Search

Background Understanding women’s perspectives can help to create an effective and acceptable artificial intelligence (AI) implementation for triaging mammograms, ensuring a high proportion of screening-detected cancer. This study aimed to explore Swedish women’s perceptions and attitudes towards the use of AI in mammography.Method Semistructured interviews were conducted with 16 women recruited in the spring of 2023 at Capio S:t Görans Hospital, Sweden, during an ongoing clinical trial of AI in screening (ScreenTrustCAD, NCT 04778670) with Philips equipment. The interview transcripts were analysed using inductive thematic content analysis.Results In general, women viewed AI as an excellent complementary tool to help radiologists in their decision-making, rather than a complete replacement of their expertise. To trust the AI, the women requested a thorough evaluation, transparency about AI usage in healthcare, and the involvement of a radiologist in the assessment. They would rather be more worried because of being called in more often for scans than risk having overlooked a sign of cancer. They expressed substantial trust in the healthcare system if the implementation of AI was to become a standard practice.Conclusion The findings suggest that the interviewed women, in general, hold a positive attitude towards the implementation of AI in mammography; nonetheless, they expect and demand more from an AI than a radiologist. Effective communication regarding the role and limitations of AI is crucial to ensure that patients understand the purpose and potential outcomes of AI-assisted healthcare.

Summary: Background: Artificial intelligence (AI) as an independent reader of screening mammograms has shown promise, but there are few prospective studies. Our aim was to conduct a prospective clinical trial to examine how AI affects cancer detection and false positive findings in a real-world setting. Methods: ScreenTrustCAD was a prospective, population-based, paired-reader, non-inferiority study done at the Capio Sankt Göran Hospital in Stockholm, Sweden. Consecutive women without breast implants aged 40–74 years participating in population-based screening in the geographical uptake area of the study hospital were included. The primary outcome was screen-detected breast cancer within 3 months of mammography, and the primary analysis was to assess non-inferiority (non-inferiority margin of 0·15 relative reduction in breast cancer diagnoses) of double reading by one radiologist plus AI compared with standard-of-care double reading by two radiologists. We also assessed single reading by AI alone and triple reading by two radiologists plus AI compared with standard-of-care double reading by two radiologists. This study is registered with ClinicalTrials.gov, NCT04778670. Findings: From April 1, 2021, to June 9, 2022, 58 344 women aged 40–74 years underwent regular mammography screening, of whom 55 581 were included in the study. 269 (0·5%) women were diagnosed with screen-detected breast cancer based on an initial positive read: double reading by one radiologist plus AI was non-inferior for cancer detection compared with double reading by two radiologists (261 [0·5%] vs 250 [0·4%] detected cases; relative proportion 1·04 [95% CI 1·00–1·09]). Single reading by AI (246 [0·4%] vs 250 [0·4%] detected cases; relative proportion 0·98 [0·93–1·04]) and triple reading by two radiologists plus AI (269 [0·5%] vs 250 [0·4%] detected cases; relative proportion 1·08 [1·04–1·11]) were also non-inferior to double reading by two radiologists. Interpretation: Replacing one radiologist with AI for independent reading of screening mammograms resulted in a 4% higher non-inferior cancer detection rate compared with radiologist double reading. Our study suggests that AI in the study setting has potential for controlled implementation, which would include risk management and real-world follow-up of performance. Funding: Swedish Research Council, Swedish Cancer Society, Region Stockholm, and Lunit.

Computer-aided detection systems based on deep learning have shown good performance in breast cancer detection. However, high-density breasts show poorer detection performance since dense tissues can mask or even simulate masses. Therefore, the sensitivity of mammography for breast cancer detection can be reduced by more than 20% in dense breasts. Additionally, extremely dense cases reported an increased risk of cancer compared to low-density breasts. This study aims to improve the mass detection performance in high-density breasts using synthetic high-density full-field digital mammograms (FFDM) as data augmentation during breast mass detection model training. To this end, a total of five cycle-consistent GAN (CycleGAN) models using three FFDM datasets were trained for low-to-high-density image translation in high-resolution mammograms. The training images were split by breast density BI-RADS categories, being BI-RADS A almost entirely fatty and BI-RADS D extremely dense breasts. Our results showed that the proposed data augmentation technique improved the sensitivity and precision of mass detection in models trained with small datasets and improved the domain generalization of the models trained with large databases. In addition, the clinical realism of the synthetic images was evaluated in a reader study involving two expert radiologists and one surgical oncologist.

Abstract Background Kidney disease and renal failure are associated with hospital deaths in patients with COVID − 19. We aimed to test if contrast enhancement affects short-term renal function in hospitalized COVID − 19 patients. Methods Plasma creatinine (P-creatinine) was measured on the day of computed tomography (CT) and 24 h, 48 h, and 4–10 days after CT. Contrast-enhanced (n = 142) and unenhanced (n = 24) groups were subdivided, based on estimated glomerular filtration rates (eGFR), > 60 and ≤ 60 ml/min/1.73 m2. Contrast-induced acute renal failure (CI-AKI) was defined as ≥27 μmol/L increase or a > 50% rise in P-creatinine from CT or initiation of renal replacement therapy during follow-up. Patients with renal replacement therapy were studied separately. We evaluated factors associated with a > 50% rise in P-creatinine at 48 h and at 4–10 days after contrast-enhanced CT. Results Median P-creatinine at 24–48 h and days 4–10 post-CT in patients with eGFR> 60 and eGFR≥30–60 in contrast-enhanced and unenhanced groups did not differ from basal values. CI-AKI was observed at 48 h and at 4–10 days post contrast administration in 24 and 36% (n = 5/14) of patients with eGFR≥30–60. Corresponding figures in the eGFR> 60 contrast-enhanced CT group were 5 and 5% respectively, (p 60.

Purpose: Severe COVID-19 is associated with inflammation, thromboembolic disease, and high mortality. We studied factors associated with fatal outcomes in consecutive COVID-19 patients examined by computed tomography pulmonary angiogram (CTPA).Methods: This retrospective, single-center cohort analysis included 130 PCR-positive patients hospitalized for COVID-19 [35 women and 95 men, median age 57 years (interquartile range 51–64)] with suspected pulmonary embolism based on clinical suspicion. The presence and extent of embolism and parenchymal abnormalities on CTPA were recorded. The severity of pulmonary parenchymal involvement was stratified by two experienced radiologists into two groups: lesions affecting ≤50% or >50% of the parenchyma. Patient characteristics, radiological aspects, laboratory parameters, and 60-day mortality data were collected.Results: Pulmonary embolism was present in 26% of the patients. Most emboli were small and peripheral. Patients with widespread parenchymal abnormalities, with or without pulmonary embolism, had increased main pulmonary artery diameter (p < 0.05) and higher C-reactive protein (p < 0.01), D-dimer (p < 0.01), and troponin T (p < 0.001) and lower hemoglobin (p < 0.001). A wider main pulmonary artery diameter correlated positively with C-reactive protein (r = 0.28, p = 0.001, and n = 130) and procalcitonin. In a multivariant analysis, D-dimer >7.2 mg/L [odds ratio (±95% confidence interval) 4.1 (1.4–12.0)] and ICU stay were significantly associated with embolism (p < 0.001). The highest 60-day mortality was found in patients with widespread parenchymal abnormalities combined with pulmonary embolism (36%), followed by patients with widespread parenchymal abnormalities without pulmonary embolism (26%). In multivariate analysis, high troponin T, D-dimer, and plasma creatinine and widespread parenchymal abnormalities on CT were associated with 60-day mortality.Conclusions: Pulmonary embolism combined with widespread parenchymal abnormalities contributed to mortality risk in COVID-19. Elevated C-reactive protein, D-dimer, troponin-T, P-creatinine, and enlarged pulmonary artery were associated with a worse outcome and may mirror a more severe systemic disease. A liberal approach to radiological investigation should be recommended at clinical deterioration, when the situation allows it. Computed tomography imaging, even without intravenous contrast to assess the severity of pulmonary infiltrates, are of value to predict outcome in COVID-19. Better radiological techniques with higher resolution could potentially improve the detection of microthromboses. This could influence anticoagulant treatment strategies, preventing clinical detoriation.

Abstract Background High mammographic density is associated with breast cancer and with delayed detection. We have examined whether localized density, at the site of the subsequent cancer, is independently associated with being diagnosed with a large-sized or interval breast cancer. Methods Within a prospective cohort of 63,130 women, we examined 891 women who were diagnosed with incident breast cancer. For 386 women, retrospective localized density assessment was possible. The main outcomes were interval cancer vs. screen-detected cancer and large (> 2 cm) vs. small cancer. In negative screening mammograms, overall and localized density were classified reflecting the BI-RADS standard. Density concordance probabilities were estimated through multinomial regression. The associations between localized density and the two outcomes were modeled through logistic regression, adjusted for overall density, age, body mass index, and other characteristics. Results The probabilities of concordant localized density were 0.35, 0.60, 0.38, and 0.32 for overall categories “A,” “B,” “C,” and “D.” Overall density was associated with large cancer, comparing density category D to A with OR 4.6 (95%CI 1.8–11.6) and with interval cancer OR 31.5 (95%CI 10.9–92) among all women. Localized density was associated with large cancer at diagnosis with OR 11.8 (95%CI 2.7–51.8) among all women and associated with first-year interval cancer with OR 6.4 (0.7 to 58.7) with a significant linear trend p = 0.027. Conclusions Overall density often misrepresents localized density at the site where cancer subsequently arises. High localized density is associated with interval cancer and with large cancer. Our findings support the continued effort to develop and examine computer-based measures of localized density for use in personalized breast cancer screening.

Abstract Background Breast cancer patients who have not previously attended mammography screening may be more likely to discontinue adjuvant hormone therapy and therefore have a worse disease prognosis. Methods We conducted a population-based cohort study using data from Stockholm Mammography Screening Program, Stockholm-Gotland Breast Cancer Register, Swedish Prescribed Drug Register, and Swedish Cause of Death Register. Women in Stockholm who were diagnosed with breast cancer between 2001 and 2008 were followed until December 31, 2015. Non-participants of mammography screening were defined as women who, prior to their breast cancer diagnosis, were invited for mammography screening but did not attend. Results Of the 5098 eligible breast cancer patients, 4156 were defined as screening participants and 942 as non-participants. Compared with mammography screening participants, non-participants were more likely to discontinue adjuvant hormone therapy, with an adjusted hazard ratio (HR) of 1.30 (95% CIs, 1.11 to 1.53). Breast cancer patients not participating in mammography screening were also more likely to have worse disease-free survival, even after adjusting for tumor characteristics and other covariates (adjusted HR 1.22 (95% CIs, 1.05 to 1.42 for a breast cancer event). Conclusions Targeted interventions to prevent discontinuation of adjuvant hormone therapy are needed to improve breast cancer outcomes among women not attending mammography screening.

Abstract Background Breast cancer prognosis is strongly associated with tumor size at diagnosis. We aimed to identify factors associated with diagnosis of large (> 2 cm) compared to small tumors, and to examine implications for long-term prognosis. Methods We examined 2012 women with invasive breast cancer, of whom 1466 had screen-detected and 546 interval cancers that were incident between 2001 and 2008 in a population-based screening cohort, and followed them to 31 December 2015. Body mass index (BMI) was ascertained after diagnosis at the time of study enrollment during 2009. PD was measured based on the contralateral mammogram within 3 years before diagnosis. We used multiple logistic regression modeling to examine the association between tumor size and body mass index (BMI), mammographic percent density (PD), or hormonal and genetic risk factors. Associations between the identified risk factors and, in turn, the outcomes of local recurrence, distant metastases, and death (153 events in total) in women with breast cancer were examined using Cox regression. Analyses were carried out according to mode of detection. Results BMI and PD were the only factors associated with tumor size at diagnosis. For BMI (≥25 vs. < 25 kg/m2), the multiple adjusted odds ratios (OR) were 1.37 (95% CI 1.02–1.83) and 2.12 (95% CI 1.41–3.18), for screen-detected and interval cancers, respectively. For PD (≥20 vs. < 20%), the corresponding ORs were 1.72 (95% CI 1.29–2.30) and 0.60 (95% CI 0.40–0.90). Among women with interval cancers, those with high BMI had worse prognosis than women with low BMI (hazard ratio 1.70; 95% CI 1.04–2.77), but PD was not associated with the hazard rate. Among screen-detected cancers, neither BMI nor PD was associated with the hazard rate. Conclusions In conclusion, high BMI was associated with the risk of having a tumor larger than 2 cm at diagnosis. Among women with interval cancer, high BMI was associated with worse prognosis. We believe that women with high BMI should be especially encouraged to attend screening.