Two Hours of Training Sharpen Residents’ Organ Contouring Skills in the AI Era

Artificial intelligence is quietly transforming nearly every corner of medicine, and radiation oncology is no exception. One of the most labor-intensive steps in planning radiotherapy, the manual outlining of healthy organs at risk on CT scans, is increasingly handled by automated segmentation software. That shift has raised an uncomfortable question for educators: if machines can contour, should junior doctors still spend their training years learning to do it by hand? A new study from the Institut de Cancérologie de Lorraine in Vandoeuvre-lès-Nancy, France, published in BMC Medical Education, offers a data-driven answer, and it suggests that the answer is a cautious yes.

The research team, led by radiation oncologist W. Gehin, set out to measure whether a short, structured teaching session could actually improve how accurately radiation oncology residents delineate organs at risk, and whether any improvement would show up in the numbers that matter most for treatment planning. Ten residents took part in the exploratory, single-institution study. Each of them independently contoured the organs at risk on a demanding clinical scenario: a left-sided breast cancer case requiring irradiation of the breast and the regional lymph nodes. This particular case was chosen deliberately, because it involves a dense cluster of critical structures, including the heart, the coronary arteries, the brachial plexuses, and the lung, all of which sit close to the target volume that must receive a curative radiation dose.

The study design was straightforward but rigorous in its measurement approach. Each resident contoured the case twice: once before a two-hour targeted teaching session, and again seven weeks afterward, with an eight-week interval separating the two teaching sessions. There was no control group, a limitation the authors acknowledge openly. The reference contours against which the residents were judged were created by a senior radiation oncologist following routine clinical practice at the institution, which involves reviewing and correcting the output of an AI-assisted auto-segmentation system, MVision AI version 1.2.7. A second commercial system, RayStation version 23B, was evaluated descriptively as a contextual benchmark, giving the researchers a sense of how resident performance compared with the tools now entering routine use.

To quantify geometric accuracy, the team used two well-established metrics. The Dice Similarity Coefficient, or DSC, measures the spatial overlap between two contours on a scale from zero, meaning no overlap at all, to one, meaning perfect agreement. The 95th-percentile Hausdorff Distance, or HD95, captures how far the surface of a resident’s contour strays from the reference contour at its worst local deviations, making it particularly sensitive to errors at the tips of thin or elongated structures. Together, these two metrics provide a complementary picture: DSC rewards overall volumetric agreement, while HD95 exposes localized geometric misses that a volume-based score might dilute.

The results were encouraging. In a mixed-effects statistical analysis that pooled all structures, training was associated with a significant improvement in contouring accuracy. The average DSC increased by 0.034, with a 95 percent confidence interval ranging from 0.017 to 0.052, and a p-value below 0.001. The HD95 told a parallel story: the geometric ratio of 0.788, with a confidence interval of 0.694 to 0.896, corresponds to a 21.2 percent reduction in the worst-case surface deviation after training. In practical terms, residents’ contours hugged the expert reference more tightly, and their largest local errors shrank by roughly a fifth after just two hours of focused instruction.

Perhaps the most striking findings emerged when the researchers broke the results down structure by structure. The largest improvements appeared for the brachial plexuses, the bundles of nerves that run from the spine through the neck and shoulder into the arm, with effect sizes expressed as rank-biserial correlations of 0.93 and 0.82 for the two sides. The left anterior descending coronary artery, a slender vessel whose accidental irradiation has been linked to long-term cardiac toxicity in breast cancer survivors, showed the largest improvement in HD95, with a rank-biserial correlation of 0.85. These are exactly the anatomically complex, small, and clinically consequential structures where manual contouring errors are most likely and where automated tools have historically struggled most.

However, the authors are careful to temper enthusiasm with statistical honesty. Because the study tested multiple structures simultaneously, they adjusted for multiple comparisons, and after that adjustment none of the structure-specific differences remained statistically significant. The same was true of the dosimetric analysis. To assess whether better contours translated into different dose reporting, the team applied a single, fixed volumetric-modulated arc therapy dose distribution to every contour set and recalculated the dose-volume metrics without re-optimizing the plan. This design choice is important: it isolates the effect of contour variation on the reported dose-volume values rather than implying any change in the dose actually delivered to a patient. The dosimetric differences observed were small, and none survived adjustment for multiple testing. Overall compliance with mandatory dose constraints did not change significantly either.

One of the most thought-provoking aspects of the study is its implicit benchmark against the machines. After training, the residents’ contouring accuracy was broadly comparable to that of the evaluated commercial auto-segmentation system, which notably performed less well on the small tubular structure available for comparison. This finding cuts both ways. On one hand, it suggests that a modest educational investment can bring trainees to a level of geometric performance similar to commercial software, at least on a single challenging case. On the other hand, it underscores that current AI tools are not infallible, particularly for fine, tortuous anatomy like coronary arteries and nerve plexuses, which is precisely where a trained human eye retains its value.

The authors are equally candid about the limits of their design. With no control group and with residents reassessed on the same case after training, the observed improvements should be interpreted as associations rather than as proof of a causal effect. Practice effects, familiarity with the case, or the simple passage of time could all have contributed. Moreover, the study involved only ten residents at a single institution, and the dosimetric changes, while directionally consistent with the geometric gains, were not demonstrably clinically meaningful. The team frames the observed changes as potentially relevant to plan evaluation, the process by which physicians review and approve a treatment plan, rather than as evidence of altered patient outcomes.

What the study does establish is that contouring skill is teachable, quickly, and measurably, even in an era when software promises to do the job automatically. The authors leave the deepest question deliberately open: whether the ability to critically appraise and correct AI-generated contours requires dedicated instruction of its own, or whether it develops naturally from conventional contouring training. As auto-segmentation becomes routine in clinics worldwide, that question will only grow in urgency. For now, the message from Nancy is clear and quietly reassuring. Two hours of structured teaching made residents measurably better at one of radiotherapy’s most fundamental tasks, and the structures that benefited most were the very ones where human expertise remains hardest to replace. In the race between human training and machine automation, the two, it seems, are best run together.

Subject of Research: Structured training for organ-at-risk contouring by radiation oncology residents in the era of AI auto-segmentation

Article Title: Teaching organ-at-risk delineation in the AI era: educational impact and dosimetric relevance of a structured training intervention

Article References: Gehin, W., Huger, S., Grandgirard, N., Faivre, J. C., Bruand, M., Martz, N., Charra-Brunaud, C., Salleron, J., Meyer, C., & Py, J. (2026). Teaching organ-at-risk delineation in the AI era: educational impact and dosimetric relevance of a structured training intervention. BMC Medical Education. https://doi.org/10.1186/s12909-026-10513-2

Image Credits: AI Generated

DOI: 10.1186/s12909-026-10513-2

Keywords: radiation oncology, organ-at-risk delineation, auto-segmentation, artificial intelligence, medical education, resident training, dosimetry, Dice Similarity Coefficient, Hausdorff Distance, VMAT, brachial plexus, breast cancer radiotherapy