Holger R. Roth

Andres Diaz-Pinto, Sachidanand Alle, Vishwesh Nath et al. · microsoft-research

The lack of annotated datasets is a major bottleneck for training new task-specific supervised machine learning models, considering that manual annotation is extremely expensive and time-consuming. To address this problem, we present MONAI Label, a free and open-source framework that facilitates the development of applications based on artificial intelligence (AI) models that aim at reducing the time required to annotate radiology datasets. Through MONAI Label, researchers can develop AI annotation applications focusing on their domain of expertise. It allows researchers to readily deploy their apps as services, which can be made available to clinicians via their preferred user interface. Currently, MONAI Label readily supports locally installed (3D Slicer) and web-based (OHIF) frontends and offers two active learning strategies to facilitate and speed up the training of segmentation algorithms. MONAI Label allows researchers to make incremental improvements to their AI-based annotation application by making them available to other researchers and clinicians alike. Additionally, MONAI Label provides sample AI-based interactive and non-interactive labeling applications, that can be used directly off the shelf, as plug-and-play to any given dataset. Significant reduced annotation times using the interactive model can be observed on two public datasets.

Holger R. Roth, Yan Cheng, Yuhong Wen et al.

Federated learning (FL) enables building robust and generalizable AI models by leveraging diverse datasets from multiple collaborators without centralizing the data. We created NVIDIA FLARE as an open-source software development kit (SDK) to make it easier for data scientists to use FL in their research and real-world applications. The SDK includes solutions for state-of-the-art FL algorithms and federated machine learning approaches, which facilitate building workflows for distributed learning across enterprises and enable platform developers to create a secure, privacy-preserving offering for multiparty collaboration utilizing homomorphic encryption or differential privacy. The SDK is a lightweight, flexible, and scalable Python package. It allows researchers to apply their data science workflows in any training libraries (PyTorch, TensorFlow, XGBoost, or even NumPy) in real-world FL settings. This paper introduces the key design principles of NVFlare and illustrates some use cases (e.g., COVID analysis) with customizable FL workflows that implement different privacy-preserving algorithms. Code is available at https://github.com/NVIDIA/NVFlare.

M. Jorge Cardoso, Wenqi Li, Richard Brown et al.

Artificial Intelligence (AI) is having a tremendous impact across most areas of science. Applications of AI in healthcare have the potential to improve our ability to detect, diagnose, prognose, and intervene on human disease. For AI models to be used clinically, they need to be made safe, reproducible and robust, and the underlying software framework must be aware of the particularities (e.g. geometry, physiology, physics) of medical data being processed. This work introduces MONAI, a freely available, community-supported, and consortium-led PyTorch-based framework for deep learning in healthcare. MONAI extends PyTorch to support medical data, with a particular focus on imaging, and provide purpose-specific AI model architectures, transformations and utilities that streamline the development and deployment of medical AI models. MONAI follows best practices for software-development, providing an easy-to-use, robust, well-documented, and well-tested software framework. MONAI preserves the simple, additive, and compositional approach of its underlying PyTorch libraries. MONAI is being used by and receiving contributions from research, clinical and industrial teams from around the world, who are pursuing applications spanning nearly every aspect of healthcare.

Pochuan Wang, Chen Shen, Weichung Wang et al.

Developing a generalized segmentation model capable of simultaneously delineating multiple organs and diseases is highly desirable. Federated learning (FL) is a key technology enabling the collaborative development of a model without exchanging training data. However, the limited access to fully annotated training data poses a major challenge to training generalizable models. We propose "ConDistFL", a framework to solve this problem by combining FL with knowledge distillation. Local models can extract the knowledge of unlabeled organs and tumors from partially annotated data from the global model with an adequately designed conditional probability representation. We validate our framework on four distinct partially annotated abdominal CT datasets from the MSD and KiTS19 challenges. The experimental results show that the proposed framework significantly outperforms FedAvg and FedOpt baselines. Moreover, the performance on an external test dataset demonstrates superior generalizability compared to models trained on each dataset separately. Our ablation study suggests that ConDistFL can perform well without frequent aggregation, reducing the communication cost of FL. Our implementation will be available at https://github.com/NVIDIA/NVFlare/tree/dev/research/condist-fl.

Pengfei Guo, Dong Yang, Ali Hatamizadeh et al.

Federated learning (FL) is a distributed machine learning technique that enables collaborative model training while avoiding explicit data sharing. The inherent privacy-preserving property of FL algorithms makes them especially attractive to the medical field. However, in case of heterogeneous client data distributions, standard FL methods are unstable and require intensive hyperparameter tuning to achieve optimal performance. Conventional hyperparameter optimization algorithms are impractical in real-world FL applications as they involve numerous training trials, which are often not affordable with limited compute budgets. In this work, we propose an efficient reinforcement learning (RL)-based federated hyperparameter optimization algorithm, termed Auto-FedRL, in which an online RL agent can dynamically adjust hyperparameters of each client based on the current training progress. Extensive experiments are conducted to investigate different search strategies and RL agents. The effectiveness of the proposed method is validated on a heterogeneous data split of the CIFAR-10 dataset as well as two real-world medical image segmentation datasets for COVID-19 lesion segmentation in chest CT and pancreas segmentation in abdominal CT.

Vishwesh Nath, Dong Yang, Holger R. Roth et al.

Which volume to annotate next is a challenging problem in building medical imaging datasets for deep learning. One of the promising methods to approach this question is active learning (AL). However, AL has been a hard nut to crack in terms of which AL algorithm and acquisition functions are most useful for which datasets. Also, the problem is exacerbated with which volumes to label first when there is zero labeled data to start with. This is known as the cold start problem in AL. We propose two novel strategies for AL specifically for 3D image segmentation. First, we tackle the cold start problem by proposing a proxy task and then utilizing uncertainty generated from the proxy task to rank the unlabeled data to be annotated. Second, we craft a two-stage learning framework for each active iteration where the unlabeled data is also used in the second stage as a semi-supervised fine-tuning strategy. We show the promise of our approach on two well-known large public datasets from medical segmentation decathlon. The results indicate that the initial selection of data and semi-supervised framework both showed significant improvement for several AL strategies.

Jingwei Sun, Ziyue Xu, Dong Yang et al.

Federated learning is a popular collaborative learning approach that enables clients to train a global model without sharing their local data. Vertical federated learning (VFL) deals with scenarios in which the data on clients have different feature spaces but share some overlapping samples. Existing VFL approaches suffer from high communication costs and cannot deal efficiently with limited overlapping samples commonly seen in the real world. We propose a practical vertical federated learning (VFL) framework called \textbf{one-shot VFL} that can solve the communication bottleneck and the problem of limited overlapping samples simultaneously based on semi-supervised learning. We also propose \textbf{few-shot VFL} to improve the accuracy further with just one more communication round between the server and the clients. In our proposed framework, the clients only need to communicate with the server once or only a few times. We evaluate the proposed VFL framework on both image and tabular datasets. Our methods can improve the accuracy by more than 46.5\% and reduce the communication cost by more than 330$\times$ compared with state-of-the-art VFL methods when evaluated on CIFAR-10. Our code will be made publicly available at \url{https://nvidia.github.io/NVFlare/research/one-shot-vfl}.

Jingwei Sun, Ziyue Xu, Hongxu Yin et al.

Pre-trained language models (PLM) have revolutionized the NLP landscape, achieving stellar performances across diverse tasks. These models, while benefiting from vast training data, often require fine-tuning on specific data to cater to distinct downstream tasks. However, this data adaptation process has inherent security and privacy concerns, primarily when leveraging user-generated, device-residing data. Federated learning (FL) provides a solution, allowing collaborative model fine-tuning without centralized data collection. However, applying FL to finetune PLMs is hampered by challenges, including restricted model parameter access, high computational requirements, and communication overheads. This paper introduces Federated Black-box Prompt Tuning (FedBPT), a framework designed to address these challenges. FedBPT does not require the clients to access the model parameters. By focusing on training optimal prompts and utilizing gradient-free optimization methods, FedBPT reduces the number of exchanged variables, boosts communication efficiency, and minimizes computational and storage costs. Experiments highlight the framework's ability to drastically cut communication and memory costs while maintaining competitive performance. Ultimately, FedBPT presents a promising solution for efficient, privacy-preserving fine-tuning of PLM in the age of large language models.

Holger R. Roth, Ali Hatamizadeh, Ziyue Xu et al.

Split learning (SL) has been proposed to train deep learning models in a decentralized manner. For decentralized healthcare applications with vertical data partitioning, SL can be beneficial as it allows institutes with complementary features or images for a shared set of patients to jointly develop more robust and generalizable models. In this work, we propose "Split-U-Net" and successfully apply SL for collaborative biomedical image segmentation. Nonetheless, SL requires the exchanging of intermediate activation maps and gradients to allow training models across different feature spaces, which might leak data and raise privacy concerns. Therefore, we also quantify the amount of data leakage in common SL scenarios for biomedical image segmentation and provide ways to counteract such leakage by applying appropriate defense strategies.

Austin Tapp, Holger R. Roth, Ziyue Xu et al.

Federated learning (FL) enables collaborative model training over privacy-sensitive, distributed data, but its environmental impact is difficult to compare across studies due to inconsistent measurement boundaries and heterogeneous reporting. We present a practical carbon-accounting methodology for FL CO2e tracking using NVIDIA NVFlare and CodeCarbon for explicit, phase-aware tasks (initialization, per-round training, evaluation, and idle/coordination). To capture non-compute effects, we additionally estimate communication emissions from transmitted model-update sizes under a network-configurable energy model. We validate the proposed approach on two representative workloads: CIFAR-10 image classification and retinal optic disk segmentation. In CIFAR-10, controlled client-efficiency scenarios show that system-level slowdowns and coordination effects can contribute meaningfully to carbon footprint under an otherwise fixed FL protocol, increasing total CO2e by 8.34x (medium) and 21.73x (low) relative to the high-efficiency baseline. In retinal segmentation, swapping GPU tiers (H100 vs.\ V100) yields a consistent 1.7x runtime gap (290 vs. 503 minutes) while producing non-uniform changes in total energy and CO2e across sites, underscoring the need for per-site and per-round reporting. Overall, our results support a standardized carbon accounting method that acts as a prerequisite for reproducible 'green' FL evaluation. Our code is available at https://github.com/Pediatric-Accelerated-Intelligence-Lab/carbon_footprint.

Baris Askin, Holger R. Roth, Zhenyu Sun et al.

Federated Learning (FL) enables collaborative model training across distributed clients without sharing raw data, yet its scalability is limited by synchronization overhead. Asynchronous Federated Learning (AFL) alleviates this issue by allowing clients to communicate independently, thereby improving wall-clock efficiency in large-scale, heterogeneous environments. However, this asynchrony introduces stale updates (client updates computed on outdated global models) that can destabilize optimization and hinder convergence. We propose FedRevive, an asynchronous FL framework that revives stale updates through data-free knowledge distillation (DFKD). FedRevive integrates parameter-space aggregation with a lightweight, server-side DFKD process that transfers knowledge from stale client models to the current global model without access to real or public data. A meta-learned generator synthesizes pseudo-samples, which enables multi-teacher distillation. A hybrid aggregation scheme that combines raw updates with DFKD updates effectively mitigates staleness while retaining the scalability of AFL. Experiments on various vision and text benchmarks show that FedRevive achieves faster training up to 32.1% and higher final accuracy up to 21.5% compared to asynchronous baselines.

Zhifan Jiang, Dong Yang, Vishwesh Nath et al.

Large vision-language models (VLMs) have evolved from general-purpose applications to specialized use cases such as in the clinical domain, demonstrating potential for decision support in radiology. One promising application is assisting radiologists in decision-making by the analysis of radiology imaging data such as chest X-rays (CXR) via a visual and natural language question-answering (VQA) interface. When longitudinal imaging is available, radiologists analyze temporal changes, which are essential for accurate diagnosis and prognosis. The manual longitudinal analysis is a time-consuming process, motivating the development of a training framework that can provide prognostic capabilities. We introduce a novel training framework LUMEN, that is optimized for longitudinal CXR interpretation, leveraging multi-image and multi-task instruction fine-tuning to enhance prognostic and diagnostic performance. We conduct experiments on the publicly available MIMIC-CXR and its associated Medical-Diff-VQA datasets. We further formulate and construct a novel instruction-following dataset incorporating longitudinal studies, enabling the development of a prognostic VQA task. Our method demonstrates significant improvements over baseline models in diagnostic VQA tasks, and more importantly, shows promising potential for prognostic capabilities. These results underscore the value of well-designed, instruction-tuned VLMs in enabling more accurate and clinically meaningful radiological interpretation of longitudinal radiological imaging data.

Hareem Nisar, Syed Muhammad Anwar, Zhifan Jiang et al.

Large vision language models (VLMs) have progressed incredibly from research to applicability for general-purpose use cases. LLaVA-Med, a pioneering large language and vision assistant for biomedicine, can perform multi-modal biomedical image and data analysis to provide a natural language interface for radiologists. While it is highly generalizable and works with multi-modal data, it is currently limited by well-known challenges that exist in the large language model space. Hallucinations and imprecision in responses can lead to misdiagnosis which currently hinder the clinical adaptability of VLMs. To create precise, user-friendly models in healthcare, we propose D-Rax -- a domain-specific, conversational, radiologic assistance tool that can be used to gain insights about a particular radiologic image. In this study, we enhance the conversational analysis of chest X-ray (CXR) images to support radiological reporting, offering comprehensive insights from medical imaging and aiding in the formulation of accurate diagnosis. D-Rax is achieved by fine-tuning the LLaVA-Med architecture on our curated enhanced instruction-following data, comprising of images, instructions, as well as disease diagnosis and demographic predictions derived from MIMIC-CXR imaging data, CXR-related visual question answer (VQA) pairs, and predictive outcomes from multiple expert AI models. We observe statistically significant improvement in responses when evaluated for both open and close-ended conversations. Leveraging the power of state-of-the-art diagnostic models combined with VLMs, D-Rax empowers clinicians to interact with medical images using natural language, which could potentially streamline their decision-making process, enhance diagnostic accuracy, and conserve their time.

Abhijeet Parida, Antonia Alomar, Zhifan Jiang et al.

Deploying deep learning-based imaging tools across various clinical sites poses significant challenges due to inherent domain shifts and regulatory hurdles associated with site-specific fine-tuning. For histopathology, stain normalization techniques can mitigate discrepancies, but they often fall short of eliminating inter-site variations. Therefore, we present Data Alchemy, an explainable stain normalization method combined with test time data calibration via a template learning framework to overcome barriers in cross-site analysis. Data Alchemy handles shifts inherent to multi-site data and minimizes them without needing to change the weights of the normalization or classifier networks. Our approach extends to unseen sites in various clinical settings where data domain discrepancies are unknown. Extensive experiments highlight the efficacy of our framework in tumor classification in hematoxylin and eosin-stained patches. Our explainable normalization method boosts classification tasks' area under the precision-recall curve(AUPR) by 0.165, 0.545 to 0.710. Additionally, Data Alchemy further reduces the multisite classification domain gap, by improving the 0.710 AUPR an additional 0.142, elevating classification performance further to 0.852, from 0.545. Our Data Alchemy framework can popularize precision medicine with minimal operational overhead by allowing for the seamless integration of pre-trained deep learning-based clinical tools across multiple sites.

Abhijeet Parida, Antonia Alomar, Zhifan Jiang et al.

Federated learning enables collaborative model training across geographically distributed medical centers while preserving data privacy. However, domain shifts and heterogeneity in data often lead to a degradation in model performance. Medical imaging applications are particularly affected by variations in acquisition protocols, scanner types, and patient populations. To address these issues, we introduce Federated Template and Task Learning (FeTTL), a novel framework designed to harmonize multi-institutional medical imaging data in federated environments. FeTTL learns a global template together with a task model to align data distributions among clients. We evaluated FeTTL on two challenging and diverse multi-institutional medical imaging tasks: retinal fundus optical disc segmentation and histopathological metastasis classification. Experimental results show that FeTTL significantly outperforms the state-of-the-art federated learning baselines (p-values <0.002) for optical disc segmentation and classification of metastases from multi-institutional data. Our experiments further highlight the importance of jointly learning the template and the task. These findings suggest that FeTTL offers a principled and extensible solution for mitigating distribution shifts in federated learning, supporting robust model deployment in real-world, multi-institutional environments.

Holger R. Roth, Sarthak Tickoo, Mayank Kumar et al.

Fraud-related financial losses continue to rise, while regulatory, privacy, and data-sovereignty constraints increasingly limit the feasibility of centralized fraud detection systems. Federated Learning (FL) has emerged as a promising paradigm for enabling collaborative model training across institutions without sharing raw transaction data. Yet, its practical effectiveness under realistic, non-IID financial data distributions remains insufficiently validated. In this work, we present a multi-institution, industry-oriented proof-of-concept study evaluating federated anomaly detection for payment transactions using the NVIDIA FLARE framework. We simulate a realistic federation of heterogeneous financial institutions, each observing distinct fraud typologies and operating under strict data isolation. Using a deep neural network trained via federated averaging (FedAvg), we demonstrate that federated models achieve a mean F1-score of 0.903 - substantially outperforming locally trained models (0.643) and closely approaching centralized training performance (0.925), while preserving full data sovereignty. We further analyze convergence behavior, showing that strong performance is achieved within 10 federated communication rounds, highlighting the operational viability of FL in latency- and cost-sensitive financial environments. To support deployment in regulated settings, we evaluate model interpretability using Shapley-based feature attribution and confirm that federated models rely on semantically coherent, domain-relevant decision signals. Finally, we incorporate sample-level differential privacy via DP-SGD and demonstrate favorable privacy-utility trade-offs...

Andres Diaz-Pinto, Pritesh Mehta, Sachidanand Alle et al.

Automatic segmentation of medical images is a key step for diagnostic and interventional tasks. However, achieving this requires large amounts of annotated volumes, which can be tedious and time-consuming task for expert annotators. In this paper, we introduce DeepEdit, a deep learning-based method for volumetric medical image annotation, that allows automatic and semi-automatic segmentation, and click-based refinement. DeepEdit combines the power of two methods: a non-interactive (i.e. automatic segmentation using nnU-Net, UNET or UNETR) and an interactive segmentation method (i.e. DeepGrow), into a single deep learning model. It allows easy integration of uncertainty-based ranking strategies (i.e. aleatoric and epistemic uncertainty computation) and active learning. We propose and implement a method for training DeepEdit by using standard training combined with user interaction simulation. Once trained, DeepEdit allows clinicians to quickly segment their datasets by using the algorithm in auto segmentation mode or by providing clicks via a user interface (i.e. 3D Slicer, OHIF). We show the value of DeepEdit through evaluation on the PROSTATEx dataset for prostate/prostatic lesions and the Multi-Atlas Labeling Beyond the Cranial Vault (BTCV) dataset for abdominal CT segmentation, using state-of-the-art network architectures as baseline for comparison. DeepEdit could reduce the time and effort annotating 3D medical images compared to DeepGrow alone. Source code is available at https://github.com/Project-MONAI/MONAILabel

Ali Hatamizadeh, Hongxu Yin, Pavlo Molchanov et al.

Federated learning (FL) allows the collaborative training of AI models without needing to share raw data. This capability makes it especially interesting for healthcare applications where patient and data privacy is of utmost concern. However, recent works on the inversion of deep neural networks from model gradients raised concerns about the security of FL in preventing the leakage of training data. In this work, we show that these attacks presented in the literature are impractical in FL use-cases where the clients' training involves updating the Batch Normalization (BN) statistics and provide a new baseline attack that works for such scenarios. Furthermore, we present new ways to measure and visualize potential data leakage in FL. Our work is a step towards establishing reproducible methods of measuring data leakage in FL and could help determine the optimal tradeoffs between privacy-preserving techniques, such as differential privacy, and model accuracy based on quantifiable metrics. Code is available at https://nvidia.github.io/NVFlare/research/quantifying-data-leakage.

Holger R. Roth, Hirohisa Oda, Xiangrong Zhou et al.

Recent advances in 3D fully convolutional networks (FCN) have made it feasible to produce dense voxel-wise predictions of volumetric images. In this work, we show that a multi-class 3D FCN trained on manually labeled CT scans of several anatomical structures (ranging from the large organs to thin vessels) can achieve competitive segmentation results, while avoiding the need for handcrafting features or training class-specific models. To this end, we propose a two-stage, coarse-to-fine approach that will first use a 3D FCN to roughly define a candidate region, which will then be used as input to a second 3D FCN. This reduces the number of voxels the second FCN has to classify to ~10% and allows it to focus on more detailed segmentation of the organs and vessels. We utilize training and validation sets consisting of 331 clinical CT images and test our models on a completely unseen data collection acquired at a different hospital that includes 150 CT scans, targeting three anatomical organs (liver, spleen, and pancreas). In challenging organs such as the pancreas, our cascaded approach improves the mean Dice score from 68.5 to 82.2%, achieving the highest reported average score on this dataset. We compare with a 2D FCN method on a separate dataset of 240 CT scans with 18 classes and achieve a significantly higher performance in small organs and vessels. Furthermore, we explore fine-tuning our models to different datasets. Our experiments illustrate the promise and robustness of current 3D FCN based semantic segmentation of medical images, achieving state-of-the-art results. Our code and trained models are available for download: https://github.com/holgerroth/3Dunet_abdomen_cascade.

Holger R. Roth, Ziyue Xu, Yuan-Ting Hsieh et al.

In the ever-evolving landscape of artificial intelligence (AI) and large language models (LLMs), handling and leveraging data effectively has become a critical challenge. Most state-of-the-art machine learning algorithms are data-centric. However, as the lifeblood of model performance, necessary data cannot always be centralized due to various factors such as privacy, regulation, geopolitics, copyright issues, and the sheer effort required to move vast datasets. In this paper, we explore how federated learning enabled by NVIDIA FLARE can address these challenges with easy and scalable integration capabilities, enabling parameter-efficient and full supervised fine-tuning of LLMs for natural language processing and biopharmaceutical applications to enhance their accuracy and robustness.

Pochuan Wang, Chen Shen, Masahiro Oda et al.

In medical imaging, developing generalized segmentation models that can handle multiple organs and lesions is crucial. However, the scarcity of fully annotated datasets and strict privacy regulations present significant barriers to data sharing. Federated Learning (FL) allows decentralized model training, but existing FL methods often struggle with partial labeling, leading to model divergence and catastrophic forgetting. We propose ConDistFL, a novel FL framework incorporating conditional distillation to address these challenges. ConDistFL enables effective learning from partially labeled datasets, significantly improving segmentation accuracy across distributed and non-uniform datasets. In addition to its superior segmentation performance, ConDistFL maintains computational and communication efficiency, ensuring its scalability for real-world applications. Furthermore, ConDistFL demonstrates remarkable generalizability, significantly outperforming existing FL methods in out-of-federation tests, even adapting to unseen contrast phases (e.g., non-contrast CT images) in our experiments. Extensive evaluations on 3D CT and 2D chest X-ray datasets show that ConDistFL is an efficient, adaptable solution for collaborative medical image segmentation in privacy-constrained settings.

Kendall Schmidt, Benjamin Bearce, Ken Chang et al.

The correct interpretation of breast density is important in the assessment of breast cancer risk. AI has been shown capable of accurately predicting breast density, however, due to the differences in imaging characteristics across mammography systems, models built using data from one system do not generalize well to other systems. Though federated learning (FL) has emerged as a way to improve the generalizability of AI without the need to share data, the best way to preserve features from all training data during FL is an active area of research. To explore FL methodology, the breast density classification FL challenge was hosted in partnership with the American College of Radiology, Harvard Medical School's Mass General Brigham, University of Colorado, NVIDIA, and the National Institutes of Health National Cancer Institute. Challenge participants were able to submit docker containers capable of implementing FL on three simulated medical facilities, each containing a unique large mammography dataset. The breast density FL challenge ran from June 15 to September 5, 2022, attracting seven finalists from around the world. The winning FL submission reached a linear kappa score of 0.653 on the challenge test data and 0.413 on an external testing dataset, scoring comparably to a model trained on the same data in a central location.

Joshua C. Zhao, Saurabh Bagchi, Salman Avestimehr et al.

Deep learning has shown incredible potential across a wide array of tasks, and accompanied by this growth has been an insatiable appetite for data. However, a large amount of data needed for enabling deep learning is stored on personal devices, and recent concerns on privacy have further highlighted challenges for accessing such data. As a result, federated learning (FL) has emerged as an important privacy-preserving technology that enables collaborative training of machine learning models without the need to send the raw, potentially sensitive, data to a central server. However, the fundamental premise that sending model updates to a server is privacy-preserving only holds if the updates cannot be "reverse engineered" to infer information about the private training data. It has been shown under a wide variety of settings that this privacy premise does not hold. In this survey paper, we provide a comprehensive literature review of the different privacy attacks and defense methods in FL. We identify the current limitations of these attacks and highlight the settings in which the privacy of an FL client can be broken. We further dissect some of the successful industry applications of FL and draw lessons for future successful adoption. We survey the emerging landscape of privacy regulation for FL and conclude with future directions for taking FL toward the cherished goal of generating accurate models while preserving the privacy of the data from its participants.

Dong Yang, Andriy Myronenko, Xiaosong Wang et al.

Lesion segmentation in medical imaging has been an important topic in clinical research. Researchers have proposed various detection and segmentation algorithms to address this task. Recently, deep learning-based approaches have significantly improved the performance over conventional methods. However, most state-of-the-art deep learning methods require the manual design of multiple network components and training strategies. In this paper, we propose a new automated machine learning algorithm, T-AutoML, which not only searches for the best neural architecture, but also finds the best combination of hyper-parameters and data augmentation strategies simultaneously. The proposed method utilizes the modern transformer model, which is introduced to adapt to the dynamic length of the search space embedding and can significantly improve the ability of the search. We validate T-AutoML on several large-scale public lesion segmentation data-sets and achieve state-of-the-art performance.

Chen Shen, Pochuan Wang, Holger R. Roth et al.

Federated learning (FL) for medical image segmentation becomes more challenging in multi-task settings where clients might have different categories of labels represented in their data. For example, one client might have patient data with "healthy'' pancreases only while datasets from other clients may contain cases with pancreatic tumors. The vanilla federated averaging algorithm makes it possible to obtain more generalizable deep learning-based segmentation models representing the training data from multiple institutions without centralizing datasets. However, it might be sub-optimal for the aforementioned multi-task scenarios. In this paper, we investigate heterogeneous optimization methods that show improvements for the automated segmentation of pancreas and pancreatic tumors in abdominal CT images with FL settings.

Holger R. Roth, Dong Yang, Wenqi Li et al.

Building robust deep learning-based models requires diverse training data, ideally from several sources. However, these datasets cannot be combined easily because of patient privacy concerns or regulatory hurdles, especially if medical data is involved. Federated learning (FL) is a way to train machine learning models without the need for centralized datasets. Each FL client trains on their local data while only sharing model parameters with a global server that aggregates the parameters from all clients. At the same time, each client's data can exhibit differences and inconsistencies due to the local variation in the patient population, imaging equipment, and acquisition protocols. Hence, the federated learned models should be able to adapt to the local particularities of a client's data. In this work, we combine FL with an AutoML technique based on local neural architecture search by training a "supernet". Furthermore, we propose an adaptation scheme to allow for personalized model architectures at each FL client's site. The proposed method is evaluated on four different datasets from 3D prostate MRI and shown to improve the local models' performance after adaptation through selecting an optimal path through the AutoML supernet.

Vishwesh Nath, Dong Yang, Bennett A. Landman et al.

Active learning is a unique abstraction of machine learning techniques where the model/algorithm could guide users for annotation of a set of data points that would be beneficial to the model, unlike passive machine learning. The primary advantage being that active learning frameworks select data points that can accelerate the learning process of a model and can reduce the amount of data needed to achieve full accuracy as compared to a model trained on a randomly acquired data set. Multiple frameworks for active learning combined with deep learning have been proposed, and the majority of them are dedicated to classification tasks. Herein, we explore active learning for the task of segmentation of medical imaging data sets. We investigate our proposed framework using two datasets: 1.) MRI scans of the hippocampus, 2.) CT scans of pancreas and tumors. This work presents a query-by-committee approach for active learning where a joint optimizer is used for the committee. At the same time, we propose three new strategies for active learning: 1.) increasing frequency of uncertain data to bias the training data set; 2.) Using mutual information among the input images as a regularizer for acquisition to ensure diversity in the training dataset; 3.) adaptation of Dice log-likelihood for Stein variational gradient descent (SVGD). The results indicate an improvement in terms of data reduction by achieving full accuracy while only using 22.69 % and 48.85 % of the available data for each dataset, respectively.

Dong Yang, Ziyue Xu, Wenqi Li et al.

The recent outbreak of COVID-19 has led to urgent needs for reliable diagnosis and management of SARS-CoV-2 infection. As a complimentary tool, chest CT has been shown to be able to reveal visual patterns characteristic for COVID-19, which has definite value at several stages during the disease course. To facilitate CT analysis, recent efforts have focused on computer-aided characterization and diagnosis, which has shown promising results. However, domain shift of data across clinical data centers poses a serious challenge when deploying learning-based models. In this work, we attempt to find a solution for this challenge via federated and semi-supervised learning. A multi-national database consisting of 1704 scans from three countries is adopted to study the performance gap, when training a model with one dataset and applying it to another. Expert radiologists manually delineated 945 scans for COVID-19 findings. In handling the variability in both the data and annotations, a novel federated semi-supervised learning technique is proposed to fully utilize all available data (with or without annotations). Federated learning avoids the need for sensitive data-sharing, which makes it favorable for institutions and nations with strict regulatory policy on data privacy. Moreover, semi-supervision potentially reduces the annotation burden under a distributed setting. The proposed framework is shown to be effective compared to fully supervised scenarios with conventional data sharing instead of model weight sharing.

Pochuan Wang, Chen Shen, Holger R. Roth et al.

The performance of deep learning-based methods strongly relies on the number of datasets used for training. Many efforts have been made to increase the data in the medical image analysis field. However, unlike photography images, it is hard to generate centralized databases to collect medical images because of numerous technical, legal, and privacy issues. In this work, we study the use of federated learning between two institutions in a real-world setting to collaboratively train a model without sharing the raw data across national boundaries. We quantitatively compare the segmentation models obtained with federated learning and local training alone. Our experimental results show that federated learning models have higher generalizability than standalone training.

Holger R. Roth, Ken Chang, Praveer Singh et al.

Building robust deep learning-based models requires large quantities of diverse training data. In this study, we investigate the use of federated learning (FL) to build medical imaging classification models in a real-world collaborative setting. Seven clinical institutions from across the world joined this FL effort to train a model for breast density classification based on Breast Imaging, Reporting & Data System (BI-RADS). We show that despite substantial differences among the datasets from all sites (mammography system, class distribution, and data set size) and without centralizing data, we can successfully train AI models in federation. The results show that models trained using FL perform 6.3% on average better than their counterparts trained on an institute's local data alone. Furthermore, we show a 45.8% relative improvement in the models' generalizability when evaluated on the other participating sites' testing data.

Masahiro Oda, Holger R. Roth, Takayuki Kitasaka et al.

This paper presents a colonoscope tracking method utilizing a colon shape estimation method. CT colonography is used as a less-invasive colon diagnosis method. If colonic polyps or early-stage cancers are found, they are removed in a colonoscopic examination. In the colonoscopic examination, understanding where the colonoscope running in the colon is difficult. A colonoscope navigation system is necessary to reduce overlooking of polyps. We propose a colonoscope tracking method for navigation systems. Previous colonoscope tracking methods caused large tracking errors because they do not consider deformations of the colon during colonoscope insertions. We utilize the shape estimation network (SEN), which estimates deformed colon shape during colonoscope insertions. The SEN is a neural network containing long short-term memory (LSTM) layer. To perform colon shape estimation suitable to the real clinical situation, we trained the SEN using data obtained during colonoscope operations of physicians. The proposed tracking method performs mapping of the colonoscope tip position to a position in the colon using estimation results of the SEN. We evaluated the proposed method in a phantom study. We confirmed that tracking errors of the proposed method was enough small to perform navigation in the ascending, transverse, and descending colons.

Masahiro Oda, Holger R. Roth, Takayuki Kitasaka et al.

We propose an estimation method using a recurrent neural network (RNN) of the colon's shape where deformation was occurred by a colonoscope insertion. Colonoscope tracking or a navigation system that navigates physician to polyp positions is needed to reduce such complications as colon perforation. Previous tracking methods caused large tracking errors at the transverse and sigmoid colons because these areas largely deform during colonoscope insertion. Colon deformation should be taken into account in tracking processes. We propose a colon deformation estimation method using RNN and obtain the colonoscope shape from electromagnetic sensors during its insertion into the colon. This method obtains positional, directional, and an insertion length from the colonoscope shape. From its shape, we also calculate the relative features that represent the positional and directional relationships between two points on a colonoscope. Long short-term memory is used to estimate the current colon shape from the past transition of the features of the colonoscope shape. We performed colon shape estimation in a phantom study and correctly estimated the colon shapes during colonoscope insertion with 12.39 (mm) estimation error.

Chenglong Wang, Holger R. Roth, Takayuki Kitasaka et al.

This paper presents a new approach for precisely estimating the renal vascular dominant region using a Voronoi diagram. To provide computer-assisted diagnostics for the pre-surgical simulation of partial nephrectomy surgery, we must obtain information on the renal arteries and the renal vascular dominant regions. We propose a fully automatic segmentation method that combines a neural network and tensor-based graph-cut methods to precisely extract the kidney and renal arteries. First, we use a convolutional neural network to localize the kidney regions and extract tiny renal arteries with a tensor-based graph-cut method. Then we generate a Voronoi diagram to estimate the renal vascular dominant regions based on the segmented kidney and renal arteries. The accuracy of kidney segmentation in 27 cases with 8-fold cross validation reached a Dice score of 95%. The accuracy of renal artery segmentation in 8 cases obtained a centerline overlap ratio of 80%. Each partition region corresponds to a renal vascular dominant region. The final dominant-region estimation accuracy achieved a Dice coefficient of 80%. A clinical application showed the potential of our proposed estimation approach in a real clinical surgical environment. Further validation using large-scale database is our future work.

Masahiro Oda, Natsuki Shimizu, Holger R. Roth et al.

This paper presents a fully automated atlas-based pancreas segmentation method from CT volumes utilizing 3D fully convolutional network (FCN) feature-based pancreas localization. Segmentation of the pancreas is difficult because it has larger inter-patient spatial variations than other organs. Previous pancreas segmentation methods failed to deal with such variations. We propose a fully automated pancreas segmentation method that contains novel localization and segmentation. Since the pancreas neighbors many other organs, its position and size are strongly related to the positions of the surrounding organs. We estimate the position and the size of the pancreas (localized) from global features by regression forests. As global features, we use intensity differences and 3D FCN deep learned features, which include automatically extracted essential features for segmentation. We chose 3D FCN features from a trained 3D U-Net, which is trained to perform multi-organ segmentation. The global features include both the pancreas and surrounding organ information. After localization, a patient-specific probabilistic atlas-based pancreas segmentation is performed. In evaluation results with 146 CT volumes, we achieved 60.6% of the Jaccard index and 73.9% of the Dice overlap.

Holger R. Roth, Chen Shen, Hirohisa Oda et al.

Recent advances in deep learning, like 3D fully convolutional networks (FCNs), have improved the state-of-the-art in dense semantic segmentation of medical images. However, most network architectures require severely downsampling or cropping the images to meet the memory limitations of today's GPU cards while still considering enough context in the images for accurate segmentation. In this work, we propose a novel approach that utilizes auto-context to perform semantic segmentation at higher resolutions in a multi-scale pyramid of stacked 3D FCNs. We train and validate our models on a dataset of manually annotated abdominal organs and vessels from 377 clinical CT images used in gastric surgery, and achieve promising results with close to 90% Dice score on average. For additional evaluation, we perform separate testing on datasets from different sources and achieve competitive results, illustrating the robustness of the model and approach.

Takayasu Moriya, Holger R. Roth, Shota Nakamura et al.

This paper presents a novel unsupervised segmentation method for 3D medical images. Convolutional neural networks (CNNs) have brought significant advances in image segmentation. However, most of the recent methods rely on supervised learning, which requires large amounts of manually annotated data. Thus, it is challenging for these methods to cope with the growing amount of medical images. This paper proposes a unified approach to unsupervised deep representation learning and clustering for segmentation. Our proposed method consists of two phases. In the first phase, we learn deep feature representations of training patches from a target image using joint unsupervised learning (JULE) that alternately clusters representations generated by a CNN and updates the CNN parameters using cluster labels as supervisory signals. We extend JULE to 3D medical images by utilizing 3D convolutions throughout the CNN architecture. In the second phase, we apply k-means to the deep representations from the trained CNN and then project cluster labels to the target image in order to obtain the fully segmented image. We evaluated our methods on three images of lung cancer specimens scanned with micro-computed tomography (micro-CT). The automatic segmentation of pathological regions in micro-CT could further contribute to the pathological examination process. Hence, we aim to automatically divide each image into the regions of invasive carcinoma, noninvasive carcinoma, and normal tissue. Our experiments show the potential abilities of unsupervised deep representation learning for medical image segmentation.

Takayasu Moriya, Holger R. Roth, Shota Nakamura et al.

This paper presents a novel method for unsupervised segmentation of pathology images. Staging of lung cancer is a major factor of prognosis. Measuring the maximum dimensions of the invasive component in a pathology images is an essential task. Therefore, image segmentation methods for visualizing the extent of invasive and noninvasive components on pathology images could support pathological examination. However, it is challenging for most of the recent segmentation methods that rely on supervised learning to cope with unlabeled pathology images. In this paper, we propose a unified approach to unsupervised representation learning and clustering for pathology image segmentation. Our method consists of two phases. In the first phase, we learn feature representations of training patches from a target image using the spherical k-means. The purpose of this phase is to obtain cluster centroids which could be used as filters for feature extraction. In the second phase, we apply conventional k-means to the representations extracted by the centroids and then project cluster labels to the target images. We evaluated our methods on pathology images of lung cancer specimen. Our experiments showed that the proposed method outperforms traditional k-means segmentation and the multithreshold Otsu method both quantitatively and qualitatively with an improved normalized mutual information (NMI) score of 0.626 compared to 0.168 and 0.167, respectively. Furthermore, we found that the centroids can be applied to the segmentation of other slices from the same sample.

Holger R. Roth, Chen Shen, Hirohisa Oda et al.

One of the most common tasks in medical imaging is semantic segmentation. Achieving this segmentation automatically has been an active area of research, but the task has been proven very challenging due to the large variation of anatomy across different patients. However, recent advances in deep learning have made it possible to significantly improve the performance of image recognition and semantic segmentation methods in the field of computer vision. Due to the data driven approaches of hierarchical feature learning in deep learning frameworks, these advances can be translated to medical images without much difficulty. Several variations of deep convolutional neural networks have been successfully applied to medical images. Especially fully convolutional architectures have been proven efficient for segmentation of 3D medical images. In this article, we describe how to build a 3D fully convolutional network (FCN) that can process 3D images in order to produce automatic semantic segmentations. The model is trained and evaluated on a clinical computed tomography (CT) dataset and shows state-of-the-art performance in multi-organ segmentation.

Chen Shen, Holger R. Roth, Hirohisa Oda et al.

Deep learning-based methods achieved impressive results for the segmentation of medical images. With the development of 3D fully convolutional networks (FCNs), it has become feasible to produce improved results for multi-organ segmentation of 3D computed tomography (CT) images. The results of multi-organ segmentation using deep learning-based methods not only depend on the choice of networks architecture, but also strongly rely on the choice of loss function. In this paper, we present a discussion on the influence of Dice-based loss functions for multi-class organ segmentation using a dataset of abdominal CT volumes. We investigated three different types of weighting the Dice loss functions based on class label frequencies (uniform, simple and square) and evaluate their influence on segmentation accuracies. Furthermore, we compared the influence of different initial learning rates. We achieved average Dice scores of 81.3%, 59.5% and 31.7% for uniform, simple and square types of weighting when the learning rate is 0.001, and 78.2%, 81.0% and 58.5% for each weighting when the learning rate is 0.01. Our experiments indicated a strong relationship between class balancing weights and initial learning rate in training.

Holger R. Roth, Hirohisa Oda, Yuichiro Hayashi et al.

Recent advances in 3D fully convolutional networks (FCN) have made it feasible to produce dense voxel-wise predictions of full volumetric images. In this work, we show that a multi-class 3D FCN trained on manually labeled CT scans of seven abdominal structures (artery, vein, liver, spleen, stomach, gallbladder, and pancreas) can achieve competitive segmentation results, while avoiding the need for handcrafting features or training organ-specific models. To this end, we propose a two-stage, coarse-to-fine approach that trains an FCN model to roughly delineate the organs of interest in the first stage (seeing $\sim$40% of the voxels within a simple, automatically generated binary mask of the patient's body). We then use these predictions of the first-stage FCN to define a candidate region that will be used to train a second FCN. This step reduces the number of voxels the FCN has to classify to $\sim$10% while maintaining a recall high of $>$99%. This second-stage FCN can now focus on more detailed segmentation of the organs. We respectively utilize training and validation sets consisting of 281 and 50 clinical CT images. Our hierarchical approach provides an improved Dice score of 7.5 percentage points per organ on average in our validation set. We furthermore test our models on a completely unseen data collection acquired at a different hospital that includes 150 CT scans with three anatomical labels (liver, spleen, and pancreas). In such challenging organs as the pancreas, our hierarchical approach improves the mean Dice score from 68.5 to 82.2%, achieving the highest reported average score on this dataset.

Mohammad Eshghi, Holger R. Roth, Masahiro Oda et al.

This paper presents an end-to-end pixelwise fully automated segmentation of the head sectioned images of the Visible Korean Human (VKH) project based on Deep Convolutional Neural Networks (DCNNs). By converting classification networks into Fully Convolutional Networks (FCNs), a coarse prediction map, with smaller size than the original input image, can be created for segmentation purposes. To refine this map and to obtain a dense pixel-wise output, standard FCNs use deconvolution layers to upsample the coarse map. However, upsampling based on deconvolution increases the number of network parameters and causes loss of detail because of interpolation. On the other hand, dilated convolution is a new technique introduced recently that attempts to capture multi-scale contextual information without increasing the network parameters while keeping the resolution of the prediction maps high. We used both a standard FCN and a dilated convolution based FCN for semantic segmentation of the head sectioned images of the VKH dataset. Quantitative results showed approximately 20% improvement in the segmentation accuracy when using FCNs with dilated convolutions.

Holger R. Roth, Kai Nagara, Hirohisa Oda et al.

Computational anatomy allows the quantitative analysis of organs in medical images. However, most analysis is constrained to the millimeter scale because of the limited resolution of clinical computed tomography (CT). X-ray microtomography ($μ$CT) on the other hand allows imaging of ex-vivo tissues at a resolution of tens of microns. In this work, we use clinical CT to image lung cancer patients before partial pneumonectomy (resection of pathological lung tissue). The resected specimen is prepared for $μ$CT imaging at a voxel resolution of 50 $μ$m (0.05 mm). This high-resolution image of the lung cancer tissue allows further insides into understanding of tumor growth and categorization. For making full use of this additional information, image fusion (registration) needs to be performed in order to re-align the $μ$CT image with clinical CT. We developed a multi-scale non-rigid registration approach. After manual initialization using a few landmark points and rigid alignment, several levels of non-rigid registration between down-sampled (in the case of $μ$CT) and up-sampled (in the case of clinical CT) representations of the image are performed. Any non-lung tissue is ignored during the computation of the similarity measure used to guide the registration during optimization. We are able to recover the volume differences introduced by the resection and preparation of the lung specimen. The average ($\pm$ std. dev.) minimum surface distance between $μ$CT and clinical CT at the resected lung surface is reduced from 3.3 $\pm$ 2.9 (range: [0.1, 15.9]) to 2.3 mm $\pm$ 2.8 (range: [0.0, 15.3]) mm. The alignment of clinical CT with $μ$CT will allow further registration with even finer resolutions of $μ$CT (up to 10 $μ$m resolution) and ultimately with histopathological microscopy images for further macro to micro image fusion that can aid medical image analysis.

Holger R. Roth, Le Lu, Nathan Lay et al.

Accurate and automatic organ segmentation from 3D radiological scans is an important yet challenging problem for medical image analysis. Specifically, the pancreas demonstrates very high inter-patient anatomical variability in both its shape and volume. In this paper, we present an automated system using 3D computed tomography (CT) volumes via a two-stage cascaded approach: pancreas localization and segmentation. For the first step, we localize the pancreas from the entire 3D CT scan, providing a reliable bounding box for the more refined segmentation step. We introduce a fully deep-learning approach, based on an efficient application of holistically-nested convolutional networks (HNNs) on the three orthogonal axial, sagittal, and coronal views. The resulting HNN per-pixel probability maps are then fused using pooling to reliably produce a 3D bounding box of the pancreas that maximizes the recall. We show that our introduced localizer compares favorably to both a conventional non-deep-learning method and a recent hybrid approach based on spatial aggregation of superpixels using random forest classification. The second, segmentation, phase operates within the computed bounding box and integrates semantic mid-level cues of deeply-learned organ interior and boundary maps, obtained by two additional and separate realizations of HNNs. By integrating these two mid-level cues, our method is capable of generating boundary-preserving pixel-wise class label maps that result in the final pancreas segmentation. Quantitative evaluation is performed on a publicly available dataset of 82 patient CT scans using 4-fold cross-validation (CV). We achieve a Dice similarity coefficient (DSC) of 81.27+/-6.27% in validation, which significantly outperforms previous state-of-the art methods that report DSCs of 71.80+/-10.70% and 78.01+/-8.20%, respectively, using the same dataset.

Holger R. Roth, Le Lu, Amal Farag et al.

Accurate automatic organ segmentation is an important yet challenging problem for medical image analysis. The pancreas is an abdominal organ with very high anatomical variability. This inhibits traditional segmentation methods from achieving high accuracies, especially compared to other organs such as the liver, heart or kidneys. In this paper, we present a holistic learning approach that integrates semantic mid-level cues of deeply-learned organ interior and boundary maps via robust spatial aggregation using random forest. Our method generates boundary preserving pixel-wise class labels for pancreas segmentation. Quantitative evaluation is performed on CT scans of 82 patients in 4-fold cross-validation. We achieve a (mean $\pm$ std. dev.) Dice Similarity Coefficient of 78.01% $\pm$ 8.2% in testing which significantly outperforms the previous state-of-the-art approach of 71.8% $\pm$ 10.7% under the same evaluation criterion.

Hoo-Chang Shin, Holger R. Roth, Mingchen Gao et al.

Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and the revival of deep CNN. CNNs enable learning data-driven, highly representative, layered hierarchical image features from sufficient training data. However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. There are currently three major techniques that successfully employ CNNs to medical image classification: training the CNN from scratch, using off-the-shelf pre-trained CNN features, and conducting unsupervised CNN pre-training with supervised fine-tuning. Another effective method is transfer learning, i.e., fine-tuning CNN models pre-trained from natural image dataset to medical image tasks. In this paper, we exploit three important, but previously understudied factors of employing deep convolutional neural networks to computer-aided detection problems. We first explore and evaluate different CNN architectures. The studied models contain 5 thousand to 160 million parameters, and vary in numbers of layers. We then evaluate the influence of dataset scale and spatial image context on performance. Finally, we examine when and why transfer learning from pre-trained ImageNet (via fine-tuning) can be useful. We study two specific computer-aided detection (CADe) problems, namely thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. We achieve the state-of-the-art performance on the mediastinal LN detection, with 85% sensitivity at 3 false positive per patient, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories. Our extensive empirical evaluation, CNN model analysis and valuable insights can be extended to the design of high performance CAD systems for other medical imaging tasks.

Yinong Wang, Jianhua Yao, Holger R. Roth et al.

Accurate spine segmentation allows for improved identification and quantitative characterization of abnormalities of the vertebra, such as vertebral fractures. However, in existing automated vertebra segmentation methods on computed tomography (CT) images, leakage into nearby bones such as ribs occurs due to the close proximity of these visibly intense structures in a 3D CT volume. To reduce this error, we propose the use of joint vertebra-rib atlases to improve the segmentation of vertebrae via multi-atlas joint label fusion. Segmentation was performed and evaluated on CTs containing 106 thoracic and lumbar vertebrae from 10 pathological and traumatic spine patients on an individual vertebra level basis. Vertebra atlases produced errors where the segmentation leaked into the ribs. The use of joint vertebra-rib atlases produced a statistically significant increase in the Dice coefficient from 92.5 $\pm$ 3.1% to 93.8 $\pm$ 2.1% for the left and right transverse processes and a decrease in the mean and max surface distance from 0.75 $\pm$ 0.60mm and 8.63 $\pm$ 4.44mm to 0.30 $\pm$ 0.27mm and 3.65 $\pm$ 2.87mm, respectively.

Holger R. Roth, Yinong Wang, Jianhua Yao et al.

Injuries of the spine, and its posterior elements in particular, are a common occurrence in trauma patients, with potentially devastating consequences. Computer-aided detection (CADe) could assist in the detection and classification of spine fractures. Furthermore, CAD could help assess the stability and chronicity of fractures, as well as facilitate research into optimization of treatment paradigms. In this work, we apply deep convolutional networks (ConvNets) for the automated detection of posterior element fractures of the spine. First, the vertebra bodies of the spine with its posterior elements are segmented in spine CT using multi-atlas label fusion. Then, edge maps of the posterior elements are computed. These edge maps serve as candidate regions for predicting a set of probabilities for fractures along the image edges using ConvNets in a 2.5D fashion (three orthogonal patches in axial, coronal and sagittal planes). We explore three different methods for training the ConvNet using 2.5D patches along the edge maps of 'positive', i.e. fractured posterior-elements and 'negative', i.e. non-fractured elements. An experienced radiologist retrospectively marked the location of 55 displaced posterior-element fractures in 18 trauma patients. We randomly split the data into training and testing cases. In testing, we achieve an area-under-the-curve of 0.857. This corresponds to 71% or 81% sensitivities at 5 or 10 false-positives per patient, respectively. Analysis of our set of trauma patients demonstrates the feasibility of detecting posterior-element fractures in spine CT images using computer vision techniques such as deep convolutional networks.

Yinong Wang, Jianhua Yao, Holger R. Roth et al.

The precise and accurate segmentation of the vertebral column is essential in the diagnosis and treatment of various orthopedic, neurological, and oncological traumas and pathologies. Segmentation is especially challenging in the presence of pathology such as vertebral compression fractures. In this paper, we propose a method to produce segmentations for osteoporotic compression fractured vertebrae by applying a multi-atlas joint label fusion technique for clinical CT images. A total of 170 thoracic and lumbar vertebrae were evaluated using atlases from five patients with varying degrees of spinal degeneration. In an osteoporotic cohort of bundled atlases, registration provided an average Dice coefficient and mean absolute surface distance of 2.7$\pm$4.5% and 0.32$\pm$0.13mm for osteoporotic vertebrae, respectively, and 90.9$\pm$3.0% and 0.36$\pm$0.11mm for compression fractured vertebrae.

Holger R. Roth, Le Lu, Amal Farag et al.

Automatic organ segmentation is an important yet challenging problem for medical image analysis. The pancreas is an abdominal organ with very high anatomical variability. This inhibits previous segmentation methods from achieving high accuracies, especially compared to other organs such as the liver, heart or kidneys. In this paper, we present a probabilistic bottom-up approach for pancreas segmentation in abdominal computed tomography (CT) scans, using multi-level deep convolutional networks (ConvNets). We propose and evaluate several variations of deep ConvNets in the context of hierarchical, coarse-to-fine classification on image patches and regions, i.e. superpixels. We first present a dense labeling of local image patches via $P{-}\mathrm{ConvNet}$ and nearest neighbor fusion. Then we describe a regional ConvNet ($R_1{-}\mathrm{ConvNet}$) that samples a set of bounding boxes around each image superpixel at different scales of contexts in a "zoom-out" fashion. Our ConvNets learn to assign class probabilities for each superpixel region of being pancreas. Last, we study a stacked $R_2{-}\mathrm{ConvNet}$ leveraging the joint space of CT intensities and the $P{-}\mathrm{ConvNet}$ dense probability maps. Both 3D Gaussian smoothing and 2D conditional random fields are exploited as structured predictions for post-processing. We evaluate on CT images of 82 patients in 4-fold cross-validation. We achieve a Dice Similarity Coefficient of 83.6$\pm$6.3% in training and 71.8$\pm$10.7% in testing.

Amal Farag, Le Lu, Holger R. Roth et al.

Robust automated organ segmentation is a prerequisite for computer-aided diagnosis (CAD), quantitative imaging analysis and surgical assistance. For high-variability organs such as the pancreas, previous approaches report undesirably low accuracies. We present a bottom-up approach for pancreas segmentation in abdominal CT scans that is based on a hierarchy of information propagation by classifying image patches at different resolutions; and cascading superpixels. There are four stages: 1) decomposing CT slice images as a set of disjoint boundary-preserving superpixels; 2) computing pancreas class probability maps via dense patch labeling; 3) classifying superpixels by pooling both intensity and probability features to form empirical statistics in cascaded random forest frameworks; and 4) simple connectivity based post-processing. The dense image patch labeling are conducted by: efficient random forest classifier on image histogram, location and texture features; and more expensive (but with better specificity) deep convolutional neural network classification on larger image windows (with more spatial contexts). Evaluation of the approach is performed on a database of 80 manually segmented CT volumes in six-fold cross-validation (CV). Our achieved results are comparable, or better than the state-of-the-art methods (evaluated by "leave-one-patient-out"), with Dice 70.7% and Jaccard 57.9%. The computational efficiency has been drastically improved in the order of 6~8 minutes, comparing with others of ~10 hours per case. Finally, we implement a multi-atlas label fusion (MALF) approach for pancreas segmentation using the same datasets. Under six-fold CV, our bottom-up segmentation method significantly outperforms its MALF counterpart: (70.7 +/- 13.0%) versus (52.5 +/- 20.8%) in Dice. Deep CNN patch labeling confidences offer more numerical stability, reflected by smaller standard deviations.