Towards interactive deep-learning for tumour segmentation in head and neck cancer radiotherapy

Wei, Zixiang; Ren, Jintao; Korreman, S.; Nijkamp, Jasper

doi:10.1016/j.phro.2022.12.005

Cited by 9 publications

(7 citation statements)

References 29 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The 3D CNN contours demonstrated a high level of accuracy when compared with ground truth contours testing in an independent dataset of 203 patients (DSC = 0.79). Wei et al 28 used a slice-based interactive deep-learning (iDL) segmentation tool to evaluate the improvement of auto-segmentation accuracy with limited input from observers in 204 HNC patients, although their iDL approach was limited only to a few slices. Median segmentation accuracy at baseline was DSC = 0.65.…”

Section: Discussionmentioning

confidence: 99%

“…The interactive deep-learning method is a different approach that combines the power of CNNs with physicians’ knowledge, reducing the need to train models using carefully curated and labeled datasets. 28 The image foundation model called Segment Anything, which was developed for 2D natural image analysis, exemplifies this approach applied to medical images. 29 This prompt tuning method provides inputs like bounding boxes and point clicks within ROI and can produce reasonable segmentations for some organs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Auto-segmentation of neck nodal metastases using self-distilled masked image transformer on longitudinal MR images

Paudyal,

Jiang,

Han

et al. 2024

BJR|Artificial Intelligence

View full text Add to dashboard Cite

Objectives Auto-segmentation promises greater speed and lower inter-reader variability than manual segmentations in radiation oncology clinical practice. This study aims to implement and evaluate the accuracy of the auto-segmentation algorithm, “Masked Image modeling using the vision Transformers (SMIT),” for neck nodal metastases on longitudinal T2-weighted (T2w) MR images in oropharyngeal squamous cell carcinoma (OPSCC) patients. Methods This prospective clinical trial study included 123 human papillomaviruses (HPV-positive [+]) related OSPCC patients who received concurrent chemoradiotherapy. T2w MR images were acquired on 3 T at pre-treatment (Tx), week 0, and intra-Tx weeks (1-3). Manual delineations of metastatic neck nodes from 123 OPSCC patients were used for the SMIT auto-segmentation, and total tumor volumes were calculated. Standard statistical analyses compared contour volumes from SMIT vs manual segmentation (Wilcoxon signed-rank test [WSRT]), and Spearman’s rank correlation coefficients (ρ) were computed. Segmentation accuracy was evaluated on the test data set using the dice similarity coefficient (DSC) metric value. P-values <0.05 were considered significant. Results No significant difference in manual and SMIT delineated tumor volume at pre-Tx (8.68 ± 7.15 vs 8.38 ± 7.01 cm3, P = 0.26 [WSRT]), and the Bland-Altman method established the limits of agreement as –1.71 to 2.31 cm3, with a mean difference of 0.30 cm3. SMIT model and manually delineated tumor volume estimates were highly correlated (ρ = 0.84-0.96, P < 0.001). The mean DSC metric values were 0.86, 0.85, 0.77, and 0.79 at the pre-Tx and intra-Tx weeks (1-3), respectively. Conclusions The SMIT algorithm provides sufficient segmentation accuracy for oncological applications in HPV+ OPSCC. Advances in knowledge First evaluation of auto-segmentation with SMIT using longitudinal T2w MRI in HPV+ OPSCC.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Auto-segmentation of neck nodal metastases using self-distilled masked image transformer on longitudinal MR images

Paudyal,

Jiang,

Han

et al. 2024

BJR|Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…For quantitative evaluation, the volumetric dice similarity coefficient was used to evaluate the degree of overlap [ 27 ] between the automatic segmentation result and expert delineation, and the 95% Hausdorff distance (95% HD) was used to evaluate the farthest distance between the two delineated boundaries [ 28 ]. Besides, the volume ratio was used to evaluate the systematic under or over-segmentation.…”

Section: Methodsmentioning

confidence: 99%

Accurate object localization facilitates automatic esophagus segmentation in deep learning

Li,

Gan,

Guo

et al. 2024

Radiat Oncol

View full text Add to dashboard Cite

Background Currently, automatic esophagus segmentation remains a challenging task due to its small size, low contrast, and large shape variation. We aimed to improve the performance of esophagus segmentation in deep learning by applying a strategy that involves locating the object first and then performing the segmentation task. Methods A total of 100 cases with thoracic computed tomography scans from two publicly available datasets were used in this study. A modified CenterNet, an object location network, was employed to locate the center of the esophagus for each slice. Subsequently, the 3D U-net and 2D U-net_coarse models were trained to segment the esophagus based on the predicted object center. A 2D U-net_fine model was trained based on the updated object center according to the 3D U-net model. The dice similarity coefficient and the 95% Hausdorff distance were used as quantitative evaluation indexes for the delineation performance. The characteristics of the automatically delineated esophageal contours by the 2D U-net and 3D U-net models were summarized. Additionally, the impact of the accuracy of object localization on the delineation performance was analyzed. Finally, the delineation performance in different segments of the esophagus was also summarized. Results The mean dice coefficient of the 3D U-net, 2D U-net_coarse, and 2D U-net_fine models were 0.77, 0.81, and 0.82, respectively. The 95% Hausdorff distance for the above models was 6.55, 3.57, and 3.76, respectively. Compared with the 2D U-net, the 3D U-net has a lower incidence of delineating wrong objects and a higher incidence of missing objects. After using the fine object center, the average dice coefficient was improved by 5.5% in the cases with a dice coefficient less than 0.75, while that value was only 0.3% in the cases with a dice coefficient greater than 0.75. The dice coefficients were lower for the esophagus between the orifice of the inferior and the pulmonary bifurcation compared with the other regions. Conclusion The 3D U-net model tended to delineate fewer incorrect objects but also miss more objects. Two-stage strategy with accurate object location could enhance the robustness of the segmentation model and significantly improve the esophageal delineation performance, especially for cases with poor delineation results.

show abstract

“… 26 Outside of direct data collection, fields of data-centric AI, like active learning, where models iteratively learn through user interaction, could be used to improve performance and minimize contouring time. Notably, interactive contouring has already been shown to be clinically feasible for HNC tumors 27 and organs-at-risk. 28 Furthermore, as additional imaging modalities like magnetic resonance imaging become relevant for RT planning, 29 data-centric AI methods such as domain adaptation and transfer learning—techniques that apply knowledge from one data environment to another—are anticipated to rise in prominence.…”

Section: Future Perspectives On Auto-contouringmentioning

confidence: 99%

Evolving Horizons in Radiation Therapy Auto-Contouring: Distilling Insights, Embracing Data-Centric Frameworks, and Moving Beyond Geometric Quantification

Wahid,

Cardenas,

Marquez

et al. 2024

Advances in Radiation Oncology

View full text Add to dashboard Cite

Towards interactive deep-learning for tumour segmentation in head and neck cancer radiotherapy

Cited by 9 publications

References 29 publications

Auto-segmentation of neck nodal metastases using self-distilled masked image transformer on longitudinal MR images

Auto-segmentation of neck nodal metastases using self-distilled masked image transformer on longitudinal MR images

Accurate object localization facilitates automatic esophagus segmentation in deep learning

Evolving Horizons in Radiation Therapy Auto-Contouring: Distilling Insights, Embracing Data-Centric Frameworks, and Moving Beyond Geometric Quantification

Contact Info

Product

Resources

About