Improved breast cancer risk models enable targeted screening strategies that achieve earlier detection and less screening harm than existing guidelines. To bring deep learning risk models to clinical practice, we need to further refine their accuracy, validate them across diverse populations, and demonstrate their potential to improve clinical workflows. We developed Mirai, a mammography-based deep learning model designed to predict risk at multiple timepoints, leverage potentially missing risk factor information, and produce predictions that are consistent across mammography machines. Mirai was trained on a large dataset from Massachusetts General Hospital (MGH) in the United States and tested on held-out test sets from MGH, Karolinska University Hospital in Sweden, and Chang Gung Memorial Hospital (CGMH) in Taiwan, obtaining C-indices of 0.76 (95% confidence interval, 0.74 to 0.80), 0.81 (0.79 to 0.82), and 0.79 (0.79 to 0.83), respectively. Mirai obtained significantly higher 5-year ROC AUCs than the Tyrer-Cuzick model (P < 0.001) and prior deep learning models Hybrid DL (P < 0.001) and Image-Only DL (P < 0.001), trained on the same dataset. Mirai more accurately identified high-risk patients than prior methods across all datasets. On the MGH test set, 41.5% (34.4 to 48.5) of patients who would develop cancer within 5 years were identified as high risk, compared with 36.1% (29.1 to 42.9) by Hybrid DL (P = 0.02) and 22.9% (15.9 to 29.6) by the Tyrer-Cuzick model (P < 0.001).

PURPOSE: Low-dose computed tomography (LDCT) for lung cancer screening is effective, although most eligible people are not being screened. Tools that provide personalized future cancer risk assessment could focus approaches toward those most likely to benefit. We hypothesized that a deep learning model assessing the entire volumetric LDCT data could be built to predict individual risk without requiring additional demographic or clinical data. METHODS: We developed a model called Sybil using LDCTs from the National Lung Screening Trial (NLST). Sybil requires only one LDCT and does not require clinical data or radiologist annotations; it can run in real time in the background on a radiology reading station. Sybil was validated on three independent data sets: a heldout set of 6,282 LDCTs from NLST participants, 8,821 LDCTs from Massachusetts General Hospital (MGH), and 12,280 LDCTs from Chang Gung Memorial Hospital (CGMH, which included people with a range of smoking history including nonsmokers). RESULTS: Sybil achieved area under the receiver-operator curves for lung cancer prediction at 1 year of 0.92 (95% CI, 0.88 to 0.95) on NLST, 0.86 (95% CI, 0.82 to 0.90) on MGH, and 0.94 (95% CI, 0.91 to 1.00) on CGMH external validation sets. Concordance indices over 6 years were 0.75 (95% CI, 0.72 to 0.78), 0.81 (95% CI, 0.77 to 0.85), and 0.80 (95% CI, 0.75 to 0.86) for NLST, MGH, and CGMH, respectively. CONCLUSION: Sybil can accurately predict an individual's future lung cancer risk from a single LDCT scan to further enable personalized screening. Future study is required to understand Sybil's clinical applications. Our model and annotations are publicly available. [Media: see text]

PURPOSE: Accurate risk assessment is essential for the success of population screening programs in breast cancer. Models with high sensitivity and specificity would enable programs to target more elaborate screening efforts to high-risk populations, while minimizing overtreatment for the rest. Artificial intelligence (AI)-based risk models have demonstrated a significant advance over risk models used today in clinical practice. However, the responsible deployment of novel AI requires careful validation across diverse populations. To this end, we validate our AI-based model, Mirai, across globally diverse screening populations. METHODS: We collected screening mammograms and pathology-confirmed breast cancer outcomes from Massachusetts General Hospital, USA; Novant, USA; Emory, USA; Maccabi-Assuta, Israel; Karolinska, Sweden; Chang Gung Memorial Hospital, Taiwan; and Barretos, Brazil. We evaluated Uno's concordance index for Mirai in predicting risk of breast cancer at one to five years from the mammogram. RESULTS: A total of 128,793 mammograms from 62,185 patients were collected across the seven sites, of which 3,815 were followed by a cancer diagnosis within 5 years. Mirai obtained concordance indices of 0.75 (95% CI, 0.72 to 0.78), 0.75 (95% CI, 0.70 to 0.80), 0.77 (95% CI, 0.75 to 0.79), 0.77 (95% CI, 0.73 to 0.81), 0.81 (95% CI, 0.79 to 0.82), 0.79 (95% CI, 0.76 to 0.83), and 0.84 (95% CI, 0.81 to 0.88) at Massachusetts General Hospital, Novant, Emory, Maccabi-Assuta, Karolinska, Chang Gung Memorial Hospital, and Barretos, respectively. CONCLUSION: Mirai, a mammography-based risk model, maintained its accuracy across globally diverse test sets from seven hospitals across five countries. This is the broadest validation to date of an AI-based breast cancer model and suggests that the technology can offer broad and equitable improvements in care.

Purpose: To evaluate diffusion‐weighted imaging (DWI) for detection of pelvic lymph node metastasis in patients with cervical and uterine cancers.Materials and Methods: Fifty patients scheduled for pelvic lymph node dissection were enrolled for 3T magnetic resonance imaging (MRI) using a single‐shot echo‐planar DWI technique, body‐phased array coil, b = 0, 1000 s/mm². We measured short/long‐axis diameters, mean apparent diffusion coefficient (ADC) values of all identifiable nodes, relative ADC values between tumors and nodes, and utilized their cutoff values to validate the diagnostic accuracy internally. Histopathologic results served as the reference standard.Results: The relative ADC values between tumor and nodes were significantly lower in metastatic than in benign nodes (0.06 vs. 0.21 × 10⁻³ mm²/s, P < 0.001; cutoff value 0.10 × 10⁻³ mm²/s). Compared to conventional MRI, the method combining size and relative ADC values resulted in better sensitivity (25% vs. 83%) and similar specificity (98% vs. 99%). The smallest metastatic lymph node detected by this method measured 5 mm on its short axis.Conclusion: The combination of size and relative ADC values was useful in detecting pelvic lymph node metastasis in patients with cervical and uterine cancers. J. Magn. Reson. Imaging 2008.

To assess the diagnostic accuracy of fused T2-weighted and high-b-value diffusion-weighted (DW) magnetic resonance (MR) images at 3 T for evaluation of myometrial invasion in patients with endometrial cancer. Institutional review board approval and informed consent were obtained. From May 2006 to October 2007, 48 consecutive patients aged 25-80 years (mean age, 57 years) who had endometrial cancer were prospectively enrolled for preoperative evaluation by using a 3-T MR unit. Two radiologists interpreted the depth of myometrial invasion on T2-weighted images, dynamic contrast material-enhanced MR images, and fused T2-weighted and DW MR images (b = 1000 sec/mm(2)). Statistical methods included kappa statistics for reader agreement, Pearson analysis for pathologic correlation, accuracy assessment, and receiver operating characteristic analysis for diagnostic performance comparison. Surgical pathologic findings were the reference standard. Reader agreement was excellent for fused T2-weighted and DW images (weighted kappa, 0.79), with a significant pathologic correlation regarding the depth of myometrial invasion (r = 0.94, P < .0001). For assessing any myometrial involvement, addition of fused T2-weighted and DW imaging to dynamic contrast-enhanced or dynamic contrast-enhanced and T2-weighted imaging was significantly better compared with dynamic contrast-enhanced imaging alone (P < .001) or dynamic contrast-enhanced and T2-weighted (P = .001) imaging; T2-weighted imaging combined with fused T2-weighted and DW imaging also was better than dynamic contrast-enhanced and T2-weighted imaging (P = .001). Tumor apparent diffusion coefficients were 0.60-1.32 x 10(-3) mm(2)/sec (median, 0.75 x 10(-3) mm(2)/sec), with no significant correlation with the depth of myometrial invasion (P = .31, r = -0.15). Fused T2-weighted and high-b-value DW images at 3 T can provide accurate information for preoperative evaluation of myometrial invasion.