Artificial intelligence model for enhancing the accuracy of transvaginal ultrasound in detecting endometrial cancer and endometrial atypical hyperplasia.

OBJECTIVES: Transvaginal ultrasound is typically the initial diagnostic approach in patients with postmenopausal bleeding for detecting endometrial atypical hyperplasia/cancer. Although transvaginal ultrasound demonstrates notable sensitivity, its specificity remains limited. The objective of this study was to enhance the diagnostic accuracy of transvaginal ultrasound through the integration of artificial intelligence. By using transvaginal ultrasound images, we aimed to develop an artificial intelligence based automated segmentation model and an artificial intelligence based classifier model. METHODS: Patients with postmenopausal bleeding undergoing transvaginal ultrasound and endometrial sampling at Mayo Clinic between 2016 and 2021 were retrospectively included. Manual segmentation of images was performed by four physicians (readers). Patients were classified into cohort A (atypical hyperplasia/cancer) and cohort B (benign) based on the pathologic report of endometrial sampling. A fully automated segmentation model was developed, and the performance of the model in correctly identifying the endometrium was compared with physician made segmentation using similarity metrics. To develop the classifier model, radiomic features were calculated from the manually segmented regions-of-interest. These features were used to train a wide range of machine learning based classifiers. The top performing machine learning classifier was evaluated using a threefold approach, and diagnostic accuracy was assessed through the F1 score and area under the receiver operating characteristic curve (AUC-ROC). RESULTS: 302 patients were included. Automated segmentation-reader agreement was 0.79±0.21 using the Dice coefficient. For the classification task, 92 radiomic features related to pixel texture/shape/intensity were found to be significantly different between cohort A and B. The threefold evaluation of the top performing classifier model showed an AUC-ROC of 0.90 (range 0.88-0.92) on the validation set and 0.88 (range 0.86-0.91) on the hold-out test set. Sensitivity and specificity were 0.87 (range 0.77-0.94) and 0.86 (range 0.81-0.94), respectively. CONCLUSIONS: We trained an artificial intelligence based algorithm to differentiate endometrial atypical hyperplasia/cancer from benign conditions on transvaginal ultrasound images in a population of patients with postmenopausal bleeding.

Understanding the patient experience in nonsurgical management of endometrial cancer and complex atypical hyperplasia due to obesity: A qualitative analysis.

Objectives: Patients with class 3 obesity (BMI ≥ 40) and significant medical comorbidities with complex atypical hyperplasia (CAH) and early-stage endometrial cancer (EC) present challenges in standard surgical management. Progestin therapy is an alternative used for patient-centered reasons, including the desire for uterine preservation or because surgery is not a safe option. Our objective was to gain insights into the patient experience when undergoing this treatment approach. Methods: We identified and recruited patients who received oral or IUD progesterone in the last 5 years for EC or CAH. We conducted semi-structured phone interviews regarding patients' experience with non-surgical management as well as decision-making factors to start progesterone and weight loss. Interviews were audio-recorded and transcriptions were analyzed for common themes. Results: A total of 20 interviews were performed. We enrolled nine patients with CAH, eight with grade 1 EC, and three with grade 2 EC. The majority of patients (18/20) were managed with IUD. We identified the following 5 common themes support in diagnostic workup and long-term outcomes, autonomy in care, thoroughness in counseling, emotional impact of diagnosis, and perception of obesity as a defining identity. Conclusion: The themes identified in the present study highlight the challenges and the stigma these patients face. It also demonstrates areas of opportunity in their counseling and care, which will help to build a more effective therapeutic relationship and ultimately lead to greater adherence in care.

Low-Volume Metastases in Apparent Early-Stage Endometrial Cancer: Prevalence, Clinical Significance, and Future Perspectives.

Endometrial cancer (EC) is the most diagnosed gynecologic malignancy, and its incidence and mortality are increasing. The prognosis is highly dependent on the disease spread. Surgical staging includes retroperitoneal evaluation to detect potential lymph node metastases. In recent years, systematic lymphadenectomy has been replaced by sentinel lymph node (SLN) biopsy and ultrastaging, allowing for the detection of macrometastases, micrometastases, and isolated tumor cells (ITCs). Micrometastases and ITCs have been grouped as low-volume metastases (LVM). The reported prevalence of LVM in studies enrolling more than one thousand patients with apparent early-stage EC ranges from 1.9% to 10.2%. Different rates of LVM are observed when patients are stratified according to disease characteristics and their risk of recurrence. Patients with EC at low risk for recurrence have low rates of LVM, while intermediate- and high-risk patients have a higher likelihood of being diagnosed with nodal metastases, including LVM. Macro- and micrometastases increase the risk of recurrence and cause upstaging, while the clinical significance of ITCs is still uncertain. A recent meta-analysis found that patients with LVM have a higher relative risk of recurrence [1.34 (95% CI: 1.07-1.67)], regardless of adjuvant treatment. In a retrospective study on patients with low-risk EC and no adjuvant treatment, those with ITCs had worse recurrence-free survival compared to node-negative patients (85.1%; CI 95% 73.8-98.2 versus 90.2%; CI 95% 84.9-95.8). However, a difference was no longer observed after the exclusion of cases with lymphovascular space invasion. There is no consensus on adjuvant treatment in ITC patients at otherwise low risk, and their recurrence rate is low. Multi-institutional, prospective studies are warranted to evaluate the clinical significance of ITCs in low-risk patients. Further stratification of patients, considering histopathological and molecular features of the disease, may clarify the role of LVM and especially ITCs in specific contexts.

Incidence of sentinel lymph node metastases in apparent early-stage endometrial cancer: a multicenter observational study.

OBJECTIVE: Ultrastaging is accurate in detecting nodal metastases, but increases costs and may not be necessary in certain low-risk subgroups. In this study we examined the risk of nodal involvement detected by sentinel lymph node (SLN) biopsy in a large population of apparent early-stage endometrial cancer and stratified by histopathologic characteristics. Furthermore, we aimed to identify a subgroup in which ultrastaging may be omitted. METHODS: We retrospectively included patients who underwent SLN (with bilateral mapping and no empty nodal packets on final pathology) ± systematic lymphadenectomy for apparent early-stage endometrial cancer at two referral cancer centers. Lymph node status was determined by SLN only, regardless of non-SLN findings. The incidence of macrometastasis, micrometastasis, and isolated tumor cells (ITC) was measured in the overall population and after stratification by histotype (endometrioid vs serous), myometrial invasion (none, <50%, ≥50%), and grade (G1, G2, G3). RESULTS: Bilateral SLN mapping was accomplished in 1570 patients: 1359 endometrioid and 211 non-endometrioid, of which 117 were serous. The incidence of macrometastasis, micrometastasis, and ITC was 3.8%, 3.4%, and 4.8%, respectively. In patients with endometrioid histology (n=1359) there were 2.9% macrometastases, 3.2% micrometastases, and 5.3% ITC. No macro/micrometastases and only one ITC were found in a subset of 274 patients with low-grade (G1-G2) endometrioid endometrial cancer without myometrial invasion (all <1%). The incidence of micro/macrometastasis was higher, 2.8%, in 708 patients with low-grade endometrioid endometrial cancer invading <50% of the myometrium. In patients with serous histology (n=117), the incidence of macrometastases, micrometastasis, and ITC was 11.1%, 6.0%, and 1.7%, respectively. For serous carcinoma without myometrial invasion (n=36), two patients had micrometastases for an incidence of 5.6%. CONCLUSIONS: Ultrastaging may be safely omitted in patients with low-grade endometrioid endometrial cancer without myometrial invasion. No other subgroups with a risk of nodal metastasis of less than 1% have been identified.

Let go of the myth: safety of indocyanine green for sentinel lymph node mapping in endometrial cancer.

OBJECTIVE: Sentinel lymph node mapping by intracervical indocyanine green injection is the preferred method for surgical staging in endometrial cancer. Adverse reactions to indocyanine green are extremely rare, and information about the safety of this tracer in patients with a history of other allergies, asthma, or comorbidities is limited. We aim to evaluate the rate of adverse reactions to indocyanine green injected during sentinel lymph node mapping in patients with endometrial cancer and review the etiology of such reactions. METHODS: All patients with endometrial cancer undergoing sentinel lymph node mapping with indocyanine green cervical stroma injection at the Mayo Clinic in Rochester, Minnesota between June 2014 and December 2018 were retrospectively evaluated. Any adverse reaction occurring intra-operatively or within 7 days after surgery was identified. A thorough chart review was performed by an allergy specialist physician for any patient with an allergic-type reaction. RESULTS: We included 923 patients of which 565 (61.2%) had a history of allergy to antibiotics, non-steroidal anti-inflammatory drugs (NSAIDs), other medications, and/or environmental exposures. Of 490 patients who had previously received contrast media, 25 (5.1%) had a history of an adverse reaction. No immediate anaphylaxis or other allergic reactions were observed after indocyanine green injection. 10 (1.1%) patients developed a transient skin reaction within 7 days after surgery. None of these patients had a history of contrast media reaction. Based on timing and clinical/peri-operative history of affected patients, it was determined that skin reactions were likely induced by other newly prescribed medications or contact sensitivity, not administration of indocyanine green. CONCLUSION: Indocyanine green injection for sentinel lymph node mapping in patients with endometrial cancer caused no immediate/delayed anaphylactic or other severe allergic reactions. This included patients with a history of other allergies, asthma, and comorbidities. The myth of iodine's relationship to allergic reactions must be refuted to allow indocyanine green use in patients with a history of contrast media or shellfish allergy.

Racial and socioeconomic disparities in adherence to preventive health services for ovarian cancer survivors.

PURPOSE: To examine ovarian cancer survivors' adherence to evidence-based guidelines for preventive health care. METHODS: A case-control, retrospective study of Medicare fee-for-service beneficiaries diagnosed with stage I, II, or III epithelial ovarian cancer from 2001 to 2010 using the Surveillance, Epidemiology, and End Results-Medicare database. Survivors were matched 1:1 to non-cancer controls from the 5% Medicare Beneficiary file on age, race, state of residence, and follow-up time. Receipt of flu vaccination, mammography, and bone density tests were examined in accordance with national guidelines. Adherence was assessed starting 1 year after cancer diagnosis, across 2 years of claims. Interaction with the health care system, including outpatient and cancer surveillance visits, was tested as a potential mechanism for receipt of services. RESULTS: 2437 survivors met the eligibility criteria (mean age, 75; 90% white). Ovarian cancer survivors were more likely to be adherent to flu vaccination (5 percentage points (pp); < 0.001) and mammography guidelines (10 pp.; < 0.001) compared to non-cancer controls, but no differences were found for bone density test guidelines (- 1 pp.; NS). Black women were less likely to be adherent to flu vaccination and bone density tests compared with white women. Women dually eligible for Medicare and Medicaid were less likely to be adherent compared to those without such support. Adherence was not influenced by measures of outpatient visits. CONCLUSION: Ovarian cancer survivors are receiving preventive services with the same or better adherence than their matched counterparts. Minority and dual-eligible survivors received preventive services at a lower rate than white survivors and those with higher income. The number of outpatient visits was not associated with increased preventive health visits. IMPLICATIONS FOR CANCER SURVIVORS: Ovarian cancer survivors are receiving adequate follow-up care to be adherent to preventive health measures. Efforts to improve care coordination post-treatment may help reduce minority and low SES disparities.

MicroRNA-205 promotes cell invasion by repressing TCF21 in human ovarian cancer.

BACKGROUND: Ovarian cancer is the leading lethal, gynecological malignancy in the United States. No doubt, the continued morbidity and mortality of ovarian cancer reflects a poor understanding of invasive mechanisms. Recent studies reveal that ovarian cancers express aberrant microRNAs (miRNAs or miRs), some of which have oncogenic or tumor suppressor properties. Several studies suggested that miR-205 is involved in tumorigenesis. Presently, we investigate the molecular mechanisms and target of miR-205 in ovarian cancer. METHODS: Quantitative real-time polymerase chain reaction and western blot were performed to assess miR-205 and transcription factor 21 (TCF21) expression in ovarian cancer and normal ovary samples. The effect of miR-205 on TCF21 was determined by luciferase reporter assay and western blot. The effect of miR-205 and TCF21 on cell invasion was quantitated using transwell invasion assay. RESULT: miR-205 expression was increased in ovarian cancer and it promoted the invasive behavior of ovarian cancer cell lines (OVCAR-5, OVCAR-8 and SKOV-3). miR-205 directly targeted TCF21, which was significantly decreased in ovarian cancer tissue. miR-205 inhibited TCF21 expression and as a consequence blunted the inhibitory effect of TCF21 on cell invasion. Matrix Metalloproteinases (MMPs) play an important role in cancer invasion and metastasis. TCF21 inhibited MMP-2 and MMP-10 and decreased ovarian cancer cell invasion. Co-transfection of TCF21 expression plasmid with miR-205 mimic diminished the inhibitory effect of TCF21 on MMP-2 and MMP-10 in ovarian cancer cells. CONCLUSION: miR-205 appears to have an important role in the spread of ovarian cancer by targeting TCF21. These findings offer a new mechanism of ovarian cancer tumorigenesis, which could be useful for the development of new therapeutic approaches to ovarian cancer treatment.

Comparison of postoperative venous thromboembolism incidence in gastrointestinal and gynecologic solid tumors.

INTRODUCTION: Studies have shown the benefit of 28days of extended postoperative venous thromboembolism (VTE) prophylaxis for patients undergoing major cancer surgery in the abdomen or pelvis. We retrospectively evaluated the VTE incidence at the University of Kansas Hospital between gynecologic (GYN) cancer patients, who receive extended prophylaxis, and gastrointestinal (GI) cancer patients, who do not. METHODS: Patients were evaluated between January of 2010 and December of 2013, and VTE data for eligible patients were collected for 30 and 90days postoperatively. RESULTS: The study population composed of 190 GYN and 204 GI patients. Colon and endometrial cancers were the most common diagnoses. For GYN and GI patients respectively, VTE occurred in 4.2% and 5.4% at 30days (p=0.584) and 7.4% and 7.8% at 90days (p=0.514). One VTE-related death occurred in the GI group. GI patients underwent more open surgeries, 77.9% versus 66.3% (p=0.010) and had longer postoperative hospital stay, median of 7 versus 4days (p<0.0001). Out of all cancer patients combined, 40% versus 17.9% had stage IV disease and 10.2% versus 0.9% had open surgery in the VTE and non-VTE groups, respectively. CONCLUSIONS: There were no significant differences in overall VTE incidence between the two patient groups at 30 and 90days postoperatively. A majority of VTEs occurred in stage IV patients and patients who underwent open surgeries regardless of diagnosis.

Analysis of outcomes of microinvasive adenocarcinoma of the uterine cervix by treatment type.

OBJECTIVE: To estimate the risk of metastatic disease in microinvasive adenocarcinoma of the cervix in a large cohort. METHODS: Thirty-six cases were identified from the Mayo Clinic health information database, and 30 cases were identified using the University of Southern California gynecologic oncology patient database. Histopathology was reviewed by a single pathologist at each institution to confirm histologic subtype and grade of tumor, depth of invasion, linear extent of the tumor, the presence or absence of lymphovascular space invasion, margin status, parametrial involvement, and the presence of nodal metastasis. RESULTS: Fifty-two patients had stage IA1 cancers and 14 had stage IA2 cancers. Therapy ranged from cold knife conization to radical hysterectomy with lymphadenectomy. No parametrial involvement was noted in any of the patients who underwent parametrial resection. One patient with stage IA1 cancer had micrometastasis to a pelvic lymph node. No recurrences were noted with an average follow-up of 80 months. CONCLUSION: The management of microinvasive adenocarcinoma remains controversial, and radical therapy is applied more frequently to microinvasive adenocarcinoma than microinvasive squamous cell carcinoma of the cervix. The risk of extracervical disease is low and the risk of recurrence is not affected by the radicality of resection. Our data suggest that microinvasive adenocarcinoma is amenable to treatment with nonradical surgery. LEVEL OF EVIDENCE: III.

Ataxia telangiectasia and rad3-related kinase contributes to cell cycle arrest and survival after cisplatin but not oxaliplatin.

The DNA cross-linking agents cisplatin and oxaliplatin are widely used in the treatment of human cancer. Lesions produced by these agents are widely known to activate the G1 and G2 cell cycle checkpoints. Less is known about the role of the intra-S-phase checkpoint in the response to these agents. In the present study, two different cell lines expressing a dominant-negative kinase dead (kd) version of the ataxia telangiectasia and rad3-related (ATR) kinase in an inducible fashion were examined for their responses to these two platinating agents and a variety of other DNA cross-linking drugs. The expression of the kdATR allele markedly sensitized the cells to cisplatin, but not to oxaliplatin, as assessed by inhibition of colony formation, induction of apoptosis, and cell cycle analysis. Similar differences in survival were noted for melphalan (ATR dependent) and 4-hydroperoxycyclophosphamide (ATR independent). Further experiments showed that ATR function is not necessary for removal of Pt-DNA adducts. The predominant difference between the responses to the two platinum drugs was the presence of a drug-specific ATR-dependent S-phase arrest after cisplatin but not oxaliplatin. These results indicate that involvement of ATR in the response to DNA cross-linking agents is lesion specific. This observation might need to be taken into account in the development and use of ATR or Chk1 inhibitors.