A review of automatic lung tumour segmentation in the era of 4DCT

Deep-learning-based segmentation using individual patient data on prostate cancer radiation therapy

PURPOSE

Organ-at-risk segmentation is essential in adaptive radiotherapy (ART). Learning-based automatic segmentation can reduce committed labor and accelerate the ART process. In this study, an auto-segmentation model was developed by employing individual patient datasets and a deep-learning-based augmentation method for tailoring radiation therapy according to the changes in the target and organ of interest in patients with prostate cancer.

METHODS

Two computed tomography (CT) datasets with well-defined labels, including contoured prostate, bladder, and rectum, were obtained from 18 patients. The labels of the CT images captured during radiation therapy (CT2nd) were predicted using CT images scanned before radiation therapy (CT1st). From the deformable vector fields (DVFs) created by using the VoxelMorph method, 10 DVFs were extracted when each of the modified CT and CT2nd images were deformed and registered to the fixed CT1st image. Augmented images were acquired by utilizing 110 extracted DVFs and spatially transforming the CT1st images and labels. An nnU-net autosegmentation network was trained by using the augmented images, and the CT2nd label was predicted. A patient-specific model was created for 18 patients, and the performances of the individual models were evaluated. The results were evaluated by employing the Dice similarity coefficient (DSC), average Hausdorff distance, and mean surface distance. The accuracy of the proposed model was compared with those of models trained with large datasets.

RESULTS

Patient-specific models were developed successfully. For the proposed method, the DSC values of the actual and predicted labels for the bladder, prostate, and rectum were 0.94 ± 0.03, 0.84 ± 0.07, and 0.83 ± 0.04, respectively.

CONCLUSION

We demonstrated the feasibility of automatic segmentation by employing individual patient datasets and image augmentation techniques. The proposed method has potential for clinical application in automatic prostate segmentation for ART.

A novel approach for estimating lung tumor motion based on dynamic features in 4D-CT

Due to the high expenses involved, 4D-CT data for certain patients may only include five respiratory phases (0%, 20%, 40%, 60%, and 80%). This limitation can affect the subsequent planning of radiotherapy due to the absence of lung tumor information for the remaining five respiratory phases (10%, 30%, 50%, 70%, and 90%). This study aims to develop an interpolation method that can automatically derive tumor boundary contours for the five omitted phases using the available 5-phase 4D-CT data. The dynamic mode decomposition (DMD) method is a data-driven and model-free technique that can extract dynamic information from high-dimensional data. It enables the reconstruction of long-term dynamic patterns using only a limited number of time snapshots. The quasi-periodic motion of a deformable lung tumor caused by respiratory motion makes it suitable for treatment using DMD. The direct application of the DMD method to analyze the respiratory motion of the tumor is impractical because the tumor is three-dimensional and spans multiple CT slices. To predict the respiratory movement of lung tumors, a method called uniform angular interval (UAI) sampling was developed to generate snapshot vectors of equal length, which are suitable for DMD analysis. The effectiveness of this approach was confirmed by applying the UAI-DMD method to the 4D-CT data of ten patients with lung cancer. The results indicate that the UAI-DMD method effectively approximates the lung tumor's deformable boundary surface and nonlinear motion trajectories. The estimated tumor centroid is within 2 mm of the manually delineated centroid, a smaller margin of error compared to the traditional BSpline interpolation method, which has a margin of 3 mm. This methodology has the potential to be extended to reconstruct the 20-phase respiratory movement of a lung tumor based on dynamic features from 10-phase 4D-CT data, thereby enabling more accurate estimation of the planned target volume (PTV).

Radiomics as a measure superior to common similarity metrics for tumor segmentation performance evaluation

PURPOSE

To propose radiomics features as a superior measure for evaluating the segmentation ability of physicians and auto-segmentation tools and to compare its performance with the most commonly used metrics: Dice similarity coefficient (DSC), surface Dice similarity coefficient (sDSC), and Hausdorff distance (HD).

MATERIALS/METHODS

The data of 10 lung cancer patients' CT images with nine tumor segmentations per tumor were downloaded from the RIDER (Reference Database to Evaluate Response) database. Radiomics features of 90 segmented tumors were extracted using the PyRadiomics program. The intraclass correlation coefficient (ICC) of radiomics features were used to evaluate the segmentation similarity and compare their performance with DSC, sDSC, and HD. We calculated one ICC per radiomics feature and per tumor for nine segmentations and 36 ICCs per radiomics feature for 36 pairs of nine segmentations. Meanwhile, there were 360 DSC, sDSC, and HD values calculated for 36 pairs for 10 tumors.

RESULTS

The ICC of radiomics features exhibited greater sensitivity to segmentation changes than DSC and sDSC. The ICCs of the wavelet-LLL first order Maximum, wavelet-LLL glcm MCC, wavelet-LLL glcm Cluster Shade features ranged from 0.130 to 0.997, 0.033 to 0.978, and 0.160 to 0.998, respectively. On the other hand, all DSC and sDSC were larger than 0.778 and 0.700, respectively, while HD varied from 0 to 1.9 mm. The results indicated that the radiomics features could capture subtle variations in tumor segmentation characteristics, which could not be easily detected by DSC and sDSC.

CONCLUSIONS

This study demonstrates the superiority of radiomics features with ICC as a measure for evaluating a physician's tumor segmentation ability and the performance of auto-segmentation tools. Radiomics features offer a more sensitive and comprehensive evaluation, providing valuable insights into tumor characteristics. Therefore, the new metrics can be used to evaluate new auto-segmentation methods and enhance trainees' segmentation skills in medical training and education.

Application of Artificial Intelligence in the Diagnosis, Treatment, and Prognostic Evaluation of Mediastinal Malignant Tumors

Artificial intelligence (AI), also known as machine intelligence, is widely utilized in the medical field, promoting medical advances. Malignant tumors are the critical focus of medical research and improvement of clinical diagnosis and treatment. Mediastinal malignancy is an important tumor that attracts increasing attention today due to the difficulties in treatment. Combined with artificial intelligence, challenges from drug discovery to survival improvement are constantly being overcome. This article reviews the progress of the use of AI in the diagnosis, treatment, and prognostic prospects of mediastinal malignant tumors based on current literature findings.

Deep learning based time-to-event analysis with PET, CT and joint PET/CT for head and neck cancer prognosis

OBJECTIVES

Recent studies have shown that deep learning based on pre-treatment positron emission tomography (PET) or computed tomography (CT) is promising for distant metastasis (DM) and overall survival (OS) prognosis in head and neck cancer (HNC). However, lesion segmentation is typically required, resulting in a predictive power susceptible to variations in primary and lymph node gross tumor volume (GTV) segmentation. This study aimed at achieving prognosis without GTV segmentation, and extending single modality prognosis to joint PET/CT to allow investigating the predictive performance of combined- compared to single-modality inputs.

METHODS

We employed a 3D-Resnet combined with a time-to-event outcome model to incorporate censoring information. We focused on the prognosis of DM and OS for HNC patients. For each clinical endpoint, five models with PET and/or CT images as input were compared: PET-GTV, PET-only, CT-GTV, CT-only, and PET/CT-GTV models, where -GTV indicates that the corresponding images were masked using the GTV contour. Publicly available delineated CT and PET scans from 4 different Canadian hospitals (293) and the MAASTRO clinic (74) were used for training by 3-fold cross-validation (CV). For independent testing, we used 110 patients from a collaborating institution. The predictive performance was evaluated via Harrell's Concordance Index (HCI) and Kaplan-Meier curves.

RESULTS

In a 5-year time-to-event analysis, all models could produce CV HCIs with median values around 0.8 for DM and 0.7 for OS. The best performance was obtained with the PET-only model, achieving a median testing HCI of 0.82 for DM and 0.69 for OS. Compared with the PET/CT-GTV model, the PET-only still had advantages of up to 0.07 in terms of testing HCI. The Kaplan-Meier curves and corresponding log-rank test results also demonstrated significant stratification capability of our models for the testing cohort.

CONCLUSION

Deep learning-based DM and OS time-to-event models showed predictive capability and could provide indications for personalized RT. The best predictive performance achieved by the PET-only model suggested GTV segmentation might be less relevant for PET-based prognosis.

Automatic contouring of normal tissues with deep learning for preclinical radiation studies

Objective.Delineation of relevant normal tissues is a bottleneck in image-guided precision radiotherapy workflows for small animals. A deep learning (DL) model for automatic contouring using standardized 3D micro cone-beam CT (μCBCT) volumes as input is proposed, to provide a fully automatic, generalizable method for normal tissue contouring in preclinical studies.Approach.A 3D U-net was trained to contour organs in the head (whole brain, left/right brain hemisphere, left/right eye) and thorax (complete lungs, left/right lung, heart, spinal cord, thorax bone) regions. As an important preprocessing step, Hounsfield units (HUs) were converted to mass density (MD) values, to remove the energy dependency of theμCBCT scanner and improve generalizability of the DL model. Model performance was evaluated quantitatively by Dice similarity coefficient (DSC), mean surface distance (MSD), 95th percentile Hausdorff distance (HD_95p), and center of mass displacement (ΔCoM). For qualitative assessment, DL-generated contours (for 40 and 80 kV images) were scored (0: unacceptable, manual re-contouring needed - 5: no adjustments needed). An uncertainty analysis using Monte Carlo dropout uncertainty was performed for delineation of the heart.Main results.The proposed DL model and accompanying preprocessing method provide high quality contours, with in general median DSC > 0.85, MSD < 0.25 mm, HD_95p < 1 mm and ΔCoM < 0.5 mm. The qualitative assessment showed very few contours needed manual adaptations (40 kV: 20/155 contours, 80 kV: 3/155 contours). The uncertainty of the DL model is small (within 2%).Significance.A DL-based model dedicated to preclinical studies has been developed for multi-organ segmentation in two body sites. For the first time, a method independent of image acquisition parameters has been quantitatively evaluated, resulting in sub-millimeter performance, while qualitative assessment demonstrated the high quality of the DL-generated contours. The uncertainty analysis additionally showed that inherent model variability is low.

Machine Learning for Auto-Segmentation in Radiotherapy Planning

Manual segmentation of target structures and organs at risk is a crucial step in the radiotherapy workflow. It has the disadvantages that it can require several hours of clinician time per patient and is prone to inter- and intra-observer variability. Automatic segmentation (auto-segmentation), using computer algorithms, seeks to address these issues. Advances in machine learning and computer vision have led to the development of methods for accurate and efficient auto-segmentation. This review surveys auto-segmentation techniques and applications in radiotherapy planning. It provides an overview of traditional approaches to auto-segmentation, including intensity analysis, shape modelling and atlas-based methods. The focus, though, is on uses of machine learning and deep learning, including convolutional neural networks. Finally, the future of machine-learning-driven auto-segmentation in clinical settings is considered, and the barriers that must be overcome for it to be widely accepted into routine practice are highlighted.

Challenges and opportunities for artificial intelligence in oncological imaging

Imaging plays a key role in oncology, including the diagnosis and detection of cancer, determining clinical management, assessing treatment response, and complications of treatment or disease. The current use of clinical oncology is predominantly qualitative in nature with some relatively crude size-based measurements of tumours for assessment of disease progression or treatment response; however, it is increasingly understood that there may be significantly more information about oncological disease that can be obtained from imaging that is not currently utilized. Artificial intelligence (AI) has the potential to harness quantitative techniques to improve oncological imaging. These may include improving the efficiency or accuracy of traditional roles of imaging such as diagnosis or detection. These may also include new roles for imaging such as risk-stratifying patients for different types of therapy or determining biological tumour subtypes. This review article outlines several major areas in oncological imaging where there may be opportunities for AI technology. These include (1) screening and detection of cancer, (2) diagnosis and risk stratification, (3) tumour segmentation, (4) precision oncology, and (5) predicting prognosis and assessing treatment response. This review will also address some of the potential barriers to AI research in oncological imaging.

Initial Clinical Experience of MR-Guided Radiotherapy for Non-Small Cell Lung Cancer

Curative-intent radiotherapy plays an integral role in the treatment of lung cancer and therefore improving its therapeutic index is vital. MR guided radiotherapy (MRgRT) systems are the latest technological advance which may help with achieving this aim. The majority of MRgRT treatments delivered to date have been stereotactic body radiation therapy (SBRT) based and include the treatment of (ultra-) central tumors. However, there is a move to also implement MRgRT as curative-intent treatment for patients with inoperable locally advanced NSCLC. This paper presents the initial clinical experience of using the two commercially available systems to date: the ViewRay MRIdian and Elekta Unity. The challenges and potential solutions associated with MRgRT in lung cancer will also be highlighted.

A narrative review on characterization of acute respiratory distress syndrome in COVID-19-infected lungs using artificial intelligence

COVID-19 has infected 77.4 million people worldwide and has caused 1.7 million fatalities as of December 21, 2020. The primary cause of death due to COVID-19 is Acute Respiratory Distress Syndrome (ARDS). According to the World Health Organization (WHO), people who are at least 60 years old or have comorbidities that have primarily been targeted are at the highest risk from SARS-CoV-2. Medical imaging provides a non-invasive, touch-free, and relatively safer alternative tool for diagnosis during the current ongoing pandemic. Artificial intelligence (AI) scientists are developing several intelligent computer-aided diagnosis (CAD) tools in multiple imaging modalities, i.e., lung computed tomography (CT), chest X-rays, and lung ultrasounds. These AI tools assist the pulmonary and critical care clinicians through (a) faster detection of the presence of a virus, (b) classifying pneumonia types, and (c) measuring the severity of viral damage in COVID-19-infected patients. Thus, it is of the utmost importance to fully understand the requirements of for a fast and successful, and timely lung scans analysis. This narrative review first presents the pathological layout of the lungs in the COVID-19 scenario, followed by understanding and then explains the comorbid statistical distributions in the ARDS framework. The novelty of this review is the approach to classifying the AI models as per the by school of thought (SoTs), exhibiting based on segregation of techniques and their characteristics. The study also discusses the identification of AI models and its extension from non-ARDS lungs (pre-COVID-19) to ARDS lungs (post-COVID-19). Furthermore, it also presents AI workflow considerations of for medical imaging modalities in the COVID-19 framework. Finally, clinical AI design considerations will be discussed. We conclude that the design of the current existing AI models can be improved by considering comorbidity as an independent factor. Furthermore, ARDS post-processing clinical systems must involve include (i) the clinical validation and verification of AI-models, (ii) reliability and stability criteria, and (iii) easily adaptable, and (iv) generalization assessments of AI systems for their use in pulmonary, critical care, and radiological settings.

Geometric and Dosimetric Evaluation of a Commercially Available Auto-segmentation Tool for Gross Tumour Volume Delineation in Locally Advanced Non-small Cell Lung Cancer: a Feasibility Study

AIMS

To quantify the reliability of a commercially available auto-segmentation tool in locally advanced non-small cell lung cancer using serial four-dimensional computed tomography (4DCT) scans during conventionally fractionated radiotherapy.

MATERIALS AND METHODS

Eight patients with serial 4DCT scans (n = 44) acquired over the course of radiotherapy were assessed. Each 4DCT had a physician-defined primary tumour manual contour (MC). An auto-contour (AC) and a user-adjusted auto-contour (UA-AC) were created for each scan. Geometric agreement of the AC and the UA-AC to the MC was assessed using the dice similarity coefficient (DSC), the centre of mass (COM) shift from the MC and the structure volume difference from the MC. Bland Altman analysis was carried out to assess agreement between contouring methods. Dosimetric reliability was assessed by comparison of planning target volume dose coverage on the MC and UA-AC. The time trend analysis of the geometric accuracy measures from the initial planning scan through to the final scan for each patient was evaluated using a Wilcoxon signed ranks test to assess the reliability of the UA-AC over the duration of radiotherapy.

RESULTS

User adjustment significantly improved all geometric comparison metrics over the AC alone. Improved agreement was observed in smaller tumours not abutting normal soft tissue and median values for geometric comparisons to the MC for DSC, tumour volume difference and COM offset were 0.80 (range 0.49-0.89), 0.8 cm³ (range 0.0-5.9 cm³) and 0.16 cm (range 0.09-0.69 cm), respectively. There were no significant differences in dose metrics measured from the MC and the UA-AC after Bonferroni correction. Variation in geometric agreement between the MC and the UA-AC were observed over the course of radiotherapy with both DSC (P = 0.035) and COM shift from the MC (ns) worsening. The median tumour volume difference from the MC improved at the later time point.

CONCLUSIONS

These findings suggest that the UA-AC can produce geometrically and dosimetrically acceptable contours for appropriately selected patients with non-small cell lung cancer. Larger studies are required to confirm the findings.

Software simulation of tumour motion dose effects during flattened and unflattened ITV-based VMAT lung SBRT

Purpose

Restricted studies comparing different dose rate parameters are available while ITV-based VMAT lung SBRT planning leads to perform the analysis of the most suitable parameters of the external beams used. The special emphasis was placed on the impact of dose rate on dose distribution variations in target volumes due to interplay effects.

Methods

Four VMAT plans were calculated for 15 lung tumours using 6 MV photon beam quality (flattening filter FF vs. flattening filter free FFF beams) and maximum dose rate of 600 MU/min, 1000 MU/min and 1400 MU/min. Three kinds of motion simulations were performed finally giving 180 plans with perturbed dose distributions.

Results

6FFF-1400 MUs/min plans were characterized by the shortest beam on time (1.8 ± 0.2 min). Analysing the performed motion simulation results, the mean dose (Dmean) is not a sensitive parameter to related interplay effects. Looking for local maximum and local minimum doses, some discrepancies were found, but their significance was presented for individual patients, not for the whole cohort. The same was observed for other verified dose metrics.

Conclusions

Generally, the evaluation of VMAT robustness between FF and FFF concepts against interplay effect showed a negligible effect of simulated motion influence on tumour coverage among different photon beam quality parameters. Due to the lack of FFF beams, smaller radiotherapy centres are able to perform ITV-based VMAT lung SBRT treatment in a safe way. Radiotherapy department having FFF beams could perform safe, fast and efficient ITV-based VMAT lung SBRT without a concern about significance of interplay effects.