurses and other health professionals into towns, cities or neighbouring countries in search of peace and employment. Scores of hospitals, health centres and dispensaries were abandoned, destroyed or looted, rendering even the limited physical facilities useless. Preventive public health services such as immunization and provision of potable drinking water were discontinued leaving huge populations susceptible to controllable infectious diseases and epidemics.

Effect of cimetidine on biotransformation of enflurane in man

This study was designed to test the hypothesis that administration of clinical doses of cimetidine could affect the metabolic degradation of enflurane to inorganic fluoride via inhibition of the mixed function oxidase enzyme (MFOE) system. In Part 1 of the study 38 female patients undergoing gynaecologic surgery received, double blind, either cimetidine, 300 mg PO the night prior to surgery and 300 mg IV 30 minutes prior to anaesthesia induction or a placebo. In Part 2, 24 patients received either cimetidine as in Part 1, but with continued administration for 24 hours into the postoperative period, or a placebo. Anaesthesia in all cases was with enflurane in oxygen, via a closed circuit. In both Parts 1 and 2 of the study there were no statistically significant differences between the two groups in serum fluoride levels at baseline, four hours or 24 hours postoperatively, or in the total urinary fluoride excretion during the first or second postoperative days. The authors speculate that this is due either to separate interactions of cimetidine and enflurane with the MFOE system or to the relatively low rate of enflurane metabolism.

Uganda--rehabilitation, or redefinition of health services?

Uganda had one of the best health care delivery systems in Africa. The decade of misrule by Amin saw a collapse of the country and an exodus of doctors and other professions. The 1979 liberation war and subsequent political instability and insecurity further aggravated the poor health services then available. When political stability was temporarily restored in December 1980 the cash crop export sector took priority over social services and the health budget declined to only 3.5% compared to a former level of 7.5% of government budget. Emergencies in West Nile, Karamoja and the Luwero triangle continued to plague rehabilitation efforts upto 1985. Alternate strategies for improving health are proposed including female education, increased budget allocations, food and nutrition policy and health information. Uganda's prospect for rebuilding the health services has begun with immunization, control of diarrhoeal diseases, nutrition surveillance in Karamoja and an essential drugs programme, but the success of these is dependent upon political stability and improvement in overall security.