Background Mammography is the current standard for breast cancer screening. This study aimed to develop an artificial intelligence (AI) algorithm for diagnosis of breast cancer in mammography, and explore whether it could benefit radiologists by improving accuracy of diagnosis. Methods In this retrospective study, an AI algorithm was developed and validated with 170 230 mammography examinations collected from five institutions in South Korea, the USA, and the UK, including 36 468 cancer positive confirmed by biopsy, 59 544 benign confirmed by biopsy (8827 mammograms) or follow-up imaging (50 717 mammograms), and 74 218 normal. For the multicentre, observer-blinded, reader study, 320 mammograms (160 cancer positive, 64 benign, 96 normal) were independently obtained from two institutions. 14 radiologists participated as readers and assessed each mammogram in terms of likelihood of malignancy (LOM), location of malignancy, and necessity to recall the patient, first without and then with assistance of the AI algorithm. The performance of AI and radiologists was evaluated in terms of LOM-based area under the receiver operating characteristic curve (AUROC) and recall-based sensitivity and specificity. Findings The AI standalone performance was AUROC 0•959 (95% CI 0•952-0•966) overall, and 0•970 (0•963-0•978) in the South Korea dataset, 0•953 (0•938-0•968) in the USA dataset, and 0•938 (0•918-0•958) in the UK dataset. In the reader study, the performance level of AI was 0•940 (0•915-0•965), significantly higher than that of the radiologists without AI assistance (0•810, 95% CI 0•770-0•850; p<0•0001). With the assistance of AI, radiologists' performance was improved to 0•881 (0•850-0•911; p<0•0001). AI was more sensitive to detect cancers with mass (53 [90%] vs 46 [78%] of 59 cancers detected; p=0•044) or distortion or asymmetry (18 [90%] vs ten [50%] of 20 cancers detected; p=0•023) than radiologists. AI was better in detection of T1 cancers (73 [91%] vs 59 [74%] of 80; p=0•0039) or node-negative cancers (104 [87%] vs 88 [74%] of 119; p=0•0025) than radiologists. Interpretation The AI algorithm developed with large-scale mammography data showed better diagnostic performance in breast cancer detection compared with radiologists. The significant improvement in radiologists' performance when aided by AI supports application of AI to mammograms as a diagnostic support tool.

Intracellular Vitamin C (VC) is maintained at high levels in the developing brain by the activity of sodium-dependent VC transporter 2 (Svct2), suggesting specific VC functions in brain development. A role of VC as a cofactor for Fe(II)-2-oxoglutarate-dependent dioxygenases has recently been suggested. We show that VC supplementation in neural stem cell (NSC) cultures derived from embryonic midbrains greatly enhanced differentiation towards midbrain-type DA (mDA) neurons, the neuronal subtype associated with Parkinson’s disease. VC induced gain of 5-hydroxymethylcytosine (5hmC) and loss of H3K27m3 in DA phenotype gene promoters, which are catalyzed by Tet1 and Jmjd3, respectively. Consequently VC enhanced DA phenotype gene transcriptions in the progenitors by Nurr1, a transcription factor critical for mDA neuron development, to be more accessible to the gene promoters. Further mechanism studies including Tet1 and Jmjd3 knockdown/inhibition experiments revealed that both the 5hmC and H3K27m3 changes, specifically in the progenitor cells, are indispensible for the VC-mediated mDA neuron differentiation. We finally show that in Svct2 knockout mouse embryos, mDA neuron formation in the developing midbrain decreased along with the 5hmC/ H3k27m3 changes. These findings together indicate an epigenetic role of VC in midbrain DA neuron development.

No abstract

The malignancy rate of AUS/FLUS nodules in our study cohort was higher than previously reported. Nodules with suspicious features on ultrasound had a higher malignancy rate than did those with indeterminate features on ultrasound. The malignancy rate differed according to histologic subcategory; therefore, management of AUS/FLUS nodules should be tailored according to histologic subcategory.