Semiautomatic segmentation of liver metastases on volumetric CT images

Deep learning models for automatic tumor segmentation and total tumor volume assessment in patients with colorectal liver metastases

BACKGROUND

We developed models for tumor segmentation to automate the assessment of total tumor volume (TTV) in patients with colorectal liver metastases (CRLM).

METHODS

In this prospective cohort study, pre- and post-systemic treatment computed tomography (CT) scans of 259 patients with initially unresectable CRLM of the CAIRO5 trial (NCT02162563) were included. In total, 595 CT scans comprising 8,959 CRLM were divided into training (73%), validation (6.5%), and test sets (21%). Deep learning models were trained with ground truth segmentations of the liver and CRLM. TTV was calculated based on the CRLM segmentations. An external validation cohort was included, comprising 72 preoperative CT scans of patients with 112 resectable CRLM. Image segmentation evaluation metrics and intraclass correlation coefficient (ICC) were calculated.

RESULTS

In the test set (122 CT scans), the autosegmentation models showed a global Dice similarity coefficient (DSC) of 0.96 (liver) and 0.86 (CRLM). The corresponding median per-case DSC was 0.96 (interquartile range [IQR] 0.95-0.96) and 0.80 (IQR 0.67-0.87). For tumor segmentation, the intersection-over-union, precision, and recall were 0.75, 0.89, and 0.84, respectively. An excellent agreement was observed between the reference and automatically computed TTV for the test set (ICC 0.98) and external validation cohort (ICC 0.98). In the external validation, the global DSC was 0.82 and the median per-case DSC was 0.60 (IQR 0.29-0.76) for tumor segmentation.

CONCLUSIONS

Deep learning autosegmentation models were able to segment the liver and CRLM automatically and accurately in patients with initially unresectable CRLM, enabling automatic TTV assessment in such patients.

RELEVANCE STATEMENT

Automatic segmentation enables the assessment of total tumor volume in patients with colorectal liver metastases, with a high potential of decreasing radiologist's workload and increasing accuracy and consistency.

KEY POINTS

• Tumor response evaluation is time-consuming, manually performed, and ignores total tumor volume. • Automatic models can accurately segment tumors in patients with colorectal liver metastases. • Total tumor volume can be accurately calculated based on automatic segmentations.

Edge Constraint and Location Mapping for Liver Tumor Segmentation from Nonenhanced Images

As there is no contrast enhancement, the liver tumor area in nonenhanced MRI exists with blurred edges and low contrast, which greatly affects the speed and accuracy of liver tumor diagnosis. As a result, precise segmentation of liver tumor from nonenhanced MRI has become an urgent and challenging task. In this paper, we propose an edge constraint and localization mapping segmentation model (ECLMS) to accurately segment liver tumor from nonenhanced MRI. It consists of two parts: localization network and dual-branch segmentation network. We build the localization network, which generates prior coarse masks to provide position mapping for the segmentation network. This part enhances the ability of the model to localize liver tumor in nonenhanced images. We design a dual-branch segmentation network, where the main decoding branch focuses on the feature representation in the core region of the tumor and the edge decoding branch concentrates on capturing the edge information of the tumor. To improve the ability of the model for capturing detailed features, sSE blocks and dense upward connections are introduced into it. We design the bottleneck multiscale module to construct multiscale feature representations using kernels of different sizes while integrating the location mapping of tumor. The ECLMS model is evaluated on a private nonenhanced MRI dataset that comprises 215 different subjects. The model achieves the best Dice coefficient, precision, and accuracy of 90.23%, 92.25%, and 92.39%, correspondingly. The effectiveness of our model is demonstrated by experiment results, and our model reaches superior results in the segmentation task of nonenhanced liver tumor compared to existing segmentation methods.

DWI-based radiomic signature: potential role for individualized adjuvant chemotherapy in intrahepatic cholangiocarcinoma after partial hepatectomy

Objectives

To develop a diffusion-weighted imaging (DWI) based radiomic signature for predicting early recurrence (ER) (i.e., recurrence within 1 year after surgery), and to explore the potential value for individualized adjuvant chemotherapy.

Methods

A total of 124 patients with intrahepatic cholangiocarcinoma (ICC) were randomly divided into the training (n = 87) and the validation set (n = 37). Radiomic signature was built using radiomic features extracted from DWI with random forest. An integrated radiomic nomogram was constructed with multivariate logistic regression analysis to demonstrate the incremental value of the radiomic signature beyond clinicopathological-radiographic factors. A clinicopathological-radiographic (CPR) model was constructed as a reference.

Results

The radiomic signature showed a comparable discrimination performance for predicting ER to CPR model in the validation set (AUC, 0.753 vs. 0.621, p = 0.274). Integrating the radiomic signature with clinicopathological-radiographic factors further improved prediction performance compared with CPR model, with an AUC of 0.821 (95%CI 0.684–0.959) in the validation set (p = 0.01). The radiomic signature succeeded to stratify patients into distinct survival outcomes according to their risk index of ER, and remained an independent prognostic factor in multivariable analysis (disease-free survival (DFS), p < 0.0001; overall survival (OS), p = 0.029). Furthermore, adjuvant chemotherapy improved prognosis in high-risk patients defined by the radiomic signature (DFS, p = 0.029; OS, p = 0.088) and defined by the nomogram (DFS, p = 0.031; OS, p = 0.023), whereas poor chemotherapy efficacy was detected in low-risk patients.

Conclusions

The preoperative DWI-based radiomic signature could improve prognostic prediction and help to identify ICC patients who may benefit from postoperative adjuvant chemotherapy.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13244-022-01179-7.

The application of artificial intelligence in hepatology: A systematic review

The integration of human and artificial intelligence (AI) in medicine has only recently begun but it has already become obvious that intelligent systems can dramatically improve the management of liver diseases. Big data made it possible to envisage transformative developments of the use of AI for diagnosing, predicting prognosis and treating liver diseases, but there is still a lot of work to do. If we want to achieve the 21^st century digital revolution, there is an urgent need for specific national and international rules, and to adhere to bioethical parameters when collecting data. Avoiding misleading results is essential for the effective use of AI. A crucial question is whether it is possible to sustain, technically and morally, the process of integration between man and machine. We present a systematic review on the applications of AI to hepatology, highlighting the current challenges and crucial issues related to the use of such technologies.

Multiparametric MRI-Based Radiomic Signature for Preoperative Evaluation of Overall Survival in Intrahepatic Cholangiocarcinoma After Partial Hepatectomy

BACKGROUND

The clinical outcomes of patients with intrahepatic cholangiocarcinoma (ICC) after partial hepatectomy remain suboptimal. Identifying patients with poor outcomes before surgery is urgently required.

PURPOSE

To develop a multiparametric magnetic resonance imaging (MRI)-based radiomic signature to evaluate overall survival (OS) preoperatively and to investigate its incremental value for disease stratification.

STUDY TYPE

Retrospective.

SUBJECTS

One hundred and sixty-three patients with pathologically defined ICC, divided into training (N = 115) and validation sets (N = 48).

SEQUENCE

Three-dimensional T1-weighted gradient-echo sequence with and without contrast agent, T2-weighted fast spin-echo sequence, and diffusion-weighted imaging with single-shot echo-planar sequence at 1.5 T or 3.0 T.

ASSESSMENT

OS was defined as the time from the date of surgery to death or last contact. The radiomic signature was built based on the least absolute shrinkage and selection operator regression model. A clinicopathologic-radiographic (CPR) model and a combined model integrating radiomic signature with CPR factors were developed with multivariable Cox regression models.

STATISTICAL TESTS

Harrell's concordance index (C-index) was used to compare the discrimination of different models. Net reclassification index (NRI) and integrated discrimination improvement (IDI) were used to quantify the improvement of prognostic accuracy after adding radiomic signature.

RESULTS

The high-risk patients of death defined by the radiomic signature showed significantly lower OS compared with low-risk patients in validation set (3-year OS 17.1% vs. 56.4%, P < 0.001). Integrating radiomic signature into tumor, node, and metastasis (TNM) staging system significantly improved the prognostic accuracy compared with TNM stage alone (validation set C-index 0.745 vs. 0.649, P = 0.039, NRI improvement 39.9%-43.8%, IDI improvement 16.1%-19.4%). The radiomic signature showed no significant difference of C-index with postoperative CPR model (validation set, 0.698 vs. 0.674, P = 0.752). Incorporating the radiomic signature into CPR model significantly improved prognostic accuracy (NRI improvement 32.5%-34.3%, IDI improvement 8.1%-12.9%).

DATA CONCLUSION

Multiparametric MRI-based radiomic signature is a potential biomarker for preoperative prognostic evaluation of ICC patients.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY: Stage 4.

Diagnostic accuracy of three-dimensional contrast-enhanced ultrasound for focal liver lesions: A protocol for systematic review and meta-analysis

BACKGROUND

Contrast-enhanced ultrasound (CEUS) examination is a well-established technique for this purpose with several unique advantages. It is a real-time technology with high temporal resolution. With its unique ability to detect microvascular perfusion, it helps in better characterization of FLL.[1-4] Three-dimensional (3D) CEUS with quantitative analysis is updated in recent years. 3D-CEUS is a new ultrasonic diagnostic technique, which can observe the nourishing vessels of lesions from multiple angles. Previous studies showed that 3D-CEUS can detect tumor nourishing vessels to differentiate benign from malignant focal liver lesions (FLLs). However, the results of these studies have been contradictory. Therefore, this meta-analysis tested the hypothesis that 3D-CEUS is accurate in distinguishing benign and malignant FLLs.

METHODS

We will search PubMed, Web of Science, Cochrane Library, and Chinese biomedical databases from their inceptions to the April 30, 2021, without language restrictions. Two authors will independently carry out searching literature records, scanning titles and abstracts, full texts, collecting data, and assessing risk of bias. Review Manager 5.2 and Stata14.0 software will be used for data analysis.

RESULTS

This systematic review will determine the accuracy of 3D-CEUS in the differential diagnosis between benign and malignant FLLs.

CONCLUSION

Its findings will provide helpful evidence for the accuracy of 3D-CEUS in the differential diagnosis between benign and malignant FLLs.

SYSTEMATIC REVIEW REGISTRATION

INPLASY202150096.

Accurate Tumor Segmentation via Octave Convolution Neural Network

Three-dimensional (3D) liver tumor segmentation from Computed Tomography (CT) images is a prerequisite for computer-aided diagnosis, treatment planning, and monitoring of liver cancer. Despite many years of research, 3D liver tumor segmentation remains a challenging task. In this paper, we propose an effective and efficient method for tumor segmentation in liver CT images using encoder-decoder based octave convolution networks. Compared with other convolution networks utilizing standard convolution for feature extraction, the proposed method utilizes octave convolutions for learning multiple-spatial-frequency features, thus can better capture tumors with varying sizes and shapes. The proposed network takes advantage of a fully convolutional architecture which performs efficient end-to-end learning and inference. More importantly, we introduce a deep supervision mechanism during the learning process to combat potential optimization difficulties, and thus the model can acquire a much faster convergence rate and more powerful discrimination capability. Finally, we integrate octave convolutions into the encoder-decoder architecture of UNet, which can generate high resolution tumor segmentation in one single forward feeding without post-processing steps. Both architectures are trained on a subset of the LiTS (Liver Tumor Segmentation) Challenge. The proposed approach is shown to significantly outperform other networks in terms of various accuracy measures and processing speed.

Radiomics of Liver Metastases: A Systematic Review

Simple Summary

Patients with liver metastases can be scheduled for different therapies (e.g., chemotherapy, surgery, radiotherapy, and ablation). The choice of the most appropriate treatment should rely on adequate understanding of tumor biology and prediction of survival, but reliable biomarkers are lacking. Radiomics is an innovative approach to medical imaging: it identifies invisible-to-the-human-eye radiological patterns that can predict tumor aggressiveness and patients outcome. We reviewed the available literature to elucidate the role of radiomics in patients with liver metastases. Thirty-two papers were analyzed, mostly (56%) concerning metastases from colorectal cancer. Even if available studies are still preliminary, radiomics provided effective prediction of response to chemotherapy and of survival, allowing more accurate and earlier prediction than standard predictors. Entropy and homogeneity were the radiomic features with the strongest clinical impact. In the next few years, radiomics is expected to give a consistent contribution to the precision medicine approach to patients with liver metastases.

Abstract

Multidisciplinary management of patients with liver metastases (LM) requires a precision medicine approach, based on adequate profiling of tumor biology and robust biomarkers. Radiomics, defined as the high-throughput identification, analysis, and translational applications of radiological textural features, could fulfill this need. The present review aims to elucidate the contribution of radiomic analyses to the management of patients with LM. We performed a systematic review of the literature through the most relevant databases and web sources. English language original articles published before June 2020 and concerning radiomics of LM extracted from CT, MRI, or PET-CT were considered. Thirty-two papers were identified. Baseline higher entropy and lower homogeneity of LM were associated with better survival and higher chemotherapy response rates. A decrease in entropy and an increase in homogeneity after chemotherapy correlated with radiological tumor response. Entropy and homogeneity were also highly predictive of tumor regression grade. In comparison with RECIST criteria, radiomic features provided an earlier prediction of response to chemotherapy. Lastly, texture analyses could differentiate LM from other liver tumors. The commonest limitations of studies were small sample size, retrospective design, lack of validation datasets, and unavailability of univocal cut-off values of radiomic features. In conclusion, radiomics can potentially contribute to the precision medicine approach to patients with LM, but interdisciplinarity, standardization, and adequate software tools are needed to translate the anticipated potentialities into clinical practice.

The application of texture quantification in hepatocellular carcinoma using CT and MRI: a review of perspectives and challenges

Recently, radiomic texture quantification of tumors has received much attention from radiologists, scientists, and stakeholders because several results have shown the feasibility of using the technique to diagnose and manage oncological conditions. In patients with hepatocellular carcinoma, radiomics has been applied in all stages of tumor evaluation, including diagnosis and characterization of the genotypic behavior of the tumor, monitoring of treatment responses and prediction of various clinical endpoints. It is also useful in selecting suitable candidates for specific treatment strategies. However, the clinical validation of hepatocellular carcinoma radiomics is limited by challenges in imaging protocol and data acquisition parameters, challenges in segmentation techniques, dimensionality reduction, and modeling methods. Identification of the best segmentation and optimal modeling methods, as well as texture features most stable to imaging protocol variability would go a long way in harmonizing HCC radiomics for personalized patient care. This article reviews the process of HCC radiomics, its clinical applications, associated challenges, and current optimization strategies.

Focal liver lesions: interobserver and intraobserver agreement of three-dimensional contrast-enhanced ultrasound-assisted volume measurements

PURPOSE

This study was conducted to assess the interobserver and intraobserver agreement of three-dimensional contrast-enhanced ultrasound (3D-CEUS) volume calculations of focal liver lesions (FLLs).

METHODS

Thirty-nine patients (15 men and 24 women; mean age, 55.4 years) with 39 FLLs (mean size, 3.1±1.8 cm; size range, 1 to 8 cm) prospectively underwent 3D-CEUS. Four readers calculated the volume of each lesion in an independent and blinded fashion in two separate sessions by means of a semi-automatic, commercially available proprietary software. The differences in lesion volumes (cm3) among sessions and readers were assessed using the Mann-Whitney U test and the Kruskal-Wallis test. Bland-Altman analysis was also performed. Intraclass correlation coefficients (ICCs) with 95% confidence intervals (95% CIs) were calculated. The statistical significance level was set at P<0.05.

RESULTS

Among readers, there were no statistically significant differences in the first (P=0.953) and second (P=0.592) reading sessions for volume calculations of the 39 FLLs, with almost perfect inter-reader agreement (ICC values of the first reading session, 0.996; 95% CI, 0.992 to 0.998 and ICC value of the second reading session, 0.994; 95% CI, 0.990 to 0.997, respectively). For each of the four readers, there were no significant differences in volume calculations between the two sessions (P=0.503-0.924), and the intrareader agreement was almost perfect for each reader (R1: ICC, 0.995; 95% CI, 0.991 to 0.998; R2: ICC, 0.995; 95% CI, 0.988 to 0.997; R3: ICC, 0.996; 95% CI, 0.992 to 0.998; R4: ICC, 0.985; 95% CI, 0.971 to 0.992).

CONCLUSION

3D-CEUS volume calculations provided consistent measurements across different readers with almost perfect intrareader agreement.

Semiautomatic Segmentation and Radiomics for Dual-Energy CT: A Pilot Study to Differentiate Benign and Malignant Hepatic Lesions

OBJECTIVE. This study assessed a machine learning-based dual-energy CT (DECT) tumor analysis prototype for semiautomatic segmentation and radiomic analysis of benign and malignant liver lesions seen on contrast-enhanced DECT. MATERIALS AND METHODS. This institutional review board-approved study included 103 adult patients (mean age, 65 ± 15 [SD] years; 53 men, 50 women) with benign (60/103) or malignant (43/103) hepatic lesions on contrast-enhanced dual-source DECT. Most malignant lesions were histologically proven; benign lesions were either stable on follow-up CT or had characteristic benign features on MRI. Low- and high-kilovoltage datasets were deidentified, exported offline, and processed with the DECT tumor analysis for semiautomatic segmentation of the volume and rim of each liver lesion. For each segmentation, contrast enhancement and iodine concentrations as well as radiomic features were derived for different DECT image series. Statistical analyses were performed to determine if DECT tumor analysis and radiomics can differentiate benign from malignant liver lesions. RESULTS. Normalized iodine concentration and mean iodine concentration in the benign and malignant lesions were significantly different (p < 0.0001-0.0084; AUC, 0.695-0.856). Iodine quantification and radiomic features from lesion rims (AUC, ≤ 0.877) had higher accuracy for differentiating liver lesions compared with the values from lesion volumes (AUC, ≤ 0.856). There was no difference in the accuracies of DECT iodine quantification (AUC, 0.91) and radiomics (AUC, 0.90) for characterizing liver lesions. CONCLUSION. DECT radiomics were more accurate than iodine quantification for differentiating solid benign and malignant hepatic lesions.

QIN Benchmarks for Clinical Translation of Quantitative Imaging Tools

The Quantitative Imaging Network of the National Cancer Institute is in its 10th year of operation, and research teams within the network are developing and validating clinical decision support software tools to measure or predict the response of cancers to various therapies. As projects progress from development activities to validation of quantitative imaging tools and methods, it is important to evaluate the performance and clinical readiness of the tools before committing them to prospective clinical trials. A variety of tests, including special challenges and tool benchmarking, have been instituted within the network to prepare the quantitative imaging tools for service in clinical trials. This article highlights the benchmarking process and provides a current evaluation of several tools in their transition from development to validation.

Liver tumor segmentation in CT volumes using an adversarial densely connected network

Background

Malignant liver tumor is one of the main causes of human death. In order to help physician better diagnose and make personalized treatment schemes, in clinical practice, it is often necessary to segment and visualize the liver tumor from abdominal computed tomography images. Due to the large number of slices in computed tomography sequence, developing an automatic and reliable segmentation method is very favored by physicians. However, because of the noise existed in the scan sequence and the similar pixel intensity of liver tumors with their surrounding tissues, besides, the size, position and shape of tumors also vary from one patient to another, automatic liver tumor segmentation is still a difficult task.

Results

We perform the proposed algorithm to the Liver Tumor Segmentation Challenge dataset and evaluate the segmentation results. Experimental results reveal that the proposed method achieved an average Dice score of 68.4% for tumor segmentation by using the designed network, and ASD, MSD, VOE and RVD improved from 27.8 to 21, 147 to 124, 0.52 to 0.46 and 0.69 to 0.73, respectively after performing adversarial training strategy, which proved the effectiveness of the proposed method.

Conclusions

The testing results show that the proposed method achieves improved performance, which corroborated the adversarial training based strategy can achieve more accurate and robustness results on liver tumor segmentation task.

Vol-PACT: A Foundation for the NIH Public-Private Partnership That Supports Sharing of Clinical Trial Data for the Development of Improved Imaging Biomarkers in Oncology

PURPOSE

To develop a public-private partnership to study the feasibility of a new approach in collecting and analyzing clinically annotated imaging data from landmark phase III trials in advanced solid tumors.

PATIENTS AND METHODS

The collection of clinical trials fulfilled the following inclusion criteria: completed randomized trials of > 300 patients, highly measurable solid tumors (non-small-cell lung cancer, colorectal cancer, renal cell cancer, and melanoma), and required sponsor and institutional review board sign-offs. The new approach in analyzing computed tomography scans was to transfer to an academic image analysis laboratory, draw contours semi-automatically by using in-house-developed algorithms integrated into the open source imaging platform Weasis, and perform serial volumetric measurement.

RESULTS

The median duration of contracting with five sponsors was 12 months. Ten trials in 7,085 patients that covered 12 treatment regimens across 20 trial arms were collected. To date, four trials in 3,954 patients were analyzed. Source imaging data were transferred to the academic core from 97% of trial patients (n = 3,837). Tumor imaging measurements were extracted from 82% of transferred computed tomography scans (n = 3,162). Causes of extraction failure were nonmeasurable disease (n = 392), single imaging time point (n = 224), and secondary captured images (n = 59). Overall, clinically annotated imaging data were extracted in 79% of patients (n = 3,055), and the primary trial end point analysis in each trial remained representative of each original trial end point.

CONCLUSION

The sharing and analysis of source imaging data from large randomized trials is feasible and offer a rich and reusable, but largely untapped, resource for future research on novel trial-level response and progression imaging metrics.

Dynamic Regulation of Level Set Parameters Using 3D Convolutional Neural Network for Liver Tumor Segmentation

Segmentation of liver tumors plays an important role in the choice of therapeutic strategies for liver disease and treatment monitoring. In this paper, we generalize the process of a level set with a novel algorithm of dynamic regulation to energy functional parameters. The presented method is fully automatic once the tumor has been detected. First, a 3D convolutional neural network with dense layers for classification is used to estimate current contour location relative to the tumor boundary. Second, the output 3D CNN probabilities can dynamically regulate parameters of the level set functional over the process of segmentation. Finally, for full automation, appropriate initializations and local window size are generated based on the current contour position probabilities. We demonstrate the proposed method on the dataset of MICCAI 2017 LiTS Challenge and 3DIRCADb that include low contrast and heterogeneous tumors as well as noisy images. To illustrate the strength of our method, we evaluated it against the state-of-the-art methods. Compared with the level set framework with fixed parameters, our method performed better significantly with an average DICE improvement of 0.15. We also analyzed a challenging dataset 3DIRCADb of tumors and obtained a competitive DICE of 0.85 ± 0.06 with the proposed method.

Management of computed tomography scan detected hemothorax in blunt chest trauma: What computed tomography scan measurements say?

AIM

To investigate the hemothorax size for which tube thoracostomy is necessary.

METHODS

Over a 5-year period, we included all patients who were admitted with blunt chest trauma to our level 1 trauma center. Focus was placed on identifying the hemothorax size requiring tube thoracostomy.

RESULTS

A total number of 274 hemothoraces were studied. All patients with hemothoraces measuring above 3 cm received a chest tube. The 50% predicted probability of tube thoracostomy was 2 cm. Pneumothorax was associated with odds of receiving tube thoracostomy for hemothoraces below 2 cm (Odds Ratio: 4.967, 95%CI: 2.225-11.097, P < 0.0001).

CONCLUSION

All patients with a hemothorax size greater than 3% underwent tube thoracostomy. Prospective studies are warranted to elucidate the clinical outcome of patients with smaller hemothoraces.

Comparison of tumor size assessments in tumor growth inhibition-overall survival models with second-line colorectal cancer data from the VELOUR study

PURPOSE

To compare lesion-level and volumetric measures of tumor burden with sum of the longest dimensions (SLD) of target lesions on overall survival (OS) predictions using time-to-growth (TTG) as predictor.

METHODS

Tumor burden and OS data from a phase 3 randomized study of second-line FOLFIRI ± aflibercept in metastatic colorectal cancer were available for 918 patients out of 1216 treated (75%). A TGI model that estimates TTG was fit to the longitudinal tumor size data (nonlinear mixed effect modeling) to estimate TTG with: SLD, sum of the measured lesion volumes (SV), individual lesion diameters (ILD), or individual lesion volumes (ILV). A parametric OS model was built with TTG estimates and assessed for prediction of the hazard ratio (HR) for survival.

RESULTS

Individual lesions had consistent dynamics within individuals. Between-lesion variability in rate constants was lower (typically < 27% CV) than inter-patient variability (typically > 50% CV). Estimates of TTG were consistent (around 12 weeks) across tumor size assessments. TTG was highly significant in a log-logistic parametric model of OS (median over 12 months). When individual lesions were considered, TTG of the fastest progressing lesions best predicted OS. TTG obtained from the lesion-level analyses were slightly better predictors of OS than estimates from the sums, with ILV marginally better than ILD. All models predicted VELOUR HR equally well and all predicted study success.

CONCLUSION

This analysis revealed consistent TGI profiles across all tumor size assessments considered. TTG predicted VELOUR HR when based on any of the tumor size measures.

Automatic segmentation of liver tumors from multiphase contrast-enhanced CT images based on FCNs

This paper presents a novel, fully automatic approach based on a fully convolutional network (FCN) for segmenting liver tumors from CT images. Specifically, we designed a multi-channel fully convolutional network (MC-FCN) to segment liver tumors from multiphase contrast-enhanced CT images. Because each phase of contrast-enhanced data provides distinct information on pathological features, we trained one network for each phase of the CT images and fused their high-layer features together. The proposed approach was validated on CT images taken from two databases: 3Dircadb and JDRD. In the case of 3Dircadb, using the FCN, the mean ratios of the volumetric overlap error (VOE), relative volume difference (RVD), average symmetric surface distance (ASD), root mean square symmetric surface distance (RMSD) and maximum symmetric surface distance (MSSD) were 15.6±4.3%, 5.8±3.5%, 2.0±0.9%, 2.9±1.5mm, 7.1±6.2mm, respectively. For JDRD, using the MC-FCN, the mean ratios of VOE, RVD, ASD, RMSD, and MSSD were 8.1±4.5%, 1.7±1.0%, 1.5±0.7%, 2.0±1.2mm, 5.2±6.4mm, respectively. The test results demonstrate that the MC-FCN model provides greater accuracy and robustness than previous methods.

Volumetry of low-contrast liver lesions with CT: Investigation of estimation uncertainties in a phantom study

PURPOSE

To evaluate the performance of lesion volumetry in hepatic CT as a function of various imaging acquisition parameters.

METHODS

An anthropomorphic abdominal phantom with removable liver inserts was designed for this study. Two liver inserts, each containing 19 synthetic lesions with varying diameter (6-40 mm), shape, contrast (10-65 HU), and both homogenous and mixed-density were designed to have background and lesion CT values corresponding to arterial and portal-venous phase imaging, respectively. The two phantoms were scanned using two commercial CT scanners (GE 750 HD and Siemens Biograph mCT) across a set of imaging protocols (four slice thicknesses, three effective mAs, two convolution kernels, two pitches). Two repeated scans were collected for each imaging protocol. All scans were analyzed using a matched-filter estimator for volume estimation, resulting in 6080 volume measurements across all of the synthetic lesions in the two liver phantoms. A subset of portal venous phase scans was also analyzed using a semi-automatic segmentation algorithm, resulting in about 900 additional volume measurements. Lesions associated with large measurement error (quantified by root mean square error) for most imaging protocols were considered not measurable by the volume estimation tools and excluded for the statistical analyses. Imaging protocols were grouped into distinct imaging conditions based on ANOVA analysis of factors for repeatability testing. Statistical analyses, including overall linearity analysis, grouped bias analysis with standard deviation evaluation, and repeatability analysis, were performed to assess the accuracy and precision of the liver lesion volume biomarker.

RESULTS

Lesions with lower contrast and size ≤10 mm were associated with higher measurement error and were excluded from further analysis. Lesion size, contrast, imaging slice thickness, dose, and scanner were found to be factors substantially influencing volume estimation. Twenty-four distinct repeatable imaging conditions were determined as protocols for each scanner with a fixed slice thickness and dose. For the matched-filter estimation approach, strong linearity was observed for all imaging data for lesions ≥20 mm. For the Siemens scanner with 50 mAs effective dose at 0.6 mm slice thickness, grouped bias was about -10%. For all other repeatable imaging conditions with both scanners, grouped biases were low (-3%-3%). There was a trend of increasing standard deviation with decreasing dose. For each fixed dose, the standard deviations were similar among the three larger slice thicknesses (1.25, 2.5, 5 mm for GE, 1.5, 3, 5 mm for Siemens). Repeatability coefficients ranged from about 8% to 75% and showed similar trend to grouped standard deviation. For the segmentation approach, the results led to similar conclusions for both lesion characteristic factors and imaging factors but with increasing magnitude in all the error metrics assessed.

CONCLUSIONS

Results showed that liver lesion volumetry was strongly dependent on lesion size, contrast, acquisition dose, and their interactions. The overall performances were similar for images reconstructed with larger slice thicknesses, clinically used pitches, kernels, and doses. Conditions that yielded repeatable measurements were identified and they agreed with the Quantitative Imaging Biomarker Alliance's (QIBA) profile requirements in general. The authors' findings also suggest potential refinements to these guidelines for the tumor volume biomarker, especially for soft-tissue lesions.

Adaptive local window for level set segmentation of CT and MRI liver lesions

We propose a novel method, the adaptive local window, for improving level set segmentation technique. The window is estimated separately for each contour point, over iterations of the segmentation process, and for each individual object. Our method considers the object scale, the spatial texture, and the changes of the energy functional over iterations. Global and local statistics are considered by calculating several gray level co-occurrence matrices. We demonstrate the capabilities of the method in the domain of medical imaging for segmenting 233 images with liver lesions. To illustrate the strength of our method, those lesions were screened by either Computed Tomography or Magnetic Resonance Imaging. Moreover, we analyzed images using three different energy models. We compared our method to a global level set segmentation, to a local framework that uses predefined fixed-size square windows and to a local region-scalable fitting model. The results indicate that our proposed method outperforms the other methods in terms of agreement with the manual marking and dependence on contour initialization or the energy model used. In case of complex lesions, such as low contrast lesions, heterogeneous lesions, or lesions with a noisy background, our method shows significantly better segmentation with an improvement of 0.25 ± 0.13 in Dice similarity coefficient, compared with state of the art fixed-size local windows (Wilcoxon, p < 0.001).

A Response Assessment Platform for Development and Validation of Imaging Biomarkers in Oncology

Quantitative imaging biomarkers are increasingly used in both oncology clinical trials and clinical practice aid evaluation of tumor response to novel therapies. To obtain these biomarkers, and to ensure smooth clinical adoption once they have been validated, it is critical to develop reliable computer-aided methods and a workflow-efficient imaging platform for integration in research and clinical settings. Here, we present a volumetric response assessment system developed based on an open-source image-viewing platform (WEASIS). Our response assessment system is designed using the Model–View–Controller concept, and it offers standard image-viewing and -manipulation functions, efficient tumor segmentation and quantification algorithms, and a reliable database containing tumor segmentation and measurement results. This prototype system is currently used in our research laboratory to foster the development and validation of new quantitative imaging biomarkers including the volumetric computed tomography technique as a more accurate and early assessment method of solid tumor response to targeted therapy and immunotherapy.