top of page
deep-neural-network-background-image2.jpg

Pedro R. A. S. Bassi

IMG_5253.JPG
  • Liknedin
  • Twitter

Pedro Bassi is a postdoctoral researcher at Johns Hopkins University (USA), working closely with Prof. Alan Yuille and Prof. Zongwei Zhou in the Department of Computer Science. He earned his PhD in Data Science and Computation from the University of Bologna (Italy) in 2025 and was also a visiting PhD student at Johns Hopkins University.

 

He has first-author publications in major venues, including Nature Communications, NeurIPS, MICCAI, ISBI and ICCV. In 2025, he received the MICCAI Best Paper Award (runner-up; top 2 out of 1,027 accepted papers).

 

His research focuses on medical AI, training methodologies, interpretability, inter-hospital generalization, and the trustworthiness of deep learning. Specific research topics include explanation-based training techniques to minimize bias, large-scale dataset creation, and methods to train tumor segmentation AI directly from medical images and radiology reports.

​

Contact: psalvad2@jh.edu

Research Interests

  • Medical AI

  • Deep learning

  • Interpretability, distributional robustness, and trustworthiness of deep neural networks

  • AI-assisted diagnosis

  • Computer vision

​

interests

Publications

Journal Papers:

 

 

  • Bassi, P. R. A. S., Dertkigil, S., & Cavalli, A. (2024). Improving deep neural network generalization and robustness to background bias via layer-wise relevance propagation optimization. Nature Communications, 15(1). https://www.nature.com/articles/s41467-023-44371-z

​

  • Li, W., Qu, C., Chen, X., Bassi, P. R. A. S., Shi, Y., Lai, Y., … Yuille, A., & Zhou, Z. (2024). AbdomenAtlas: A large-scale, detailed-annotated, & multi-center dataset for efficient transfer learning and open algorithmic benchmarking. Medical Image Analysis, 97, 103285. https://doi.org/10.1016/j.media.2024.103285

​

​

  • Bassi, P. R. A. S., & Attux, R. (2022). COVID-19 detection using chest X-rays: Is lung segmentation important for generalization? Research on Biomedical Engineering, Springer. https://doi.org/10.1007/s42600-022-00242-y

​

  • Bassi, P. R. A. S., & Attux, R. (2022). FBDNN: Filter banks and deep neural networks for portable and fast brain-computer interfaces. Biomedical Physics & Engineering Express, IOP. https://doi.org/10.1088/2057-1976/ac6300

​

​

  • Bassi, P. R. A. S., Rampazzo, W., & Attux, R. (2021). Transfer learning and SpecAugment applied to SSVEP-based BCI classification. Biomedical Signal Processing and Control, Elsevier. https://doi.org/10.1016/j.bspc.2021.102542

​​

Conference Papers:

​

  • Bassi, P. R. A. S., Li, W., Cheng, J., Zhu, Z., Lin, T., Decherchi, S., Cavalli, A., Wang, K., Yang, Y., Yuille, A., & Zhou, Z. (2025). Learning segmentation from radiology reports. Proceedings of the 28th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). https://arxiv.org/abs/2507.05582 (MICCAI 2025 Best Paper Award Runner-up; top 2 of 1,027 accepted papers; covered by JHU CS News)

​

  • Bassi, P. R. A. S., Can Yavuz, M., Wang, K., Chen, X., Li, W., Decherchi, S., Cavalli, A., Yang, Y., Yuille, A., & Zhou, Z. (2025). RadGPT: Constructing 3D image-text tumor datasets. Proceedings of the International Conference on Computer Vision (ICCV). https://arxiv.org/abs/2501.04678

​

  • Bassi, P. R. A. S., Wu, Q., Li, W., Decherchi, S., Cavalli, A., Yuille, A., & Zhou, Z. (2025). Label Critic: Design data before models. IEEE 22nd International Symposium on Biomedical Imaging (ISBI). https://doi.org/10.1109/ISBI60581.2025.10981154

​

  • Lubonja, A., Bassi, P. R. A. S., Li, W., Qiao, H., Burns, R., Yuille, A. L., & Zhou, Z. (2025). Auditing significance, metric choice, and demographic fairness in medical AI challenges. MICCAI Workshop on Machine Learning in Medical Imaging (MLMI).

​

  • Bassi, P. R. A. S., Li, W., Tang, Y., Isensee, F., … Yuille, A., & Zhou, Z. (2024). Touchstone Benchmark: Are we on the right way for evaluating AI algorithms for medical segmentation? Advances in Neural Information Processing Systems 37 (NeurIPS). https://nips.cc/virtual/2024/poster/97634 (Covered by JHU CS News)

​

  • Bassi, P. R. A. S., Rampazzo, W., & Attux, R. (2019). Deep triplet neural networks applied to signal classification in brain-computer interfaces. Anais do XXXVII Simpósio Brasileiro de Telecomunicações e Processamento de Sinais (SBrT). https://doi.org/10.14209/sbrt.2019.1570559203

​

  • Bassi, P. R. A. S., & Attux, R. (2019). Deep neural networks: Implementation in the context of pattern recognition. Revista dos Trabalhos de Iniciação Científica da UNICAMP. https://doi.org/10.20396/revpibic2720192824

​

 

Conference Abstracts:

​

  • Bassi, P. R. A. S., Chen, J., Li, W., Zhu, Z., Decherchi, S., Cavalli, A., Wang, K., Yang, Y., Yuille, A. L., & Zhou, Z. (2025). 16 readily available radiology reports are worth 1 time-consuming voxel-wise annotation for whole-body CT tumor detection. Radiological Society of North America (RSNA).

​

  • Bassi, P. R. A. S., Li, W., Gao, Y., Sadegheih, Y., Bozorgpour, A., Merhof, D., Decherchi, S., Cavalli, A., Yuille, A. L., & Zhou, Z. (2025). A Touchstone of medical artificial intelligence. RSNA.

​

  • Li, W., Zhou, X., Chen, Q., Bassi, P. R. A. S., Chen, X., Zhu, Z., Yang, Y., Wang, K., Yuille, A. L., & Zhou, Z. (2025). CancerVerse: Robust segmentation of 16 major cancers in computed tomography. RSNA.

​

  • Li, W., Bassi, P. R. A. S., Zhou, X., Chen, Q., Lin, T., Chen, X., PÅ‚otka, S., ĆwikÅ‚a, J. B., Jiang, S., Lall, C. G., Zhu, Z., Yang, Y., Ding, K., Li, H., Wang, K., Yuille, A. L., & Zhou, Z. (2025). Early pancreatic cancer detection via prediagnostic CT and artificial intelligence. RSNA.

​

  • Cai, Y., Zhu, Z., Bassi, P. R. A. S., Zhou, Z., Wang, K., & Yang, Y. (2025). Feasibility of automated liver metastasis detection and report generation in gadoxetate-enhanced abdominal MRI using vision-language models. ISMRM & ISMRT Annual Meeting, Oral presentation.

​

  • Bassi, P. R. A. S., Wang, K., Chen, X., Decherchi, S., Cavalli, A., Yang, Y., Yuille, A. L., & Zhou, Z. (2024). Segment2Report: Enhancing AI-assisted radiology report generation with per-voxel organ and tumor segmentation. RSNA, Oral presentation.

​

  • Bassi, P. R. A. S., Li, W., Rokuss, M., Kirchhoff, Y., Ulrich, C., Roy, S., Tang, Y., Decherchi, S., Cavalli, A., Maier-Hein, K., Isensee, F., Yuille, A. L., & Zhou, Z. (2024). Dataset Profiler: Study traceback, error detection, and label refinement for multicenter radiology datasets. RSNA, Oral presentation.

​

  • Bassi, P. R. A. S., Li, W., Tang, Y., … Yuille, A. L., & Zhou, Z. (2024). Are we on the right way for evaluating AI algorithms for medical segmentation? RSNA.​

 

Preprints:

 

  • Li, W., Zhou, X., Chen, Q., Lin, T., Bassi, P. R. A. S., PÅ‚otka, S., ĆwikÅ‚a, J. B., Chen, X., Ye, C., Zhu, Z., Ding, K., Li, H., Wang, K., Yang, Y., Tang, Y., Xu, D., Yuille, A., & Zhou, Z. (2025). PanTS: The pancreatic tumor segmentation dataset. arXiv:2507.01291. https://arxiv.org/abs/2507.01291

​

  • Chen, Y., Xiao, W., Bassi, P. R. A. S., Zhou, X., Er, S., Hamamci, I. E., Yuille, A., & Zhou, Z. (2025). Are vision-language models ready for clinical diagnosis? A 3D medical benchmark for tumor-centric visual question answering. arXiv:2505.18915. https://arxiv.org/abs/2505.18915

​

  • Guo, P., Zhao, C., Yang, D., He, Y., Nath, V., Xu, Z., Bassi, P. R. A. S., Zhou, Z., … Turkbey, B., & Xu, D. (2025). Text2CT: Towards 3D CT volume generation from free-text descriptions using diffusion models. arXiv:2505.04522. https://arxiv.org/abs/2505.04522

​

  • Li, W., Bassi, P. R. A. S., Lin, T., Chou, Y.-C., Zhou, X., Tang, Y., Isensee, F., Wang, K., Chen, Q., Xu, X., Chen, X., Wu, L., Wu, Q., Zhao, Y., Yu, D., Ding, K., Kirchhoff, Y., Rokuss, M. R., Roy, S., Ulrich, C., Maier-Hein, K., Yang, Y., Yuille, A. L., & Zhou, Z. (2025). ScaleMAI: Accelerating the development of trusted datasets and AI models. arXiv:2501.03410. https://arxiv.org/abs/2501.03410

​

  • Li, X., Shuai, Y., Liu, C., Chen, Q., Wu, Q., Guo, P., Yang, D., Zhao, C., Bassi, P. R. A. S., … Yuille, A. L., & Zhou, Z. (2024). Text-driven tumor synthesis. arXiv:2412.18589. https://arxiv.org/abs/2412.18589

​

  • Bassi, P. R. A. S., Cavalli, A., & Decherchi, S. (2024). Explanation is all you need in distillation: Mitigating bias and shortcut learning. arXiv:2407.09788. https://arxiv.org/abs/2407.09788​

 

Challenges and Workshops:

​

  • Hamamci, I. E., …, Rajpurkar, P., Bassi, P. R. A. S., Li, W., Yuille, A., Zhou, Z., Reynaud, H., Kainz, B., Wu, C., Xie, W., Hou, B., Lu, Z., Xu, D., Yang, D., & Guo, P. (2025). Challenge for vision-language modeling in 3D medical imaging (VLM3D). Organizer. MICCAI; ICCV.

​

  • Li, W., Bassi, P. R. A. S., Tang, Y., Chen, X., Li, J., … Yuille, A. L., & Zhou, Z. (2024). Body Maps: Towards a 3D atlas of the human body. Organizer. MICCAI; ISBI.​

 

Thesis:

​

  • Bassi, P. R. A. S. (2021). A study of deep neural networks for image recognition in BCIs and COVID-19 detection. M.Sc. thesis. acervus.unicamp.br

Anchor 1

Education

Johns Hopkins University - Baltimore, MD, USA

  • 08/2024-02/2025: Visiting Ph.D. Student at the CCVL (Computational Cognition, Vision, and Learning) research lab 

    • Doctoral advisors: Professor Alan Yuille and Dr. Zongwei Zhou

​

University of Bologna - Bologna, BO, Italy

  • 11/2021-11/2025: Ph.D. in Data Science and Computation 

    • Doctoral advisors: Professor Andrea Cavalli and Dr. Sergio Decherchi

    • Affiliated with IIT (Italian Institute of Technology)

 

Campinas State University (UNICAMP) - Campinas, SP, Brazil

  • 08/2019-08/2021: Masters in Computer Engineering

    • Thesis: A study of deep neural networks for image recognition in BCIs and COVID-19 detection

    • Advisor: Professor Romis Attux

    • Final GPA: 4.0/4.0

​

Campinas State University (UNICAMP) - Campinas, SP, Brazil

  • 02/2014-07/2019: B.S. in Electrical Engineering

    • Certificate of Study: ​Fundamentals of computer engineering. Workload: 270 hours

    • Certificate of Study: ​Electronics, microelectronics and optoelectronics. Workload: 270 hours

    • Thesis: A study of electrical mobility in strained silicon transistors with the software Synopsis

​

​

Publications

Anchor 2

Research 
Experience

Johns Hopkins University - Baltimore, MD, USA

  • 12/2025-present: Postdoctoral Researcher

    • Created new AI training methods that leverage radiology reports for teach AI to segment tumors in multiple abdominal organs.​

​

Johns Hopkins University - Baltimore, MD, USA

  • 08/2024-02/2025: Visiting Ph.D. Student Ph.D. Student | Deep learning for 3D medical image analysis

    • Organized and led Touchstone (NeurIPS, 2024), a large-scale benchmark for organ segmentation in CT volumes. It involved the collaboration of 14 international research teams and focused on out-of-distribution generalization

    • Studied demographic biases and generalization in 3D medical segmentation

    • Participated in the creation of AbdomenAtlas, the largest fully-annotated abdominal CT dataset

    • Used large vision-language models to improve per-voxel organ annotations

    • Used large vision-language models to generate radiology reports for CT scans

​

University of Bologna - Bologna, BO, Italy

  • 11/2021-11/2025 (expected): Ph.D. Researcher | Deep Learning Trustworthiness, Explainability and Distributional Robustness

    • Introduced the optimization of Layer-wise Relevance Propagation to control deep classifiers and improve out-of-distribution generalization​

    • Introduced and investigated methods to improve the inter-institution generalizability of deep X-ray classifiers

    • Studied shortcut learning in computer vision

    • Elaborated novel solutions to the problem of spurious correlations in the backgrounds of natural and biomedical images

​​​

Campinas State University (UNICAMP) - Campinas, SP, Brazil

  • 08/2019-08/2021: M.Sc. Researcher | Deep Learning for Image Recognition in Brain-Computer Interfaces and X-ray Classification​

    • Studied the utilization of deep neural networks for AI-assisted diagnosis in chest X-rays​

    • Used explanation techniques to interpret the decisions of deep X-ray classifiers and compare them to radiologists' reasoning

    • Identified spurious correlations in early Covid-19 chest X-ray datasets

    • Evaluated the importance of lung segmentation for the inter-institutional generalizability of deep X-ray classifiers

    • Introduced the combination of filter banks and deep neural networks to improve the speed, portability and accuracy of brain-computer interfaces

    • Introduced the utilization of the SpecAugment data augmentation technique for the classification of EEG spectrograms in brain-computer interfaces​​

​

Campinas State University (UNICAMP) - Campinas, SP, Brazil

  • 08/2018-07/2019: Undergraduate Researcher | Applications of deep learning in SSVEP (steady state visually evoked potential) based brain-computer interfaces

    • Utilized deep learning to classify spectrograms of EEG signals in SSVEP-based brain-computer interfaces

    • Introduced the use of deep triplet neural networks in brain-computer interfaces

​​​

Campinas State University (UNICAMP) - Campinas, SP, Brazil

  • 08/2017-07/2018: Undergraduate Researcher | â€‹Fundamentals of deep neural networks

    • Studied machine learning and deep learning, encompassing fundamental concepts in linear algebra, information theory and probability​

    • Studied the book Deep Learning, written by Ian Goodfellow, Yoshua Bengio, and Aaron Courville

    • Implemented deep neural networks in Python, employing PyTorch and Tensorflow

    • Studied regularization and overfitting in deep neural networks

Anchor 8
Anchor 3

Scholarships
and Awards

  • 09/2021: Selected for a Ph.D. scholarship by Fulbright and CAPES 

​

  • 07/2021-Present: Awarded a Ph.D. scholarship by IIT (Italian Institute of Technology)

​

  • 08/2019-08/2021: Awarded a M.Sc. scholarship by CAPES

​

  • 08/2018-07/2019: Awarded an undergraduate research project scholarship by UNICAMP

​

  • 08/2017-07/2018: Awarded an undergraduate research project scholarship by CNPq

Teaching
Experience

  • ​08/2020-01/2021: Co-advisor (with Professor Romis Attux) in Mauricio Bernardini’s undergraduate thesis, on the subject of deep learning in medical applications. UNICAMP, SP, Brazil

Anchor 4

Language
Skills

  • English - Fluent (108/120 score on TOEFL IBT, ETS)

  • Portuguese - Fluent (native)

  • German - Fluent (B2 on Deutsches Sprachdiplom der Kultusministerkonferenz/DSD, Kultusministerkonferenz)

  • Spanish - Fluent (B2 on Diploma de Español como Lengua Extranjera/DELE, Instituto Cervantes)

  • Italian - Upper intermediate (currently studying)

Anchor 5

Programming and
Research Skills

  • Python, PyTorch, TensorFlow, and Keras

  • Neural networks and deep learning

  • Artificial Intelligence

  • Deep learning explainability

  • Computer vision

  • Natural language processing and vision-language models

  • Signal processing

  • Computational analysis of biomedical data

  • AI-assisted diagnosis

  • C

  • Matlab and Wolfram Mathematica

  • Assembly

  • Android programming (Kotlin)

  • Embedded systems

Anchor 6
Contact

Reviewer
Activity

  • Scientific Reports, Nature Portfolio

  • NeurIPS

  • CVPR

  • ICLR

  • IEEE Transactions on Cybernetics, IEEE

  • Neural Networks, Elsevier

  • Biomedical Signal Processing and Control, BSPC, Elsevier

  • Medical & Biological Engineering & Computing, MBEC, Springer

  • Research on Biomedical Engineering, RBME, Springer

  • Simpósio Brasileiro de Telecomunicações e Processamento de Sinais, SBrT

Anchor 7
bottom of page