Pros and cons of artificial intelligence implementation in diagnostic pathology.

The rapid introduction of digital pathology has greatly facilitated development of artificial intelligence (AI) models in pathology that have shown great promise in assisting morphological diagnostics and quantitation of therapeutic targets. We are now at a tipping point where companies have started to bring algorithms to the market, and questions arise whether the pathology community is ready to implement AI in routine workflow. However, concerns also arise about the use of AI in pathology. This article reviews the pros and cons of introducing AI in diagnostic pathology.

The Diagnostic Value of microRNA Expression Analysis in Detecting Intraductal Papillomas in Patients with Pathological Nipple Discharge.

Patients with pathological nipple discharge (PND) often undergo local surgical procedures because standard radiologic imaging fails to identify the underlying cause. MicroRNA (MiRNA) expression analysis of nipple fluid holds potential for distinguishing between breast diseases. This study aimed to compare miRNA expression levels between nipple fluids from patients with PND to identify possible relevant miRNAs that could differentiate between intraductal papillomas and no abnormalities in the breast tissue. Nipple fluid samples from patients with PND without radiological and pathological suspicion for malignancy who underwent a ductoscopy procedure were analyzed. We used univariate and multivariate regression analyses to identify nipple fluid miRNAs differing between pathologically confirmed papillomas and breast tissue without abnormalities. A total of 27 nipple fluid samples from patients with PND were included for miRNA expression analysis. Out of the 22 miRNAs examined, only miR-145-5p was significantly differentially expressed (upregulated) in nipple fluid from patients with an intraductal papilloma compared to patients showing no breast abnormalities (OR 4.76, p = 0.046), with a diagnostic accuracy of 92%. miR-145-5p expression in nipple fluid differs for intraductal papillomas and breast tissue without abnormalities and, therefore, has potential as a diagnostic marker to signal presence of papillomas in PND patients. However, further refinement and validation in clinical trials are necessary to establish its clinical applicability.

A Second Ductoscopy Procedure in Patients with Recurrent and Persistent Pathological Nipple Discharge.

Background: Most patients suffering from pathological nipple discharge (PND) undergo local surgical procedures because standard radiological imaging often fails to reveal the cause. Ductoscopy is a minimally invasive endoscopic technique that enables direct intraductal visualization and can avoid unnecessary diagnostic surgical procedures. Hence, patients with recurrent or persistent PND after an unsuccessful ductoscopy procedure still undergo unnecessary surgery. This study describes the experience of a second ductoscopy procedure in patients with recurrent or persistent PND without suspicious radiological findings. Methods: Patients with recurrent or persistent PND who underwent two ductoscopy procedures between 2010 and 2017 were retrospectively analyzed. The second ductoscopy was performed when the first ductoscopic attempt was unsuccessful due to technical problems. The primary outcome was the number of preventable surgical procedures. Results: A total of 17 patients underwent two ductoscopy procedures. The first ductoscopy showed a polypoid lesion in 10 patients (58.8%), no abnormalities in 3 patients (17.6%), and in 4 patients (23.5%), it was not possible to visualize the ductal tree. Post-procedure, all patients suffered from PND. After two ductoscopic attempts, PND stopped in 10 patients (58.8%), and 7 patients (41.2%) still suffered from PND and were operated on. Pathology of the resection specimens showed no abnormalities in 1 patient, a papilloma in 5 patients, and ductal carcinoma in situ in 1 patient. Conclusion: A second ductoscopy procedure can be considered in the diagnostic work-up of patients suffering from persistent or recurrent PND after an unsuccessful first ductoscopic attempt to avoid unnecessary surgery in about 59% of the cases.

Predictors of postoperative lumpectomy size in breast-conserving surgery in breast cancer patients: a retrospective cohort study.

BACKGROUND: Oncoplastic reconstructive surgery as an extension of breast-conserving surgery leads to better aesthetic results, an increase in tumor-free margins, and a reduction of re-excision rates. However, oncologic resection is often more extensive than expected, sometimes resulting in the plastic surgeon deviating from the predetermined plan. For optimal planning of the reconstruction, it is mandatory to estimate volume defects after lumpectomy as accurately as possible. This study aims to find preoperative predictors of lumpectomy resection size. METHODS: All consecutive patients diagnosed with invasive breast carcinoma or carcinoma in situ and treated primarily with breast-conserving surgery between 2018 and 2020 at the University Medical Center Utrecht and Alexander Monro Hospital were included. Variables measured were patient characteristics and tumor characteristics. Data was analyzed in a multiple linear regression analysis. RESULTS: A total of 423 cases (410 patients) were included, with a median age of 58 (range 32-84) and a mean BMI of 25.0 (SD=9.3). The mean maximum radiological tumor diameter was 18.0 mm (SD=13.2), and the mean maximum lumpectomy diameter was 58.8 mm (SD=19.2). Multiple linear regression analysis found an explained variance of R 2 = 0.60 (p = < .00), corrected for operating surgeon. Significant predictors for postoperative lumpectomy size were BMI, breast size, and maximum preoperative radiological tumor diameter. Moreover, a predictive tool for lumpectomy size was developed and a web-based application was created on www.evidencio.com under the title ''Predicted lumpectomy size'', to facilitate the use of our tool in a clinical setting. CONCLUSION: Postoperative lumpectomy size can be predicted with BMI, breast size and radiological tumor size. This model could be beneficial for (plastic) breast surgeons in planning reconstructions and to prepare and inform their patients more accurately.

Role of duct excision surgery in the treatment of pathological nipple discharge and detection of breast carcinoma: systematic review.

BACKGROUND: The role of duct excision surgery is not clearly defined in patients with pathological nipple discharge without other clinical and radiological abnormalities. The primary aim of this systematic review was to determine the malignancy rate in patients with pathological nipple discharge after duct excision surgery (microdochectomy/major duct excision). The secondary aims were to determine the recurrence rate of pathological nipple discharge after surgery and to assess breast cancer development after surgery. METHODS: MEDLINE and Embase were searched from inception to March 2023, using search terms related to 'nipple discharge', 'nipple fluid', 'microdochectomy', 'duct excision', and 'minimally invasive surgical procedure'. Studies reporting data about women who underwent duct excision surgery for pathological nipple discharge without clinical and radiological suspicion of breast cancer, as well as reporting data on women diagnosed with breast cancer after duct excision surgery, were included. RESULTS: A total of 318 titles were identified, of which nine publications were included in the analysis. This resulted in 1108 patients with pathological nipple discharge who underwent a duct excision. The weighted mean rate of malignancy after duct excision surgery was 8.1 per cent (ranging from 2.3 to 13.5 per cent). Three studies described the recurrence rate of pathological nipple discharge (ranging from 0 to 12 per cent) and two studies reported breast cancer development in the follow-up in a total of three patients (less than 1 per cent). CONCLUSION: The malignancy rate after duct excision surgery for pathological nipple discharge was low in patients with pathological nipple discharge without radiological and clinical abnormalities and approximately 9 of 10 patients undergo surgery for a benign cause. Improvement of the diagnostic and therapeutic workup is needed to prevent patients from undergoing (unnecessary) exploratory surgery.