Breast cancer detection accuracy of AI in an entire screening population: a retrospective, multicentre study.

BACKGROUND: Artificial intelligence (AI) systems are proposed as a replacement of the first reader in double reading within mammography screening. We aimed to assess cancer detection accuracy of an AI system in a Danish screening population. METHODS: We retrieved a consecutive screening cohort from the Region of Southern Denmark including all participating women between Aug 4, 2014, and August 15, 2018. Screening mammograms were processed by a commercial AI system and detection accuracy was evaluated in two scenarios, Standalone AI and AI-integrated screening replacing first reader, with first reader and double reading with arbitration (combined reading) as comparators, respectively. Two AI-score cut-off points were applied by matching at mean first reader sensitivity (AIsens) and specificity (AIspec). Reference standard was histopathology-proven breast cancer or cancer-free follow-up within 24 months. Coprimary endpoints were sensitivity and specificity, and secondary endpoints were positive predictive value (PPV), negative predictive value (NPV), recall rate, and arbitration rate. Accuracy estimates were calculated using McNemar's test or exact binomial test. RESULTS: Out of 272,008 screening mammograms from 158,732 women, 257,671 (94.7%) with adequate image data were included in the final analyses. Sensitivity and specificity were 63.7% (95% CI 61.6%-65.8%) and 97.8% (97.7-97.8%) for first reader, and 73.9% (72.0-75.8%) and 97.9% (97.9-98.0%) for combined reading, respectively. Standalone AIsens showed a lower specificity (-1.3%) and PPV (-6.1%), and a higher recall rate (+ 1.3%) compared to first reader (p < 0.0001 for all), while Standalone AIspec had a lower sensitivity (-5.1%; p < 0.0001), PPV (-1.3%; p = 0.01) and NPV (-0.04%; p = 0.0002). Compared to combined reading, Integrated AIsens achieved higher sensitivity (+ 2.3%; p = 0.0004), but lower specificity (-0.6%) and PPV (-3.9%) as well as higher recall rate (+ 0.6%) and arbitration rate (+ 2.2%; p < 0.0001 for all). Integrated AIspec showed no significant difference in any outcome measures apart from a slightly higher arbitration rate (p < 0.0001). Subgroup analyses showed higher detection of interval cancers by Standalone AI and Integrated AI at both thresholds (p < 0.0001 for all) with a varying composition of detected cancers across multiple subgroups of tumour characteristics. CONCLUSIONS: Replacing first reader in double reading with an AI could be feasible but choosing an appropriate AI threshold is crucial to maintaining cancer detection accuracy and workload.

Population-wide evaluation of artificial intelligence and radiologist assessment of screening mammograms.

OBJECTIVES: To validate an AI system for standalone breast cancer detection on an entire screening population in comparison to first-reading breast radiologists. MATERIALS AND METHODS: All mammography screenings performed between August 4, 2014, and August 15, 2018, in the Region of Southern Denmark with follow-up within 24 months were eligible. Screenings were assessed as normal or abnormal by breast radiologists through double reading with arbitration. For an AI decision of normal or abnormal, two AI-score cut-off points were applied by matching at mean sensitivity (AIsens) and specificity (AIspec) of first readers. Accuracy measures were sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and recall rate (RR). RESULTS: The sample included 249,402 screenings (149,495 women) and 2033 breast cancers (72.6% screen-detected cancers, 27.4% interval cancers). AIsens had lower specificity (97.5% vs 97.7%; p < 0.0001) and PPV (17.5% vs 18.7%; p = 0.01) and a higher RR (3.0% vs 2.8%; p < 0.0001) than first readers. AIspec was comparable to first readers in terms of all accuracy measures. Both AIsens and AIspec detected significantly fewer screen-detected cancers (1166 (AIsens), 1156 (AIspec) vs 1252; p < 0.0001) but found more interval cancers compared to first readers (126 (AIsens), 117 (AIspec) vs 39; p < 0.0001) with varying types of cancers detected across multiple subgroups. CONCLUSION: Standalone AI can detect breast cancer at an accuracy level equivalent to the standard of first readers when the AI threshold point was matched at first reader specificity. However, AI and first readers detected a different composition of cancers. CLINICAL RELEVANCE STATEMENT: Replacing first readers with AI with an appropriate cut-off score could be feasible. AI-detected cancers not detected by radiologists suggest a potential increase in the number of cancers detected if AI is implemented to support double reading within screening, although the clinicopathological characteristics of detected cancers would not change significantly. KEY POINTS: • Standalone AI cancer detection was compared to first readers in a double-read mammography screening population. • Standalone AI matched at first reader specificity showed no statistically significant difference in overall accuracy but detected different cancers. • With an appropriate threshold, AI-integrated screening can increase the number of detected cancers with similar clinicopathological characteristics.

FDG-PET/CT in high-risk primary breast cancer-a prospective study of stage migration and clinical impact.

PURPOSE: To investigate the clinical impact of FDG-PET/CT for staging and treatment planning in high-risk primary breast cancer. METHODS: Women with high-risk primary breast cancer were enrolled between September 2017 and August 2019 at Odense University Hospital, Denmark. Conventional mammography with/without MRI was performed before staging by FDG-PET/CT. We studied the accuracy of FDG-PET/CT for the detection of distant metastases, the effect on the change of treatment, and the prevalence of incidental findings. Biopsy and follow-up were used as a reference standard for the accuracy analysis. RESULTS: Of 103 women, 24 (23%) were diagnosed with distant metastases by FDG-PET/CT. Among these, breast surgery was omitted in 18 and could have been spared in six. Another sixteen (16%) patients were upstaged to more advanced loco-regional disease, leading to more extensive radiotherapy. Sensitivity and specificity for diagnosing distant metastases were 1.00 (95% confidence interval: 0.86-1.00) and 0.95 (0.88-0.99), respectively. Twenty-nine incidental findings were detected in 24 women (23%), leading to further examinations in 22 and diagnosis of eight (8/22, 36%) synchronous diseases: cancer (n = 4), thyroiditis (n = 2), aorta aneurysm (n = 1), and meningioma (n = 1). CONCLUSIONS: FDG-PET/CT had a substantial impact on staging and change of treatment in women with high-risk primary breast cancer, and further examination of incidental findings was considered clinically relevant. Our findings suggest that FDG-PET/CT should be considered for primary staging in high-risk primary breast cancer to improve treatment planning.

[Artificial intelligence for cancer detection in breast cancer screening].

Artificial intelligence (AI) has the potential to increase quality and efficiency of breast cancer screening. Recent studies have provided comparative data on AI versus human performance in cancer detection with encouraging results, and commercially available AI systems are used worldwide as a clinical tool for mammography screening. There are, however, a number of methodological concerns in relation to the evaluation of AI systems. This review discusses these aspects as well as the opportunities and challenges of clinical validation and implementation in breast cancer screening practice.

Prevalence of focal incidental breast uptake on FDG-PET/CT and risk of malignancy: a systematic review and meta-analysis.

BACKGROUND: FDG-PET/CT is increasingly used for oncologic and inflammatory diseases. Focal incidental FDG uptake occurs rarely in breast tissue but has often significant consequences. This study aimed to systematically review literature regarding focal incidental breast uptake (FIBU) on FDG-PET/CT in order to yield an update on the prevalence and risk of malignancy for FIBU. METHODS: A systematic search for relevant articles published between 2012 and 2018 was performed through MEDLINE, Embase, and Cochrane databases. Studies addressing the detection of FIBU in patients without a previous history of breast malignancy were included. The QUADAS-2 was used for quality assessment, and eligible data were pooled using a fixed-effects model. I2 was calculated for the heterogeneity between studies. RESULTS: Eight studies containing 180,002 scans were included in the systematic review. The median prevalence of FIBU for both genders was 0.52% (range 0.18-22.5%). Prevalence for women was mentioned separately in five studies and varied from 0.51 to 23.5%. One study reporting a high prevalence was based on patients being staged for known malignancy, and the word "breast" was used in the search, which may have caused selection bias. Data from four studies were eligible for meta-analysis. A high degree of heterogeneity was observed for prevalence data (I2 of 97.5%), while moderate heterogeneity was observed for data on malignancy risk assessment (I2 of 62.8%). The pooled prevalence of FIBU in women was 0.61% (range 0.56-0.66%), and the pooled prevalence of malignancy of FIBUs was 38.7% (range 34.4-43.0%). The most commonly detected malignancy was invasive ductal carcinoma. CONCLUSION: FIBU occurs rarely on FDG-PET/CT for female patients but yields a high risk of malignancy according to the results of published papers. Therefore, it should be considered relevant to further elucidate patients with incidentally detected FDG uptake in breast in clinical practice.

Comparison of screening performance metrics and patient dose of two mammographic image acquisition modes in the Danish National Breast Cancer Screening Programme.

INTRODUCTION: In this study, screening performance metrics and radiation dose were compared for two image acquisition modes for breast cancer screening with MAMMOMAT Inspiration (Siemens Healthcare GmbH, Forchheim, Germany). This mammography system can operate without an anti-scatter grid in place but using software scatter correction instead. This grid-less acquisition mode (PRIME) requires less patient dose due to the increase in primary radiation reaching the detector. This study retrospectively analyses data from the Region of Southern Denmark where the grid-less mode has been installed in November 2013 and replaced grid-based screening. METHODS AND MATERIALS: A total of 72,188 screening cases from the same geographical region in Denmark were included in the study. They were subdivided into two study populations: cases acquired before and after installation of the grid-less acquisition mode. Sensitivity and specificity of breast cancer screening were calculated for the two populations; thus representing the performance of grid-less and grid-based screening. To measure the entrance surface air kerma (ESAK) additional phantom tests were carried out. Polymethylmethacrylate (PMMA) attenuation plates with different thicknesses (20-70 mm in steps of 10 mm) simulated the compressed breast (21 mm-90 mm) and a solid-state dosimeter was used. RESULTS: Statistical testing of the results showed that screening with grid-less acquisition provides equivalent performance with respect to sensitivity and specificity compared to grid-based screening. The specificity was 98.11% (95% confidence interval (CI) from 97.93% to 98.29%) and 97.96% (95% CI from 97.84% to 98.09%) for screening with grid-less acquisition and grid-based acquisition, respectively. The cancer detection rate as a measure for sensitivity was equal (0.55%) for grid-less screening and grid-based screening. An average glandular dose saving between 13.5% and 36.4% depending on breast thickness in grid-less acquisition was obtained compared to grid-based acquisition. CONCLUSION: Statistically significant equivalence was shown with an equivalence margin of 0.12% points for cancer detection rate and with an equivalence margin of 0.40% points for specificity. A marked patient dose savings in grid-less acquisition of up to 36% compared to grid-based acquisition was achieved. It can be concluded that grid-less acquisition with software scatter correction is an alternative to grid-based acquisition in mammography.

[18F]Fluorodeoxyglucose (FDG)-Positron Emission Tomography (PET)/Computed Tomography (CT) in Suspected Recurrent Breast Cancer: A Prospective Comparative Study of Dual-Time-Point FDG-PET/CT, Contrast-Enhanced CT, and Bone Scintigraphy.

PURPOSE: To prospectively investigate the diagnostic accuracy of [(18)F]fluorodeoxyglucose (FDG)-positron emission tomography (PET)/computed tomography (CT) with dual-time-point imaging, contrast-enhanced CT (ceCT), and bone scintigraphy (BS) in patients with suspected breast cancer recurrence. PATIENTS AND METHODS: One hundred women with suspected recurrence of breast cancer underwent 1-hour and 3-hour FDG-PET/CT, ceCT, and BS within approximately 10 days. The study was powered to estimate the precision of the individual imaging tests. Images were visually interpreted using a four-point assessment scale, and readers were blinded to other test results. The reference standard was biopsy along with treatment decisions and clinical follow-up (median, 17 months). RESULTS: FDG-PET/CT resulted in no false negatives and fewer false positives than the other imaging techniques. Accuracy of results were similar for 1-hour and 3-hour FDG-PET/CT. For distant recurrence, the area under the receiver operating curve was 0.99 (95% CI, 0.97 to 1) for FDG-PET/CT, 0.84 (95% CI, 0.73 to 0.94) for ceCT, and 0.86 (95% CI, 0.77 to 0.94) for the combined ceCT+BS. Of 100 patients, 22 (22%) were verified with distant recurrence, and 18 of these had bone involvement. Nineteen patients (19%) had local recurrence only. In exploratory analyses, diagnostic accuracy of FDG-PET/CT was better than ceCT alone or ceCT combined with BS in diagnosing distant, bone, and local recurrence, shown by a greater area under the receiver operating curve and higher sensitivity, specificity, and superior likelihood ratios. CONCLUSION: FDG-PET/CT was accurate in diagnosing recurrence in breast cancer patients. It allowed for distant recurrence to be correctly ruled out and resulted in only a small number of false-positive cases. Exploratory findings suggest that FDG-PET/CT has greater accuracy than conventional imaging technologies in this patient group.

[Seminal vesicle cyst with ipsilateral renal agenesis]. / Vesicula seminalis-cyste med ipsilateral nyreagenesi.

A formerly healthy 41-year-old male with monosymptomatic swelling of his left testicle was diagnosed with testicular cancer (seminoma). During staging of the cancer a computed tomography showed left renal agenesis and an 8 x 6 cm retrovesical space-occupying lesion in the left side of the pelvis. The lesion was interpreted as a group of enlarged lymph nodes, but PET/CT and MRI later demonstrated that it was a left seminal vesicle cyst. An association between congenital seminal vesicle cysts and ipsilateral renal agenesis is rare and can be explained by their common embryologic origin.