Purpose:We evaluated oncologic risks in a large cohort of patients with radiographic cystic renal masses who underwent active surveillance or intervention.Materials and Methods:A single-institutional database of 4,340 kidney lesions managed with either active surveillance or intervention between 2000-2020 was queried for radiographically cystic renal masses. Association of radiographic tumor characteristics and high-grade pathology was evaluated.Results:We identified 387 radiographically confirmed cystic lesions in 367 patients. Of these, 247 were resected (n=240) or ablated (n=7; n=247, 203 immediate vs 44 delayed intervention). Pathologically, 23% (n=56) demonstrated high-grade pathology. Cystic features were explicitly described by pathology in only 18% (n=33) of all lesions and in 7% (n=4) of high-grade lesions. Of the intervention cohort, African American race, male gender, and Bosniak score were associated with high-grade pathology (P < .05). On active surveillance (n=184), Bosniak IV lesions demonstrated faster growth rates than IIF and III lesions (2.7 vs 0.6 and 0.5 mm/y, P ≤ .001); however, growth rates were not associated with high-grade pathology (P = .5). No difference in cancer-specific survival was identified when comparing intervention vs active surveillance at 5 years (99% vs 100%, P = .2). No difference in recurrence was observed between immediate intervention vs delayed intervention (P > .9).Conclusions:A disconnect between “cystic” designation on imaging and pathology exists for renal lesions. Over 80% of radiographic Bosniak cystic lesions are not described as “cystic” on pathology reports. More than 1 in 5 resected cystic renal lesions demonstrated high-grade disease. Despite this finding, judiciously managed active surveillance ± delayed intervention is a safe and effective management option for most radiographic cystic renal masses.
Reirradiation with PLDR is effective and well-tolerated. The risk of late toxicity and the durability of local control were limited by the relatively short follow-up duration in the present cohort.
Purpose of review
Artificial intelligence holds tremendous potential for disrupting clinical medicine. Here we review the current role of artificial intelligence in the kidney cancer space.
Recent findings
Machine learning and deep learning algorithms have been developed using information extracted from radiomic, histopathologic, and genomic datasets of patients with renal masses.
Summary
Although artificial intelligence applications in medicine are still in their infancy, they already hold immediate promise to improve accuracy of renal mass characterization, grade, and prognostication. As algorithms become more robust and generalizable, artificial intelligence is poised to significantly disrupt kidney cancer care.
The actionable intelligence metric and the reduction metric are novel, clinically relevant quantification metrics to standardize the reporting of multiparametric magnetic resonance/ultrasound targeted prostate biopsy deliverables. Targeted biopsy provides actionable information in about 25% of men. Reduction metric assessment highlights that transrectal ultrasound guided prostate biopsy may only be omitted after carefully considering the risk of missing clinically significant cancers.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.