Radiomics workflow definition & challenges - German priority program 2177 consensus statement on clinically applied radiomics.

OBJECTIVES: Achieving a consensus on a definition for different aspects of radiomics workflows to support their translation into clinical usage. Furthermore, to assess the perspective of experts on important challenges for a successful clinical workflow implementation. MATERIALS AND METHODS: The consensus was achieved by a multi-stage process. Stage 1 comprised a definition screening, a retrospective analysis with semantic mapping of terms found in 22 workflow definitions, and the compilation of an initial baseline definition. Stages 2 and 3 consisted of a Delphi process with over 45 experts hailing from sites participating in the German Research Foundation (DFG) Priority Program 2177. Stage 2 aimed to achieve a broad consensus for a definition proposal, while stage 3 identified the importance of translational challenges. RESULTS: Workflow definitions from 22 publications (published 2012-2020) were analyzed. Sixty-nine definition terms were extracted, mapped, and semantic ambiguities (e.g., homonymous and synonymous terms) were identified and resolved. The consensus definition was developed via a Delphi process. The final definition comprising seven phases and 37 aspects reached a high overall consensus (> 89% of experts "agree" or "strongly agree"). Two aspects reached no strong consensus. In addition, the Delphi process identified and characterized from the participating experts' perspective the ten most important challenges in radiomics workflows. CONCLUSION: To overcome semantic inconsistencies between existing definitions and offer a well-defined, broad, referenceable terminology, a consensus workflow definition for radiomics-based setups and a terms mapping to existing literature was compiled. Moreover, the most relevant challenges towards clinical application were characterized. CRITICAL RELEVANCE STATEMENT: Lack of standardization represents one major obstacle to successful clinical translation of radiomics. Here, we report a consensus workflow definition on different aspects of radiomics studies and highlight important challenges to advance the clinical adoption of radiomics. KEY POINTS: Published radiomics workflow terminologies are inconsistent, hindering standardization and translation. A consensus radiomics workflow definition proposal with high agreement was developed. Publicly available result resources for further exploitation by the scientific community.

Rapid artificial intelligence solutions in a pandemic-The COVID-19-20 Lung CT Lesion Segmentation Challenge.

Artificial intelligence (AI) methods for the automatic detection and quantification of COVID-19 lesions in chest computed tomography (CT) might play an important role in the monitoring and management of the disease. We organized an international challenge and competition for the development and comparison of AI algorithms for this task, which we supported with public data and state-of-the-art benchmark methods. Board Certified Radiologists annotated 295 public images from two sources (A and B) for algorithms training (n=199, source A), validation (n=50, source A) and testing (n=23, source A; n=23, source B). There were 1,096 registered teams of which 225 and 98 completed the validation and testing phases, respectively. The challenge showed that AI models could be rapidly designed by diverse teams with the potential to measure disease or facilitate timely and patient-specific interventions. This paper provides an overview and the major outcomes of the COVID-19 Lung CT Lesion Segmentation Challenge - 2020.

Automated segmentation and quantification of the healthy and diseased aorta in CT angiographies using a dedicated deep learning approach.

OBJECTIVES: To develop and validate a deep learning-based algorithm for segmenting and quantifying the physiological and diseased aorta in computed tomography angiographies. METHODS: CTA exams of the aorta of 191 patients (68.1 ± 14 years, 128 male), performed between 2015 and 2018, were retrospectively identified from our imaging archive and manually segmented by two investigators. A 3D U-Net model was trained on the data, which was divided into a training, a validation, and a test group at a ratio of 7:1:2. Cases in the test group (n = 41) were evaluated to compare manual and automatic segmentations. Dice similarity coefficient (DSC), mean surface distance (MSD), and Hausdorff surface distance (HSD) were extracted. Maximum diameter, effective diameter, and area were quantified and compared between both segmentations at eight anatomical landmarks, and at the maximum area of an aneurysms if present (n = 14). Statistics included error calculation, intraclass correlation coefficient, and Bland-Altman analysis. RESULTS: A DSC of 0.95 [0.94; 0.95] and an MSD of 0.76 [0.06; 0.99] indicated close agreement between segmentations. HSD was 8.00 [4.47; 10.00]. The largest absolute errors were found in the ascending aorta with 0.8 ± 1.5 mm for maximum diameter and at the coeliac trunk with - 30.0 ± 81.6 mm2 for area. Results for absolute errors in aneurysms were - 0.5 ± 2.3 mm for maximum diameter, 0.3 ± 1.6 mm for effective diameter, and 64.9 ± 114.9 mm2 for area. ICC showed excellent agreement (> 0.9; p < 0.05) between quantitative measurements. CONCLUSIONS: Automated segmentation of the aorta on CTA data using a deep learning algorithm is feasible and allows for accurate quantification of the aortic lumen even if the vascular architecture is altered by disease. KEY POINTS: • A deep learning-based algorithm can automatically segment the aorta, mostly within acceptable margins of error, even if the vascular architecture is altered by disease. • Quantifications performed in the segmentations were mostly within clinically acceptable limits, even in pathologically altered segments of the aorta.

Rapid Artificial Intelligence Solutions in a Pandemic - The COVID-19-20 Lung CT Lesion Segmentation Challenge.

Artificial intelligence (AI) methods for the automatic detection and quantification of COVID-19 lesions in chest computed tomography (CT) might play an important role in the monitoring and management of the disease. We organized an international challenge and competition for the development and comparison of AI algorithms for this task, which we supported with public data and state-of-the-art benchmark methods. Board Certified Radiologists annotated 295 public images from two sources (A and B) for algorithms training (n=199, source A), validation (n=50, source A) and testing (n=23, source A; n=23, source B). There were 1,096 registered teams of which 225 and 98 completed the validation and testing phases, respectively. The challenge showed that AI models could be rapidly designed by diverse teams with the potential to measure disease or facilitate timely and patient-specific interventions. This paper provides an overview and the major outcomes of the COVID-19 Lung CT Lesion Segmentation Challenge - 2020.

Automatic liver tumor segmentation in CT with fully convolutional neural networks and object-based postprocessing.

Automatic liver tumor segmentation would have a big impact on liver therapy planning procedures and follow-up assessment, thanks to standardization and incorporation of full volumetric information. In this work, we develop a fully automatic method for liver tumor segmentation in CT images based on a 2D fully convolutional neural network with an object-based postprocessing step. We describe our experiments on the LiTS challenge training data set and evaluate segmentation and detection performance. Our proposed design cascading two models working on voxel- and object-level allowed for a significant reduction of false positive findings by 85% when compared with the raw neural network output. In comparison with the human performance, our approach achieves a similar segmentation quality for detected tumors (mean Dice 0.69 vs. 0.72), but is inferior in the detection performance (recall 63% vs. 92%). Finally, we describe how we participated in the LiTS challenge and achieved state-of-the-art performance.

Algorithm Variability in the Estimation of Lung Nodule Volume From Phantom CT Scans: Results of the QIBA 3A Public Challenge.

RATIONALE AND OBJECTIVES: Quantifying changes in lung tumor volume is important for diagnosis, therapy planning, and evaluation of response to therapy. The aim of this study was to assess the performance of multiple algorithms on a reference data set. The study was organized by the Quantitative Imaging Biomarker Alliance (QIBA). MATERIALS AND METHODS: The study was organized as a public challenge. Computed tomography scans of synthetic lung tumors in an anthropomorphic phantom were acquired by the Food and Drug Administration. Tumors varied in size, shape, and radiodensity. Participants applied their own semi-automated volume estimation algorithms that either did not allow or allowed post-segmentation correction (type 1 or 2, respectively). Statistical analysis of accuracy (percent bias) and precision (repeatability and reproducibility) was conducted across algorithms, as well as across nodule characteristics, slice thickness, and algorithm type. RESULTS: Eighty-four percent of volume measurements of QIBA-compliant tumors were within 15% of the true volume, ranging from 66% to 93% across algorithms, compared to 61% of volume measurements for all tumors (ranging from 37% to 84%). Algorithm type did not affect bias substantially; however, it was an important factor in measurement precision. Algorithm precision was notably better as tumor size increased, worse for irregularly shaped tumors, and on the average better for type 1 algorithms. Over all nodules meeting the QIBA Profile, precision, as measured by the repeatability coefficient, was 9.0% compared to 18.4% overall. CONCLUSION: The results achieved in this study, using a heterogeneous set of measurement algorithms, support QIBA quantitative performance claims in terms of volume measurement repeatability for nodules meeting the QIBA Profile criteria.

Comparison of volumetric and linear serial CT assessments of lung metastases in renal cell carcinoma patients in a clinical phase IIB study.

RATIONALE AND OBJECTIVES: Accuracy of radiologic assessment may have a crucial impact on clinical studies and therapeutic decisions. We compared the variability of a central radiologic assessment (RECIST) and computer-aided volume-based assessment of lung lesions in patients with metastatic renal cell carcinoma (RCC). MATERIALS AND METHODS: The investigation was prospectively planned as a substudy of a clinical randomized phase IIB therapeutic trial in patients with RCC. Starting with the manual study diameter (SDM) of the central readers using RECIST in the clinical study, we performed computer-aided volume measurements. We compared SDM to an automated RECIST diameter (aRDM) and the diameter of a volume-equivalent sphere (effective diameter [EDM]), both for the individual size measurements and for the change rate (CR) between consecutive time points. One hundred thirty diameter pairs of 30 lung lesions from 14 patients were evaluable, forming 55 change pairs over two consecutive time points each. RESULTS: The SDMs of two different readers showed a correlation of 95.6%, whereas the EDMs exhibited an excellent correlation of 99.4%. Evaluation of CRs showed an SDM-CR correlation of 63.9%, which is substantially weaker than the EDM-CR correlation of 87.6%. The variability of SDM-CR is characterized by a median absolute difference of 11.4% points versus the significantly lower 1.8% points EDM-CRs variability (aRDM: 3.2% points). The limits of agreement between readers suggest that an EDM change of 10% or 1 mm can already be significant. CONCLUSIONS: Computer-aided volume-based assessments result in markedly reduced variability of parameters describing size and change, which may offer an advantage of earlier response evaluations and treatment decisions for patients.

Workflow-centred evaluation of an automatic lesion tracking software for chemotherapy monitoring by CT.

OBJECTIVES: In chemotherapy monitoring, an estimation of the change in tumour size is an important criterion for the assessment of treatment success. This requires a comparison between corresponding lesions in the baseline and follow-up computed tomography (CT) examinations. We evaluate the clinical benefits of an automatic lesion tracking tool that identifies the target lesions in the follow-up CT study and pre-computes the lesion volumes. METHODS: Four radiologists performed volumetric follow-up examinations for 52 patients with and without lesion tracking. In total, 139 lung nodules, liver metastases and lymph nodes were given as target lesions. We measured reading time, inter-reader variability in lesion identification and volume measurements, and the amount of manual adjustments of the segmentation results. RESULTS: With lesion tracking, target lesion assessment time decreased by 38 % or 22 s per lesion. Relative volume difference between readers was reduced from 0.171 to 0.1. Segmentation quality was comparable with and without lesion tracking. CONCLUSIONS: Our automatic lesion tracking tool can make interpretation of follow-up CT examinations quicker and provide results that are less reader-dependent. KEY POINTS: Computed tomography is widely used to follow-up lesions in oncological patients. Novel software automatically identifies and measures target lesions in oncological follow-up examinations. This enables a reduction of target lesion assessment. The automated measurements are less reader-dependent.

Object-based analysis of CT images for automatic detection and segmentation of hypodense liver lesions.

PURPOSE: Hypodense liver lesions are commonly detected in CT, so their segmentation and characterization are essential for diagnosis and treatment. Methods for automatic detection and segmentation of liver lesions were developed to support this task. METHODS: The detection algorithm uses an object-based image analysis approach, allowing for effectively integrating domain knowledge and reasoning processes into the detection logic. The method is intended to succeed in cases typically difficult for computer-aided detection systems, especially low contrast of hypodense lesions relative to healthy tissue. The detection stage is followed by a dedicated segmentation algorithm needed to synthesize 3D segmentations for all true-positive findings. RESULTS: The automated method provides an overall detection rate of 77.8% with a precision of 0.53 and performs better than other related methods. The final lesion segmentation delivers appropriate quality in 89% of the detected cases, as evaluated by two radiologists. CONCLUSIONS: A new automated liver lesion detection algorithm employs the strengths of an object-based image analysis approach. The combination of automated detection and segmentation provides promising results with potential to improve diagnostic liver lesion evaluation.

State of the art in computer-assisted planning, intervention, and assessment of liver-tumor ablation.

Percutaneous, image-guided thermal tumor ablation procedures are used increasingly for minimally invasive, local treatment of tumors in the liver. The planning of these procedures; the support of targeting, monitoring, and controlling during the intervention itself; and the assessment of the treatment response can all benefit significantly from computer assistance. The outcome can be optimized by supporting the physician in the process of determining an intervention strategy that enables complete destruction of the targeted tumor while reducing the danger of complications. During the intervention, computer-assisted methods can be used to guide the physician in the implementation of the intended strategy by providing planning information. Assessment of the intervention result is carried out by comparison of the achieved coagulation with the target tumor volume. Supporting this comparison facilitates the early detection of potential recurrences. This report provides an overview of state-of-the-art computer-assisted methods for the support of thermal tumor ablations in the liver. Proper approaches for image segmentation, access-path determination, simulation, visualization, interventional guidance, and post-interventional assessment, as well as integrated work flow-oriented solutions, are reviewed with respect to technical aspects and applicability in the clinical setting.