Development and Evaluation of Machine Learning in Whole-Body Magnetic Resonance Imaging for Detecting Metastases in Patients With Lung or Colon Cancer: A Diagnostic Test Accuracy Study.

OBJECTIVES: Whole-body magnetic resonance imaging (WB-MRI) has been demonstrated to be efficient and cost-effective for cancer staging. The study aim was to develop a machine learning (ML) algorithm to improve radiologists' sensitivity and specificity for metastasis detection and reduce reading times. MATERIALS AND METHODS: A retrospective analysis of 438 prospectively collected WB-MRI scans from multicenter Streamline studies (February 2013-September 2016) was undertaken. Disease sites were manually labeled using Streamline reference standard. Whole-body MRI scans were randomly allocated to training and testing sets. A model for malignant lesion detection was developed based on convolutional neural networks and a 2-stage training strategy. The final algorithm generated lesion probability heat maps. Using a concurrent reader paradigm, 25 radiologists (18 experienced, 7 inexperienced in WB-/MRI) were randomly allocated WB-MRI scans with or without ML support to detect malignant lesions over 2 or 3 reading rounds. Reads were undertaken in the setting of a diagnostic radiology reading room between November 2019 and March 2020. Reading times were recorded by a scribe. Prespecified analysis included sensitivity, specificity, interobserver agreement, and reading time of radiology readers to detect metastases with or without ML support. Reader performance for detection of the primary tumor was also evaluated. RESULTS: Four hundred thirty-three evaluable WB-MRI scans were allocated to algorithm training (245) or radiology testing (50 patients with metastases, from primary 117 colon [n = 117] or lung [n = 71] cancer). Among a total 562 reads by experienced radiologists over 2 reading rounds, per-patient specificity was 86.2% (ML) and 87.7% (non-ML) (-1.5% difference; 95% confidence interval [CI], -6.4%, 3.5%; P = 0.39). Sensitivity was 66.0% (ML) and 70.0% (non-ML) (-4.0% difference; 95% CI, -13.5%, 5.5%; P = 0.344). Among 161 reads by inexperienced readers, per-patient specificity in both groups was 76.3% (0% difference; 95% CI, -15.0%, 15.0%; P = 0.613), with sensitivity of 73.3% (ML) and 60.0% (non-ML) (13.3% difference; 95% CI, -7.9%, 34.5%; P = 0.313). Per-site specificity was high (>90%) for all metastatic sites and experience levels. There was high sensitivity for the detection of primary tumors (lung cancer detection rate of 98.6% with and without ML [0.0% difference; 95% CI, -2.0%, 2.0%; P = 1.00], colon cancer detection rate of 89.0% with and 90.6% without ML [-1.7% difference; 95% CI, -5.6%, 2.2%; P = 0.65]). When combining all reads from rounds 1 and 2, reading times fell by 6.2% (95% CI, -22.8%, 10.0%) when using ML. Round 2 read-times fell by 32% (95% CI, 20.8%, 42.8%) compared with round 1. Within round 2, there was a significant decrease in read-time when using ML support, estimated as 286 seconds (or 11%) quicker ( P = 0.0281), using regression analysis to account for reader experience, read round, and tumor type. Interobserver variance suggests moderate agreement, Cohen κ = 0.64; 95% CI, 0.47, 0.81 (with ML), and Cohen κ = 0.66; 95% CI, 0.47, 0.81 (without ML). CONCLUSIONS: There was no evidence of a significant difference in per-patient sensitivity and specificity for detecting metastases or the primary tumor using concurrent ML compared with standard WB-MRI. Radiology read-times with or without ML support fell for round 2 reads compared with round 1, suggesting that readers familiarized themselves with the study reading method. During the second reading round, there was a significant reduction in reading time when using ML support.

2018 FIGO Staging Classification for Cervical Cancer: Added Benefits of Imaging.

Cervical cancer is the fourth most common cancer in women of all ages worldwide. The disease is staged using the International Federation of Gynecology and Obstetrics (FIGO) system, which was updated in 2018. The authors explain the key changes from the 2009 version and the rationale behind them. The changes have been made to reflect common clinical practice, differentiate prognostic outcomes, and guide treatment stratification. Treatment options are dependent on the stage of disease and include fertility-sparing and non-fertility-sparing surgical options as well as chemoradiotherapy for locally advanced disease. The updated FIGO staging gives added importance to MRI as a method of accurately measuring tumor size and depicting the presence of parametrial involvement. With the inclusion of lymph node involvement in the updated 2018 FIGO staging, cross-sectional imaging-and in particular, fluorodeoxyglucose PET/CT-has an increasing role in the depiction of nodal disease. Understanding the radiologic techniques used, the literature supporting them, and common imaging pitfalls ensures accurate staging of disease and optimization of treatment. ©RSNA, 2020 See discussion on this article by Javitt (pp 1823-1824).

Defining a national reference level for intraoperative radiation exposure in urological procedures: FLASH, a retrospective multicentre UK study.

OBJECTIVES: To define reference levels for intraoperative radiation during stent insertion, ureteroscopy (URS), and percutaneous nephrolithotomy (PCNL); to identify variation in radiation exposure between individual hospitals across the UK, between low- and high-volume PCNL centres, and between grade of lead surgeon. PATIENTS/SUBJECTS AND METHODS: In all, 3651 patients were identified retrospectively across 12 UK hospitals over a 1-year period. Radiation exposure was defined in terms of total fluoroscopy time (FT) and dose area product (DAP). The 75th percentiles of median values for each hospital were used to define reference levels for each procedure. RESULTS: Reference levels: ureteric stent insertion/replacement (DAP, 2.3 Gy/cm2 ; FT, 49 s); URS (DAP, 2.8 Gy/cm2 ; FT, 57 s); PCNL (DAP, 24.1 Gy/cm2 ; FT, 431 s). Significant variations in the median DAP and FT were identified between individual centres for all procedures (P < 0.001). For PCNL, there was a statistically significant difference between DAP for low- (<50 cases/annum) and high-volume centres (>50 cases/annum), at a median DAP of 15.0 Gy/cm2 vs 4.2 Gy/cm2 (P < 0.001). For stent procedures, the median DAP and FT differed significantly between grade of lead surgeon: Consultant (DAP, 2.17 Gy/cm2 ; FT, 41 s) vs Registrar (DAP, 1.38 Gy/cm2 ; FT, 26 s; P < 0.001). CONCLUSION: This multicentre study is the largest of its kind. It provides the first national reference level to guide fluoroscopy use in urological procedures, thereby adding a quantitative and objective value to complement the principles of keeping radiation exposure 'as low as reasonably achievable'. This snapshot of real-time data shows significant variation around the country, as well as significant differences between low- and high-volume centres for PCNL, and grade of lead surgeon for stent procedures.