Deep learning image segmentation approaches for malignant bone lesions: a systematic review and meta-analysis.

Introduction: Image segmentation is an important process for quantifying characteristics of malignant bone lesions, but this task is challenging and laborious for radiologists. Deep learning has shown promise in automating image segmentation in radiology, including for malignant bone lesions. The purpose of this review is to investigate deep learning-based image segmentation methods for malignant bone lesions on Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and Positron-Emission Tomography/CT (PET/CT). Method: The literature search of deep learning-based image segmentation of malignant bony lesions on CT and MRI was conducted in PubMed, Embase, Web of Science, and Scopus electronic databases following the guidelines of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). A total of 41 original articles published between February 2017 and March 2023 were included in the review. Results: The majority of papers studied MRI, followed by CT, PET/CT, and PET/MRI. There was relatively even distribution of papers studying primary vs. secondary malignancies, as well as utilizing 3-dimensional vs. 2-dimensional data. Many papers utilize custom built models as a modification or variation of U-Net. The most common metric for evaluation was the dice similarity coefficient (DSC). Most models achieved a DSC above 0.6, with medians for all imaging modalities between 0.85-0.9. Discussion: Deep learning methods show promising ability to segment malignant osseous lesions on CT, MRI, and PET/CT. Some strategies which are commonly applied to help improve performance include data augmentation, utilization of large public datasets, preprocessing including denoising and cropping, and U-Net architecture modification. Future directions include overcoming dataset and annotation homogeneity and generalizing for clinical applicability.

Cost-effectiveness of Contrast-Enhanced Ultrasound for Diagnosis and Active Surveillance of Complex Cystic Renal Lesions.

Purpose: To determine the cost-effectiveness of Contrast-Enhanced Ultrasound (ceUS) for the active surveillance of complex renal masses compared to the more established imaging modalities of CT and MRI. Methods: A decision-analytic Markov state microsimulation model was constructed in TreeAge Pro. We simulated independent cohorts of 100,000 60-year-old individuals with either a Bosniak IIF or Bosniak III complex renal mass who were followed for 10 years or until death. The model compared three imaging strategies: (1) ceUS, (2) contrast-enhanced magnetic-resonance imaging (ceMRI), and (3) contrast-enhanced computed tomography (ceCT) for active surveillance of a complex renal mass. Results: For 60-year-old patients with either Bosniak IIF or III renal masses, ceUS was the most cost-effective strategy even after varying rates of active surveillance from 10-100%. Conclusion: ceUS is a viable and cost-effective option in the active surveillance of Bosniak class IIF and III renal cysts. Even after varying the rates of active surveillance usage, ceUS was robust and remained the most dominant strategy. For patients who have impaired kidney functions, ceUS is can be a safer alternative than non-contrast enhanced CT or MRI in the management of patients with Bosniak III renal cysts.

Impact of Renal Hilar Control on Outcomes of Robotic Partial Nephrectomy: Systematic Review and Cumulative Meta-analysis.

CONTEXT: During robotic partial nephrectomy (RPN), various techniques of hilar control have been described, including on-clamp, early unclamping, selective/super-selective clamping, and completely-unclamped RPN. OBJECTIVE: To evaluate the impact of various hilar control techniques on perioperative, functional, and oncological outcomes of RPN for tumors. EVIDENCE ACQUISITION: We conducted a systematic literature review and meta-analysis of all comparative studies on various hilar control techniques during RPN using PubMed, Scopus, and Web of Science according to the Preferred Reporting Items for Systematic Review and Meta-analysis statement, and Methods and Guide for Effectiveness and Comparative Effectiveness Review of the Agency for Healthcare Research and Quality. Cumulative meta-analysis of comparative studies was conducted using Review Manager 5.3. EVIDENCE SYNTHESIS: Of 987 RPN publications in the literature, 19 qualified for this analysis. Comparison of off-clamp versus on-clamp RPN (n=9), selective clamping versus on-clamp RPN (n=3), super selective clamping versus on-clamp RPN (n=5), and early unclamped versus on-clamp (n=3) were reported. Patients undergoing RPN using off-clamp, selective/super selective, or early unclamp techniques had higher estimated blood loss compared with on-clamp RPN (weight mean difference [WMD]: 47.83, p=0.000, WMD: 41.06, p=0.02, and WMD: 37.50, p=0.47); however, this did not seem clinically relevant, since transfusion rates were similar (odds ratio [OR]: 0.98, p=0.95, OR: 0.72, p=0.7, and OR: 1.36, p=0.33, respectively). All groups appeared similar with regards to hospital stay, transfusions, overall and major complications, and positive cancer margin rates. Short- and long-term renal functional outcomes appeared superior in the off-clamp and super selective clamp groups compared with the on-clamp RPN cohort. CONCLUSIONS: Off-clamp, selective/super selective clamp, and early unclamp hilar control techniques are safe and feasible approaches for RPN surgery, with similar perioperative and oncological outcomes compared with on-clamp RPN. Minimizing global renal ischemia may provide superior renal function preservation. However, higher quality data are necessary for definitive conclusions in this regard. PATIENT SUMMARY: The objective of partial nephrectomy is to treat the cancer while maximizing renal function preservation. Clamping the main vessels is done primarily to reduce the blood loss during partial nephrectomy; however, vascular clamping can compromise kidney function. In order to avoid clamping, various techniques have been described. Our analysis showed that techniques that avoid main renal artery clamping during RPN are associated with better renal function preservation, yet deliver non-inferior perioperative and oncological outcomes as compared with RPN procedures that clamp the main vessels.