Can multi-modal radiomics using pretreatment ultrasound and tomosynthesis predict response to neoadjuvant systemic treatment in breast cancer?

OBJECTIVES: Response assessment to neoadjuvant systemic treatment (NAST) to guide individualized treatment in breast cancer is a clinical research priority. We aimed to develop an intelligent algorithm using multi-modal pretreatment ultrasound and tomosynthesis radiomics features in addition to clinical variables to predict pathologic complete response (pCR) prior to the initiation of therapy. METHODS: We used retrospective data on patients who underwent ultrasound and tomosynthesis before starting NAST. We developed a support vector machine algorithm using pretreatment ultrasound and tomosynthesis radiomics features in addition to patient and tumor variables to predict pCR status (ypT0 and ypN0). Findings were compared to the histopathologic evaluation of the surgical specimen. The main outcome measures were area under the curve (AUC) and false-negative rate (FNR). RESULTS: We included 720 patients, 504 in the development set and 216 in the validation set. Median age was 51.6 years and 33.6% (242 of 720) achieved pCR. The addition of radiomics features significantly improved the performance of the algorithm (AUC 0.72 to 0.81; p = 0.007). The FNR of the multi-modal radiomics and clinical algorithm was 6.7% (10 of 150 with missed residual cancer). Surface/volume ratio at tomosynthesis and peritumoral entropy characteristics at ultrasound were the most relevant radiomics. Hormonal receptors and HER-2 status were the most important clinical predictors. CONCLUSION: A multi-modal machine learning algorithm with pretreatment clinical, ultrasound, and tomosynthesis radiomics features may aid in predicting residual cancer after NAST. Pending prospective validation, this may facilitate individually tailored NAST regimens. CLINICAL RELEVANCE STATEMENT: Multi-modal radiomics using pretreatment ultrasound and tomosynthesis showed significant improvement in assessing response to NAST compared to an algorithm using clinical variables only. Further prospective validation of our findings seems warranted to enable individualized predictions of NAST outcomes. KEY POINTS: • We proposed a multi-modal machine learning algorithm with pretreatment clinical, ultrasound, and tomosynthesis radiomics features to predict response to neoadjuvant breast cancer treatment. • Compared with the clinical algorithm, the AUC of this integrative algorithm is significantly higher. • Used prior to the initiative of therapy, our algorithm can identify patients who will experience pathologic complete response following neoadjuvant therapy with a high negative predictive value.

Relationship of Ki-67 index in biopsies of metastatic breast cancer tissue and circulating tumor cells (CTCs) at the time of biopsy collection.

BACKGROUND: The proliferation marker Ki-67 is a major pathological feature for the description of the state of disease in breast cancer. It helps to define the molecular subtype and to stratify between therapy regimens in early breast cancer and helps to assess the therapy response. Circulating tumor cells (CTCs) are a negative prognostic biomarker for progression free (PFS) and overall survival (OS) in patients with metastatic breast cancer. Therefore, the CTC count is often described as surrogate for the tumor burden. Both, decrease of Ki-67 and CTC count are considered as evidence for therapy response. The presented work analyzed the correlation between the Ki-67 indices of metastatic tissue biopsies and CTC counts in biopsy time-adjacent peripheral blood samples. PATIENTS AND METHODS: Blood samples from 70 metastatic breast cancer patients were obtained before the start of a new line of systemic therapy. CTCs were enumerated using CellSearch® (Menarini Silicon Biosystems, Bologna, Italy) whereas intact CTCs (iCTCs) and non-intact or apoptotic CTCs (aCTCs) were distinguished using morphologic criteria. The proportion of cells expressing Ki-67 was evaluated using immunohistochemistry on biopsies of metastases obtained concurrently with CTC sampling before the start of a new line of systemic therapy. RESULTS: 65.7% of patients had a Ki-67 index of > 25%. 28.6% of patients had ≥ 5, 47.1% ≥ 1 iCTCs. 37.1% had ≥ 5, 51.4% ≥ 1 aCTCs. No correlation was shown between Ki-67 index and iCTC and aCTC count (r = 0.05 resp. r = 0.05, Spearman's correlation index). High CTC-counts did not coincide with high Ki-67 index. High Ki-67, ≥ 5 iCTCs and aCTCs are associated with poor progression free (PFS) and overall survival (OS). CONCLUSION: CTCs and Ki-67 are independent prognostic markers in metastatic breast cancer. High Ki-67 in metastatic tumor tissue is not correlated to high iCTC or aCTC counts in peripheral blood.

Conventional specimen radiography in breast-conserving therapy: a useful tool for intraoperative margin assessment after neoadjuvant therapy?

PURPOSE: A previous study in our breast unit showed that the diagnostic accuracy of intraoperative specimen radiography and its potential to reduce second surgeries in a cohort of patients treated with neoadjuvant chemotherapy were low, which questions the routine use of Conventional specimen radiography (CSR) in this patient group. This is a follow-up study in a larger cohort to further evaluate these findings. METHODS: This retrospective study included 376 cases receiving breast-conserving surgery (BCS) after neoadjuvant chemotherapy (NACT) of primary breast cancer. CSR was performed to assess potential margin infiltration and recommend an intraoperative re-excision of any radiologically positive margin. The histological workup of the specimen served as gold standard for the evaluation of the accuracy of CSR and the potential reduction of second surgeries by CSR-guided re-excisions. RESULTS: 362 patients with 2172 margins were assessed. The prevalence of positive margins was 102/2172 (4.7%). CSR had a sensitivity of 37.3%, a specificity of 85.6%, a positive predictive value (PPV) of 11.3%, and a negative predictive value (NPV) of 96.5%. The rate of secondary procedures was reduced from 75 to 37 with a number needed to treat (NNT) of CSR-guided intraoperative re-excisions of 10. In the subgroup of patients with clinical complete response (cCR), the prevalence of positive margins was 38/1002 (3.8%), PPV was 6.5% and the NNT was 34. CONCLUSION: This study confirms our previous finding that the rate of secondary surgeries cannot be significantly reduced by CSR-guided intraoperative re-excisions in cases with cCR after NACT. The routine use CSR after NACT is questionable, and alternative tools of intraoperative margin assessment should be evaluated.

Machine learning and patient-reported outcomes for longitudinal monitoring of disease progression in metastatic breast cancer: a multicenter, retrospective analysis.

BACKGROUND: Assessments of health-related quality of life (HRQoL) play an important role in transition to palliative care for women with metastatic breast cancer. We developed machine learning (ML) algorithms to analyse longitudinal HRQoL data and identify patients who may benefit from palliative care due to disease progression. METHODS: We recruited patients from two institutions and administered the EuroQoL Visual Analog Scale (EQ-VAS) via an online platform over a 6-month period. We trained a regularised regression algorithm using 10-fold cross-validation to determine if a patient was at high or low risk of disease progression based on changes in the EQ-VAS scores using data of one institution and validated the performance on data of the other institution. Progression-free survival (PFS) was the end-point. We conducted Kaplan-Meier and Cox regression analysis adjusted for clinical risk factors. RESULTS: Of 179 patients, 98 (54.7%) had progressive disease after a median follow-up of 14weeks. Using EQ-VAS scores collected at weeks 1-6 to predict disease progression at week 12, in the validation set (n = 63), PFS was significantly lower in the intelligent EQ-VAS high-risk versus low-risk group: median PFS 7 versus 10weeks, log-rank P < 0.038). Intelligent EQ-VAS had the strongest association with PFS (adjusted hazard ratio 2.69, 95% confidence interval 1.17-6.18, P = 0.02). CONCLUSION: ML algorithms can analyse changes in longitudinal HRQoL data to identify patients with disease progression earlier than standard follow-up methods. Intelligent EQ-VAS scores were identified as independent prognostic factor. Future studies may validate these results to remotely monitor patients.

Potential of Lesion-to-Fat Elasticity Ratio Measured by Shear Wave Elastography to Reduce Benign Biopsies in BI-RADS 4 Breast Lesions.

OBJECTIVES: We evaluated whether lesion-to-fat ratio measured by shear wave elastography in patients with Breast Imaging Reporting and Data System (BI-RADS) 3 or 4 lesions has the potential to further refine the assessment of B-mode ultrasound alone in breast cancer diagnostics. METHODS: This was a secondary analysis of an international diagnostic multicenter trial (NCT02638935). Data from 1288 women with breast lesions categorized as BI-RADS 3 and 4a-c by conventional B-mode ultrasound were analyzed, whereby the focus was placed on differentiating lesions categorized as BI-RADS 3 and BI-RADS 4a. All women underwent shear wave elastography and histopathologic evaluation functioning as reference standard. Reduction of benign biopsies as well as the number of missed malignancies after reclassification using lesion-to-fat ratio measured by shear wave elastography were evaluated. RESULTS: Breast cancer was diagnosed in 368 (28.6%) of 1288 lesions. The assessment with conventional B-mode ultrasound resulted in 53.8% (495 of 1288) pathologically benign lesions categorized as BI-RADS 4 and therefore false positives as well as in 1.39% (6 of 431) undetected malignancies categorized as BI-RADS 3. Additional lesion-to-fat ratio in BI-RADS 4a lesions with a cutoff value of 1.85 resulted in 30.11% biopsies of benign lesions which correspond to a reduction of 44.04% of false positives. CONCLUSIONS: Adding lesion-to-fat ratio measured by shear wave elastography to conventional B-mode ultrasound in BI-RADS 4a breast lesions could help reduce the number of benign biopsies by 44.04%. At the same time, however, 1.98% of malignancies were missed, which would still be in line with American College of Radiology BI-RADS 3 definition of <2% of undetected malignancies.

Imaging of lumpectomy surface with large field-of-view confocal laser scanning microscopy 'Histolog® scanner' for breast margin assessment in comparison with conventional specimen radiography.

PURPOSE: The Histolog® Scanner (SamanTree Medical SA, Lausanne, Switzerland) is a large field-of-view confocal laser scanning microscope designed to allow intraoperative margin assessment by the production of histological images ready for assessment in the operating room. We evaluated the feasibility and the performance of the Histolog® Scanner (HS) to correctly identify infiltrated margins in clinical practice of lumpectomy specimens. It was extrapolated if the utilization of the HS has the potential to reduce infiltrated margins and therefore reduce re-operation rates in patients undergoing breast conserving surgery (BCS) due to a primarily diagnosed breast cancer including ductal carcinoma in situ. METHODS: This is a single-center, prospective, non-interventional, diagnostic pilot study including 50 consecutive patients receiving BCS. The complete surface of the specimen was scanned using the HS intraoperatively. The surgery and the intraoperative margin assessment of the specimen was performed according to the clinical routine consisting of conventional specimen radiography as well as the clinical impression of the surgeon. Three surgeons and an experienced pathologist assessed the scans produced by the HS for cancer cells on the surface. The potential of the HS to correctly identify involved margins was compared to the results of the conventional specimen radiography alone as well as the clinical routine. The histopathological report served as the gold standard. RESULTS: 50 specimens corresponding to 300 surfaces were scanned by the HS. The mean sensitivity of the surgeons to identify involved margins with the HS was 37.5% ± 5.6%, the specificity was 75.2% ± 13.0%. The assessment of resection margins by the pathologist resulted in a sensitivity of 37.5% and a specificity of 81.0%, while the local clinical routine resulted in a sensitivity of 37.5% and a specificity of 78.2%. CONCLUSION: Acquisition of high-resolution histological images using the HS was feasible in clinical practice. Sensitivity and specificity were comparable to clinical routine. With more specific training and experience on image interpretation and acquisition, the HS may have the potential to enable more accuracy in the margin assessment of BCS specimens.

Impact of age on indication for chemotherapy in early breast cancer patients: results from 104 German institutions from 2008 to 2017.

PURPOSE: Today, the decision to treat patients with chemotherapy for early breast cancer (EBC) is made based on the patient's individual risk stratification and tumor biology. In cases with chemotherapy indication, the neoadjuvant application (NACT) is the preferred option in comparison with primary surgery and adjuvant chemotherapy (ACT). Age remains a relevant factor in the decision-making process. The aim of the present study was to illustrate the impact of age on the use of systemic therapy in clinical routine. METHODS: The study separately analyzed chemotherapy use among six age cohorts of EBC patients who had been treated at 104 German breast units between January 2008 and December 2017. RESULTS: In total, 124,084 patients were included, 46,279 (37.3%) of whom had received chemotherapy. For 44,765 of these cases, detailed information on treatment was available. Within this cohort, chemotherapy was administered as NACT to 14,783 patients (33.0%) and as ACT to 29,982 (67.0%) patients. Due to the higher prevalence of unfavorable tumor subtypes, younger patients had a higher rate of chemotherapy (≤ 29y: 74.2%; 30-39y: 71.3%) and a higher proportion of NACT administration ( ≤ 29y: 66.9%; 30-39y: 56.0%) in comparison with elderly patients, who had lower rates for overall chemotherapy (60-69y: 37.5%; ≥ 70y: 17.6%) and NACT (60-69y: 25.5%; ≥ 70y: 22.8%). Pathologic complete response was higher in younger than in older patients (≤ 29y: 30.4% vs. ≥ 70y: 16.7%), especially for HER2- subtypes. CONCLUSION: The data from the nationwide German cohort reveal relevant age-dependent discrepancies concerning the use of chemotherapy for EBC.

Intelligent multi-modal shear wave elastography to reduce unnecessary biopsies in breast cancer diagnosis (INSPiRED 002): a retrospective, international, multicentre analysis.

BACKGROUND: Breast ultrasound identifies additional carcinomas not detected in mammography but has a higher rate of false-positive findings. We evaluated whether use of intelligent multi-modal shear wave elastography (SWE) can reduce the number of unnecessary biopsies without impairing the breast cancer detection rate. METHODS: We trained, tested, and validated machine learning algorithms using SWE, clinical, and patient information to classify breast masses. We used data from 857 women who underwent B-mode breast ultrasound, SWE, and subsequent histopathologic evaluation at 12 study sites in seven countries from 2016 to 2019. Algorithms were trained and tested on data from 11 of the 12 sites and externally validated using the additional site's data. We compared findings to the histopathologic evaluation and compared the diagnostic performance between B-mode breast ultrasound, traditional SWE, and intelligent multi-modal SWE. RESULTS: In the external validation set (n = 285), intelligent multi-modal SWE showed a sensitivity of 100% (95% CI, 97.1-100%, 126 of 126), a specificity of 50.3% (95% CI, 42.3-58.3%, 80 of 159), and an area under the curve of 0.93 (95% CI, 0.90-0.96). Diagnostic performance was significantly higher compared to traditional SWE and B-mode breast ultrasound (P < 0.001). Unlike traditional SWE, positive-predictive values of intelligent multi-modal SWE were significantly higher compared to B-mode breast ultrasound. Unnecessary biopsies were reduced by 50.3% (79 versus 159, P < 0.001) without missing cancer compared to B-mode ultrasound. CONCLUSION: The majority of unnecessary breast biopsies might be safely avoided by using intelligent multi-modal SWE. These results may be helpful to reduce diagnostic burden for patients, providers, and healthcare systems.

Circulating miR-200 Family and CTCs in Metastatic Breast Cancer before, during, and after a New Line of Systemic Treatment.

The extracellular circulating microRNA (miR)-200 regulates epithelial-mesenchymal transition and, thus, plays an essential role in the metastatic cascade and has shown itself to be a promising prognostic and predictive biomarker in metastatic breast cancer (MBC). Expression levels of the plasma miR-200 family were analyzed in relationship to systemic treatment, circulating tumor cells (CTC) count, progression-free survival (PFS), and overall survival (OS). Expression of miR-200a, miR-200b, miR-200c, miR-141, and miR-429, and CTC status (CTC-positive ≥ 5 CTC/7.5 mL) was assessed in 47 patients at baseline (BL), after the first completed cycle of a new line of systemic therapy (1C), and upon the progression of disease (PD). MiR-200a, miR-200b, and miR-141 expression was reduced at 1C compared to BL. Upon PD, all miR-200s were upregulated compared to 1C. At all timepoints, the levels of miR-200s were elevated in CTC-positive versus CTC-negative patients. Further, heightened miR-200s expression and positive CTC status were associated with poorer OS at BL and 1C. In MBC patients, circulating miR-200 family members decreased after one cycle of a new line of systemic therapy, were elevated during PD, and were indicative of CTC status. Notably, increased levels of miR-200s and elevated CTC count correlated with poorer OS and PFS. As such, both are promising biomarkers for optimizing the clinical management of MBC.

Shear wave elastography as a supplemental tool in the assessment of unsuspicious axillary lymph nodes in patients undergoing breast ultrasound examination.

OBJECTIVES: To define reference values for shear wave elastography (SWE) in unsuspicious axillary lymph nodes in patients undergoing breast ultrasound examination. METHODS: In total, 177 clinically and sonographically unsuspicious axillary lymph nodes were prospectively evaluated with SWE using Virtual Touch Tissue Imaging Quantification (VTIQ) in 175 women. Mean values of tissue stiffness for axillary fatty tissue, lymph node cortex, and lymph node hilus were measured. Additionally, test-retest reliability of SWE in the assessment of axillary lymph node stiffness was evaluated by repeating each measurement three times. RESULTS: In 177 axillary lymph nodes, the mean stiffness of lymph node cortex, hilus, and surrounding fatty tissue as quantified by SWE was 1.90 m/s (SD: 0.34 m/s), 2.02 m/s (SD: 0.37 m/s), and 1.75 m/s (SD: 0.38 m/s), respectively. The mean stiffness of cortex and hilus was significantly higher compared to fatty tissue (p < 0.0001). SWE demonstrated good test-retest reliability in the assessment of stiffness of the lymph node hilus, cortex, and the surrounding fatty tissue with an intraclass correlation of 0.79 (95% CI: 0.75; 0.83), 0.75 (95% CI: 0.70; 0.79), and 0.78 (95% CI: 0.74; 0.82), respectively, (p < 0.0001). CONCLUSIONS: Reference values for SWE in unsuspicious axillary lymph nodes are determined. These results may help to better identify axillary lymph node metastasis for breast cancer patients when combined with other lymph node features. SWE is a reliable method for the objective quantification of tissue stiffness of axillary lymph nodes. ADVANCES IN KNOWLEDGE: This study presents physiological reference values for tissue stiffness by examining the axillary lymph nodes with SWE in 175 women with sonomorphologically unsuspicious lymph nodes.

Predictive value of neutrophil-to-lymphocyte-ratio in neoadjuvant-treated patients with breast cancer.

PURPOSE: Breast cancer (BC) is the most common malignancy among women and prognosis is strongly influenced by tumor subtype. Neoadjuvant chemotherapy (NAC) is the standard treatment for both locally advanced- and early-stage triple-negative and Her2-positive BC. Pathologic complete response (pCR) to NAC is an important predictor of patient outcomes. Neutrophil-to-lymphocyte-ratio (NLR) in peripheral blood is associated with prognosis in various malignancies. Here, we investigated the value of the pretreatment NLR as a response predictor in neoadjuvant-treated patients with BC. METHODS: A retrospective chart analysis of 862 patients with invasive BC treated with NAC at the Heidelberg University Hospital during 2003-2015 was conducted. NLR was calculated as the ratio of the absolute neutrophil and lymphocyte counts in peripheral blood, and pCR was defined as absence of invasive or in situ carcinoma in breast and axillary lymph nodes. RESULTS: A total of 151 patients with invasive BC who underwent NAC were included in this study. NLR tended to be higher in the pCR group than the non-pCR group (p < 0.1). Analyses of BC subtypes demonstrated that NLR was significantly higher in the pCR- compared with the non-pCR group (3.304 vs. 2.379, respectively; p = 0.048) in patients with luminal B/Her2-negative tumors. Further, we found a significant difference in NLR according to remission status in postmenopausal patients (2.861 vs. 2.313, respectively; p = 0.043). CONCLUSION: NLR was significantly higher only for patients achieving pCR in the Luminal B/Her2-negative and postmenopausal subgroups. Hence, NLR is a candidate additional predictive factor in patients with Luminal B/Her2-negative BC.

The COVID-19 pandemic and its impact on medical teaching in obstetrics and gynecology-A nationwide expert survey among teaching coordinators at German university hospitals.

PURPOSE: The COVID-19 pandemic has imposed severe challenges on medical education at German university hospitals. In this first German nationwide expert survey, we addressed the responsible university teaching coordinators in obstetrics and gynecology departments and investigated their experiences during the pandemic as well as their opinions on future developments, especially with regard to the broader implementation of e-learning in the standard curriculum. METHODS: The questionnaire included 42 items and was disseminated among teaching coordinators at all 41 departments of obstetrics and gynecology at German university hospitals via an email that included a weblink to the online survey provider. Responses were collected between 19 April and 7 June 2021. RESULTS: In total, 30 responses were collected from 41 departments across Germany and their respective teaching coordinators in obstetrics and gynecology. The general opinion of the medical teaching provided during the pandemic was positive, whereas the teaching quality in practical skills was considered inferior and not equivalent to the standard face-to-face curriculum. Lectures and seminars had to be substituted by remote-learning alternatives, while clinical clerkships were reduced in length and provided less patient contact. Students in their final year experienced only a few differences in the clinical and teaching routine. Teaching coordinators in obstetrics and gynecology stated that they intend to incorporate more e-learning into the curriculum in the future. CONCLUSION: The medical educators' views presented here may help to complement the already-thoroughly investigated experiences of students under the restrictions of the COVID-19 pandemic. Medical educators in obstetrics and gynecology at German university hospitals have successfully established online and hybrid teaching alternatives to their standard face-to-face courses. Building on recent experiences, digitalization could help to improve future medical education.

How to make students satisfied with digital teaching? Investigative results from teaching evaluations in Gynecology and Obstetrics.

PURPOSE: The aim of this study was to investigate whether students' attitude towards online learning in Gynecology and Obstetrics changed during the COVID-19 pandemic. We further examined which variables impacted students' satisfaction with digital learning. METHODS: A specifically developed questionnaire was used from June 2020-July 2021 for N = 234 medical students participating in the course "Gynecology and Obstetrics" at University of Heidelberg. Thirty-five items were repeatedly applied in different cohorts to assess structure- and content-related quality of teaching. In addition, their influence on overall satisfaction with digital teaching was analyzed by applying investigative analyses like multiple regression and extreme group comparisons. RESULTS: Especially items associated with content-related quality of teaching (ß = 0.24), organization of teaching (ß = 0.25) and subjective learning success (ß = 0.27) seemed to be relevant predictors for overall satisfaction with courses. Fears and changes due to the pandemic situation also played a role for a subgroup of students. Aspects linked to technical quality of teaching, interactions with teachers and students or advantages of web-based learning appeared to play a subordinate role for overall satisfaction with digital teaching. Comparisons of ratings over time revealed that teaching evaluations almost remained the same. CONCLUSION: Our results give several hints regarding how digital teaching should be designed and how it can be improved. Further studies are needed to validate our results and to develop methods to improve digital teaching in medicine.

Circulating miR-200 family as predictive markers during systemic therapy of metastatic breast cancer.

PURPOSE: Circulating miRNAs can provide valid prognostic and predictive information for breast cancer diagnosis and subsequent management. They may comprise quintessential biomarkers that can be obtained minimally invasively from liquid biopsy in metastatic breast cancer patients. Therefore, they would be clinically crucial for monitoring therapy response, with the goal of detecting early relapse. This study investigated miRNA expression in patients with early and/or late relapse, and the predictive value for assessing overall (OS) and progression-free survival (PFS). METHODS: Forty-seven patients with metastatic breast cancer from the University Women's Hospital Heidelberg were enrolled in this study. Expression of miR-200a, miR-200b, miR-200c, miR-141, and miR-429 was analyzed by RT-qPCR before a new line of systemic therapy and after the first cycle of a respective therapy. Tumor response was assessed every 3 months using the RECIST criteria. Statistical analysis focused on the relation of miR-200s expression and early vs. late cancer relapse in relation to systemic treatment. The association of miRNAs with PFS and OS was investigated. RESULTS: Before starting a new line of systemic therapy, miR-429 (p = 0.024) expression was significantly higher in patients with early relapse (PFS ≤ 4 months) than in patients with late relapse (PFS > 4 months). After one cycle of systemic therapy, miR-200a (p = 0.039), miR-200b (p = 0.003), miR-141 (p = 0.017), and miR-429 (p = 0.010) expression was higher in early than in late progressive cancer. In addition, 4 out of 5 miR-200 family members (miR-200a, miR-200b, miR-141, and miR-429) predicted PFS (p = 0.048, p = 0.008, p = 0.026, and p = 0.016, respectively). Patients with heightened miRNA levels showed a significant reduction in OS and PFS. CONCLUSION: Circulating miR-200s were differentially expressed among patients with late and/or early relapse. 4 of 5 members of the miR-200 family predicted significantly early relapse after systemic treatment. Our results encourage the use of circulating miR-200s as valuable prognostic biomarkers during metastatic breast cancer therapy.

The importance of multi-modal imaging and clinical information for humans and AI-based algorithms to classify breast masses (INSPiRED 003): an international, multicenter analysis.

OBJECTIVES: AI-based algorithms for medical image analysis showed comparable performance to human image readers. However, in practice, diagnoses are made using multiple imaging modalities alongside other data sources. We determined the importance of this multi-modal information and compared the diagnostic performance of routine breast cancer diagnosis to breast ultrasound interpretations by humans or AI-based algorithms. METHODS: Patients were recruited as part of a multicenter trial (NCT02638935). The trial enrolled 1288 women undergoing routine breast cancer diagnosis (multi-modal imaging, demographic, and clinical information). Three physicians specialized in ultrasound diagnosis performed a second read of all ultrasound images. We used data from 11 of 12 study sites to develop two machine learning (ML) algorithms using unimodal information (ultrasound features generated by the ultrasound experts) to classify breast masses which were validated on the remaining study site. The same ML algorithms were subsequently developed and validated on multi-modal information (clinical and demographic information plus ultrasound features). We assessed performance using area under the curve (AUC). RESULTS: Of 1288 breast masses, 368 (28.6%) were histopathologically malignant. In the external validation set (n = 373), the performance of the two unimodal ultrasound ML algorithms (AUC 0.83 and 0.82) was commensurate with performance of the human ultrasound experts (AUC 0.82 to 0.84; p for all comparisons > 0.05). The multi-modal ultrasound ML algorithms performed significantly better (AUC 0.90 and 0.89) but were statistically inferior to routine breast cancer diagnosis (AUC 0.95, p for all comparisons ≤ 0.05). CONCLUSIONS: The performance of humans and AI-based algorithms improves with multi-modal information. KEY POINTS: • The performance of humans and AI-based algorithms improves with multi-modal information. • Multimodal AI-based algorithms do not necessarily outperform expert humans. • Unimodal AI-based algorithms do not represent optimal performance to classify breast masses.

Experiences with alternative online lectures in medical education in obstetrics and gynecology during the COVID-19 pandemic-possible efficient and student-orientated models for the future?

PURPOSE: The onset of the COVID-19 pandemic posed an eminent challenge for medical teachers worldwide. Face-to-face lectures and seminars were no longer possible, and alternatives had to be found. E-learning concepts quickly emerged as the only practicable solutions and also offered the opportunity to evaluate whether traditional face-to-face lectures could be translated into an online format, independent of the COVID-19 pandemic. METHODS: We offered an e-learning program consisting of lecture notes, screencasts with audio narration, and online webinars that covered topics normally taught in traditional lectures and seminars. To evaluate the learning behavior and quality of our e-learning program, we drafted a questionnaire that students completed at the end of the 2020 summer semester that had been designed to enable a comparative analysis of the different e-learning modules. RESULTS: Voluntary participation in the online courses was high. Survey analysis revealed high satisfaction with and a distinctive preference for the format, even under regular, COVID-19-independent conditions. In general, a positive appraisal of e-learning-especially as a substitute for regular lectures-was found. Students also reported higher studying efficiency. Exam results were equal to those of previous semesters. CONCLUSION: Both acceptance of and satisfaction with our e-learning modules were high, and students displayed increased demand for this kind of e-learning format. We, therefore, conclude that e-learning offerings could serve as reasonable, efficient, student-orientated substitutes for certain medical courses, especially lectures. These curricular adaptations would correlate with the high digitalization seen in students' everyday lives. This correlation may also hold true independent of the ongoing COVID-19 pandemic.

Does conventional specimen radiography after neoadjuvant chemotherapy of breast cancer help to reduce the rate of second surgeries?

PURPOSE: This is the first study to systematically evaluate the diagnostic accuracy of intraoperative specimen radiography on margin level and its potential to reduce second surgeries in patients treated with neoadjuvant chemotherapy. METHODS: This retrospective study included 174 cases receiving breast conserving surgery (BCS) after neoadjuvant chemotherapy (NACT) of primary breast cancer. Conventional specimen radiography (CSR) was performed to assess potential margin infiltration and recommend an intraoperative re-excision of any radiologically positive margin. The histological workup of the specimen served as gold standard for the evaluation of the accuracy of CSR and the potential reduction of second surgeries by CSR-guided re-excisions. RESULTS: 1044 margins were assessed. Of 47 (4.5%) histopathological positive margins, CSR identified 9 correctly (true positive). 38 infiltrated margins were missed (false negative). This resulted in a sensitivity of 19.2%, a specificity of 89.2%, a positive predictive value (PPV) of 7.7%, and a negative predictive value (NPV) of 95.9%. The rate of secondary procedures was reduced from 23 to 16 with a number needed to treat (NNT) of CSR-guided intraoperative re-excisions of 25. In the subgroup of patients with cCR, the prevalence of positive margins was 10/510 (2.0%), PPV was 1.9%, and the NNT was 85. CONCLUSION: Positive margins after NACT are rare and CSR has only a low sensitivity to detect them. Thus, the rate of secondary surgeries cannot be significantly reduced by recommending targeted re-excisions, especially in cases with cCR. In summary, CSR after NACT is inadequate for intraoperative margin assessment but remains useful to document removal of the biopsy site clip.

Retrospective, Multicenter Analysis Comparing Conventional with Oncoplastic Breast Conserving Surgery: Oncological and Surgical Outcomes in Women with High-Risk Breast Cancer from the OPBC-01/iTOP2 Study.

INTRODUCTION: Recent data suggest that margins ≥2 mm after breast-conserving surgery may improve local control in invasive breast cancer (BC). By allowing large resection volumes, oncoplastic breast-conserving surgery (OBCII; Clough level II/Tübingen 5-6) may achieve better local control than conventional breast conserving surgery (BCS; Tübingen 1-2) or oncoplastic breast conservation with low resection volumes (OBCI; Clough level I/Tübingen 3-4). METHODS: Data from consecutive high-risk BC patients treated in 15 centers from the Oncoplastic Breast Consortium (OPBC) network, between January 2010 and December 2013, were retrospectively reviewed. RESULTS: A total of 3,177 women were included, 30% of whom were treated with OBC (OBCI n = 663; OBCII n = 297). The BCS/OBCI group had significantly smaller tumors and smaller resection margins compared with OBCII (pT1: 50% vs. 37%, p = 0.002; proportion with margin <1 mm: 17% vs. 6%, p < 0.001). There were significantly more re-excisions due to R1 ("ink on tumor") in the BCS/OBCI compared with the OBCII group (11% vs. 7%, p = 0.049). Univariate and multivariable regression analysis adjusted for tumor biology, tumor size, radiotherapy, and systemic treatment demonstrated no differences in local, regional, or distant recurrence-free or overall survival between the two groups. CONCLUSIONS: Large resection volumes in oncoplastic surgery increases the distance from cancer cells to the margin of the specimen and reduces reexcision rates significantly. With OBCII larger tumors are resected with similar local, regional and distant recurrence-free as well as overall survival rates as BCS/OBCI.

A New Practical Decision Rule to Better Differentiate BI-RADS 3 or 4 Breast Masses on Breast Ultrasound.

OBJECTIVES: The BI-RADS classification provides a standardized way to describe ultrasound findings in breast cancer diagnostics. However, there is little information regarding which BI-RADS descriptors are most strongly associated with malignancy, to better distinguish BI-RADS 3 (follow-up imaging) and 4 (diagnostic biopsy) breast masses. METHODS: Patients were recruited as part of an international, multicenter trial (NCT02638935). The trial enrolled 1294 women (6 excluded) categorized as BI-RADS 3 or 4 upon routine B-mode ultrasound examination. Ultrasound images were evaluated by three expert physicians according to BI-RADS. All patients underwent histopathological confirmation (reference standard). We performed univariate and multivariate analyses (chi-square test, logistic regression, and Krippendorff's alpha). RESULTS: Histopathologic evaluation showed malignancy in 368 of 1288 masses (28.6%). Upon performing multivariate analysis, the following descriptors were significantly associated with malignancy (P < .05): age ≥50 years (OR 8.99), non-circumscribed indistinct (OR 4.05) and microlobulated margin (OR 2.95), nonparallel orientation (OR 2.69), and calcification (OR 2.64). A clinical decision rule informed by these results demonstrated a 97% sensitivity and missed fewer cancers compared to three physician experts (range of sensitivity 79-95%) and a previous decision rule (sensitivity 59%). Specificity was 44% versus 22-83%, respectively. The inter-reader reliability of the BI-RADS descriptors and of the final BI-RADS score was fair-moderate. CONCLUSIONS: A patient should undergo a diagnostic biopsy (BI-RADS 4) instead of follow-up imaging (BI-RADS 3) if the patient is 50 years or older or exhibits at least one of the following features: calcification, nonparallel orientation of mass, non-circumscribed margin, or posterior shadowing.

The role of gender-specific factors in the choice of specialty training in obstetrics and gynecology: results from a survey among medical students in Germany.

PURPOSE: The field of obstetrics and gynecology (OB/GYN) is facing growing competition for young professionals in Germany, with high interest rates among female graduates and a declining proportion of male students who choose residency training in the field. The aim of this study is to analyze general and gender-dependent factors that influence the decision for or against specialty training in OB/GYN among medical students in Germany. METHODS: Between February and November 2019, n = 346 medical students in their 5th and 6th year of undergraduate training at Heidelberg University received a questionnaire with 44 items. RESULTS: n = 286 students (61.3 female; 38.7% male) participated in the study. 28% of the female students and 9% of the male students had considered OB/GYN for their specialty training. The students reported different general and gender-specific influencing factors in their choice of a specialty. Both genders desired a good work-life-balance, however, in comparison with their female colleagues, male students had heavily weighted factors related to their later careers and professional success, including competition among colleagues. Male students had gained little practical experience during compulsory internships (26.9% for females vs. 8.8% for males) or had chosen their final-year elective in OB/GYN (15.9% for females vs. 5.5% for males). Female students had worried about the negative effects of their sex on their career (35.4% for females vs. 5.9% for males). CONCLUSION: OB/GYN must become more appealing and attractive to young female and male professionals alike. A better compatibility of career and family should go hand in hand with the implementation of differentiated, (extra) curricular teaching approaches that take the different preferences of female and male students into account.