SU-E-J-102: The Impact of the Number of Subjects for Atlas-Based Automatic Segmentation

Evaluation of manual and automated approaches for segmentation and extraction of quantitative indices from [18F]FDG PET-CT images

Utilisation of whole organ volumes to extract anatomical and functional information from computed tomography (CT) and positron emission tomography (PET) images may provide key information for the treatment and follow-up of cancer patients. However, manual organ segmentation, is laborious and time-consuming. In this study, a CT-based deep learning method and a multi-atlas method were evaluated for segmenting the liver and spleen on CT images to extract quantitative tracer information from Fluorine-18 fluorodeoxyglucose ([18F]FDG) PET images of 50 patients with advanced Hodgkin lymphoma (HL). Manual segmentation was used as the reference method. The two automatic methods were also compared with a manually defined volume of interest (VOI) within the organ, a technique commonly performed in clinical settings. Both automatic methods provided accurate CT segmentations, with the deep learning method outperforming the multi-atlas with a DICE coefficient of 0.93 ± 0.03 (mean ± standard deviation) in liver and 0.87 ± 0.17 in spleen compared to 0.87 ± 0.05 (liver) and 0.78 ± 0.11 (spleen) for the multi-atlas. Similarly, a mean relative error of -3.2% for the liver and -3.4% for the spleen across patients was found for the mean standardized uptake value (SUVmean) using the deep learning regions while the corresponding errors for the multi-atlas method were -4.7% and -9.2%, respectively. For the maximum SUV (SUVmax), both methods resulted in higher than 20% overestimation due to the extension of organ boundaries to include neighbouring, high-uptake regions. The conservative VOI method which did not extend into neighbouring tissues, provided a more accurate SUVmaxestimate. In conclusion, the automatic, and particularly the deep learning method could be used to rapidly extract information of the SUVmeanwithin the liver and spleen. However, activity from neighbouring organs and lesions can lead to high biases in SUVmaxand current practices of manually defining a volume of interest in the organ should be considered instead.

The clinical evaluation of atlas-based auto-segmentation for automatic contouring during cervical cancer radiotherapy

Purpose

Our purpose was to investigate the influence of atlas library size and CT cross-slice number on the accuracy and efficiency of the atlas-based auto-segmentation (ABAS) method for the automatic contouring of clinical treatment volume (CTV) and organs at risk (OARs) during cervical cancer radiotherapy.

Methods

Of 140 cervical cancer patients, contours from 20, 40, 60, 80, 100, and 120 patients were selected incrementally to create six atlas library groups in ABAS. Another 20 tested patients were automatically contoured with the ABAS method and manually contoured by the same professional oncologist. Contours included CTV, bladder, rectum, femoral head-L, femoral head-R, and spinal cord. The CT cross-slice numbers of the 20 tested patients included 61, 65, 72, 75, 81, and 84. The index of dice similarity coefficients (DSCs) and Hausdorff distance (HD) were used to assess the consistency between ABAS automatic contouring and manual contouring. The randomized block analysis of variance and paired t-test were used for statistical analysis.

Results

The mean DSC values of “CTV, bladder, femoral head, and spinal cord” were all larger than 0.8. The femoral head and spinal cord showed a high degree of agreement between ABAS automatic contouring and manual contouring, with a mean DC >0.80 and HD <1 cm in all atlas library groups. A post-hoc least significant difference comparison indicated that no significant difference had been found between different atlas library sizes with DSC and HD values. For ABAS efficiency, the atlas library size had no effect on the time of ABAS automatic contouring. The time of automatic contouring increased slightly with the increase in CT cross-slice numbers, which were 99.9, 106.8, 114.0, 120.6, 127.9, and 134.8 s with CT cross-slices of 61, 65, 72, 75, 81, and 84, respectively.

Conclusion

A total of 20 atlas library sizes and a minimum CT cross-slice number including CTV and OARs are enough for ensuring the accuracy and efficiency of ABAS automatic contouring during cervical cancer radiotherapy.

A Preliminary Experience of Implementing Deep-Learning Based Auto-Segmentation in Head and Neck Cancer: A Study on Real-World Clinical Cases

Purpose

While artificial intelligence has shown great promise in organs-at-risk (OARs) auto segmentation for head and neck cancer (HNC) radiotherapy, to reach the level of clinical acceptance of this technology in real-world routine practice is still a challenge. The purpose of this study was to validate a U-net-based full convolutional neural network (CNN) for the automatic delineation of OARs of HNC, focusing on clinical implementation and evaluation.

Methods

In the first phase, the CNN was trained on 364 clinical HNC patients’ CT images with annotated contouring from routine clinical cases by different oncologists. The automated delineation accuracy was quantified using the Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD). To assess efficiency, the time required to edit the auto-contours to a clinically acceptable standard was evaluated by a questionnaire. For subjective evaluation, expert oncologists (more than 10 years’ experience) were randomly presented with automated delineations or manual contours of 15 OARs for 30 patient cases. In the second phase, the network was retrained with an additional 300 patients, which were generated by pre-trained CNN and edited by oncologists until to meet clinical acceptance.

Results

Based on DSC, the CNN performed best for the spinal cord, brainstem, temporal lobe, eyes, optic nerve, parotid glands and larynx (DSC >0.7). Higher conformity for the OARs delineation was achieved by retraining our architecture, largest DSC improvement on oral cavity (0.53 to 0.93). Compared with the manual delineation time, after using auto-contouring, this duration was significantly shortened from hours to minutes. In the subjective evaluation, two observes showed an apparent inclination on automatic OARs contouring, even for relatively low DSC values. Most of the automated OARs segmentation can reach the clinical acceptance level compared to manual delineations.

Conclusions

After retraining, the CNN developed for OARs automated delineation in HNC was proved to be more robust, efficiency and consistency in clinical practice. Deep learning-based auto-segmentation shows great potential to alleviate the labor-intensive contouring of OAR for radiotherapy treatment planning.