Validation of a deep neural network-based algorithm supporting clinical management of adnexal mass.

Background: Conservative management of adnexal mass is warranted when there is imaging-based and clinical evidence of benign characteristics. Malignancy risk is, however, a concern due to the mortality rate of ovarian cancer. Malignancy occurs in 10-15% of adnexal masses that go to surgery, whereas the rate of malignancy is much lower in masses clinically characterized as benign or indeterminate. Additional diagnostic tests could assist conservative management of these patients. Here we report the clinical validation of OvaWatch, a multivariate index assay, with real-world evidence of performance that supports conservative management of adnexal masses. Methods: OvaWatch utilizes a previously characterized neural network-based algorithm combining serum biomarkers and clinical covariates and was used to examine malignancy risk in prospective and retrospective samples of patients with an adnexal mass. Retrospective data sets were assembled from previous studies using patients who had adnexal mass and were scheduled for surgery. The prospective study was a multi-center trial of women with adnexal mass as identified on clinical examination and indeterminate or asymptomatic by imaging. The performance to detect ovarian malignancy was evaluated at a previously validated score threshold. Results: In retrospective, low prevalence (N = 1,453, 1.5% malignancy rate) data from patients that received an independent physician assessment of benign, OvaWatch has a sensitivity of 81.8% [95% confidence interval (CI) 65.1-92.7] for identifying a histologically confirmed malignancy, and a negative predictive value (NPV) of 99.7%. OvaWatch identified 18/22 malignancies missed by physician assessment. A prospective data set had 501 patients where 106 patients with adnexal mass went for surgery. The prevalence was 2% (10 malignancies). The sensitivity of OvaWatch for malignancy was 40% (95% CI: 16.8-68.7%), and the specificity was 87% (95% CI: 83.7-89.7) when patients were included in the analysis who did not go to surgery and were evaluated as benign. The NPV remained 98.6% (95% CI: 97.0-99.4%). An independent analysis set with a high prevalence (45.8%) the NPV value was 87.8% (95% CI: 95% CI: 75.8-94.3%). Conclusion: OvaWatch demonstrated high NPV across diverse data sets and promises utility as an effective diagnostic test supporting management of suspected benign or indeterminate mass to safely decrease or delay unnecessary surgeries.

Analytical Validation of a Deep Neural Network Algorithm for the Detection of Ovarian Cancer.

PURPOSE: Early detection of ovarian cancer, the deadliest gynecologic cancer, is crucial for reducing mortality. Current noninvasive risk assessment measures include protein biomarkers in combination with other clinical factors, which vary in their accuracy. Machine learning can be applied to optimizing the combination of these features, leading to more accurate assessment of malignancy. However, the low prevalence of the disease can make rigorous validation of these tests challenging and can result in unbalanced performance. METHODS: MIA3G is a deep feedforward neural network for ovarian cancer risk assessment, using seven protein biomarkers along with age and menopausal status as input features. The algorithm was developed on a heterogenous data set of 1,067 serum specimens from women with adnexal masses (prevalence = 31.8%). It was subsequently validated on a cohort almost twice that size (N = 2,000). RESULTS: In the analytical validation data set (prevalence = 4.9%), MIA3G demonstrated a sensitivity of 89.8% and a specificity of 84.02%. The positive predictive value was 22.45%, and the negative predictive value was 99.38%. When stratified by cancer type and stage, MIA3G achieved sensitivities of 94.94% for epithelial ovarian cancer, 76.92% for early-stage cancer, and 98.04% for late-stage cancer. CONCLUSION: The balanced performance of MIA3G leads to a high sensitivity and high specificity, a combination that may be clinically useful for providers in evaluating the appropriate management strategy for their patients. Limitations of this work include the largely retrospective nature of the data set and the unequal, albeit random, assignment of histologic subtypes between the training and validation data sets. Future directions may include the addition of new biomarkers or other modalities to strengthen the performance of the algorithm.

Salvaging Detection of Early-Stage Ovarian Malignancies When CA125 Is Not Informative.

BACKGROUND: Ovarian cancer is the deadliest gynecologic cancer, with no recommended screening test to assist with early detection. Cancer antigen 125 (CA125) is a serum biomarker commonly used by clinicians to assess preoperative cancer risk, but it underperforms in premenopausal women, early-stage malignancies, and several histologic subtypes. OVA1 is a multivariate index assay that combines CA125 and four other serum proteins to assess the malignant risk of an adnexal mass. OBJECTIVE: To evaluate the performance of OVA1 in a cohort of patients with low-risk serum CA125 values. STUDY DESIGN: We analyzed patient data from previous collections (N = 2305, prevalence = 4.5%) where CA125 levels were at or below 67 units/milliliter (U/mL) for pre-menopausal women and 35 U/mL for post-menopausal women. We compare the performance of OVA1 to CA125 in classifying the risk of malignancy in this cohort, including sensitivity, specificity, positive and negative predictive values. RESULTS: The overall sensitivity of OVA1 in patients with a low-risk serum CA125 was 59% with a false-positive rate of 30%. OVA1 detected over 50% of ovarian malignancies in premenopausal women despite a low-risk serum CA125. OVA1 also correctly identified 63% of early-stage cancers missed by CA125. The most common epithelial ovarian cancer subtypes in the study population were mucinous (25%) and serous (23%) carcinomas. Despite a low-risk CA125, OVA1 successfully detected 83% of serous, 58% of mucinous, and 50% of clear cell ovarian cancers. CONCLUSIONS: As a standalone test, CA125 misses a significant number of ovarian malignancies that can be detected by OVA1. This is particularly important for premenopausal women and early-stage cancers, which have a much better long-term survival than late-stage malignancies. Using OVA1 in the setting of a normal serum CA125 can help identify at-risk ovarian tumors for referral to a gynecologic oncologist, potentially improving overall survival.

Low-risk multivariate index assay scores, physician referral and surgical choices in women with adnexal masses.

OBJECTIVE: To assess the use of Multivariate Index Assay (MIA OVA1) by gynecologists and determine referral practices and surgical decision making for women with adnexal masses and low-risk MIA OVA1 scores. METHODS: Information on patients who received an OVA1 test was collected retrospectively from 22 gynecologic practices through a chart review. Referral patterns were examined for patients with low-risk OVA1 results prior to first surgical intervention. Chart reviews were from a variety of practice and hospital settings representing major geographic regions within the United States. RESULTS: A total of 282 independent patient charts were reviewed. Low-risk results were found for 146 patients (52%). Surgery was performed on 82 (56%) patients with low-risk scores. The referral rate to specialty care was 21% (17/82) for low-risk OVA1 patients. Three low-malignant potential tumors were identified in the low-risk patients, with no cases of invasive malignancy. Eighty-six percent of the surgeries performed on low-risk OVA1 patients were minimally invasive. In 44% of the low-risk OVA1 patients, no surgical intervention was performed. CONCLUSIONS: A high proportion of low-risk OVA1 patients were not referred to a gynecologic oncologist prior to surgery, indicating gynecologists may use MIA OVA1 along with clinical and radiographic findings to appropriately retain patients for their care. This practice is safe and may be cost-saving, with patient satisfaction implications.

Insights from HuR biology point to potential improvement for second-line ovarian cancer therapy.

This retrospective study aimed to investigate the role that an RNA-binding protein, HuR, plays in the response of high-grade serous ovarian tumors to chemotherapeutics. We immunohistochemically stained sections of 31 surgically-debulked chemo-naïve ovarian tumors for HuR and scored the degree of HuR cytoplasmic staining. We found no correlation between HuR intracellular localization in tumor sections and progression free survival (PFS) of these patients, 29 of whom underwent second-line gemcitabine/platin combination therapy for recurrent disease. Ribonucleoprotein immunoprecipitation (RNP-IP) analysis of ovarian cancer cells in culture showed that cytoplasmic HuR increases deoxycytidine kinase (dCK), a metabolic enzyme that activates gemcitabine. The effects of carboplatin treatment on HuR and WEE1 (a mitotic inhibitor) expression, and on cell cycle kinetics, were also examined. Treatment of ovarian cancer cells with carboplatin results in increased HuR cytoplasmic expression and elevated WEE1 expression, arresting cell cycle G2/M transition. This may explain why HuR cytoplasmic localization in chemo-naïve tumors is not predictive of therapeutic response and PFS following second-line gemcitabine/platin combination therapy. These results suggest treatment of recurrent ovarian tumors with a combination of gemcitabine, carboplatin, and a WEE1 inhibitor may be potentially advantageous as compared to current clinical practices.

Recommendations for a national agenda to substantially reduce cervical cancer.

PURPOSE: Prophylactic human papillomavirus (HPV) vaccines and new HPV screening tests, combined with traditional Pap test screening, provide an unprecedented opportunity to greatly reduce cervical cancer in the USA. Despite these advances, thousands of women continue to be diagnosed with and die of this highly preventable disease each year. This paper describes the initiatives and recommendations of national cervical cancer experts toward preventing and possibly eliminating this disease. METHODS: In May 2011, Cervical Cancer-Free America, a national initiative, convened a cervical cancer summit in Washington, DC. Over 120 experts from the public and private sector met to develop a national agenda for reducing cervical cancer morbidity and mortality in the USA. RESULTS: Summit participants evaluated four broad challenges to reducing cervical cancer: (1) low use of HPV vaccines, (2) low use of cervical cancer screening, (3) screening errors, and (4) lack of continuity of care for women diagnosed with cervical cancer. The summit offered 12 concrete recommendations to guide future national and local efforts toward this goal. CONCLUSIONS: Cervical cancer incidence and mortality can be greatly reduced by better deploying existing methods and systems. The challenge lies in ensuring that the array of available prevention options are accessible and utilized by all age-appropriate women-particularly minority and underserved women who are disproportionately affected by this disease. The consensus was that cervical cancer can be greatly reduced and that prevention efforts can lead the way towards a dramatic reduction in this preventable disease in our country.

Posthysterectomy cytology screening: indications and clinical implications.

OBJECTIVE: To review the results of patients who were referred for posthysterectomy of abnormal cytology based on screening indications. MATERIALS AND METHODS: We performed a retrospective review of 64 patients who have been referred for posthysterectomy vaginal colposcopy to the gynecologic oncology service. Patients' demographics, clinical features, reason for screening, and final diagnosis were recorded. Patients were divided into 2 groups based on posthysterectomy screening guidelines. Group A was considered to have undergone unnecessary screening based on national guidelines, and group B had risk factors that appropriately called for continued surveillance. The number of colposcopic examinations and the incidence of neoplasia were recorded for each group. RESULTS: The mean age of the patients was 65 years (range = 35-95 y). Group A included 22 patients with history of abnormal cytology posthysterectomy for benign disease. Of the 22 abnormal cytology results, 21 were low-grade squamous intraepithelial lesion (n = 14) or atypical squamous cells of undetermined significance (n = 7) with 1 high-grade squamous intraepithelial lesion. After referral and colposcopy of this group, no neoplasia was found. Group B included 42 total patients. Of these 42 patients, 20 (48%) had a history of cervical intraepithelial neoplasia, 12 (28%) had a history of vaginal intraepithelial neoplasia, 6 (14%) had history of cervical cancer, 2 (5%) had history of diethylstilbestrol exposure, and 2 (5%) had a history of radiation therapy. In group B, 8 (9%) and 1 (2%) of the patients had vaginal intraepithelial neoplasia 2/3 and squamous cell carcinoma, respectively. CONCLUSIONS: Current national guidelines are appropriate. Adherence to these guidelines will decrease intervention and not affect the detection of vaginal neoplasia. Patients with risk factors for lower genital tract neoplasia warrant continued screening after hysterectomy.

Reducing excessive toxicity in ovarian cancer treatment: a personalized approach.

The management of ovarian cancer is not only multifactorial, but also patient-specific. Different treatment modalities lead to varying levels of toxicity and individual patient responses, necessitating a personalized approach to each treatment plan. Surgical treatment along with first-line and salvage chemotherapies, are standard modalities but recent innovations in chemotherapy delivery and innovative therapy with mechanism of action are reviewed in this article. Extensive experience with standard chemotherapy has outlined algorithms for managing various toxicities. The focus of treatment may ultimately point towards palliative care and clinicians must be comfortable and well versed in addressing this important option. Overall, management of ovarian cancer requires a multi-faceted approach, keeping the patients' overall health, curative goals and well-being at the forefront. It is nearly impossible to detail exact management plans for every possible toxicity for every patient; formulating personalized treatment plans should be based on evidence and clinician experience, all part of the art of medicine. The objective of this article is to highlight the most frequently encountered and most limiting toxicities of current standard therapies for epithelial ovarian cancer.

Endometrial cancer surgery costs: robot vs laparoscopy.

STUDY OBJECTIVE: To compare surgical costs for endometrial cancer staging between robotic-assisted and traditional laparoscopic methods. DESIGN: Retrospective chart review from November 2005 to July 2006 (Canadian Task Force classification II-3). SETTING: Non-university-affiliated teaching hospital. PATIENTS: Thirty-three women with diagnosed endometrial cancer undergoing hysterectomy, bilateral salpingo-oophorectomy, and pelvic and paraaortic lymph node resection. INTERVENTIONS: Patients underwent either robotic or traditional laparoscopic surgery without randomization. MEASUREMENTS AND MAIN RESULTS: Hospital cost data were obtained for operating room time, instrument use, and disposable items from hospital billing records and provided by the finance department. Separate overall hospital stay costs were also obtained. Mean operative costs were higher for robotic procedures ($3323 vs $2029; p<.001), due in part to longer operating room time ($1549 vs $1335; p=.03). The more significant cost difference was due to disposable instrumentation ($1755 vs $672; p<.001). Total hospital costs were also higher for robotic-assisted procedures ($5084 vs $ 3615; p=.002). CONCLUSION: Robotic surgery costs were significantly higher than traditional laparoscopy costs for staging of endometrial cancer in this small cohort of patients.

Treatment of recurrent endometrial stromal sarcoma with letrozole: a case report and literature review.

Endometrial stromal sarcomas are rare tumors that recur long after initial excision. We report a case of recurrent endometrial stromal sarcoma treated with the aromatase inhibitor letrozole and an overview of research completed to date. A 59-year-old female presented with new abdominal onset pain, fatigue, and nausea. She had a computed tomography that showed a pelvic mass, an enlarged right internal iliac lymph node, an atypical liver hemangioma, and a severe left hydronephrosis. The patient underwent an exploratory laparotomy, and attempted surgical resection of the pelvic mass was attempted. Pathology was consistent with recurrent endometrial stromal sarcoma. Since these tumors are hormonally sensitive, the patient was started on letrozole 2.5 mg daily. The patient had complete clinical and radiographic response by 11 months. After 24 months of therapy, the patient remained free of disease. Endometrial stromal sarcomas are hormonally sensitive tumors. Progestins function to decrease the effects of estrogen on target cells and have been used for primary therapy of endometrial stromal sarcomas. Aromatase inhibitors block peripheral synthesis of estrogen. Letrozole is a type 2 aromatase inhibitor that effectively reduces serum estrogen levels. Letrozole has been described as treatment for endometrial stromal sarcoma. Letrozole is well tolerated and is a good option for long-term management of this disease.

Interpretability of excisional biopsies of the cervix: cone biopsy and loop excision.

OBJECTIVE: To compare the results of cold knife conization (CKC) and loop electrosurgical excision procedure (LEEP) for cervical intraepithelial neoplasia to determine if excisional method has effects on pathologic interpretation. METHODS: Retrospective review of the perioperative medical records of patients who had a CKC and electrosurgical loop excision of cervix. Patients selected had either primary treatment for cervical intraepithelial neoplasia, suspected invasion, glandular abnormalities or discordant cytology. RESULTS: Among the eligible patients, 61 had CKC and 96 had LEEP. Overall, CKC specimens had interpretable surgical margins more frequently than LEEP (95% vs 85%); however, it was not statistically significant (p=.1). Margins were less likely to be involved with neoplasia in CKC specimens (16% vs 38%; p=.005). Loop electrosurgical excision procedure specimens were less likely to yield a single intact specimen (1.1 vs 1.9; p=.000). Logistic regression showed a significant effect of specimen number (p=.04) on interpretability. CONCLUSION: Current American Society for Colposcopy and Cervical Pathology (ASCCP) guidelines for diagnostic excisional procedure used for glandular lesions suggest that the procedure provides "an intact specimen with interpretable margins." Loop electrosurgical excision procedure in the current study was associated with an increased number of specimens that limited interpretability and an increased number of positive margins. Cold knife conization is preferred in cases where margin status is critical, such as glandular lesions and suspected microinvasion. If LEEP is performed, clinicians should attempt to obtain a single surgical specimen maximizing the pathologic interpretation and disease-free margins.

Management of atypical glandular cells and adenocarcinoma in situ.

Glandular abnormalities of the cervix remain a difficult clinical problem. It is a challenge for the clinician to manage and follow this unusual cytologic finding properly. This article highlights the definitions of glandular abnormalities, reviews current published guidelines for clinical management, and discusses the underlying rates of neoplasia associated with these cytology reports. It reviews proper follow-up of patients found not to have neoplasia and current treatment options for patients who have significant neoplasia. It also discusses the diagnosis of associated endometrial lesions and the use of human papillomavirus DNA testing in the management of glandular lesions of the lower genital tract.

A review of topotecan in combination chemotherapy for advanced cervical cancer.

Treatment of advanced, recurrent or persistent cervical cancer includes radiotherapy and chemotherapy. Radiation has been the primary treatment modality for locoregionally advanced cervical cancer. Concomitant systemic cisplatin chemotherapy and radiation have shown high response rates with improvements in durable remissions and overall survival. Cisplatin has been the standard medication for the treatment of advanced cervical cancer. Combinations with other chemotherapeutic agents have been the subject of clinical trials with varying results. The toxicity of combination chemotherapy and tolerability of patients are other factors that should be considered in the management of patients with advanced disease. Recently topotecan, in combination with cisplatin, achieved increased response and overall survival rates without further compromising the patients' quality of life. This review focuses on the mechanism of action and toxicities of topotecan, as well as its role as a radio-sensitizer and chemotherapeutic agent in the management of advanced, recurrent, or persistent cervical cancer. Other combination modalities and dosages are also discussed.

Acceptance of human papillomavirus vaccine by gynecologists in an urban setting.

OBJECTIVE: To determine the percentage of patients vaccinated per individual provider and to document attitudes and reasons for the acceptance of the human papillomavirus vaccine. METHODS: Computerized records were reviewed for individual practitioners in an urban department of obstetrics and gynecology to determine vaccination rates. Questionnaires filled out by practitioners were used to assess individual attitudes and reasons for the unequal distribution of vaccination. RESULTS: Overall vaccination rate was 28% (range 6%-55.8%) for the initial 3-month period when the vaccine became available. Barriers to acceptance included patient concerns, provider concerns over safety, and provider concerns over cost. Experience in practice and self-described attitudes toward early acceptance of new medication were not predictive. CONCLUSIONS: Early acceptance of human papillomavirus vaccination was provider dependent and was not related to provider experience or attitude. Concerns over cost and safety may be barriers to increasing vaccination rates by gynecologists.

2006 consensus guidelines for the management of women with cervical intraepithelial neoplasia or adenocarcinoma in situ.

A group of 146 experts representing 29 organizations and professional societies met Sept. 18-19, 2006, in Bethesda, MD, to develop revised evidence-based, consensus guidelines for managing women with abnormal cervical cancer screening tests. The management of low-grade cervical intraepithelial neoplasia (CIN) grade 1 has been modified significantly. Previously, management depended on whether colposcopy was satisfactory and treatment using ablative or excisional was acceptable for all women with CIN 1. In the new guidelines, cytological follow-up is the only recommended management option for women with CIN 1 who have low-grade referral cervical cytology, regardless of whether the colposcopic examination is satisfactory. Treatment is particularly discouraged in adolescents. The basic management of women in the general population with CIN 2,3 underwent only minor modifications, but options for the conservative management of adolescents with CIN 2,3 have been expanded. Moreover, management recommendations for women with biopsy-confirmed adenocarcinoma in situ are now included.

2006 consensus guidelines for the management of women with abnormal cervical cancer screening tests.

A group of 146 experts representing 29 organizations and professional societies met September 18-19, 2006, in Bethesda, MD, to develop revised evidence-based, consensus guidelines for managing women with abnormal cervical cancer screening tests. Recommendations for managing atypical squamous cells of undetermined significance and low-grade squamous intraepithelial lesion (LSIL) are essentially unchanged. Changes were made for managing these conditions in adolescents for whom cytological follow-up for 2 years was approved. Recommendations for managing high-grade squamous intraepithelial lesion (HSIL) and atypical glandular cells (AGC) also underwent only minor modifications. More emphasis is placed on immediate screen-and-treat approaches for HSIL. Human papillomavirus (HPV) testing is incorporated into the management of AGC after their initial evaluation with colposcopy and endometrial sampling. The 2004 Interim Guidance for HPV testing as an adjunct to cervical cytology for screening in women 30 years of age and older was formally adopted with only very minor modifications.