Camyla: Scaling Autonomous Research in Medical Image Segmentation

• URL: http://arxiv.org/abs/2604.10696v1
• Date: Sun, 12 Apr 2026 15:43:50 GMT
• Title: Camyla: Scaling Autonomous Research in Medical Image Segmentation
• Abstract summary: Camyla is a system for fully autonomous research within the scientific domain of medical image segmentation.<n>It transforms raw datasets into literature-grounded research proposals, executable experiments, and complete manuscripts without human intervention.
• Score: 17.06413651643779
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present Camyla, a system for fully autonomous research within the scientific domain of medical image segmentation. Camyla transforms raw datasets into literature-grounded research proposals, executable experiments, and complete manuscripts without human intervention. Autonomous experimentation over long horizons poses three interrelated challenges: search effort drifts toward unpromising directions, knowledge from earlier trials degrades as context accumulates, and recovery from failures collapses into repetitive incremental fixes. To address these challenges, the system combines three coupled mechanisms: Quality-Weighted Branch Exploration for allocating effort across competing proposals, Layered Reflective Memory for retaining and compressing cross-trial knowledge at multiple granularities, and Divergent Diagnostic Feedback for diversifying recovery after underperforming trials. The system is evaluated on CamylaBench, a contamination-free benchmark of 31 datasets constructed exclusively from 2025 publications, under a strict zero-intervention protocol across two independent runs within a total of 28 days on an 8-GPU cluster. Across the two runs, Camyla generates more than 2,700 novel model implementations and 40 complete manuscripts, and surpasses the strongest per-dataset baseline selected from 14 established architectures, including nnU-Net, on 22 and 18 of 31 datasets under identical training budgets, respectively (union: 24/31). Senior human reviewers score the generated manuscripts at the T1/T2 boundary of contemporary medical imaging journals. Relative to automated baselines, Camyla outperforms AutoML and NAS systems on aggregate segmentation performance and exceeds six open-ended research agents on both task completion and baseline-surpassing frequency. These results suggest that domain-scale autonomous research is achievable in medical image segmentation.

Related papers

• 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)
• Standardized Evaluation of Automatic Methods for Perivascular Spaces Segmentation in MRI -- MICCAI 2024 Challenge Results [11.040060608562362]
  This paper presents the EPVS Challenge organized at MICCAI 2024.<n>It aims to advance the development of automated algorithms for EPVS segmentation across multi-site data.<n>The winning method employed MedNeXt architecture with a dual 2D/3D strategy for handling varying slice thicknesses.
  arXiv  Detail & Related papers  (2025-12-20T03:45:14Z)
• Extreme Cardiac MRI Analysis under Respiratory Motion: Results of the CMRxMotion Challenge [56.28872161153236]
  Deep learning models have achieved state-of-the-art performance in automated Cardiac Magnetic Resonance (CMR) analysis.<n>The efficacy of these models is highly dependent on the availability of high-quality, artifact-free images.<n>To promote research in this domain, we organized the MICCAI CMRxMotion challenge.
  arXiv  Detail & Related papers  (2025-07-25T11:12:21Z)
• TUS-REC2024: A Challenge to Reconstruct 3D Freehand Ultrasound Without External Tracker [25.14284964227897]
  TUS-REC2024 Challenge was established to benchmark and accelerate progress in trackerless 3D ultrasound reconstruction.<n>Challenge attracted over 43 registered teams, of which 6 teams submitted 21 valid dockerized solutions.<n>Results highlight both the progress and current limitations of state-of-the-art approaches in this domain.
  arXiv  Detail & Related papers  (2025-06-26T20:52:18Z)
• crossMoDA Challenge: Evolution of Cross-Modality Domain Adaptation Techniques for Vestibular Schwannoma and Cochlea Segmentation from 2021 to 2023 [20.87321022049113]
  We report the findings of the 2022 and 2023 editions of the cross-Modality Domain Adaptation (crossMoDA) challenge series.<n>The winning approach of the 2023 edition reduced the number of outliers on the 2021 and 2022 testing data.<n>While progress is still needed for clinically acceptable VS segmentation, the plateauing performance suggests that a more challenging cross-modal task may better serve future benchmarking.
  arXiv  Detail & Related papers  (2025-06-13T17:56:39Z)
• The state-of-the-art 3D anisotropic intracranial hemorrhage segmentation on non-contrast head CT: The INSTANCE challenge [19.72232714668029]
  The INSTANCE 2022 was a grand challenge held in conjunction with the 2022 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) It is intended to resolve the above-mentioned problems and promote the development of both intracranial hemorrhage segmentation and anisotropic data processing. The winner method achieved an average DSC of 0.6925, demonstrating a significant growth over our proposed baseline method.
  arXiv  Detail & Related papers  (2023-01-09T11:48:05Z)
• FetReg2021: A Challenge on Placental Vessel Segmentation and Registration in Fetoscopy [52.3219875147181]
  Fetoscopic laser photocoagulation is a widely adopted procedure for treating Twin-to-Twin Transfusion Syndrome (TTTS) The procedure is particularly challenging due to the limited field of view, poor manoeuvrability of the fetoscope, poor visibility, and variability in illumination. Computer-assisted intervention (CAI) can provide surgeons with decision support and context awareness by identifying key structures in the scene and expanding the fetoscopic field of view through video mosaicking. Seven teams participated in this challenge and their model performance was assessed on an unseen test dataset of 658 pixel-annotated images from 6 fet
  arXiv  Detail & Related papers  (2022-06-24T23:44:42Z)
• Lung-Originated Tumor Segmentation from Computed Tomography Scan (LOTUS) Benchmark [48.30502612686276]
  Lung cancer is one of the deadliest cancers, and its effective diagnosis and treatment depend on the accurate delineation of the tumor. Human-centered segmentation, which is currently the most common approach, is subject to inter-observer variability. The 2018 VIP Cup started with a global engagement from 42 countries to access the competition data. In a nutshell, all the algorithms proposed during the competition, are based on deep learning models combined with a false positive reduction technique.
  arXiv  Detail & Related papers  (2022-01-03T03:06:38Z)
• Robust Medical Instrument Segmentation Challenge 2019 [56.148440125599905]
  Intraoperative tracking of laparoscopic instruments is often a prerequisite for computer and robotic-assisted interventions. Our challenge was based on a surgical data set comprising 10,040 annotated images acquired from a total of 30 surgical procedures. The results confirm the initial hypothesis, namely that algorithm performance degrades with an increasing domain gap.
  arXiv  Detail & Related papers  (2020-03-23T14:35:08Z)
• VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images [121.31355003451152]
  Large Scale Vertebrae Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2019 and 2020. We present the the results of this evaluation and further investigate the performance-variation at vertebra-level, scan-level, and at different fields-of-view.
  arXiv  Detail & Related papers  (2020-01-24T21:09:18Z)

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.