Searcharxiv⌕ Search

arXiv subjects

Ehud Rivlin

Publications and source records attributed to Ehud Rivlin.

34 records · Page 2Linked to original sources
arXiv2023

The unreasonable effectiveness of AI CADe polyp detectors to generalize to new countries

$\textbf{Background and aims}$: Artificial Intelligence (AI) Computer-Aided Detection (CADe) is commonly used for polyp detection, but data seen in clinical settings can differ from model training. Few studies evaluate how well CADe detectors perform on colonoscopies from countries not seen during training, and none are able to evaluate performance without collecting expensive and time-intensive labels. $\textbf{Methods}$: We trained a CADe polyp detector on Israeli colonoscopy videos (5004 videos, 1106 hours) and evaluated on Japanese videos (354 videos, 128 hours) by measuring the True Positive Rate (TPR) versus false alarms per minute (FAPM). We introduce a colonoscopy dissimilarity measure called "MAsked mediCal Embedding Distance" (MACE) to quantify differences between colonoscopies, without labels. We evaluated CADe on all Japan videos and on those with the highest MACE. $\textbf{Results}$: MACE correctly quantifies that narrow-band imaging (NBI) and chromoendoscopy (CE) frames are less similar to Israel data than Japan whitelight (bootstrapped z-test, |z| > 690, p < $10^{-8}$ for both). Despite differences in the data, CADe performance on Japan colonoscopies was non-inferior to Israel ones without additional training (TPR at 0.5 FAPM: 0.957 and 0.972 for Israel and Japan; TPR at 1.0 FAPM: 0.972 and 0.989 for Israel and Japan; superiority test t > 45.2, p < $10^{-8}$). Despite not being trained on NBI or CE, TPR on those subsets were non-inferior to Japan overall (non-inferiority test t > 47.3, p < $10^{-8}$, $δ$ = 1.5% for both). $\textbf{Conclusion}$: Differences that prevent CADe detectors from performing well in non-medical settings do not degrade the performance of our AI CADe polyp detector when applied to data from a new country. MACE can help medical AI models internationalize by identifying the most "dissimilar" data on which to evaluate models.

cs.LG↗
arXiv2023

Weakly-Supervised Surgical Phase Recognition

A key element of computer-assisted surgery systems is phase recognition of surgical videos. Existing phase recognition algorithms require frame-wise annotation of a large number of videos, which is time and money consuming. In this work we join concepts of graph segmentation with self-supervised learning to derive a random-walk solution for per-frame phase prediction. Furthermore, we utilize within our method two forms of weak supervision: sparse timestamps or few-shot learning. The proposed algorithm enjoys low complexity and can operate in lowdata regimes. We validate our method by running experiments with the public Cholec80 dataset of laparoscopic cholecystectomy videos, demonstrating promising performance in multiple setups.

cs.CV↗
arXiv2023

Self-Supervised Learning for Endoscopic Video Analysis

Self-supervised learning (SSL) has led to important breakthroughs in computer vision by allowing learning from large amounts of unlabeled data. As such, it might have a pivotal role to play in biomedicine where annotating data requires a highly specialized expertise. Yet, there are many healthcare domains for which SSL has not been extensively explored. One such domain is endoscopy, minimally invasive procedures which are commonly used to detect and treat infections, chronic inflammatory diseases or cancer. In this work, we study the use of a leading SSL framework, namely Masked Siamese Networks (MSNs), for endoscopic video analysis such as colonoscopy and laparoscopy. To fully exploit the power of SSL, we create sizable unlabeled endoscopic video datasets for training MSNs. These strong image representations serve as a foundation for secondary training with limited annotated datasets, resulting in state-of-the-art performance in endoscopic benchmarks like surgical phase recognition during laparoscopy and colonoscopic polyp characterization. Additionally, we achieve a 50% reduction in annotated data size without sacrificing performance. Thus, our work provides evidence that SSL can dramatically reduce the need of annotated data in endoscopy.

cs.CV↗
arXiv2023

Semantic Parsing of Colonoscopy Videos with Multi-Label Temporal Networks

Following the successful debut of polyp detection and characterization, more advanced automation tools are being developed for colonoscopy. The new automation tasks, such as quality metrics or report generation, require understanding of the procedure flow that includes activities, events, anatomical landmarks, etc. In this work we present a method for automatic semantic parsing of colonoscopy videos. The method uses a novel DL multi-label temporal segmentation model trained in supervised and unsupervised regimes. We evaluate the accuracy of the method on a test set of over 300 annotated colonoscopy videos, and use ablation to explore the relative importance of various method's components.

cs.CV↗
arXiv2023

Self-Supervised Polyp Re-Identification in Colonoscopy

Computer-aided polyp detection (CADe) is becoming a standard, integral part of any modern colonoscopy system. A typical colonoscopy CADe detects a polyp in a single frame and does not track it through the video sequence. Yet, many downstream tasks including polyp characterization (CADx), quality metrics, automatic reporting, require aggregating polyp data from multiple frames. In this work we propose a robust long term polyp tracking method based on re-identification by visual appearance. Our solution uses an attention-based self-supervised ML model, specifically designed to leverage the temporal nature of video input. We quantitatively evaluate method's performance and demonstrate its value for the CADx task.

cs.CV↗
arXiv2023

Semi-supervised Quality Evaluation of Colonoscopy Procedures

Colonoscopy is the standard of care technique for detecting and removing polyps for the prevention of colorectal cancer. Nevertheless, gastroenterologists (GI) routinely miss approximately 25% of polyps during colonoscopies. These misses are highly operator dependent, influenced by the physician skills, experience, vigilance, and fatigue. Standard quality metrics, such as Withdrawal Time or Cecal Intubation Rate, have been shown to be well correlated with Adenoma Detection Rate (ADR). However, those metrics are limited in their ability to assess the quality of a specific procedure, and they do not address quality aspects related to the style or technique of the examination. In this work we design novel online and offline quality metrics, based on visual appearance quality criteria learned by an ML model in an unsupervised way. Furthermore, we evaluate the likelihood of detecting an existing polyp as a function of quality and use it to demonstrate high correlation of the proposed metric to polyp detection sensitivity. The proposed online quality metric can be used to provide real time quality feedback to the performing GI. By integrating the local metric over the withdrawal phase, we build a global, offline quality metric, which is shown to be highly correlated to the standard Polyp Per Colonoscopy (PPC) quality metric.

cs.CV↗
arXiv2023

Clinical BERTScore: An Improved Measure of Automatic Speech Recognition Performance in Clinical Settings

Automatic Speech Recognition (ASR) in medical contexts has the potential to save time, cut costs, increase report accuracy, and reduce physician burnout. However, the healthcare industry has been slower to adopt this technology, in part due to the importance of avoiding medically-relevant transcription mistakes. In this work, we present the Clinical BERTScore (CBERTScore), an ASR metric that penalizes clinically-relevant mistakes more than others. We demonstrate that this metric more closely aligns with clinician preferences on medical sentences as compared to other metrics (WER, BLUE, METEOR, etc), sometimes by wide margins. We collect a benchmark of 18 clinician preferences on 149 realistic medical sentences called the Clinician Transcript Preference benchmark (CTP) and make it publicly available for the community to further develop clinically-aware ASR metrics. To our knowledge, this is the first public dataset of its kind. We demonstrate that CBERTScore more closely matches what clinicians prefer.

eess.AS↗
arXiv2023

Weakly-supervised Representation Learning for Video Alignment and Analysis

Many tasks in video analysis and understanding boil down to the need for frame-based feature learning, aiming to encapsulate the relevant visual content so as to enable simpler and easier subsequent processing. While supervised strategies for this learning task can be envisioned, self and weakly-supervised alternatives are preferred due to the difficulties in getting labeled data. This paper introduces LRProp -- a novel weakly-supervised representation learning approach, with an emphasis on the application of temporal alignment between pairs of videos of the same action category. The proposed approach uses a transformer encoder for extracting frame-level features, and employs the DTW algorithm within the training iterations in order to identify the alignment path between video pairs. Through a process referred to as ``pair-wise position propagation'', the probability distributions of these correspondences per location are matched with the similarity of the frame-level features via KL-divergence minimization. The proposed algorithm uses also a regularized SoftDTW loss for better tuning the learned features. Our novel representation learning paradigm consistently outperforms the state of the art on temporal alignment tasks, establishing a new performance bar over several downstream video analysis applications.

cs.CV↗
arXiv2022

GoToNet: Fast Monocular Scene Exposure and Exploration

Autonomous scene exposure and exploration, especially in localization or communication-denied areas, useful for finding targets in unknown scenes, remains a challenging problem in computer navigation. In this work, we present a novel method for real-time environment exploration, whose only requirements are a visually similar dataset for pre-training, enough lighting in the scene, and an on-board forward-looking RGB camera for environmental sensing. As opposed to existing methods, our method requires only one look (image) to make a good tactical decision, and therefore works at a non-growing, constant time. Two direction predictions, characterized by pixels dubbed the Goto and Lookat pixels, comprise the core of our method. These pixels encode the recommended flight instructions in the following way: the Goto pixel defines the direction in which the agent should move by one distance unit, and the Lookat pixel defines the direction in which the camera should be pointing at in the next step. These flying-instruction pixels are optimized to expose the largest amount of currently unexplored areas. Our method presents a novel deep learning-based navigation approach that is able to solve this problem and demonstrate its ability in an even more complicated setup, i.e., when computational power is limited. In addition, we propose a way to generate a navigation-oriented dataset, enabling efficient training of our method using RGB and depth images. Tests conducted in a simulator evaluating both the sparse pixels' coordinations inferring process, and 2D and 3D test flights aimed to unveil areas and decrease distances to targets achieve promising results. Comparison against a state-of-the-art algorithm shows our method is able to overperform it, that while measuring the new voxels per camera pose, minimum distance to target, percentage of surface voxels seen, and compute time metrics.

cs.CV↗
arXiv2022

Finding a Landing Site on an Urban Area: A Multi-Resolution Probabilistic Approach

This paper considers the problem of finding a landing spot for a drone in a dense urban environment. The conflicting requirement of fast exploration and high resolution is solved using a multi-resolution approach, by which visual information is collected by the drone at decreasing altitudes so that spatial resolution of the acquired images increases monotonically. A probability distribution is used to capture the uncertainty of the decision process for each terrain patch. The distributions are updated as information from different altitudes is collected. When the confidence level for one of the patches becomes larger than a pre-specified threshold, suitability for landing is declared. One of the main building blocks of the approach is a semantic segmentation algorithm that attaches probabilities to each pixel of a single view. The decision algorithm combines these probabilities with a priori data and previous measurements to obtain the best estimates. Feasibility is illustrated by presenting a number of examples generated by a realistic closed-loop simulator.

cs.RO↗
arXiv2021

Local Trajectory Planning For UAV Autonomous Landing

An important capability of autonomous Unmanned Aerial Vehicles (UAVs) is autonomous landing while avoiding collision with obstacles in the process. Such capability requires real-time local trajectory planning. Although trajectory-planning methods have been introduced for cases such as emergency landing, they have not been evaluated in real-life scenarios where only the surface of obstacles can be sensed and detected. We propose a novel optimization framework using a pre-planned global path and a priority map of the landing area. Several trajectory planning algorithms were implemented and evaluated in a simulator that includes a 3D urban environment, LiDAR-based obstacle-surface sensing and UAV guidance and dynamics. We show that using our proposed optimization criterion can successfully improve the landing-mission success probability while avoiding collisions with obstacles in real-time.

cs.RO↗
arXiv2020

Detecting Deficient Coverage in Colonoscopies

Colonoscopy is the tool of choice for preventing Colorectal Cancer, by detecting and removing polyps before they become cancerous. However, colonoscopy is hampered by the fact that endoscopists routinely miss 22-28% of polyps. While some of these missed polyps appear in the endoscopist's field of view, others are missed simply because of substandard coverage of the procedure, i.e. not all of the colon is seen. This paper attempts to rectify the problem of substandard coverage in colonoscopy through the introduction of the C2D2 (Colonoscopy Coverage Deficiency via Depth) algorithm which detects deficient coverage, and can thereby alert the endoscopist to revisit a given area. More specifically, C2D2 consists of two separate algorithms: the first performs depth estimation of the colon given an ordinary RGB video stream; while the second computes coverage given these depth estimates. Rather than compute coverage for the entire colon, our algorithm computes coverage locally, on a segment-by-segment basis; C2D2 can then indicate in real-time whether a particular area of the colon has suffered from deficient coverage, and if so the endoscopist can return to that area. Our coverage algorithm is the first such algorithm to be evaluated in a large-scale way; while our depth estimation technique is the first calibration-free unsupervised method applied to colonoscopies. The C2D2 algorithm achieves state of the art results in the detection of deficient coverage. On synthetic sequences with ground truth, it is 2.4 times more accurate than human experts; while on real sequences, C2D2 achieves a 93.0% agreement with experts.

cs.CV↗
arXiv2015

CFORB: Circular FREAK-ORB Visual Odometry

We present a novel Visual Odometry algorithm entitled Circular FREAK-ORB (CFORB). This algorithm detects features using the well-known ORB algorithm [12] and computes feature descriptors using the FREAK algorithm [14]. CFORB is invariant to both rotation and scale changes, and is suitable for use in environments with uneven terrain. Two visual geometric constraints have been utilized in order to remove invalid feature descriptor matches. These constraints have not previously been utilized in a Visual Odometry algorithm. A variation to circular matching [16] has also been implemented. This allows features to be matched between images without having to be dependent upon the epipolar constraint. This algorithm has been run on the KITTI benchmark dataset and achieves a competitive average translational error of $3.73 \%$ and average rotational error of $0.0107 deg/m$. CFORB has also been run in an indoor environment and achieved an average translational error of $3.70 \%$. After running CFORB in a highly textured environment with an approximately uniform feature spread across the images, the algorithm achieves an average translational error of $2.4 \%$ and an average rotational error of $0.009 deg/m$.

cs.CV↗
arXiv2011

Vision-Based Navigation III: Pose and Motion from Omnidirectional Optical Flow and a Digital Terrain Map

An algorithm for pose and motion estimation using corresponding features in omnidirectional images and a digital terrain map is proposed. In previous paper, such algorithm for regular camera was considered. Using a Digital Terrain (or Digital Elevation) Map (DTM/DEM) as a global reference enables recovering the absolute position and orientation of the camera. In order to do this, the DTM is used to formulate a constraint between corresponding features in two consecutive frames. In this paper, these constraints are extended to handle non-central projection, as is the case with many omnidirectional systems. The utilization of omnidirectional data is shown to improve the robustness and accuracy of the navigation algorithm. The feasibility of this algorithm is established through lab experimentation with two kinds of omnidirectional acquisition systems. The first one is polydioptric cameras while the second is catadioptric camera.

cs.CV↗
arXiv2011

Vision-Based Navigation II: Error Analysis for a Navigation Algorithm based on Optical-Flow and a Digital Terrain Map

The paper deals with the error analysis of a navigation algorithm that uses as input a sequence of images acquired by a moving camera and a Digital Terrain Map (DTM) of the region been imaged by the camera during the motion. The main sources of error are more or less straightforward to identify: camera resolution, structure of the observed terrain and DTM accuracy, field of view and camera trajectory. After characterizing and modeling these error sources in the framework of the CDTM algorithm, a closed form expression for their effect on the pose and motion errors of the camera can be found. The analytic expression provides a priori measurements for the accuracy in terms of the parameters mentioned above.

cs.CV↗