Oz Haim1, Shani Abramov1, Ben Shofty1,2, Claudia Fanizzi3, Francesco DiMeco3, Netanell Avisdris4,5, Zvi Ram1, Moran Artzi5, Rachel Grossman6. 1. Department of Neurosurgery, Tel Aviv Medical Center, Affiliated to the Sackler Faculty of Medicine, Tel-Aviv University, 6 Weizman Street, 6423906, Tel-Aviv, Israel. 2. Department of Neurosurgery, Baylor College of Medicine, Houston, TX, USA. 3. Department of Neurosurgery, Fondazione IRCCS Istituto Neurologico C. Besta, Milan, Italy. 4. School of Computer Science and Engineering, Hebrew University of Jerusalem, Jerusalem, Israel. 5. Sagol Brain Institute, Tel Aviv Medical Center, and the Sackler Faculty of Medicine and Sagol School of Neuroscience, Tel Aviv University, Tel-Aviv, Israel. 6. Department of Neurosurgery, Tel Aviv Medical Center, Affiliated to the Sackler Faculty of Medicine, Tel-Aviv University, 6 Weizman Street, 6423906, Tel-Aviv, Israel. rachelgr@tlvmc.gov.il.
Abstract
PURPOSE: Non-small cell lung cancer (NSCLC) tends to metastasize to the brain. Between 10 and 60% of NSCLCs harbor an activating mutation in the epidermal growth-factor receptor (EGFR), which may be targeted with selective EGFR inhibitors. However, due to a high discordance rate between the molecular profile of the primary tumor and the brain metastases (BMs), identifying an individual patient's EGFR status of the BMs necessitates tissue diagnosis via an invasive surgical procedure. We employed a deep learning (DL) method with the aim of noninvasive detection of the EGFR mutation status in NSCLC BM. METHODS: We retrospectively collected clinical, radiological, and pathological-molecular data of all the NSCLC patients who had been diagnosed with BMs and underwent resection of their BM during 2009-2019. The study population was then divided into two groups based upon EGFR mutational status. We further employed a DL technique to classify the two groups according to their preoperative magnetic resonance imaging features. Augmentation techniques, transfer learning approach, and post-processing of the predicted results were applied to overcome the relatively small cohort. Finally, we established the accuracy of our model in predicting EGFR mutation status of BM of NSCLC. RESULTS: Fifty-nine patients were included in the study, 16 patients harbored EGFR mutations. Our model predicted mutational status with mean accuracy of 89.8%, sensitivity of 68.7%, specificity of 97.7%, and a receiver operating characteristic curve value of 0.91 across the 5 validation datasets. CONCLUSION: DL-based noninvasive molecular characterization is feasible, has high accuracy and should be further validated in large prospective cohorts.
PURPOSE: Non-small cell lung cancer (NSCLC) tends to metastasize to the brain. Between 10 and 60% of NSCLCs harbor an activating mutation in the epidermal growth-factor receptor (EGFR), which may be targeted with selective EGFR inhibitors. However, due to a high discordance rate between the molecular profile of the primary tumor and the brain metastases (BMs), identifying an individual patient's EGFR status of the BMs necessitates tissue diagnosis via an invasive surgical procedure. We employed a deep learning (DL) method with the aim of noninvasive detection of the EGFR mutation status in NSCLC BM. METHODS: We retrospectively collected clinical, radiological, and pathological-molecular data of all the NSCLC patients who had been diagnosed with BMs and underwent resection of their BM during 2009-2019. The study population was then divided into two groups based upon EGFR mutational status. We further employed a DL technique to classify the two groups according to their preoperative magnetic resonance imaging features. Augmentation techniques, transfer learning approach, and post-processing of the predicted results were applied to overcome the relatively small cohort. Finally, we established the accuracy of our model in predicting EGFR mutation status of BM of NSCLC. RESULTS: Fifty-nine patients were included in the study, 16 patients harbored EGFR mutations. Our model predicted mutational status with mean accuracy of 89.8%, sensitivity of 68.7%, specificity of 97.7%, and a receiver operating characteristic curve value of 0.91 across the 5 validation datasets. CONCLUSION: DL-based noninvasive molecular characterization is feasible, has high accuracy and should be further validated in large prospective cohorts.
Authors: Rafael Rosell; Enric Carcereny; Radj Gervais; Alain Vergnenegre; Bartomeu Massuti; Enriqueta Felip; Ramon Palmero; Ramon Garcia-Gomez; Cinta Pallares; Jose Miguel Sanchez; Rut Porta; Manuel Cobo; Pilar Garrido; Flavia Longo; Teresa Moran; Amelia Insa; Filippo De Marinis; Romain Corre; Isabel Bover; Alfonso Illiano; Eric Dansin; Javier de Castro; Michele Milella; Noemi Reguart; Giuseppe Altavilla; Ulpiano Jimenez; Mariano Provencio; Miguel Angel Moreno; Josefa Terrasa; Jose Muñoz-Langa; Javier Valdivia; Dolores Isla; Manuel Domine; Olivier Molinier; Julien Mazieres; Nathalie Baize; Rosario Garcia-Campelo; Gilles Robinet; Delvys Rodriguez-Abreu; Guillermo Lopez-Vivanco; Vittorio Gebbia; Lioba Ferrera-Delgado; Pierre Bombaron; Reyes Bernabe; Alessandra Bearz; Angel Artal; Enrico Cortesi; Christian Rolfo; Maria Sanchez-Ronco; Ana Drozdowskyj; Cristina Queralt; Itziar de Aguirre; Jose Luis Ramirez; Jose Javier Sanchez; Miguel Angel Molina; Miquel Taron; Luis Paz-Ares Journal: Lancet Oncol Date: 2012-01-26 Impact factor: 41.316
Authors: Lecia V Sequist; James Chih-Hsin Yang; Nobuyuki Yamamoto; Kenneth O'Byrne; Vera Hirsh; Tony Mok; Sarayut Lucien Geater; Sergey Orlov; Chun-Ming Tsai; Michael Boyer; Wu-Chou Su; Jaafar Bennouna; Terufumi Kato; Vera Gorbunova; Ki Hyeong Lee; Riyaz Shah; Dan Massey; Victoria Zazulina; Mehdi Shahidi; Martin Schuler Journal: J Clin Oncol Date: 2013-07-01 Impact factor: 44.544
Authors: Freddie Bray; Jacques Ferlay; Isabelle Soerjomataram; Rebecca L Siegel; Lindsey A Torre; Ahmedin Jemal Journal: CA Cancer J Clin Date: 2018-09-12 Impact factor: 508.702