Pedro Piovesan Lago
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Pedro Piovesan Lago has a total of 87 co-authors. Here are the top co-authors by number of shared publications:
- Felipe Costa
Department of Anatomic Pathology, AC Camargo Cancer Center, São Paulo, Brazil
3 shared publications - Adelheid Woehrer
Division of Neuropathology and Neurochemistry, Department of Neurology, Medical University of Vienna, Vienna, Austria
2 shared publications - Andreas von Deimling
Department of Neuropathology, Heidelberg University Hospital, University of Heidelberg, Heidelberg, Germany
2 shared publications - Antje Habel
Department of Neuropathology, University Hospital Heidelberg, Heidelberg, Germany
2 shared publications Areeba Patel
Division of AI in Oncology, German Cancer Research Center (DKFZ), Heidelberg, Germany
2 shared publicationsBogdana Suchorska
Department of Neurosurgery, University Hospital Heidelberg, Heidelberg, Germany
2 shared publications
Latest Publications
- Open Access
- 4 July 2026
- Published by Springer Nature in Acta Neuropathologica Communications
- Vol. 14 (1)
Challenging anatomical paradigms: unexpected supratentorial localization of posterior fossa B ependymomas identified by DNA methylation
Molecular subgroups of ependymomas are strongly associated with their primary anatomical compartments, namely the supratentorial region, posterior fossa and spine locations. Although it is generally accepted that posterior fossa ependymomas may arise from radial glia-like progenitor cells, the precise cellular origin of the distinct posterior fossa molecular subgroups remains to be determined. Given that DNA methylation profile strongly recapitulates developmental lineage and the cell of origin, the characterization of unexpectedly located molecular subgroups of ependymomas may provide insights into their cells of origin and potential migratory dynamics during embryogenesis and brain development. Herein, we describe two male school-aged pediatric patients with supratentorial tumors located in the third ventricle/pineal region that were classified as posterior fossa group B ependymomas based on DNA methylation profiling. To our knowledge, this represents the first reports of posterior fossa group B ependymomas identified outside the posterior fossa compartment.
- 4 July 2026
- Published by Springer Nature in Acta Neuropathologica Communications
- Vol. 14 (1)
Open AccessChallenging anatomical paradigms: unexpected supratentorial localization of posterior fossa B ependymomas identified by DNA methylation
Molecular subgroups of ependymomas are strongly associated with their primary anatomical compartments, namely the supratentorial region, posterior fossa and spine locations. Although it is generally accepted that posterior fossa ependymomas may arise from radial glia-like progenitor cells, the precise cellular origin of the distinct posterior fossa molecular subgroups remains to be determined. Given that DNA methylation profile strongly recapitulates developmental lineage and the cell of origin, the characterization of unexpectedly located molecular subgroups of ependymomas may provide insights into their cells of origin and potential migratory dynamics during embryogenesis and brain development. Herein, we describe two male school-aged pediatric patients with supratentorial tumors located in the third ventricle/pineal region that were classified as posterior fossa group B ependymomas based on DNA methylation profiling. To our knowledge, this represents the first reports of posterior fossa group B ependymomas identified outside the posterior fossa compartment.
- Open Access
- 10 June 2026
- Published by Springer Nature in Nature Cancer
- Vol. 7 (6) , 884-898
Hetairos is a histology-based artificial intelligence model for predicting central nervous system tumor methylation subtypes
Molecular testing is essential for classifying central nervous system (CNS) tumors, with methylation profiling providing the highest diagnostic granularity. However, this requires more resources and time than conventional hematoxylin and eosin (H&E) histopathology, which is widely available globally. Here we propose Hetairos, an artificial intelligence algorithm that predicts 102 methylation-based CNS tumor subtypes from digital H&E slides. Built and validated on 9,606 patients and over 11,000 slides from 11 centers across four continents, Hetairos identified 50–70% of cases with high confidence, achieving an accuracy of 0.87 for its highest-rated predictions. Hetairos outperformed five board-certified neuropathologists in a direct histology-only comparison (0.68 versus 0.30). Prospective evaluation in routine diagnostics confirmed its performance, reducing turnaround time from 12 days (molecular testing) to 12 min. Hetairos supports diagnostic decision-making across the full spectrum of pediatric and adult CNS tumors by narrowing differential diagnoses and guiding efficient testing.
- 10 June 2026
- Published by Springer Nature in Nature Cancer
- Vol. 7 (6) , 884-898
Open AccessHetairos is a histology-based artificial intelligence model for predicting central nervous system tumor methylation subtypes
Molecular testing is essential for classifying central nervous system (CNS) tumors, with methylation profiling providing the highest diagnostic granularity. However, this requires more resources and time than conventional hematoxylin and eosin (H&E) histopathology, which is widely available globally. Here we propose Hetairos, an artificial intelligence algorithm that predicts 102 methylation-based CNS tumor subtypes from digital H&E slides. Built and validated on 9,606 patients and over 11,000 slides from 11 centers across four continents, Hetairos identified 50–70% of cases with high confidence, achieving an accuracy of 0.87 for its highest-rated predictions. Hetairos outperformed five board-certified neuropathologists in a direct histology-only comparison (0.68 versus 0.30). Prospective evaluation in routine diagnostics confirmed its performance, reducing turnaround time from 12 days (molecular testing) to 12 min. Hetairos supports diagnostic decision-making across the full spectrum of pediatric and adult CNS tumors by narrowing differential diagnoses and guiding efficient testing.
- Open Access
- 1 October 2025
- Published by Practical Medicine Publishing House in Clinical oncohematology
- Vol. 18 (4) , 395-400
Spontaneous Regression of Pulmonary Lymphomatoid Granulomatosis in a Patient with a Solid Tumor: A Case Report
Lymphomatoid granulomatosis (LG) is a rare B-cell lymphoproliferative disease associated with Epstein-Barr virus (EBV). Characteristic for this disease is angiocentric and angiodestructive lymphoid infiltration with atypical EBV-positive В-cells, among which the reactive T lymphocytes predominate, often necrosis is identified. LG is mainly diagnosed in middle and old age, more often in immunocompromised subjects. Morphological grading depends on the proportion of EBV-positive В lymphocytes with different grades of atypia and coagulative necrosis severity. In most cases, lung tissue lesions are identified, other extranodal areas of involvement include CNS, kidney, liver, and skin. The clinical course of LG varies from indolent to aggressive. With a low-grade disease, spontaneous regression is possible, whereas Grade 3 requires treatment and differential diagnosis with diffuse large B-cell lymphoma. This paper reports a case of a 85-year-old prostate cancer patient with LG Grade 3 and lung tissue involvement. As the patient was free of any clinical manifestations, surveillance approach seemed to be reasonable. A series of control CT scans showed a gradual reduction of tumor mass in the left lung with its complete spontaneous regression in 14 months. This case highlights the potential for a favorable outcome of LG Grade 3 without special therapy. This is particularly relevant for elderly patients with various comorbidities.
- 1 October 2025
- Published by Practical Medicine Publishing House in Clinical oncohematology
- Vol. 18 (4) , 395-400
Open AccessSpontaneous Regression of Pulmonary Lymphomatoid Granulomatosis in a Patient with a Solid Tumor: A Case Report
Lymphomatoid granulomatosis (LG) is a rare B-cell lymphoproliferative disease associated with Epstein-Barr virus (EBV). Characteristic for this disease is angiocentric and angiodestructive lymphoid infiltration with atypical EBV-positive В-cells, among which the reactive T lymphocytes predominate, often necrosis is identified. LG is mainly diagnosed in middle and old age, more often in immunocompromised subjects. Morphological grading depends on the proportion of EBV-positive В lymphocytes with different grades of atypia and coagulative necrosis severity. In most cases, lung tissue lesions are identified, other extranodal areas of involvement include CNS, kidney, liver, and skin. The clinical course of LG varies from indolent to aggressive. With a low-grade disease, spontaneous regression is possible, whereas Grade 3 requires treatment and differential diagnosis with diffuse large B-cell lymphoma. This paper reports a case of a 85-year-old prostate cancer patient with LG Grade 3 and lung tissue involvement. As the patient was free of any clinical manifestations, surveillance approach seemed to be reasonable. A series of control CT scans showed a gradual reduction of tumor mass in the left lung with its complete spontaneous regression in 14 months. This case highlights the potential for a favorable outcome of LG Grade 3 without special therapy. This is particularly relevant for elderly patients with various comorbidities.
- Open Access
- 13 January 2025
- Published by Springer Nature in Research Square
AI-based histopathological classification of central nervous system tumours
DNA methylation analysis has become an essential diagnostic assay for classifying tumours of the central nervous system (CNS). However, this test requires additional resources and time compared to conventional histopathological diagnosis using haematoxylin and eosin (H&E) stained tissue sections, which are available globally. Here, we propose to reduce time and resource requirements using Hetairos, an artificial intelligence (AI) algorithm that predicts 102 methylation-based CNS tumour subtypes from digital images of H&E slides. Hetairos is built and assessed using over 11,000 slides from 10 centres across four continents. Hetairos produces well-calibrated probabilities for each subtype. Across cohorts, Hetairos identifies 50-70% of cases, which it classifies with high confidence and an accuracy of 0.87 for its highest-rated predictions. Hetairos achieved higher accuracy than four board-certified neuropathologists in a direct comparison using only histology images (0.68 vs 0.28). A prospective evaluation within a routine diagnostic setting confirmed Hetairos’ performance and highlighted its 2-day turnaround time compared to an average of 12 days for molecular testing. Hetairos can assist diagnostic decision-making by limiting the number of likely diagnoses, informing efficient further testing, and by highlighting tissue areas indicative of specific diagnoses. These capabilities suggest Hetairos is a valuable tool assisting in the diagnosis of the full spectrum of paediatric and adult CNS tumours.
- 13 January 2025
- Published by Springer Nature in Research Square
Open AccessAI-based histopathological classification of central nervous system tumours
DNA methylation analysis has become an essential diagnostic assay for classifying tumours of the central nervous system (CNS). However, this test requires additional resources and time compared to conventional histopathological diagnosis using haematoxylin and eosin (H&E) stained tissue sections, which are available globally. Here, we propose to reduce time and resource requirements using Hetairos, an artificial intelligence (AI) algorithm that predicts 102 methylation-based CNS tumour subtypes from digital images of H&E slides. Hetairos is built and assessed using over 11,000 slides from 10 centres across four continents. Hetairos produces well-calibrated probabilities for each subtype. Across cohorts, Hetairos identifies 50-70% of cases, which it classifies with high confidence and an accuracy of 0.87 for its highest-rated predictions. Hetairos achieved higher accuracy than four board-certified neuropathologists in a direct comparison using only histology images (0.68 vs 0.28). A prospective evaluation within a routine diagnostic setting confirmed Hetairos’ performance and highlighted its 2-day turnaround time compared to an average of 12 days for molecular testing. Hetairos can assist diagnostic decision-making by limiting the number of likely diagnoses, informing efficient further testing, and by highlighting tissue areas indicative of specific diagnoses. These capabilities suggest Hetairos is a valuable tool assisting in the diagnosis of the full spectrum of paediatric and adult CNS tumours.