Trygve Eftestøl

Øyvind Meinich-Bache, Simon Lennart Austnes, Kjersti Engan et al.

Objective: Birth asphyxia is one of the leading causes of neonatal deaths. A key for survival is performing immediate and continuous quality newborn resuscitation. A dataset of recorded signals during newborn resuscitation, including videos, has been collected in Haydom, Tanzania, and the aim is to analyze the treatment and its effect on the newborn outcome. An important step is to generate timelines of relevant resuscitation activities, including ventilation, stimulation, suction, etc., during the resuscitation episodes. Methods: We propose a two-step deep neural network system, ORAA-net, utilizing low-quality video recordings of resuscitation episodes to do activity recognition during newborn resuscitation. The first step is to detect and track relevant objects using Convolutional Neural Networks (CNN) and post-processing, and the second step is to analyze the proposed activity regions from step 1 to do activity recognition using 3D CNNs. Results: The system recognized the activities newborn uncovered, stimulation, ventilation and suction with a mean precision of 77.67 %, a mean recall of 77,64 %, and a mean accuracy of 92.40 %. Moreover, the accuracy of the estimated number of Health Care Providers (HCPs) present during the resuscitation episodes was 68.32 %. Conclusion: The results indicate that the proposed CNN-based two-step ORAAnet could be used for object detection and activity recognition in noisy low-quality newborn resuscitation videos. Significance: A thorough analysis of the effect the different resuscitation activities have on the newborn outcome could potentially allow us to optimize treatment guidelines, training, debriefing, and local quality improvement in newborn resuscitation.

Øyvind Meinich-Bache, Kjersti Engan, Ivar Austvoll et al.

Birth asphyxia is a major newborn mortality problem in low-resource countries. International guideline provides treatment recommendations; however, the importance and effect of the different treatments are not fully explored. The available data is collected in Tanzania, during newborn resuscitation, for analysis of the resuscitation activities and the response of the newborn. An important step in the analysis is to create activity timelines of the episodes, where activities include ventilation, suction, stimulation etc. Methods: The available recordings are noisy real-world videos with large variations. We propose a two-step process in order to detect activities possibly overlapping in time. The first step is to detect and track the relevant objects, like bag-mask resuscitator, heart rate sensors etc., and the second step is to use this information to recognize the resuscitation activities. The topic of this paper is the first step, and the object detection and tracking are based on convolutional neural networks followed by post processing. Results: The performance of the object detection during activities were 96.97 % (ventilations), 100 % (attaching/removing heart rate sensor) and 75 % (suction) on a test set of 20 videos. The system also estimate the number of health care providers present with a performance of 71.16 %. Conclusion: The proposed object detection and tracking system provides promising results in noisy newborn resuscitation videos. Significance: This is the first step in a thorough analysis of newborn resuscitation episodes, which could provide important insight about the importance and effect of different newborn resuscitation activities

Saul Fuster, Farbod Khoraminia, Trygve Eftestøl et al.

Accurate segmentation of tissue in histopathological images can be very beneficial for defining regions of interest (ROI) for streamline of diagnostic and prognostic tasks. Still, adapting to different domains is essential for histopathology image analysis, as the visual characteristics of tissues can vary significantly across datasets. Yet, acquiring sufficient annotated data in the medical domain is cumbersome and time-consuming. The labeling effort can be significantly reduced by leveraging active learning, which enables the selective annotation of the most informative samples. Our proposed method allows for fine-tuning a pre-trained deep neural network using a small set of labeled data from the target domain, while also actively selecting the most informative samples to label next. We demonstrate that our approach performs with significantly fewer labeled samples compared to traditional supervised learning approaches for similar F1-scores, using barely a 59\% of the training set. We also investigate the distribution of class balance to establish annotation guidelines.

Alvaro Fernandez-Quilez, Christoffer Gabrielsen Andersen, Trygve Eftestøl et al.

Masked Image Modelling (MIM) has been shown to be an efficient self-supervised learning (SSL) pre-training paradigm when paired with transformer architectures and in the presence of a large amount of unlabelled natural images. The combination of the difficulties in accessing and obtaining large amounts of labeled data and the availability of unlabelled data in the medical imaging domain makes MIM an interesting approach to advance deep learning (DL) applications based on 3D medical imaging data. Nevertheless, SSL and, in particular, MIM applications with medical imaging data are rather scarce and there is still uncertainty. around the potential of such a learning paradigm in the medical domain. We study MIM in the context of Prostate Cancer (PCa) lesion classification with T2 weighted (T2w) axial magnetic resonance imaging (MRI) data. In particular, we explore the effect of using MIM when coupled with convolutional neural networks (CNNs) under different conditions such as different masking strategies, obtaining better results in terms of AUC than other pre-training strategies like ImageNet weight initialization.

Saul Fuster, Farbod Khoraminia, Julio Silva-Rodríguez et al.

We present a pioneering investigation into the application of deep learning techniques to analyze histopathological images for addressing the substantial challenge of automated prognostic prediction. Prognostic prediction poses a unique challenge as the ground truth labels are inherently weak, and the model must anticipate future events that are not directly observable in the image. To address this challenge, we propose a novel three-part framework comprising of a convolutional network based tissue segmentation algorithm for region of interest delineation, a contrastive learning module for feature extraction, and a nested multiple instance learning classification module. Our study explores the significance of various regions of interest within the histopathological slides and exploits diverse learning scenarios. The pipeline is initially validated on artificially generated data and a simpler diagnostic task. Transitioning to prognostic prediction, tasks become more challenging. Employing bladder cancer as use case, our best models yield an AUC of 0.721 and 0.678 for recurrence and treatment outcome prediction respectively.

Neel Kanwal, Trygve Eftestol, Farbod Khoraminia et al.

Computational Pathology (CPATH) systems have the potential to automate diagnostic tasks. However, the artifacts on the digitized histological glass slides, known as Whole Slide Images (WSIs), may hamper the overall performance of CPATH systems. Deep Learning (DL) models such as Vision Transformers (ViTs) may detect and exclude artifacts before running the diagnostic algorithm. A simple way to develop robust and generalized ViTs is to train them on massive datasets. Unfortunately, acquiring large medical datasets is expensive and inconvenient, prompting the need for a generalized artifact detection method for WSIs. In this paper, we present a student-teacher recipe to improve the classification performance of ViT for the air bubbles detection task. ViT, trained under the student-teacher framework, boosts its performance by distilling existing knowledge from the high-capacity teacher model. Our best-performing ViT yields 0.961 and 0.911 F1-score and MCC, respectively, observing a 7% gain in MCC against stand-alone training. The proposed method presents a new perspective of leveraging knowledge distillation over transfer learning to encourage the use of customized transformers for efficient preprocessing pipelines in the CPATH systems.

Saul Fuster, Trygve Eftestøl, Kjersti Engan

Strongly supervised learning requires detailed knowledge of truth labels at instance levels, and in many machine learning applications this is a major drawback. Multiple instance learning (MIL) is a popular weakly supervised learning method where truth labels are not available at instance level, but only at bag-of-instances level. However, sometimes the nature of the problem requires a more complex description, where a nested architecture of bag-of-bags at different levels can capture underlying relationships, like similar instances grouped together. Predicting the latent labels of instances or inner-bags might be as important as predicting the final bag-of-bags label but is lost in a straightforward nested setting. We propose a Nested Multiple Instance with Attention (NMIA) model architecture combining the concept of nesting with attention mechanisms. We show that NMIA performs as conventional MIL in simple scenarios and can grasp a complex scenario providing insights to the latent labels at different levels.