Deep-learning based surface region selection for deep inspiration breath hold (DIBH) monitoring in left breast cancer radiotherapy

Motion analysis comparing surface imaging and diaphragm tracking on kV projections for deep inspiration breath hold (DIBH)

BACKGROUND

Surface-guided imaging (SGI) is increasingly utilized to monitor patient motion during deep inspiration breath hold (DIBH) in radiotherapy. Understanding the association between surface and internal motion is crucial for effective monitoring.

PURPOSE

To investigate the relation between motion detected by SGI using surface-guided radiotherapy (SGRT) and internal motion measured through diaphragm tracking on kV projections acquired with DIBH for online CBCT.

METHODS

Both SGI and kV were simultaneously acquired for ten patients over a total of 200 breath holds (BH). Diaphragm tracking was performed using second-degree polynomial curve fitting on the derivative images for each kV projection and high-pass filtering at 1/30 Hz to remove rotational effects. The superior-inferior (SI) and anterior-posterior (AP) motions of SGI were then compared to kV tracking using various statistical measures.

RESULTS

The correlation (individuals' median: -0.07 to 0.73) was a suboptimal metric for the BH data. The median and 95th percentile absolute differences between SGI-SI and kV were 0.73 mm and 3.46 mm, respectively, during DIBH. For SGI-AP, the corresponding values were 0.55 mm and 2.80 mm. For inter-BH measurements, the contingency table based on a 3 mm threshold indicated surface/diaphragm motion agreement for SGI-SI/kV and SGI-AP/kV was 61 % and 56 %, respectively.

CONCLUSION

Both intra- and inter-BH measurements indicated a limited association between surface and diaphragm motion, with certain constraints noted due to kV tracking and DIBH data. These findings warrant further investigation into the association between surface and internal motion.

Optimizing Choice of Skin Surrogates for Surface-Guided Stereotactic Body Radiotherapy of Lung Lesions Using Four-Dimensional Computed Tomography

Image-guided radiotherapy supported by surface guidance can help to track lower lung lesions' respiratory motion while reducing a patient's exposure to ionizing radiation. However, it is not always clear how the skin's respiratory motion magnitude and its correlation with the lung lesion's respiratory motion vary between different skin regions of interest (ROI). Four-dimensional computed tomography (4DCT) images provide information on both the skin and lung respiratory motion and are routinely acquired for the purpose of treatment planning in our institution. An analysis of 4DCT images for 57 patients treated in our institution has been conducted to provide information on the respiratory motion magnitudes of nine skin ROIs of the torso, a tracking structure (TS) representing a lower lung lobe lesion, as well as the respiratory motion correlations between the nine ROIs and the TS. The effects of gender and the adipose tissue volume and distribution on these correlations and magnitudes have been analyzed. Significant differences between the ROIs in both the respiratory motion magnitudes and their correlations with the TS have been detected. An overall negative correlation between the ROI respiratory magnitudes and the adipose tissue has been detected for ROIs with rib cage support. A weak to moderate negative correlation between the adipose tissue volume and ROI-to-TS respiratory correlations has been detected for upper thorax ROIs. The respiratory magnitudes in regions without rib support tend to be larger for men than for women, but no differences in the ROI-to-TS correlation between sexes have been detected. The described findings should be considered when choosing skin surrogates for lower lung lesion motion management.

Development of automated region of interest selection algorithms for surface-guided radiation therapy of breast cancer

To investigate automation of the preparation of the region of interest (ROI) for surface-guided radiotherapy (SGRT) of the whole breast with two algorithms based on contour anatomies: using the body contour, and using the breast contour. The patient dataset used for modeling consisted of 39 breast cancer patients previously treated with SGRT. The patient's anatomical structures (body and ipsilateral breast) were retrieved from the planning system, and the clinical ROI (cROI) drawn by the planners was retrieved from the SGRT system for comparison. For the body-contour-based algorithm, a convolutional neural network (MobileNet-v2) was utilized to train a synthetic human model dataset to predict body joint locations. With the body joint location knowledge, an automated ROI (aROIbody ) can be created based on: (1) the superior-inferior (S-I) borders defined by the joint locations, (2) the left-right (L-R) borders defined with 3/4 of chest width, and (3) a curation of the ROI to avoid the ipsilateral armpit. For the breast-contour-based algorithm, an aROIbreast was created by first defining the ROI in the S-I direction with the ipsilateral breast boundaries. Other steps are the same as with the body-contour-based algorithm. Among the 39 patients, 24 patients were used to fine-tune the algorithm parameters, and the remaining 15 patients were used to evaluate the quality of the aROIs against the cROIs. A blinded evaluation was performed by three SGRT expert physicists to rate the acceptability and the quality (1-10 scale) of the aROIs and cROIs, and the dice similarity coefficient (DSC) was also calculated to compare the similarity between the aROIs and cROIs. The results showed that the average acceptability was 14/15 (range: 13/15-15/15) for cROIs, 13.3/15 (range: 13/15-14/15) for aROIbody , and 14.6/15 (range: 14/15-15/15) for aROIbreast . The average quality was 7.4 ± 0.8 for cROIs, 8.1 ± 1.2 for aROIbody , and 8.2 ± 0.9 for aROIbreast . The DSC with cROIs was 0.81 ± 0.06 for aROIbody , and 0.83 ± 0.04 for aROIbreast . The ROI creation time was ∼120 s for clinical, 1.3 s for aROIbody , and 1.2 s for aROIbreast . The proposed automated algorithms can improve the ROI compliance with the SGRT protocol, with a shortened preparation time. It is ready to be integrated into the clinical workflow for automated ROI preparation.

A Potential Pitfall and Clinical Solutions in Surface-Guided Deep Inspiration Breath Hold Radiation Therapy for Left-Sided Breast Cancer

Purpose

Deep inspiration breath hold (DIBH) is an effective technique to spare the heart in treating left-sided breast cancer. Surface-guided radiation therapy (SGRT) is increasingly applied in DIBH setup and motion monitoring. Patient-specific breathing behavior, either thoracically driven or abdominally driven (A-DIBH), should be unaltered, online identified, and monitored accordingly to ensure reproducible heart-sparing treatment.

Methods and Materials

Sixty patients with left-sided breast cancer treated with SGRT were analyzed: 20 A-DIBH patients with vertical chest elevation (VCE ≤ 5 mm) were prospectively identified, and 40 control patients were retrospectively and randomly selected for comparison. At simulation, both free-breathing (FB) and DIBH computed tomography (CT) were acquired, guided by a motion surrogate placed around the xiphoid process. For SGRT treatment setups, the region of interest (ROI) was defined on the CT chest surface, and the surrogate-based setup was a backup. For all 60 patients, the VCE was measured as the average of the FB-to-DIBH elevations at the breast and xiphoid process, together with abdominal elevation. In the 40-patient control group, A-DIBH patients (VCE ≤ 5 mm) were identified. Of the 20 A-DIBH patients, 10 were treated with volumetric modulated arc therapy plans, and 10 patients were treated with tangent plans. Clinical DIBH plans were recalculated on FB CT to compare maximum dose (DMax), 5% of the maximum dose (D5%), mean dose (DMean), and V30Gy, V20Gy, and V5Gy of the heart and lungs and their significance.

Results

In the 20 A-DIBH patients, VCE = 3 ± 2 mm, surrogate motion (9 ± 6 mm), and abdomen motion of 14 ± 5 mm are found. Heart dose reduction from FB to DIBH is significant (P < .01): ∆DMax = -8.4 ± 9.8 Gy, ∆D5% = -2.4 ± 4.4 Gy, and ∆DMean = -0.6 ± 0.9 Gy. Six out of 40 control patients (15%) are found to have VCE ≤ 5 mm.

Conclusions

A-DIBH (VCE ≤ 5 mm) patient population is significant (15%), and they should be identified in the SGRT workflow and monitored accordingly. A new abdominal ROI or an abdominal surrogate should be used instead of the conventional chest-only ROI. Patient-specific DIBH should be preserved for higher reproducibility to ensure heart sparing.

A Survey on Deep Learning for Precision Oncology

Precision oncology, which ensures optimized cancer treatment tailored to the unique biology of a patient’s disease, has rapidly developed and is of great clinical importance. Deep learning has become the main method for precision oncology. This paper summarizes the recent deep-learning approaches relevant to precision oncology and reviews over 150 articles within the last six years. First, we survey the deep-learning approaches categorized by various precision oncology tasks, including the estimation of dose distribution for treatment planning, survival analysis and risk estimation after treatment, prediction of treatment response, and patient selection for treatment planning. Secondly, we provide an overview of the studies per anatomical area, including the brain, bladder, breast, bone, cervix, esophagus, gastric, head and neck, kidneys, liver, lung, pancreas, pelvis, prostate, and rectum. Finally, we highlight the challenges and discuss potential solutions for future research directions.