Human-in-the-Loop Enhances Machine Learning Inference in Intraoperative Optical Coherence Tomography Glioma Imaging.

Overview

1. Russian Academy of Sciences, Institute of Applied Physics, 46 Ulyanov Str., 603951 Nizhny Novgorod, Russia; (R.Z.); (A.S.); (A.M.); (V.Z.); (K.Y.)
2. Department of Neurosurgery, Privolzhsky Research Medical University, 10/1, Minin and Pozharsky Sq., 603950 Nizhny Novgorod, Russia; (A.G.); (E.K.); (L.K.); (S.K.)

Abstract

Background/Objectives: The integration of Artificial Intelligence (AI) into clinical workflows raises critical questions regarding decision-making responsibility, as fully autonomous systems inevitably carry a margin of error that can be fatal in high-stakes fields like surgery. This study addresses this challenge by evaluating a “Human-in-the-Loop” (HITL) workflow, using intraoperative Optical Coherence Tomography (OCT) for glioma detection. We aimed to determine if integrating Machine Learning (ML)-generated segmentation maps with human contextual analysis resolves the tension between automation and clinical responsibility, yielding superior diagnostic reliability compared to structural or quantitative imaging alone. Methods: We retrospectively analyzed 86 intraoperative OCT scans from 27 patients. Five neurosurgeons blindly assessed the data across three progressive levels of processing: (1) structural scans, (2) physics-based parametric maps, and (3) SVM-based generated segmentation maps. Crucially, the HITL inference performance on segmentation maps was benchmarked against “models-only” inference pipeline: a SVM and a state-of-the-art multimodal reasoning model, Gemini 3.1 Pro. To evaluate interpretability and the operator’s ability to confidently exercise their authority, we measured inter-rater consistency alongside diagnostic performance. Results: The results demonstrate that, while quantitative parametric maps improved Global Accuracy (87% [95% CI: 82–92%]) compared to structural scans (80% [95% CI: 73–86%]), they suffered from an “interpretability gap,” resulting in a moderate inter-rater consistency of 0.68 [95% CI: 0.59–0.78]. In contrast, the HITL approach using segmentation maps maximized consensus to 0.98 [95% CI: 0.95–1.00] and achieved the highest performance (Accuracy 94% [95% CI: 88–98%] and Sensitivity 98% [95% CI: 92–100%]). Compared to the standalone models, the HITL approach significantly outperformed the SVM baseline (Accuracy 84% [95% CI: 81–87%]; Sensitivity 83% [95% CI: 78–88%]). Furthermore, it surpassed the SOTA Gemini 3.1 Pro model (Accuracy 90% [95% CI: 83–95%]; Sensitivity 86% [95% CI: 74–95%]). While the HITL sensitivity demonstrated a definitive and statistically significant edge over the Gemini model, the accuracy improvement fell just slightly short of undisputed statistical significance due to overlapping confidence intervals. Conclusions: By utilizing their clinical domain knowledge of tumor invasion patterns and topological priors, surgeons effectively filtered algorithmic noise—overriding ML errors in 69% (9 out of 13) false positive cases that models alone could not resolve. This demonstrates exactly how and where HITL optimally utilizes human contextual intelligence to outperform autonomous “models-only” pipelines, confirming a human-ML synergy that augments the objectivity of machine learning with human domain knowledge. This paradigm ensures that the ultimate responsibility for diagnostic inference remains safely and practically in human hands. Open Data Initiative: To ensure essential reproducibility, enable independent multi-center validation and support open science, all examples of intraoperative in vivo OCT brain scans used in this study are made publicly available. To the best of our knowledge, this represents the first open-access data of its kind globally.

Reproduced under the paper's license (CC BY), from the paper cited above.

Repositories

Its files are read in the Code ↔ Paper reader above, with 2 matches between paragraphs and lines of code.

The paper's code and data availability statement is in the Data section.

Tracing map

Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.

What the map holds:

• 2 repositories of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
• 6 scripts, each with its path and the digest of its content;
• 2 matches between paragraphs of the paper and lines of the code (method lexical-v1);
• neither the text of the paper nor the code itself.

Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.

Data

No dataset and no data link were found in the paper.

Data Availability Statement

The data presented in this study are available in this article or Supplementary Material. All scan examples used in this study are available in the Supplementary Material. To support reviewer-requested reproducibility and open science, and to facilitate independent multi-center validation, the intraoperative in vivo OCT scans used in this study are attached to this paper under a Conditional Non-Exclusive License. To the best of our knowledge, this dataset represents the first publicly available intraoperative in vivo OCT scans of human brain gliomas globally. Under this Conditional Non-Exclusive License, the use of these materials is permitted subject to prior notification of the authors and on the condition that this article is appropriately cited. The data used in this retrospective study were originally acquired during RSF project No. 23-75-10068; however, that project did not provide financial support for the specific research presented in this paper. The code that converts OCT scans into physics-based maps (OAC and RSC) can be found at https://github.com/SynthOCTChallenge/SynthOCT_Baseline (accessed on 28 April 2026) (Part3_Processor.py) and on the OpticElastograph LLC cloud-based platform: https://accounts.opticelastograph.com (accessed on 28 April 2026) (requires registration). These solutions were developed under RSF project No. 25-12-20032, which solely funded this research.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 28 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 10 authors, 6 keywords, 9 MeSH terms, 1 funder, 18 references.

Cite

This paper

Zinatullin, R., Sovetsky, A., Grishin, A., Kiseleva, E., Kukhnina, L., Korikova, S., Matveyev, A., Zaitsev, V., Yashin, K., & Matveev, L. (2026). Human-in-the-Loop Enhances Machine Learning Inference in Intraoperative Optical Coherence Tomography Glioma Imaging. Medical sciences (Basel, Switzerland), 14(2), 263. https://doi.org/10.3390/medsci14020263

The tracing map gets a citation of its own once an author has validated it and it has a DOI.

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1080/07853890.2026.2685416 [code]

Pulmonary and cerebral damage in COVID-19 survivors: is there any association?

Journal: Annals of medicine

In common: scikit-image, PyTorch, seaborn, 4 other tools, other, other condition

[2] doi:10.1007/s12021-026-09817-x [code]

Circle of Willis-Guided Localization for Simultaneous Detection and Classification of Large Vessel Occlusions in Brain CTA.

Journal: Neuroinformatics

In common: scikit-image, PyTorch, seaborn, 4 other tools, other

[3] doi:10.1371/journal.pcbi.1014555 [code]

Body surface potential driven personalisation of electrophysiological digital twins in hypertrophic cardiomyopathy.

Journal: PLoS computational biology

In common: scikit-image, PyTorch, seaborn, 4 other tools, other

[4] doi:10.1371/journal.pone.0348866 [code]

Using deep learning to identify inherited retinal diseases based on wide-field retinal imaging data.

Journal: PloS one

In common: scikit-image, PyTorch, seaborn, 4 other tools, other

[5] doi:10.1126/sciadv.aed4944 [code]

Focused ultrasound blood-brain barrier opening reveals a paradoxical remote metabolic response in the primate brain.

Journal: Science advances

In common: scikit-image, PyTorch, seaborn, 4 other tools, other

[6] doi:10.1038/s41467-026-76837-1 [code]

Drug screen and machine learning predict neuroprotective agents in a preclinical human model of childhood dementia.

Journal: Nature communications

In common: scikit-image, PyTorch, seaborn, 4 other tools, other condition

[7] doi:10.1002/alz.71649 [code]

Postmortem brain MRI reveals differential associations of subcortical and limbic volumes with cortical thinning and neurodegenerative pathologies.

Journal: Alzheimer's & dementia : the journal of the Alzheimer's Association

In common: scikit-image, PyTorch, seaborn, 4 other tools, other condition

[8] doi:10.21037/qims-2026-0792 [code]

An nnU-Net-based framework with adaptive feature representation for 3D brain tumor segmentation.

Journal: Quantitative imaging in medicine and surgery

In common: scikit-image, PyTorch, seaborn, 4 other tools, other condition

[9] doi:10.1016/j.phro.2026.101056 [code]

Toward uncertainty-aware manual delineation of brain tumours using eye-tracking and image-derived features.

Journal: Physics and imaging in radiation oncology

In common: scikit-image, PyTorch, seaborn, 4 other tools, other condition

[10] doi:10.1016/j.adro.2026.102092 [code]

Effect of Anatomic Contextual Information on the Performance of a Convolutional Neural Network Tasked With Brain Metastasis Detection.

Journal: Advances in radiation oncology

In common: scikit-image, PyTorch, seaborn, 4 other tools, other condition

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.