[Detection of white blood cells in microscopic leucorrhea images based on deep active learning]

The number of white blood cells in the leucorrhea microscopic image can indicate the severity of vaginal inflammation. At present, the detection of white blood cells in leucorrhea mainly relies on manual microscopy by medical experts, which is time-consuming, expensive and error-prone. In recent years, some studies have proposed to implement intelligent detection of leucorrhea white blood cells based on deep learning technology. However, such methods usually require manual labeling of a large number of samples as training sets, and the labeling cost is high. Therefore, this study proposes the use of deep active learning algorithms to achieve intelligent detection of white blood cells in leucorrhea microscopic images. In the active learning framework, a small number of labeled samples were firstly used as the basic training set, and a faster region convolutional neural network (Faster R-CNN) training detection model was performed. Then the most valuable samples were automatically selected for manual annotation, and the training set and the corresponding detection model were iteratively updated, which made the performance of the model continue to increase. The experimental results show that the deep active learning technology can obtain higher detection accuracy under less manual labeling samples, and the average precision of white blood cell detection could reach 90.6%, which meets the requirements of clinical routine examination.

Automatic identification of fungi in microscopic leucorrhea images

Identifying fungi in microscopic leucorrhea images provides important information for evaluating gynecological diseases. Subjective judgment and fatigue can greatly affect recognition accuracy. This paper proposes an automatic identification system to detect fungi in leucorrhea images that incorporates a convolutional neural network, the histogram of oriented gradients algorithm, and a binary support vector machine. In experiments, the detection rate of the positive samples was as high as 99.8%. The experimental results demonstrate the effectiveness of the proposed method and its potential as a primary software component of a completely automated system.

[Sexual transmissible diseases and "returning leukorrhea"]

White discharges and sexual transmissive diseases are now increasing. Confronted to this symptom, the general practician can easily diagnose and treat his patient. Therefore he must keep in his mind that behind this common symptom, a much more serious disease can be hidden.

Leukorrhea and bacterial vaginosis as in-office predictors of cervical infection in high-risk women

OBJECTIVE

To evaluate 1) whether microscopic detection of leukorrhea or bacterial vaginosis identifies patients at high risk for cervical infection with Chlamydia trachomatis or Neisseria gonorrhoeae, and 2) if pregnancy alters the predictive value of these findings.

METHODS

Wet-mount screening examination of vaginal discharge was performed on all new patients seen at two resident-staffed clinics serving primarily indigent women. Leukorrhea was defined as >10 white blood cells per high-power field on microscopic examination; Amsel criteria were used to determine the presence of bacterial vaginosis, with a positive clue cell test result defined as >20% of epithelial cells. The diagnoses of C trachomatis and N gonorrhoeae infection were established by deoxyribonucleic acid amplification tests.

RESULTS

The study population consisted of 194 women, 118 (61%) of whom were pregnant. Overall, 11% of women had positive cultures for chlamydia or gonorrhea. Although both leukorrhea and clue cells were independently associated with positive cervical cultures, multivariate analysis found that clue cells did not contribute to the predictive value of leukorrhea alone among both pregnant (relative risk [RR] = 15.7) and nonpregnant (RR = 58.7) women. Negative predictive values for the screening test were comparably high (98-100%), independent of pregnancy status.

CONCLUSION

Leukorrhea, in the presence or absence of bacterial vaginosis, was strongly associated with cervical infections with C trachomatis or N gonorrhoeae among both pregnant and nonpregnant patients. In settings where patient follow-up is uncertain, on-site screening tests identify women for whom empiric antibiotic therapy for sexually transmitted diseases may be appropriate.

[Colpocytology in a preventive gynecological ambulatory service]

BACKGROUND

evaluate the results of Pap smear in women attended at a gynecology preventive ambulatory (University of São Paulo Medical School Clinical Hospital).

METHODS

6821 women were submitted to a medical interview, clinical and gynecologic exam. Cervical and vaginal cytology (Pap smear) were analyzed according to the Papanicolaou method and classification. All women were grouped according to their age into three categories:under 40 years old, between 41 and 60 years and over 60 years.

RESULTS

most of them, and mainly the younger ones, had been submitted to a previous Pap smear in a period shorter than 1 year (44.2%). The majority of women recognized the usefulness of the exam and knew its interval; the group that best knew its importance and interval was the one with ages between 41 and 60 years, while most women over 60 years did not know both its importance and interval. Cytological material was considered insufficient for analysis in 15,1% and inadequate in 1.1%, and for those with adequate material results were classes I (21.7%), II (59.9%), III (2.0%), IV (0.1%) and V (0.1%). Distribution of cervical intraepithelial neoplasia (CIN) were similar in the three groups. The main microbiologic findings was Gardnerella sp. (8,6%) and Human papillomavirus (HPV) incidence was significantly lower among women over 60 years.

CONCLUSION

Cytological diagnoses of neoplastic modifications were performed in 2,2% and Gardnerella sp. was the most prevalent microbiologic agent. Distribution of HPV showed a decrease with age. Older women had lower knowledge on the importance of regular Pap smear examination.

Vaginal discharge in the adult: a practice guideline

A practice guideline as a preformatted chart is presented. It is designed to be simple in concept and design, easy to use, parsimonious of data, easily scanned for quality assurance, and to provide clinical and cost-effectiveness prompts. It has supporting medical information for all recommendations that is literature- and experience-based. A patient aftercare instruction sheet is appended. An abbreviated "pocket practice guideline" is also provided. This format is clearly appropriate only for simple, not complex, clinical encounters.

[The use of the direct method for the diagnosis of Gardnerella vaginalis vaginitis]

A study was carried out on 200 patients divided in two groups of 100, labeled 1 and 2. They underwent vaginal secretion tests by the direct method in order to assess its appropriateness for Gardnerella vaginalis presumptive diagnosis. This study was related with patients' symptoms, such as leukorrhea and fetidity prevailing in Group 1 and lower abdomen pain prevailing in Group 2, as well as the proportions of germs isolated and the association with this symptom for defining the microorganism role in the occurrence of so-called unspecific vaginitis; Group 1 had 100% of positive plates and Group 2 had 55%, who were given adequate treatment for the couple with further confirmation of the results which were effective in 96.7% of the cases. No relation could be seen between IUD and the presence of germ, since it is likely that its existence was not taken into account on inserting IUD.

Vaginal discharge

The problem of vaginal discharge requires careful attention to the diagnostic process with analysis of the nature of the discharge, physical examination including a thorough inspection and the performing of a wet film. Physiological discharge and other non infective causes, including feminine hygiene preparations, should be considered. Treatment should be tailored to the cause and psychosexual sequelae should be prevented by proper advice and counselling.

Persistent vaginal discharge in a sexually active adolescent female

With the high prevalence of unprotected sexual activity among adolescents, health-care providers are frequently called upon to evaluate patients with abnormal vaginal discharges. Usually, thorough pelvic and laboratory examinations will identify offending organisms which can be promptly eradicated with the judicious use of antibiotics. Occasionally, however, an abnormal discharge may persist despite these interventions. Health-care providers need to be aware of the fact that anal intercourse may be a common practice among sexually active teenagers. Penile-vaginal contact after anal intercourse may cause vaginal discharge due to contamination. Health-care providers should make it a routine part of their history-taking of adolescent patients to inquire about anal intercourse. Not only might it reveal useful clinical information, but it may indicate the need for additional health education and counseling.

Investigation and treatment of vaginal discharge and pruritus vulvae

The causes of vaginal discharge for pruritus vulvae in a patient are considered in three categories: common causes like vaginal candidosis, Trichomonal vaginitis, Gardnerella vaginitis; less common causes like gonococcal infection, Chlamydia infection and T-mycoplasma infection; and uncommon causes which include allergy to nylon underwear, human papilloma infection and eczema. The clinical features of each and a suggested treatment regime are given.

A model-based system to determine the relative value of different variables in a diagnostic system using Bayes theorem

A model system is described which simulates the presenting features of cases of vaginal discharge. This system was used to examine the effects of removing individual clinical features on the overall efficiency of diagnosis by Bayes theorem. The diagnostic efficiency was significantly reduced by elimination of inflammation, of a frothy discharge, or of a curdy discharge. Elimination of more than one significant factor further reduced the number of correct diagnoses, but elimination of more than one non-significant factor made no obvious difference. The most significant clinical feature was presence of inflammation; elimination of this feature had a substantial effect on the diagnosis of gardnerella, viral, gonorrhoea and foreign body. Elimination of two of the variables (bloodstaining and odour) which did not influence overall diagnostic efficiency nevertheless had a substantial effect on the diagnosis of neoplasms and foreign bodies. It is proposed that a simulation of this type is of potential practical value in determining a minimum subset of clinical features for diagnostic systems involving Bayes theorem.

An illustrated guide to adolescent gynecology

The gynecologic examination should be considered an essential part of a complete physical examination in the adolescent girl. Many symptoms and signs which at first may seem to be unrelated to the reproductive tract are found to be due to gynecologic pathology after a careful gynecologic examination has been completed. Most of the diagnostic tests which are needed as part of the gynecologic examination can be easily performed in a pediatrician's office including wet preps, KOH preps, and Gram's stains of vaginal discharge. Other ancillary tests, including Pap smears and cultures for sexually transmitted diseases, can be obtained by the examining pediatrician and sent to local clinical laboratories. The pelvic ultrasound can be a helpful adjunct to the gynecologic examination when congenital anomalies, or adnexal masses, are suspected.

Is routine antenatal booking vaginal examination necessary for reasons other than cervical cytology if ultrasound examination is planned?

Sixteen ovarian cysts, including one borderline ovarian malignancy, and ten trichomonal vaginal discharges but no cases of cervical incompetence or ectopic pregnancy had been detected at booking vaginal examination in 11,622 consecutive antenatal case records abstracted retrospectively. In an attitude survey of pregnant women 77% believed that vaginal examination was reassuring, 55% found it unpleasant, and 18% thought it could cause miscarriage. This, and a review of the literature, suggests that routine vaginal examination if ultrasound is planned has few advantages beyond the taking of a cervical smear.

Diagnostic aspects of primary tubal malignancy

Eleven cases of primary tubal malignancy are reported to characterize clinical symptoms and diagnostic procedures. The importance of a yellow vaginal discharge is emphasized as being a diagnostic sign.

Diagnostic value of clinical examination, direct microscopy, and culture in the Gardnerella vaginalis syndrome

In a general practice 467 women aged 15-49 years with vaginal discharge were consecutively examined in order to compare the diagnostic value in the Gardnerella vaginalis syndrome of the clinical examination, direct microscopy of the vaginal secretion, and culture. We found significant correlations between all relevant combinations of the diagnostic methods. The predictive value of a positive test for the clinical examination, the microscopy, and the clinical examination combined with microscopy, respectively, was 0.75, 0.89 and 0.90, whereas the predictive values of the negative test were 0.59, 0.72 and 0.61, respectively. Because even small numbers of Gardnerella vaginalis may yield growth on selective culture media, the clinical examination and the microscopy are often negative despite positive culture. To avoid overtreatment of a benign condition we therefore conclude that the presence of a characteristic clinical picture and positive microscopy constitute a safe basis for the diagnosis of the Gardnerella vaginalis syndrome, and that the diagnosis should be based on this combination or on the fulfilment of three of the following four criteria: 1) characteristic vaginal secretion; 2) vaginal pH greater than 4.5; 3) positive potassium hydroxide test or characteristic herring-brine smell, and 4) clue cells at microscopy. With the present methods culture for Gardnerella vaginalis should not routinely be performed, until the value of quantitated methods has been proved. Coexistence of other microorganisms rendered the diagnosis difficult. We recommend to treat the most predominant infection first.

Probability of vaginal foreign body in girls with genital complaints

We used Bayes' theorem to evaluate the probability of vaginal foreign bodies in girls with genital complaints. The prevalence of vaginal foreign bodies in outpatient girls under 13 years of age with gynecologic disorders was found to be 4%. Review of the charts of 17 pre-menarcheal girls who had foreign bodies on 19 occasions and of 28 girls with infectious or nonspecific vaginitis demonstrated that patients with foreign bodies reported vaginal bleeding more frequently than discharge (14 and two of 15 symptomatic cases, respectively), while in contrast, patients with infectious or nonspecific vaginitis reported vaginal discharge more often than bleeding (23 and five of 28 symptomatic controls, respectively). Bayes' theorem indicates that, in populations resembling the one we studied, approximately 18% of preteenage girls with vaginal bleeding with or without discharge and 50% of those with bleeding and no discharge will prove to have vaginal foreign bodies.

Atypical presentation of female genital tract tuberculosis

Three patients with atypical presentation of female genital tract tuberculosis are reported. Tuberculous hydrosalpinx with abdominal peritonitis, concomitant ectopic gestation with active salpingitis and tuberculous endometritis presenting as postmenopausal vaginal discharge are uncommon clinical manifestations. The age distribution, the importance of careful histological examination and the available methods for follow-up are discussed in the appropriate cases.

Vaginitis

The normal physiology of the vagina, the six most common causes of vaginal discharge, current accepted methods of treatment, and specific nurse practitioner implications are reviewed.

ABC of sexually transmitted diseases. Vaginal discharge: diagnosis

Images

[Metronidazole as the therapeutic choice in bacterial leukorrhea. Report from a gynecologic practice on the diagnosis and therapy of non-physiologic bacterial discharge]

Diagnosis and therapy of different kinds of fluor in gynaecological practice are reported. Subjective criteria are completed by investigations with phase-contrast-microscope. Unphysiological bacterial fluor has been found most frequently and was treated by metronidazole (Rathimed N) per os during one day without regard of bacteria species. Of 239 patients 83.7 per cent were cured, 11.3 per cent got better and only 5 per cent were not cured. According to these results metronidazole therapy is one of the shortest and most effective therapeutical methods in fluor treatment.

Vaginal discharge in children and adolescents. Evolution and management: a review

Vaginal discharge is one of the most common gynecologic problems encountered in the pediatric and adolescent populations and may have many causes. A useful way of approaching the diagnosis of a discharge is by categorizing the patient as being prepubertal of postpubertal. In the prepubertal age group, discharge is generally associated with vulvovaginitis. In the postpubertal age group, discharge may be physiologic, or may associated with cervicitis or vaginitis. In each group, gonorrhea and sexual abuse must be ruled out. A practical approach to therapy is outlined.

The management of vaginal discharge in general practice

A group of general practitioners in active practice were asked to report how they preferred to manage the symptoms of vaginal discharge presented by a woman in her twenties. Subsequently the same practitioners reported their management of such patients in their practice.A shortfall was found for all practitioners between their declared intention and their actual practice.This method of analysis offers a way of working towards a consensus in clinical care and also of auditing medical performance in general practice.

Premenarchal vulvovaginitis

The general subject of premenarchal vulvovaginitis has been reviewed. Vulvovaginal inflammations and infections in the premenarchal child are caused by a large number of etiologic agents. The symptoms, diagnosis, and treatment of the most common of these, namely, nonspecific infections, specific nongonorrheal infections, gonorrhea, protozoal infestations, helminthiasis, mycotic infections, and inflammations due to physical, chemical, and allergenic agents, have been discussed. Reference has been made not only to the older literature but also to some of the pertinent reports published during the last 10 years.

[The diagnosis and treatment of mixed anaerobic vaginal dischargs (authors' transl)]

In about 5% of 3355 patients the microscopic examination of the vaginal discharge in normal saline showed a characteristic fast moving rod. More than 80% of these patients complained of a discharge with a foul smell during the menstrual period. Bactriology showed an anaerob gram negative rod which was difficult to grow and is as yet unclassified. Following treatment with one gram of Mimorazol every 12 hours for 3 doses, 71,5% of the patients were cured and showed a normal vaginal flora without further treatment. In around 24,13% of the patients the gram negative rod disappeared but a persistent mixed flora required further treatment. In 4.3% of the patients a recurrence occurred. An attempt was made to prevent recurrent infection prior to the follow-up examination by prohibition of sexual intercourse with an untreated partner, bathing in public swimming pools, and the use of sponges or wash cloths. In the course of the investigation the suspicion of contamination from the water of public pools became apparent. The diagnosis, treatment and transmission and the pathogenecity of the fast moving negative rod is discussed.

[Epidemiology and diagnosis of vaginal discharge. First Report (author's transl)]

In 700 patients, 1336 tests of vaginal discharge were performed by culture, wet mount with the phase contrast microscope and the Papanicolaou stain. The diagnosis of yeast is best done by culture. Yeast was found only in 68% of the culture positive cases by the wet mount method and in 47% of the cases by the Papanicolaou stain. Wet mount and Papanicolaou stain results for yeast are therefore only useful if they are positive. In the diagnosis of trichomonas, culture and wet mount are of the same effeciency. The incidence of yeast and trichomonas was dependant upon the age of the patients. In pregnancy and in cases with diabetes, yeast was found more often but no increase of yeast was found in cases on oral contraception. The diagnosis of bacterial mixed infections poses the most difficult problem and can only be improved by expensive culture methods.

Adolescent genital dermatoses

The female adolescent period rivals the menopausal years as a most tumultuous interval. Hormonal changes account for many dermatoses not seen in older women. Vulvar problems that commonly affect the adolescent are discussed in reference to the pathophysiology which may induce these changes. The hormonal milium at this time period is emphasized. A concise grouping of disease processes, as well as a description, clue to diagnosis, and treatment of each entity is presented.