Search Results for author: Nicolas Padoy

Found 37 papers, 18 papers with code

Dissecting Self-Supervised Learning Methods for Surgical Computer Vision

1 code implementation1 Jul 2022 Sanat Ramesh, Vinkle Srivastav, Deepak Alapatt, Tong Yu, Aditya Murali, Luca Sestini, Chinedu Innocent Nwoye, Idris Hamoud, Antoine Fleurentin, Georgios Exarchakis, Alexandros Karargyris, Nicolas Padoy

Correct transfer of these methods to surgery, as described and conducted in this work, leads to substantial performance gains over generic uses of SSL - up to 7% on phase recognition and 20% on tool presence detection - as well as state-of-the-art semi-supervised phase recognition approaches by up to 14%.

Self-Supervised Learning

Federated Cycling (FedCy): Semi-supervised Federated Learning of Surgical Phases

no code implementations14 Mar 2022 Hasan Kassem, Deepak Alapatt, Pietro Mascagni, AI4SafeChole Consortium, Alexandros Karargyris, Nicolas Padoy

With these constraints in mind, we propose FedCy, a federated semi-supervised learning (FSSL) method that combines FL and self-supervised learning to exploit a decentralized dataset of both labeled and unlabeled videos, thereby improving performance on the task of surgical phase recognition.

Federated Learning Self-Supervised Learning

Live Laparoscopic Video Retrieval with Compressed Uncertainty

no code implementations8 Mar 2022 Tong Yu, Pietro Mascagni, Juan Verde, Jacques Marescaux, Didier Mutter, Nicolas Padoy

Searching through large volumes of medical data to retrieve relevant information is a challenging yet crucial task for clinical care.

Video Retrieval

FUN-SIS: a Fully UNsupervised approach for Surgical Instrument Segmentation

no code implementations16 Feb 2022 Luca Sestini, Benoit Rosa, Elena De Momi, Giancarlo Ferrigno, Nicolas Padoy

We then use the obtained instrument masks as pseudo-labels in order to train a per-frame segmentation model; to this aim, we develop a learning-from-noisy-labels architecture, designed to extract a clean supervision signal from these pseudo-labels, leveraging their peculiar noise properties.

Optical Flow Estimation

Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos

5 code implementations7 Sep 2021 Chinedu Innocent Nwoye, Tong Yu, Cristians Gonzalez, Barbara Seeliger, Pietro Mascagni, Didier Mutter, Jacques Marescaux, Nicolas Padoy

To achieve this task, we introduce our new model, the Rendezvous (RDV), which recognizes triplets directly from surgical videos by leveraging attention at two different levels.

Action Triplet Recognition

Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating room

1 code implementation26 Aug 2021 Vinkle Srivastav, Afshin Gangi, Nicolas Padoy

Second, to address the domain shift and the lack of annotations, we propose a novel unsupervised domain adaptation method, called AdaptOR, to adapt a model from an in-the-wild labeled source domain to a statistically different unlabeled target domain.

Privacy Preserving Semi-Supervised Human Pose Estimation +3

Multi-Task Temporal Convolutional Networks for Joint Recognition of Surgical Phases and Steps in Gastric Bypass Procedures

no code implementations24 Feb 2021 Sanat Ramesh, Diego Dall'Alba, Cristians Gonzalez, Tong Yu, Pietro Mascagni, Didier Mutter, Jacques Marescaux, Paolo Fiorini, Nicolas Padoy

Conclusion: In this work, we present a multi-task multi-stage temporal convolutional network for surgical activity recognition, which shows improved results compared to single-task models on the Bypass40 gastric bypass dataset with multi-level annotations.

Activity Recognition

Encode the Unseen: Predictive Video Hashing for Scalable Mid-Stream Retrieval

no code implementations30 Sep 2020 Tong Yu, Nicolas Padoy

This paper tackles a new problem in computer vision: mid-stream video-to-video retrieval.

Video Retrieval

Artificial Intelligence in Surgery: Neural Networks and Deep Learning

1 code implementation28 Sep 2020 Deepak Alapatt, Pietro Mascagni, Vinkle Srivastav, Nicolas Padoy

Deep neural networks power most recent successes of artificial intelligence, spanning from self-driving cars to computer aided diagnosis in radiology and pathology.

Self-Driving Cars

Human Pose Estimation on Privacy-Preserving Low-Resolution Depth Images

1 code implementation16 Jul 2020 Vinkle Srivastav, Afshin Gangi, Nicolas Padoy

Human pose estimation (HPE) is a key building block for developing AI-based context-aware systems inside the operating room (OR).

Pose Estimation Privacy Preserving +1

Self-supervision on Unlabelled OR Data for Multi-person 2D/3D Human Pose Estimation

1 code implementation16 Jul 2020 Vinkle Srivastav, Afshin Gangi, Nicolas Padoy

2D/3D human pose estimation is needed to develop novel intelligent tools for the operating room that can analyze and support the clinical activities.

3D Human Pose Estimation 3D Pose Estimation +1

CAI4CAI: The Rise of Contextual Artificial Intelligence in Computer Assisted Interventions

no code implementations20 Oct 2019 Tom Vercauteren, Mathias Unberath, Nicolas Padoy, Nassir Navab

Data-driven computational approaches have evolved to enable extraction of information from medical images with a reliability, accuracy and speed which is already transforming their interpretation and exploitation in clinical practice.

Decision Making

Weakly Supervised Convolutional LSTM Approach for Tool Tracking in Laparoscopic Videos

1 code implementation4 Dec 2018 Chinedu Innocent Nwoye, Didier Mutter, Jacques Marescaux, Nicolas Padoy

Results: We build a baseline tracker on top of the CNN model and demonstrate that our approach based on the ConvLSTM outperforms the baseline in tool presence detection, spatial localization, and motion tracking by over 5. 0%, 13. 9%, and 12. 6%, respectively.

Instrument Recognition Surgical tool detection +2

Learning from a tiny dataset of manual annotations: a teacher/student approach for surgical phase recognition

no code implementations30 Nov 2018 Tong Yu, Didier Mutter, Jacques Marescaux, Nicolas Padoy

Vision algorithms capable of interpreting scenes from a real-time video stream are necessary for computer-assisted surgery systems to achieve context-aware behavior.

Face Detection in the Operating Room: Comparison of State-of-the-art Methods and a Self-supervised Approach

no code implementations29 Nov 2018 Thibaut Issenhuth, Vinkle Srivastav, Afshin Gangi, Nicolas Padoy

Methods: We propose a comparison of 6 state-of-the-art face detectors on clinical data using Multi-View Operating Room Faces (MVOR-Faces), a dataset of operating room images capturing real surgical activities.

Domain Adaptation Face Detection

Future-State Predicting LSTM for Early Surgery Type Recognition

no code implementations28 Nov 2018 Siddharth Kannan, Gaurav Yengera, Didier Mutter, Jacques Marescaux, Nicolas Padoy

This work presents a novel approach for the early recognition of the type of a laparoscopic surgery from its video.

MVOR: A Multi-view RGB-D Operating Room Dataset for 2D and 3D Human Pose Estimation

1 code implementation24 Aug 2018 Vinkle Srivastav, Thibaut Issenhuth, Abdolrahim Kadkhodamohammadi, Michel de Mathelin, Afshin Gangi, Nicolas Padoy

In this paper, we present the dataset, its annotations, as well as baseline results from several recent person detection and 2D/3D pose estimation methods.

3D Human Pose Estimation 3D Pose Estimation +2

Weakly-Supervised Learning for Tool Localization in Laparoscopic Videos

1 code implementation14 Jun 2018 Armine Vardazaryan, Didier Mutter, Jacques Marescaux, Nicolas Padoy

We propose a deep architecture, trained solely on image level annotations, that can be used for both tool presence detection and localization in surgical videos.

Surgical tool detection

Less is More: Surgical Phase Recognition with Less Annotations through Self-Supervised Pre-training of CNN-LSTM Networks

no code implementations22 May 2018 Gaurav Yengera, Didier Mutter, Jacques Marescaux, Nicolas Padoy

In this work, we propose a new self-supervised pre-training approach based on the prediction of remaining surgery duration (RSD) from laparoscopic videos.


A generalizable approach for multi-view 3D human pose regression

2 code implementations27 Apr 2018 Abdolrahim Kadkhodamohammadi, Nicolas Padoy

As 2D poses are collected at test time using a SV pose detector, which might generate inaccurate detections, we model its characteristics and incorporate this information during training.

3D Pose Estimation

RSDNet: Learning to Predict Remaining Surgery Duration from Laparoscopic Videos Without Manual Annotations

no code implementations9 Feb 2018 Andru Putra Twinanda, Gaurav Yengera, Didier Mutter, Jacques Marescaux, Nicolas Padoy

In this paper, we propose a deep learning pipeline, referred to as RSDNet, which automatically estimates the remaining surgery duration (RSD) intraoperatively by using only visual information from laparoscopic videos.

A Multi-view RGB-D Approach for Human Pose Estimation in Operating Rooms

1 code implementation25 Jan 2017 Abdolrahim Kadkhodamohammadi, Afshin Gangi, Michel de Mathelin, Nicolas Padoy

In this paper, we propose an approach for multi-view 3D human pose estimation from RGB-D images and demonstrate the benefits of using the additional depth channel for pose refinement beyond its use for the generation of improved features.

3D Human Pose Estimation

Single- and Multi-Task Architectures for Surgical Workflow Challenge at M2CAI 2016

no code implementations27 Oct 2016 Andru P. Twinanda, Didier Mutter, Jacques Marescaux, Michel de Mathelin, Nicolas Padoy

On top of these architectures we propose to use two different approaches to enforce the temporal constraints of the surgical workflow: (1) HMM-based and (2) LSTM-based pipelines.

Single- and Multi-Task Architectures for Tool Presence Detection Challenge at M2CAI 2016

no code implementations27 Oct 2016 Andru P. Twinanda, Didier Mutter, Jacques Marescaux, Michel de Mathelin, Nicolas Padoy

The tool presence detection challenge at M2CAI 2016 consists of identifying the presence/absence of seven surgical tools in the images of cholecystectomy videos.

Articulated Clinician Detection Using 3D Pictorial Structures on RGB-D Data

1 code implementation10 Feb 2016 Abdolrahim Kadkhodamohammadi, Afshin Gangi, Michel de Mathelin, Nicolas Padoy

Proposed methods for the operating room (OR) rely either on foreground estimation using a multi-camera system, which is a challenge in real ORs due to color similarities and frequent illumination changes, or on wearable sensors or markers, which are invasive and therefore difficult to introduce in the room.

Pose Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.