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.

Prostate cancer metastasis mimicking appendicitis-A rare but important differential diagnosis in PET/CT imaging.

Prostate cancer most commonly metastasizes to lymph nodes, bones, the liver, and the lungs. Prostate cancer carcinomatosis with an affinity for the appendix is not well described in current literature and is usually reported with acute appendicitis as the primary presentation. A 65-year-old male with a history of recurrent prostate cancer presented with an increase in PSA value. 18F-PSMA-1007 PET/CT showed nodular tissue growth and increased PSMA uptake in the prostate, on the appendix, in the umbilicus, and in several intra- and extra pelvic lymph nodes. The patient had no symptomatic complaints at time of referral. Imaging findings of the appendix resembling characteristic findings of acute appendicitis raised doubts about the interpretation of these as inflammatory disease or peritoneal carcinomatosis secondary to prostate cancer. This case demonstrates the importance of correct differentiation between the 2 conditions based on imaging, clinical symptomatology, and patient history to provide proper care in time.

The incidence of schizophrenia and schizophrenia spectrum disorders in Denmark in the period 2000-2012. A register-based study.

INTRODUCTION: We aimed to examine changes over time in the incidence of broad and narrow schizophrenia spectrum disorders in Denmark from 2000 to 2012. METHODS: Patients were classified as incident schizophrenia if registered with a first time in- or outpatient contact with relevant diagnostic codes in the Danish Psychiatric Central Register between 2000 and 2012. Their history of contacts was traced back to 1969. Broad schizophrenia included schizophrenia, schizotypal disorder, persistent delusional disorder, acute and transient psychotic disorders, schizoaffective disorders, and other nonorganic and unspecified psychotic disorders, (ICD 10 codes F20-F29). Narrow schizophrenia was defined with the ICD 10 codes F20.0-F20.9. Incidence rates (IR) and incidence rate ratios (IRR) were calculated using Poisson regression. RESULTS: The IRR for broad schizophrenia increased by 1.43 (CI 95% 1.34-1.52) for females and 1.26 (CI 95% 1.20-1.33) for males. IRR for narrow schizophrenia increased by 1.36 (CI 95% 1.24-1.48) for females and 1.20 (CI 95% 1.11-1.29) for males. There was a significantly increased incidence in patients up to 32years of age. This was mainly explained by a significant 2-3 fold increase in outpatient incidence. We found a significant decrease in IRR for patients with broad and narrow schizophrenia aged 33 or older for both in- and outpatients. CONCLUSION: The increased incidence of schizophrenia could partly be explained by better implementation of the diagnostic criteria for schizophrenia in child and adolescent psychiatry and improved access to early intervention services, but a true increase in incidence of schizophrenia cannot be excluded. The decrease of incidence in the older age group could indicate that the national Danish early intervention strategy was successful.