General and custom deep learning autosegmentation models for organs in head and neck, abdomen, and male pelvis

Abstract

Purpose To reduce workload and inconsistencies in organ segmentation for radiation treatment planning, we developed and evaluated general and custom autosegmentation models on computed tomography (CT) for three major tumor sites using a well‐established deep convolutional neural network (DCNN). Methods Five CT‐based autosegmentation models for 42 organs at risk (OARs) in head and neck (HN), abdomen (ABD), and male pelvis (MP) were developed using a full three‐dimensional (3D) DCNN architecture. Two types of deep learning (DL) models were separately trained using either general diversified multi‐institutional datasets or custom well‐controlled single‐institution datasets. To improve segmentation accuracy, an adaptive spatial resolution approach for small and/or narrow OARs and a pseudo scan extension approach, when CT scan length is too short to cover entire organs, were implemented. The performance of the obtained models was evaluated based on accuracy and clinical applicability of the autosegmented contours using qualitative visual inspection and quantitative calculation of dice similarity coefficient (DSC), mean distance to agreement (MDA), and time efficiency. Results The five DL autosegmentation models developed for the three anatomical sites were found to have high accuracy (DSC ranging from 0.8 to 0.98) for 74% OARs and marginally acceptable for 26% OARs. The custom models performed slightly better than the general models, even with smaller custom datasets used for the custom model training. The organ‐based approaches improved autosegmentation accuracy for small or complex organs (e.g., eye lens, optic nerves, inner ears, and bowels). Compared with traditional manual contouring times, the autosegmentation times, including subsequent manual editing, if necessary, were substantially reduced by 88% for MP, 80% for HN, and 65% for ABD models. Conclusions The obtained autosegmentation models, incorporating organ‐based approaches, were found to be effective and accurate for most OARs in the male pelvis, head and neck, and abdomen. We have demonstrated that our multianatomical DL autosegmentation models are clinically useful for radiation treatment planning.

Automatic Contour Refinement for Deep Learning Auto-segmentation of Complex Organs in MRI-guided Adaptive Radiation Therapy

“…This study on ACR is a part of our effort to develop a 4-step segmentation pipeline for MRI-guided ART, including (1) auto-segmentation of MRI based on DL 22 ; (2) auto-check of the obtained auto-segmented contours to detect their inaccuracies 32 ; (3) auto-refinement of the detected inaccurate contours; and (4) manual editing using robust tools for the uncorrectable contours. Such a segmentation pipeline would effectively address the current slowness in the recontouring process, making MRI-guided daily online adaptive replanning more practical.…”

“…The obtained MRIs were then input into a DL auto-segmentation research tool (Admire, Elekta Inc), previously developed based on a 3D deep CNN architecture (a modified 3D-ResUNet) 22 , 23 to generate auto-segmented contours of the small bowel, large bowel, combined bowels, pancreas, duodenum, and stomach. To assess contour accuracy, the auto-segmented contours were compared with the ground truth contours delineated manually by an experienced researcher and independently verified by 2 radiation oncologists.…”

Optimising a 3D convolutional neural network for head and neck computed tomography segmentation with limited training data

“…The external validation additionally confirmed that our model was more widely applicable than just the original model development dataset. Amjad et al recently proposed a custom HN auto-segmentation CNN with a similar Res-UNet3D architecture to ours [28] . However, this model was trained with the MICCAI’15 dataset and 24 additional CT scans so we could not include their results in Table 2 .…”

Stress-testing pelvic autosegmentation algorithms using anatomical edge cases

“…Artificial intelligence (AI) is emerging as a powerful transformative technology, with numerous applications in the radiation oncology clinic. In particular, autosegmentation algorithms, which automatically delineate structures of interest from imaging data, have demonstrated compelling accuracy across numerous sites [1] , [2] , [3] . Autosegmentation algorithms have also demonstrated the potential to improve clinical efficiency [4] , [5] , to standardize a high level of accuracy of segmented volumes across providers [6] , and to enable more complex tasks such as automated treatment planning [7] .…”