Endometrial Pipelle Biopsy Computer-Aided Diagnosis: A Feasibility Study.

Endometrial biopsies are important in the diagnostic workup of women who present with abnormal uterine bleeding or hereditary risk of endometrial cancer. In general, approximately 10% of all endometrial biopsies demonstrate endometrial (pre)malignancy that requires specific treatment. As the diagnostic evaluation of mostly benign cases results in a substantial workload for pathologists, artificial intelligence (AI)-assisted preselection of biopsies could optimize the workflow. This study aimed to assess the feasibility of AI-assisted diagnosis for endometrial biopsies (endometrial Pipelle biopsy computer-aided diagnosis), trained on daily-practice whole-slide images instead of highly selected images. Endometrial biopsies were classified into 6 clinically relevant categories defined as follows: nonrepresentative, normal, nonneoplastic, hyperplasia without atypia, hyperplasia with atypia, and malignant. The agreement among 15 pathologists, within these classifications, was evaluated in 91 endometrial biopsies. Next, an algorithm (trained on a total of 2819 endometrial biopsies) rated the same 91 cases, and we compared its performance using the pathologist's classification as the reference standard. The interrater reliability among pathologists was moderate with a mean Cohen's kappa of 0.51, whereas for a binary classification into benign vs (pre)malignant, the agreement was substantial with a mean Cohen's kappa of 0.66. The AI algorithm performed slightly worse for the 6 categories with a moderate Cohen's kappa of 0.43 but was comparable for the binary classification with a substantial Cohen's kappa of 0.65. AI-assisted diagnosis of endometrial biopsies was demonstrated to be feasible in discriminating between benign and (pre)malignant endometrial tissues, even when trained on unselected cases. Endometrial premalignancies remain challenging for both pathologists and AI algorithms. Future steps to improve reliability of the diagnosis are needed to achieve a more refined AI-assisted diagnostic solution for endometrial biopsies that covers both premalignant and malignant diagnoses.

Confocal laser microscopy for assessment of surgical margins during radical prostatectomy.

OBJECTIVE: To evaluate the feasibility of confocal laser microscopy (CLM) for intraoperative margin assessment as faster alternative to neurovascular structure-adjacent frozen-section examination (NeuroSAFE) during robot-assisted radical prostatectomy (RARP). PATIENTS AND METHODS: Surgical margins were assessed during 50 RARP procedures in patients scheduled for NeuroSAFE. Posterolateral sections were cut and imaged with CLM and further processed to conform with the NeuroSAFE protocol. Secondary resection (SR) was performed in case a positive surgical margin (PSM) was observed with NeuroSAFE. Afterwards, the CLM images were non-blinded assessed for the presence of PSMs. The accuracy of both NeuroSAFE and CLM was compared with conventional histopathology. Agreement for detection of PSMs between NeuroSAFE and CLM was evaluated with Cohen's kappa coefficient. Procedure times were compared with a Wilcoxon signed-ranks test. RESULTS: In total, 96 posterolateral sections of RP specimens were evaluated for the presence of PSMs. CLM identified 15 (16%) PSMs and NeuroSAFE identified 14 (15%) PSMs. CLM had a calculated sensitivity, specificity, positive predictive value and negative predictive value of 86%, 96%, 80% and 98% respectively for the detection of PSMs compared to definite pathology. After SR, residual tumour was found in six of 13 cases (46%), which were all identified by both techniques. There was a substantial level of agreement between CLM and NeuroSAFE (κ = 0.80). The median procedure time for CLM was significantly shorter compared to NeuroSAFE (8 vs 50 min, P < 0.001). The main limitation of this study was the non-blinded assessment of the CLM images. CONCLUSIONS: Compared to NeuroSAFE, CLM is a promising technique for intraoperative margin assessment and is able to reduce the time of intraoperative margin assessment.

Measuring the depth of invasion in vulvar squamous cell carcinoma: interobserver agreement and pitfalls.

AIMS: The depth of invasion is an important prognostic factor for patients with vulvar squamous cell carcinoma (SCC). The threshold of 1 mm distinguishes between FIGO stages IA and ≥IB disease and guides the need for groin surgery. Therefore, high interobserver agreement is crucial. The conventional and the alternative method are described to measure the depth of invasion. The aims of this study were to assess interobserver agreement for classifying the depth of invasion using both methods and to identify pitfalls. METHODS AND RESULTS: Fifty slides of vulvar SCC with a depth of invasion approximately 1 mm were selected, digitally scanned and independently assessed by 10 pathologists working in a referral or oncology centre and four pathologists in training. The depth of invasion was measured using both the conventional and alternative method in each slide and categorised into ≤1 and >1 mm. The percentage of agreement and Light's kappa for multi-rater agreement were calculated, and 95% confidence intervals were calculated by bootstrapping (1000 runs). The agreement using the conventional method was moderate (κ = 0.57, 95% confidence interval = 0.45-0.68). The percentage of agreement among the participating pathologists using the conventional method was 85.0% versus 89.4% using the alternative method. Six pitfalls were identified: disagreement concerning which invasive nest is deepest, recognition of invasive growth and where it starts, curved surface, carcinoma situated on the edge of the tissue block, ulceration and different measurement methods. CONCLUSIONS: Pathologists reached only moderate agreement in determining the depth of invasion in vulvar SCC, without a notable difference between the two measurement methods.

Cervical cytology in serous and endometrioid endometrial cancer.

The aim of this study was to determine the frequency of abnormal cervical cytology in preoperative cervical cytology of patients diagnosed with uterine papillary serous carcinoma (UPSC) and endometrioid endometrial carcinoma (EEC). In addition, associations between abnormal cervical cytology and clinicopathologic factors were evaluated. In this multicentre study, EEC patients diagnosed at two hospitals from 1999 to 2009 and UPSC patients diagnosed at five hospitals from 1992 to 2009, were included. Revision of the histologic slides was performed systematically and independently by 3 gynecopathologists. Cervical cytology within six months before histopathologic diagnosis of endometrial carcinoma was available for 267 EEC and 80 UPSC patients. Cervical cytology with atypical, malignant, or normal endometrial cells in postmenopausal women was considered as abnormal cytology, specific for endometrial pathology. Abnormal cervical cytology was found in 87.5% of UPSC patients, compared with 37.8% in EEC patients. In UPSC, abnormal cytology was associated with extrauterine spread of disease (P=0.043). In EEC, abnormal cytology was associated with cervical involvement (P=0.034). In both EEC and UPSC patients, abnormal cervical cytology was not associated with survival. In conclusion, abnormal cervical cytology was more frequently found in UPSC patients. It was associated with extrauterine disease in UPSC patients, and with cervical involvement in EEC patients. More prospective research should be performed to assess the true clinical value of preoperative cervical cytology in endometrial cancer patients.

Pure compared with mixed serous endometrial carcinoma: two different entities?

OBJECTIVE: To analyze whether mixed compared with pure uterine papillary serous carcinoma histology affects clinical outcome, and to assess uterine papillary serous carcinoma for its association with the precursor lesion endometrial intraepithelial carcinoma. METHODS: A multi-institution observational study of stage I-IV uterine papillary serous carcinoma patients was performed. Histopathologic slides were reviewed by four expert pathologists, with determination of the percentage serous histology within each tumor. The pre-existent endometrium was evaluated for the presence of endometrial intraepithelial carcinoma. RESULTS: We included 108 uterine papillary serous carcinoma patients. Fifty-eight patients had mixed and 50 patients had pure uterine papillary serous carcinoma histology. On multivariable analysis, advanced International Federation of Gynecology and Obstetrics (FIGO) stage (hazard ratio [HR] 3.15, 95% confidence interval [CI] 1.57-6.32), mixed uterine papillary serous carcinoma histology (HR 0.35, 95% CI 0.19-0.66), and lymphovascular space invasion (HR 2.10, 95% CI 1.07-4.16) were significantly associated with recurrence. International Federation of Gynecology and Obstetrics stage (HR 4.67, 95% CI 2.25-9.70) and mixed uterine papillary serous carcinoma histology (HR 0.39, 95% CI 0.20-0.76) were significantly and independently associated with survival. Endometrial intraepithelial carcinoma was identified in 83.9% of all cases, with no significant difference between mixed and pure uterine papillary serous carcinoma patients. Atrophic or weakly proliferative endometrium was found in 90.7% of pure uterine papillary serous carcinoma cases, whereas hyperplastic endometrium with atypia was more commonly found in 34.7% of mixed carcinoma patients with uterine papillary serous carcinoma (P=.004). CONCLUSION: Pure uterine papillary serous carcinoma histology and FIGO stage are the most important risk factors for recurrence and survival in patients with uterine papillary serous carcinoma. Adjusted for covariates, patients with pure uterine papillary serous carcinoma had a 2.9-times greater risk for recurrence and a 2.6-times higher risk of death compared with patients with mixed uterine papillary serous carcinoma. Furthermore, endometrial intraepithelial carcinoma was equally found among pure and mixed uterine papillary serous carcinoma cases, whereas the nonneoplastic endometrium was atrophic or weakly proliferative in pure uterine papillary serous carcinoma cases compared with more hyperplastic endometrium with atypia in mixed uterine papillary serous carcinoma cases.