Incidence and evolution of imaging changes on cone-beam CT during and after radical radiotherapy for non-small cell lung cancer

Characterisation of quantitative imaging biomarkers for inflammatory and fibrotic radiation-induced lung injuries using preclinical radiomics

BACKGROUND AND PURPOSE

Radiomics is a rapidly evolving area of research that uses medical images to develop prognostic and predictive imaging biomarkers. In this study, we aimed to identify radiomics features correlated with longitudinal biomarkers in preclinical models of acute inflammatory and late fibrotic phenotypes following irradiation.

MATERIALS AND METHODS

Female C3H/HeN and C57BL6 mice were irradiated with 20 Gy targeting the upper lobe of the right lung under cone-beam computed tomography (CBCT) image-guidance. Blood samples and lung tissue were collected at baseline, weeks 1, 10 & 30 to assess changes in serum cytokines and histological biomarkers. The right lung was segmented on longitudinal CBCT scans using ITK-SNAP. Unfiltered and filtered (wavelet) radiomics features (n = 842) were extracted using PyRadiomics. Longitudinal changes were assessed by delta analysis and principal component analysis (PCA) was used to remove redundancy and identify clustering. Prediction of acute (week 1) and late responses (weeks 20 & 30) was performed through deep learning using the Random Forest Classifier (RFC) model.

RESULTS

Radiomics features were identified that correlated with inflammatory and fibrotic phenotypes. Predictive features for fibrosis were detected from PCA at 10 weeks yet overt tissue density was not detectable until 30 weeks. RFC prediction models trained on 5 features were created for inflammation (AUC 0.88), early-detection of fibrosis (AUC 0.79) and established fibrosis (AUC 0.96).

CONCLUSIONS

This study demonstrates the application of deep learning radiomics to establish predictive models of acute and late lung injury. This approach supports the wider application of radiomics as a non-invasive tool for detection of radiation-induced lung complications.

The spine and carina as a surrogate for target registration in cone-beam CT imaging verification in locally advanced lung cancer radiotherapy

BACKGROUND

The aim of the study was to evaluate the accuracy of volumetric lung image guidance using the spine or carina as a surrogate to target for image registration, as the best approach is not established.

PATIENTS AND METHODS

Cone beam computed tomography images from the 1^st, 10^th, 15^th, and 20^th fraction in 40 lung cancer patients treated with radical radiotherapy were retrospectively registered to planning CT, using three approaches. The spine and carina alignment set-up deviations from a reference (tumour/lymph nodes) registration in the lateral (LAT), longitudinal (LONG) and vertical (VRT) directions were analysed and compared. Tumour location and nodal stage influence on registration accuracy were explored.

RESULTS

The spine and carina mean set-up deviation from reference were largest in the LONG, with the best match in the VRT and LAT, respectively. Both strategies were more accurate in central tumours, with the carina being more precise in 50% LAT and 66% LONG mean deviations. For all measurements in all patients a carina vs. spine registration comparison showed improved carina accuracy in LAT and LONG. In comparative subgroup analysis the carina was superior compared to spine in LAT and LONG in centrally located tumours, N2 and N3. Both strategies were comparable for peripheral tumours and N0.

CONCLUSIONS

Carina registration shows greater accuracy compared to spine in the LAT and LONG directions and is superior in central tumours, N2 and N3. The spine and carina surrogates are equally accurate for peripheral tumours and N0. We propose the carina as a surrogate to target for CBCT image registration in locally advanced lung cancer.

Timing of tumor-induced atelectasis resolution and pulmonary function restoration in the course of image-guided moderate hypofractionated thoracic irradiation: a case report and mini-review of literature

This case report describes a patient with squamous cell carcinoma of the lung (cT4 (Infiltration of left pulmonary artery) cN2 cM0, TNM eighth edition) and subsequent tumor-induced atelectasis of the left upper lobe. Despite initially presenting himself with a poor performance status (ECOG-PS III) and diminished lung function, the patient was treated with image-guided thoracic irradiation to a total dose of 45.0 Gy (to the whole planning target volume) / 52.5 Gy (as simultaneous integrated boost to the Primary Tumor) applied in 15 daily fractions. Through the radiation treatment, the upper lobe could be reaerated, and the patient’s lung function and performance were improved.

Improved adaptive radiotherapy to adjust for anatomical alterations during curative treatment for locally advanced lung cancer

Anatomical changes during chemoradiation for lung cancer may decrease dose to the target or increase dose to organs at risk. To assess our ability to identify clinically significant anatomical alterations, we followed 67 lung cancer patients by daily cone-beam CT scans to ensure correct patient positioning and observe anatomical alterations. We also re-calculated the original dose distribution on a planned control CT scan obtained halfway during the treatment course to identify anatomical changes that potentially affected doses to the target or organs at risk. Of 66 patients who completed the treatment, 12 patients needed adaptation, two patients were adapted twice. We conclude that daily cone-beam CT and routines at the treatment machine discover relevant anatomical changes during curative radiotherapy for patients with lung cancer without additional imaging.

Take Action Protocol: A radiation therapist led approach to act on anatomical changes seen on CBCT

•

Take Action Protocol is an accurate RTT led method to act on anatomical changes.

•

The Take Action Protocol gives RTTs more responsibility in IGRT treatment evaluation.

•

RTTs experience the responsibility of decision making on anatomical changes as satisfactory.

•

The TAP improves the balance of the workload vs. clinical relevance of anatomical changes.

Until recently Traffic Light Protocols (TLP) have been developed to recognize and react to Anatomical Changes (ACs) seen on Cone Beam Computer Tomography (CBCT) scans for the most common treatment sites. This involves alerting the Radiation Oncologist (RO), handing over findings, and RO providing the final decision, making it quite labour-intensive for the ROs as well as the Radiation Therapists (RTTs). A new approach was developed to act on ACs: the Take Action Protocol (TAP). In this protocol the RTTs do not only have a role in detecting ACs, but also decide on the appropriate action and follow up, resulting in a significant shift in responsibility. In this study we present the TAP and evaluated the benefit and outcomes of the implementation of TAP compared to the TLP. During a pilot period of six months the TAP was applied for 34 bladder and prostate patients. In 2 bladder and 6 prostate patients further decision making by an RO was required (compared to all 34 in the TLP), showing a large reduction in workload. ACs were accurately assessed by RTTs in >99% of the cases. In 5/34 patients RTTs specialized in Image Guided Radiotherapy provided additional instructions to improve accurate use of the TAP. Two surveys conducted by both ROs and RTTs on the TLP and TAP showed that the perceived involvement of the ROs and burden of responsibility for RTTs was comparable between the two protocols. The identification of patients with truly clinical relevant ACs and the adaptation of treatment for the remaining fractions improved according to ROs and RTTs responses. The TAP provides a better balance between workload and efficiency in relation to the clinical relevance of acting on ACs.

Differences in Lung and Lobe Volumes between Supine and Standing Positions Scanned with Conventional and Newly Developed 320-Detector-Row Upright CT: Intra-Individual Comparison

BACKGROUND

No clinical studies to date have compared unilateral lung or lobe volumes between the supine and standing positions.

OBJECTIVES

To compare lung/lobe volumes on computed tomography (CT) between these two positions and evaluate the correlation between the total lung volume and total lung capacity (TLC) on pulmonary function tests (PFTs).

METHODS

Thirty-two asymptomatic volunteers underwent both conventional CT (supine position) and upright CT (standing position), during deep inspiration breath-hold, and PFTs on the same day. We measured lung/lobe volumes on CT in each position. Paired t tests were used for statistical analysis.

RESULTS

The volumes of the total lung (10.9% increase), right lung (10.3% increase), right upper lobe (8.6% increase), right lower lobe (14.6% increase), left lung (11.6% increase), left upper lobe (7.1% increase), and left lower lobe (16.0% increase) were significantly greater in the standing position than in the supine position (all p < 0.0001). The right middle lobe volume was similar between the two positions (p = 0.16). Intraclass correlation coefficients for agreement between total lung volumes on CT in the supine/standing positions and the TLC on PFT were 0.891/0.938, respectively.

CONCLUSIONS

While the volumes of the bilateral upper and lower lobes and bilateral lungs were significantly greater in the standing than in the supine position, with lower lobes showing larger changes, the right middle lobe volume did not change significantly between positions. The total lung volume on upright CT in the standing position was more similar to TLC on PFT than that in the supine position.