NeoLoc-68: End-to-end 68-point neonatal facial landmark localisation in neonatal clinical environments

• URL: http://arxiv.org/abs/2606.20823v1
• Date: Thu, 18 Jun 2026 18:08:30 GMT
• Title: NeoLoc-68: End-to-end 68-point neonatal facial landmark localisation in neonatal clinical environments
• Abstract summary: We propose an end-to-end facial landmark detector capable of predicting 68 landmarks on neonatal faces in clinical environments.<n>We combined 37,459 single-face images from 11 public datasets, standardised to 68-point markup, with 1,123 manually annotated frames from a neonatal research dataset.<n>A YOLO-based keypoint model was adapted to regress the facial landmarks, initialised with weights from a pretrained neonatal face detector.
• Score: 1.5484719004172118
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Facial landmark localisation is a prerequisite for developing automated, non-contact neonatal pain assessment methods. Clinicians use pain scales to judge the severity of pain, many of which rely on facial expression. However, facial landmark detectors trained on adult faces perform poorly in neonatal clinical environments due to frequent occlusions caused by medical equipment, varied head poses, and challenging imaging conditions, including motion blur triggered by sudden pain-related movements. We propose an end-to-end facial landmark detector capable of predicting 68 landmarks on neonatal faces in clinical environments. We combined 37,459 single-face images from 11 public datasets, standardised to 68-point markup, with 1,123 manually annotated frames from a neonatal research dataset (totalling over 76,000 landmarks). A YOLO-based keypoint model was adapted to regress the facial landmarks, initialised with weights from a pretrained neonatal face detector. On public datasets, our proposed model achieved state-of-the-art performance: Normalised Mean Error (NME) = 5.37, Failure Rate (FR) = 12.5%, Area Under the Cumulative Error Curve (AUC) at AUC0.08 = 38.00% and AUC0.1 = 48.70%. On the clinical neonatal test set, before fine-tuning, the model achieved the lowest Detection Failure Rate (DFR) = 5.3% among all baselines and showed strong generalisation. After fine-tuning, performance improved further to NME = 6.36, FR = 22.30%, DFR = 1.77%, AUC0.08 = 29.24% and AUC0.1 = 40.25%. To the best of our knowledge, this represents the first end-to-end 68-point neonatal facial landmark detection model. With further dataset expansion and refinement, it could support downstream tasks in neonatal health monitoring and pain-related facial analysis.

Related papers

• InfantFace: Detecting infant faces in neonatal clinical environments [1.5484719004172118]
  We propose a one-stage YOLOv11m-based model tailored for face detection of infants in neonatal clinical environments.<n>We combined multiple publicly available datasets (VGGFace2, CelebA, FDDB, WIDER FACE) to train and evaluate our proposed model.<n>Our model achieved an AP50 of 0.87, surpassing the performance of three state-of-the-art general face detectors.
  arXiv  Detail & Related papers  (2026-06-18T16:28:00Z)
• A Breast Vision Pathology Foundation Model for Real-world Clinical Utility [65.57568187389113]
  We present bfBRAVE, a breast-adaptive pathology foundation model developed and evaluated using a total resource of 101,638 breast wholeslide images.<n>BRAVE supported practical roles in the clinical workflow, including safe exclusion of low-risk cases from routine AI-assisted second-review rescue of initially missed positives and prioritization of cases for further assessment.
  arXiv  Detail & Related papers  (2026-05-06T07:44:39Z)
• Simulating clinical interventions with a generative multimodal model of human physiology [49.828582089394445]
  HealthFormer is a decoder-only transformer that models the human physiological trajectory generatively.<n>We tokenise each participant's health trajectory across 667 measurements spanning seven domains.<n>HealthFormer improves prediction for 27 of 30 incident-disease and mortality endpoints, exceeding established clinical risk scores in every comparison.
  arXiv  Detail & Related papers  (2026-04-30T14:10:30Z)
• Beyond Benchmarks of IUGC: Rethinking Requirements of Deep Learning Methods for Intrapartum Ultrasound Biometry from Fetal Ultrasound Videos [58.71502465551297]
  Intrapartum Ultrasound Grand Challenge (IUGC) co-hosted with MICCAI 2024 was launched.<n>IUGC introduces a clinically oriented multi-task automatic measurement framework that integrates standard plane classification, fetal head-pubic symphysis segmentation, and biometry.<n>The challenge releases the largest multi-center intrapartum ultrasound video dataset to date, comprising 774 videos (68,106 frames) collected from three hospitals.
  arXiv  Detail & Related papers  (2026-02-13T13:28:22Z)
• FUGC: Benchmarking Semi-Supervised Learning Methods for Cervical Segmentation [63.7829089874007]
  This paper introduces the Fetal Ultrasound Grand Challenge (FUGC), the first benchmark for semi-supervised learning in cervical segmentation.<n>FUGC provides a dataset of 890 TVS images, including 500 training images, 90 validation images, and 300 test images.<n> Methods were evaluated using the Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), and runtime (RT), with a weighted combination of 0.4/0.4/0.2.
  arXiv  Detail & Related papers  (2026-01-22T01:34:39Z)
• Evaluating Deep Learning-Based Face Recognition for Infants and Toddlers: Impact of Age Across Developmental Stages [0.688204255655161]
  Face recognition for infants and toddlers presents unique challenges due to rapid facial morphology changes, high inter-class similarity, and limited dataset availability.<n>This study evaluates the performance of four deep learning-based face recognition models FaceNet, ArcFace, MagFace, and CosFace on a newly developed longitudinal dataset collected over a 24 month period in seven sessions involving children aged 0 to 3 years.
  arXiv  Detail & Related papers  (2026-01-04T22:30:28Z)
• Time-to-Event Pretraining for 3D Medical Imaging [44.46415168541444]
  We introduce time-to-event pretraining, a pretraining framework for 3D medical imaging models.<n>We use a dataset of 18,945 CT scans (4.2 million 2D images) and time-to-event distributions across thousands of EHR-derived tasks.<n>Our method improves outcome prediction, achieving an average AUROC increase of 23.7% and a 29.4% gain in Harrell's C-index across 8 benchmark tasks.
  arXiv  Detail & Related papers  (2024-11-14T11:08:54Z)
• Neonatal Face and Facial Landmark Detection from Video Recordings [2.6091909702028584]
  This paper explores automated face and facial landmark detection of neonates. It is an important first step in many video-based neonatal health applications, such as vital sign estimation, pain assessment, sleep-wake classification, and jaundice detection.
  arXiv  Detail & Related papers  (2023-02-08T21:18:18Z)
• Towards early prediction of neurodevelopmental disorders: Computational model for Face Touch and Self-adaptors in Infants [0.0]
  evaluating a baby's movements is key to understanding possible risks of developmental disorders in their growth. Previous research in psychology has shown that measuring specific movements or gestures such as face touches in babies is essential to analyse how babies understand themselves and their context. This research proposes the first automatic approach that detects face touches from video recordings by tracking infants' movements and gestures.
  arXiv  Detail & Related papers  (2023-01-07T18:08:43Z)
• Intelligent Sight and Sound: A Chronic Cancer Pain Dataset [74.77784420691937]
  This paper introduces the first chronic cancer pain dataset, collected as part of the Intelligent Sight and Sound (ISS) clinical trial. The data collected to date consists of 29 patients, 509 smartphone videos, 189,999 frames, and self-reported affective and activity pain scores. Using static images and multi-modal data to predict self-reported pain levels, early models show significant gaps between current methods available to predict pain.
  arXiv  Detail & Related papers  (2022-04-07T22:14:37Z)
• Robust Neonatal Face Detection in Real-world Clinical Settings [4.263900348596098]
  Current face detection algorithms are extremely generalized and can obtain decent accuracy when detecting the adult faces. By training a state-of-the-art face detection model, You-Only-Look-Once, on a proprietary dataset containing labelled neonate faces in a clinical setting, this work achieves near real time neonate face detection. Preliminary findings show an accuracy of 68.7%, compared to the off the shelf solution which detected neonate faces with an accuracy of 7.37%.
  arXiv  Detail & Related papers  (2022-04-01T18:50:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.