Artificial intelligence in neuro-oncology

Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.

The fifth edition of the WHO Classification of Tumors of the Central Nervous System (CNS), published in 2021, is the sixth version of the international standard for the classification of brain and spinal cord tumors. Building on the 2016 updated fourth edition and the work of the Consortium to Inform Molecular and Practical Approaches to CNS Tumor Taxonomy, the 2021 fifth edition introduces major changes that advance the role of molecular diagnostics in CNS tumor classification. At the same time, it remains wedded to other established approaches to tumor diagnosis such as histology and immunohistochemistry. In doing so, the fifth edition establishes some different approaches to both CNS tumor nomenclature and grading and it emphasizes the importance of integrated diagnoses and layered reports. New tumor types and subtypes are introduced, some based on novel diagnostic technologies such as DNA methylome profiling. The present review summarizes the major general changes in the 2021 fifth edition classification and the specific changes in each taxonomic category. It is hoped that this summary provides an overview to facilitate more in-depth exploration of the entire fifth edition of the WHO Classification of Tumors of the Central Nervous System.

In 2004, a randomised phase III trial by the European Organisation for Research and Treatment of Cancer (EORTC) and National Cancer Institute of Canada Clinical Trials Group (NCIC) reported improved median and 2-year survival for patients with glioblastoma treated with concomitant and adjuvant temozolomide and radiotherapy. We report the final results with a median follow-up of more than 5 years. Adult patients with newly diagnosed glioblastoma were randomly assigned to receive either standard radiotherapy or identical radiotherapy with concomitant temozolomide followed by up to six cycles of adjuvant temozolomide. The methylation status of the methyl-guanine methyl transferase gene, MGMT, was determined retrospectively from the tumour tissue of 206 patients. The primary endpoint was overall survival. Analyses were by intention to treat. This trial is registered with Clinicaltrials.gov, number NCT00006353. Between Aug 17, 2000, and March 22, 2002, 573 patients were assigned to treatment. 278 (97%) of 286 patients in the radiotherapy alone group and 254 (89%) of 287 in the combined-treatment group died during 5 years of follow-up. Overall survival was 27.2% (95% CI 22.2-32.5) at 2 years, 16.0% (12.0-20.6) at 3 years, 12.1% (8.5-16.4) at 4 years, and 9.8% (6.4-14.0) at 5 years with temozolomide, versus 10.9% (7.6-14.8), 4.4% (2.4-7.2), 3.0% (1.4-5.7), and 1.9% (0.6-4.4) with radiotherapy alone (hazard ratio 0.6, 95% CI 0.5-0.7; p<0.0001). A benefit of combined therapy was recorded in all clinical prognostic subgroups, including patients aged 60-70 years. Methylation of the MGMT promoter was the strongest predictor for outcome and benefit from temozolomide chemotherapy. Benefits of adjuvant temozolomide with radiotherapy lasted throughout 5 years of follow-up. A few patients in favourable prognostic categories survive longer than 5 years. MGMT methylation status identifies patients most likely to benefit from the addition of temozolomide. EORTC, NCIC, Nélia and Amadeo Barletta Foundation, Schering-Plough.