Breast cancer screening in BRCA1/2 pathogenic sequence variant carriers during pregnancy and lactation.

OBJECTIVES: Women harboring germline BRCA1/BRCA2 pathogenic sequence variants (PSVs) are at an increased risk for breast cancer. There are no established guidelines for screening during pregnancy and lactation in BRCA carriers. The aim of this study was to evaluate the utility of whole-breast ultrasound (US) screening in pregnant and lactating BRCA PSV carriers. METHODS: Data were retrospectively collected from medical records of BRCA PSV carriers between 2014 and 2020, with follow-up until 2021. Associations between imaging intervals, number of examinations performed and pregnancy-associated breast cancers (PABCs) were examined. PABCs and cancers diagnosed at follow-up were evaluated and characteristics were compared between the two groups. RESULTS: Overall 212 BRCA PSV carriers were included. Mean age was 33.6 years (SD 3.93, range 25-43 years). During 274 screening periods at pregnancy and lactation, eight (2.9 %) PABCs were diagnosed. An additional eight cancers were diagnosed at follow-up. Three out of eight (37.5 %) PABCs were diagnosed by US, whereas clinical breast examination (n = 3), mammography (n = 1) and MRI (n = 1) accounted for the other PACB diagnoses. One PABC was missed by US. The interval from negative imaging to cancer diagnosis was significantly shorter for PABCs compared with cancers diagnosed at follow-up (3.96 ± 2.14 vs. 11.2 ± 4.46 months, P = 0.002). CONCLUSION: In conclusion, pregnant BRCA PSV carriers should not delay screening despite challenges like altered breast tissue and hesitancy towards mammography. If no alternatives exist, whole-breast ultrasound can be used. For lactating and postpartum women, a regular screening routine alternating between mammography and MRI is recommended.

Utilizing large language models in breast cancer management: systematic review.

PURPOSE: Despite advanced technologies in breast cancer management, challenges remain in efficiently interpreting vast clinical data for patient-specific insights. We reviewed the literature on how large language models (LLMs) such as ChatGPT might offer solutions in this field. METHODS: We searched MEDLINE for relevant studies published before December 22, 2023. Keywords included: "large language models", "LLM", "GPT", "ChatGPT", "OpenAI", and "breast". The risk bias was evaluated using the QUADAS-2 tool. RESULTS: Six studies evaluating either ChatGPT-3.5 or GPT-4, met our inclusion criteria. They explored clinical notes analysis, guideline-based question-answering, and patient management recommendations. Accuracy varied between studies, ranging from 50 to 98%. Higher accuracy was seen in structured tasks like information retrieval. Half of the studies used real patient data, adding practical clinical value. Challenges included inconsistent accuracy, dependency on the way questions are posed (prompt-dependency), and in some cases, missing critical clinical information. CONCLUSION: LLMs hold potential in breast cancer care, especially in textual information extraction and guideline-driven clinical question-answering. Yet, their inconsistent accuracy underscores the need for careful validation of these models, and the importance of ongoing supervision.

Adversarial attacks in radiology - A systematic review.

PURPOSE: The growing application of deep learning in radiology has raised concerns about cybersecurity, particularly in relation to adversarial attacks. This study aims to systematically review the literature on adversarial attacks in radiology. METHODS: We searched for studies on adversarial attacks in radiology published up to April 2023, using MEDLINE and Google Scholar databases. RESULTS: A total of 22 studies published between March 2018 and April 2023 were included, primarily focused on image classification algorithms. Fourteen studies evaluated white-box attacks, three assessed black-box attacks and five investigated both. Eleven of the 22 studies targeted chest X-ray classification algorithms, while others involved chest CT (6/22), brain MRI (4/22), mammography (2/22), abdominal CT (1/22), hepatic US (1/22), and thyroid US (1/22). Some attacks proved highly effective, reducing the AUC of algorithm performance to 0 and achieving success rates up to 100 %. CONCLUSIONS: Adversarial attacks are a growing concern. Although currently the threats are more theoretical than practical, they still represent a potential risk. It is important to be alert to such attacks, reinforce cybersecurity measures, and influence the formulation of ethical and legal guidelines. This will ensure the safe use of deep learning technology in medicine.

Treatment-Induced Bone Marrow Enhancement at MRI in Breast Cancer Patients Receiving Granulocyte-Colony Stimulating Factor Adjunct to Chemotherapy.

RATIONALE AND OBJECTIVES: Granulocyte-colony stimulating factor (G-CSF) induces the reconversion of fatty bone marrow to hematopoietic bone marrow. The bone marrow changes are detectable as signal intensity changes at MRI. The aim of this study was to evaluate sternal bone marrow enhancement following G-CSF and chemotherapy treatment in women with breast cancer. MATERIALS AND METHODS: This retrospective study included breast cancer patients who received neoadjuvant chemotherapy with adjunct G-CSF. The signal intensity of sternal bone marrow at MRI on T1-weighted contrast-enhanced subtracted images was measured before treatment, at the end of treatment, and at 1-year follow-up. The bone marrow signal intensity (BM SI) index was calculated by dividing the signal intensity of sternal marrow by the signal intensity of the chest wall muscle. Data were collected between 2012 and 2017, with follow-up until August 2022. Mean BM SI indices were compared before and after treatment, and at 1-year follow-up. Differences in bone marrow enhancement between time points were analyzed using a one-way repeated measures ANOVA. RESULTS: A total of 109 breast cancer patients (mean age 46.1 ± 10.4 years) were included in our study. None of the women had distal metastases at presentation. A repeated-measures ANOVA determined that mean BM SI index scores differed significantly across the three time points (F[1.62, 100.67] = 44.57, p < .001). At post hoc pairwise comparison using the Bonferroni correction BM SI index significantly increased between initial assessment and following treatment (2.15 vs 3.33, p < .001), and significantly decreased at 1-year follow-up (3.33 vs 1.45, p < .001). In a subgroup analysis, while women younger than 50 years had a significant increase in marrow enhancement after G-CSF treatment, in women aged 50 years and older, the difference was not statistically significant. CONCLUSION: Treatment with G-CSF as an adjunct to chemotherapy can result in increased sternal bone marrow enhancement due to marrow reconversion. Radiologists should be aware of this effect in order to avoid misinterpretation as false marrow metastases.

Large language model (ChatGPT) as a support tool for breast tumor board.

Large language models (LLM) such as ChatGPT have gained public and scientific attention. The aim of this study is to evaluate ChatGPT as a support tool for breast tumor board decisions making. We inserted into ChatGPT-3.5 clinical information of ten consecutive patients presented in a breast tumor board in our institution. We asked the chatbot to recommend management. The results generated by ChatGPT were compared to the final recommendations of the tumor board. They were also graded independently by two senior radiologists. Grading scores were between 1-5 (1 = completely disagree, 5 = completely agree), and in three different categories: summarization, recommendation, and explanation. The mean age was 49.4, 8/10 (80%) of patients had invasive ductal carcinoma, one patient (1/10, 10%) had a ductal carcinoma in-situ and one patient (1/10, 10%) had a phyllodes tumor with atypia. In seven out of ten cases (70%), ChatGPT's recommendations were similar to the tumor board's decisions. Mean scores while grading the chatbot's summarization, recommendation and explanation by the first reviewer were 3.7, 4.3, and 4.6 respectively. Mean values for the second reviewer were 4.3, 4.0, and 4.3, respectively. In this proof-of-concept study, we present initial results on the use of an LLM as a decision support tool in a breast tumor board. Given the significant advancements, it is warranted for clinicians to be familiar with the potential benefits and harms of the technology.

Large language models for oncological applications.

Large language models such as ChatGPT have gained public and scientific attention. These models may support oncologists in their work. Oncologists should be familiar with large language models to harness their potential while being aware of potential dangers and limitations.

[CONTRAST ENHANCED SPECTRAL MAMMOGRAPHY IN WOMEN WITH INTERMEDIATE BREAST CANCER RISK AND DENSE BREAST].

INTRODUCTION: Breast cancer screening decreases mortality and enables early diagnosis of breast cancer. Mammography is the only modality approved for breast cancer screening. Yet, mammography is limited in women with dense breasts. Contrast-enhanced mammography is a new imaging modality. OBJECTIVES: The aim of this study was to evaluate the diagnostic performance of contrast-enhanced mammography for breast cancer screening in women with dense breasts and intermediate breast cancer risk. The study strives to compare the diagnostic performance of contrast-enhanced mammography to standard digital mammography in women with intermediate-risk and dense breasts. METHODS: A retrospective cohort of 270 consecutive women who underwent screening with contrast mammography between the years 2015-2016. BI-RADS scores of both conventional and contrast-enhanced mammography were compared with the actual disease status, assessed by histopathology or imaging follow-up. Sensitivities, specificities, positive and negative predictive values were calculated. RESULTS: Conventional mammography detected 7 out of 11 breast cancers, with sensitivity of 63.6%, specificity 91.1%, positive predictive value 23.3% and negative predictive value of 98.3%. Contrast-enhanced mammography detected 10 out of 11 cancers. Sensitivity was 90.9%, specificity 70.7%, positive predictive value 11.6%, and negative predictive value 99.4. CONCLUSIONS: Contrast-enhanced mammography was more sensitive than digital mammography at detecting breast cancer in women with dense breasts and intermediate breast cancer risk. DISCUSSION: The technological development in breast imaging can be part of personalized medicine including contrast mammography for women with intermediate risk. Contrast mammography can be the screening examination for women with dense breasts and intermediate risk.

Alerting on mortality among patients discharged from the emergency department: a machine learning model.

OBJECTIVES: Physicians continuously make tough decisions when discharging patients. Alerting on poor outcomes may help in this decision. This study evaluates a machine learning model for predicting 30-day mortality in emergency department (ED) discharged patients. METHODS: We retrospectively analysed visits of adult patients discharged from a single ED (1/2014-12/2018). Data included demographics, evaluation and treatment in the ED, and discharge diagnosis. The data comprised of both structured and free-text fields. A gradient boosting model was trained to predict mortality within 30 days of release from the ED. The model was trained on data from the years 2014-2017 and validated on data from the year 2018. In order to reduce potential end-of-life bias, a subgroup analysis was performed for non-oncological patients. RESULTS: Overall, 363 635 ED visits of discharged patients were analysed. The 30-day mortality rate was 0.8%. A majority of the mortality cases (65.3%) had a known oncological disease. The model yielded an area under the curve (AUC) of 0.97 (95% CI 0.96 to 0.97) for predicting 30-day mortality. For a sensitivity of 84% (95% CI 0.81 to 0.86), this model had a false positive rate of 1:20. For patients without a known malignancy, the model yielded an AUC of 0.94 (95% CI 0.92 to 0.95). CONCLUSIONS: Although not frequent, patients may die following ED discharge. Machine learning-based tools may help ED physicians identify patients at risk. An optimised decision for hospitalisation or palliative management may improve patient care and system resource allocation.

MRI of the Lactating Breast: Computer-Aided Diagnosis False Positive Rates and Background Parenchymal Enhancement Kinetic Features.

RATIONALE AND OBJECTIVES: To investigate the application of computer-added diagnosis (CAD) in dynamic contrast-enhanced (DCE) MRI of the healthy lactating breast, focusing on false-positive rates and background parenchymal enhancement (BPE) coloring patterns in comparison with breast cancer features in non-lactating patients. MATERIALS AND METHODS: The study population was composed of 58 healthy lactating patients and control groups of 113 healthy premenopausal non-lactating patients and 55 premenopausal non-lactating patients with newly-diagnosed breast cancer. Patients were scanned on 1.5-T MRI using conventional DCE protocol. A retrospective analysis of DCE-derived CAD properties was conducted using a commercial software that is regularly utilized in our routine radiological work-up. Qualitative morphological characterization and automatically-obtained quantitative parametric measurements of the BPE-induced CAD coloring were categorized and subgroups' trends and differences between the lactating and cancer cohorts were statistically assessed. RESULTS: CAD false-positive coloring was found in the majority of lactating cases (87%). Lactation BPE coloring was characteristically non-mass enhancement (NME)-like shaped (87%), bilateral (79%) and symmetric (64%), whereas, unilateral coloring was associated with prior irradiation (p <0.0001). Inter-individual variability in CAD appearance of both scoring-grade and kinetic-curve dominance was found among the lactating cohort. When compared with healthy non-lactating controls, CAD false positive probability was significantly increased [Odds ratio 40.2, p <0001], while in comparison with the breast cancer cohort, CAD features were mostly inconclusive, even though increased size parameters were significantly associated with lactation-BPE (p <0.00001). CONCLUSION: BPE was identified as a common source for false-positive CAD coloring on breast DCE-MRI among lactating population. Despite several typical characteristics, overlapping features with breast malignancy warrant a careful evaluation and clinical correlation in all cases with suspected lactation induced CAD coloring.

Contrast-enhanced spectral mammography (CESM) in women presenting with palpable breast findings.

OBJECTIVE: Palpable breast abnormalities in women warrant diagnostic evaluation. Contrast-enhanced spectral mammography (CESM) is a novel technique which has demonstrated early promising results in the diagnostic imaging setting. The purpose of this study was to evaluate the role of CESM for imaging of palpable breast abnormalities and compare it to the current routine imaging work-up. MATERIALS AND METHODS: This retrospective study included women with palpable breast masses who underwent diagnostic CESM and ultrasound between 2012 and 2019. Diagnostic parameters for low-energy images, CESM and targeted ultrasound were calculated and compared. Analysis was performed at the lesion level. Additional incidental findings were reported separately. RESULTS: Included in this study were 138 women with 147 palpable breast abnormalities, of which 38 were cancers. Standard 2D mammography revealed 36/38 cancers (sensitivity 94.7%). All 38 cancers (100%) were detected at CESM and at targeted ultrasound. Negative predictive value for 2D mammography was 97.8% (91/93), and 100% for both ultrasound (74/74) and for CESM (80/80). None of the palpable masses that were negative at CESM but positive at ultrasound (n = 13) were malignant. Two additional incidental cancers were detected with CESM at the contralateral breast to the palpable lump. CONCLUSION: CESM could be useful for assessment of palpable breast abnormalities, potentially decreasing the number of unnecessary benign biopsies performed.

Background Parenchymal Enhancement at Contrast-Enhanced Spectral Mammography (CESM) as a Breast Cancer Risk Factor.

RATIONALE AND OBJECTIVES: To assess the extent of background parenchymal enhancement (BPE) at contrast-enhanced spectral mammography (CESM), association between clinical factors and BPE, and between BPE extent and breast cancer. MATERIALS AND METHODS: This study included 516 women who underwent CESM imaging for screening and diagnostic purposes between 2012 and 2015 in a single center. BPE at CESM images was retrospectively, independently and blindly graded by six experienced radiologists using the following scale: minimal, mild, moderate, or marked. Agreement between readers was estimated using Kendall's W coefficient of concordance. Associations between clinical factors and BPE, and between BPE and breast cancer were examined using generalized estimating equations. Association between BPE and breast cancer was assessed for the whole study group, and for the screening population separately. RESULTS: Most women underwent CESM for breast cancer screening (424/516, 82.2%). Mean age was 53 years, the majority had dense breasts (50.4-94%, depending on the reviewer), and minimal to mild BPE (75.8-89.9%). A total of 53/516 women had breast cancer. Overall concordance (W) values between the readers were 0.611 for breast density and 0.789 on BPE. Increased breast density and younger age were positive predictors for increased BPE (odds ratio [OR] 4.07, 95% confidence interval [CI] 2.32-7.14, p < 0.001; OR 2.88, 95% CI 1.87-4.42, p < 0.001, respectively). Breast radiation therapy was a negative predictor for BPE (OR 0.13, 95% CI 0.06-0.31, p < 0.001). Women with increased BPE had increased odds for breast cancer (OR 2.24, 95% CI 1.23-4.09, p = 0.008). This result was consistent when screening cases were analyzed separately (OR 6.27, 95% CI 2.38-16.53, p < 0.001). CONCLUSION: BPE at CESM was associated with breast density. Women with increased BPE had increased odds for breast cancer, independently of other potential risk factors.

Refractive surgery in the late adulthood and adolescent age groups.

PURPOSE: Most refractive surgeries are performed in the young-adult age group, and less is known about the clinical outcomes of patients in late adulthood and of adolescents. The purpose of this study was to describe the outcomes of refractive surgery in patients over the age of 60 years and under the age of 18 years compared with a control group of patients aged 20-40 years. METHODS: This retrospective cohort analysis consisted of 64,970 consecutive cases of 32,074 patients who underwent laser-assisted in situ keratomileusis and photorefractive keratectomy during a 10-year period in a single center. The populations were characterized, and a comparison of safety, efficacy, and retreatment rates was performed following propensity score matching, separately for hyperopic and myopic treatments. RESULTS: Included in the analysis after matching were 143 patients above the age of 60, 608 patients aged < 18, and 2313 patients aged 20-40. Older patients undergoing hyperopic treatments had worse safety (0.95 ± 0.1 versus 0.99 ± 0.2, P = 0.023) and efficacy indices (0.89 ± 0.2 versus 0.97 ± 0.2, P = 0.004) compared with young adults. Lower efficacy was also seen in myopic treatments (0.88 ± 0.3 versus 0.97 ± 0.2, P = 0.001). Higher retreatment rates were also seen among older adults (6.2% versus 2.5%, P = 0.044 in hyperopic treatments, 11% versus 1.1%, P < 0.001 in myopic treatments). In adolescents, the safety and efficacy outcomes were slightly better compared with patients aged 20-40, with lower retreatment rates (1% versus 2.7%, P = 0.001). CONCLUSIONS: Refractive surgery in the late adulthood population of our cohort was a relatively safe procedure, yet manifesting lower efficacy and requiring more retreatments. In adolescents, results were comparable to those achieved in young adults.

Contrast-Enhanced Spectral Mammography in Women With Intermediate Breast Cancer Risk and Dense Breasts.

OBJECTIVE: The purpose of this study was to compare the diagnostic performance of contrast-enhanced spectral mammography (CESM) and ultrasound with that of standard digital mammography for breast cancer screening of women at intermediate risk who have dense breasts. MATERIALS AND METHODS: In a retrospective cohort of 611 consecutively registered women who underwent screening CESM from 2012 to 2017, BI-RADS scores of the screening modalities were compared with actual disease status, assessed by histopathologic analysis or imaging follow-up. Sensitivity, specificity, and positive and negative predictive values were calculated. RESULTS: Among the 611 women included, 48.3% (295/611) had family or personal history of breast cancer, the BI-RADS breast density score was C or D in 93.1% (569/611). The mean follow-up period was 20 months. Mammography depicted 11 of 21 malignancies, sensitivity of 52.4%, specificity of 90.5% (534/590), positive predictive value of 16.4% (11/67), and negative predictive value of 98.2% (534/544). CESM depicted 19 of 21 malignancies, sensitivity of 90.5%, specificity of 76.1% (449/590), positive predictive value of 11.9% (19/160), and negative predictive value of 99.6% (449/451). Differences in sensitivity (p = 0.008) and specificity (p < 0.001) were statistically significant. Adjunct ultrasound revealed 73 additional suspicious findings; all were false-positive. In 39 women MRI was needed to assess screening abnormalities; two MRI-guided biopsies were performed and yielded one cancer. The incremental cancer detection rate of CESM was 13.1/1000 women (95% CI, 6.1-20.1). Of eight cancers seen only with CESM, seven were invasive (mean size, 9 mm; two of four cancers lymph-node positive). CONCLUSION: CESM was significantly more sensitive than standard digital mammography for detecting breast cancer in this screening population. No added benefit was found in the performance of ultrasound as an adjunct to CESM screens with negative results. CESM may be a valuable supplemental screening modality for women at intermediate risk who have dense breasts.