Objectives This study evaluated the usefulness of artificial intelligence (AI) algorithms as tools in improving the accuracy of histologic classification of breast tissue. Methods Overall, 100 microscopic photographs (test A) and 152 regions of interest in whole-slide images (test B) of breast tissue were classified into 4 classes: normal, benign, carcinoma in situ (CIS), and invasive carcinoma. The accuracy of 4 pathologists and 3 pathology residents were evaluated without and with the assistance of algorithms. Results In test A, algorithm A had accuracy of 0.87, with the lowest accuracy in the benign class (0.72). The observers had average accuracy of 0.80, and most clinically relevant discordances occurred in distinguishing benign from CIS (7.1% of classifications). With the assistance of algorithm A, the observers significantly increased their average accuracy to 0.88. In test B, algorithm B had accuracy of 0.49, with the lowest accuracy in the CIS class (0.06). The observers had average accuracy of 0.86, and most clinically relevant discordances occurred in distinguishing benign from CIS (6.3% of classifications). With the assistance of algorithm B, the observers maintained their average accuracy. Conclusions AI tools can increase the classification accuracy of pathologists in the setting of breast lesions.

No abstract

Relapsing polychondritis (RP) is a rare autoimmune systemic disease, especially in childhood. To report three new pediatric RP cases, to provide a literature review and to compare with adulthood disease, retrospective data collection from three childhood RP cases was observed in a Brazilian Pediatric Rheumatology Division. A literature review based on a MEDLINE database search was performed. Arthritis and auricular chondritis were present in our three patients. Two cases presented with early and severe laryngotracheal chondritis, besides initial and symptomatic costochondritis. The other case developed prominent epiphyseal plate involvement. Two patients were refractory to corticosteroids and immunosuppressants and required the use of TNF-alpha inhibitors to improve the symptoms, while corticosteroids plus methotrexate induced remission in the other patient. The literature review showed 44 cases of pediatric-onset disease in English language. Arthritis and ear chondritis are the most common initial and cumulative manifestations of RP in children and adults. Nasal and laryngotracheobronchial chondritis are also common manifestations observed during follow-up in childhood. There is also an early severity of respiratory chondritis in childhood, requiring aggressive treatment with corticosteroids, immunosuppressants and biologic agents. The data presented by those 3 children, considered in conjunction with the data from the 44 published cases, may reflect some distinguishing childhood RP features, such as more severe and frequent respiratory tract involvement, symptomatic costochondritis and the atypical pattern of persistent and destructive arthritis with epiphyseal plate involvement. Response to immunosuppressants and biologic agents is anecdotal, but steroids remain the main drug during the flares.

No abstract