Radiation Oncology

Brain tumors edged out by artificial intelligence: VBrain applies auto-contouring to the three most common types of brain tumors: brain metastasis, meningioma and acoustic neuroma.

Ultimately, because LYFS-CT may exclude minority patients who could benefit from LCS and underestimate the benefits of LCS, the authors of this AJR article suggested "augmenting LCS eligibility for minority patients using combinations of models"--specifically, the PLCOm2012 model in conjunction with LYFS-CT and USPSTF-2020. Image courtesy of American Roentgen Ray Society (ARRS), American Journal of Roentgenology (AJR)

Detection of tumor-infiltrating lymphocytes (TILs) using explainable AI. The AI-technique is used to generate a heatmap showing TILs (red) and other tissues and cells (blue and green). Image courtesy of Klauschen/Charité

Boston Scientific's TheraSphere Y-90 Glass Microspheres enable selective internal radiation therapy (SIRT), or radioembolization, for hepatocellular carcinoma. This treats liver cancer with low toxicity using millions of microscopic glass beads containing radioactive yttrium (Y-90), delivered directly to liver tumors via catheter. The result in minimal radiation exposure to surrounding healthy tissue.

Getty Images

Getty Images

Methodology for evaluation of tumor cell density (TCD) and allocation of radiotherapy response categories. (A) Virtual graticule of approximately 300 points applied to tumor area on a digital H&E section. (B) Demonstration of TCD point scoring. (C) Box and whisker plot to show the relationship between ΔTCD and American Joint Committee on Cancer (AJCC) Tumour Regression Grade System (TRG). (D, E) Allocation of three radiotherapy response groups according to change in TCD (ΔTCD) for short-course radiotherapy (SCRT) (D) and long-course chemoradiotherapy (LCRT) (E). The Kruskall-Wallis test was used for statistical comparisons. Image courtesy of BMJ