Tumor Cell Load and Heterogeneity Estimation From Diffusion-Weighted MRI Calibrated With Histological Data: an Example From Lung Cancer

Imaging-based characterization of tumoral heterogeneity for personalized cancer treatment

With personalized tumor therapy, understanding and addressing the heterogeneity of malignant tumors is becoming increasingly important. Heterogeneity can be found within one lesion (intralesional) and between several tumor lesions emerging from one primary tumor (interlesional). The heterogeneous tumor cells may show a different response to treatment due to their biology, which in turn influences the outcome of the affected patients and the choice of therapeutic agents. Therefore, both intra- and interlesional heterogeneity should be addressed at the diagnostic stage. While genetic and biological heterogeneity are important parameters in molecular tumor characterization and in histopathology, they are not yet addressed routinely in medical imaging. This article summarizes the recently established markers for tumor heterogeneity in imaging as well as heterogeneous/mixed response to therapy. Furthermore, a look at emerging markers is given. The ultimate goal of this overview is to provide comprehensive understanding of tumor heterogeneity and its implications for radiology and for communication with interdisciplinary teams in oncology. KEY POINTS::   · Tumor heterogeneity can be described within one lesion (intralesional) or between several lesions (interlesional).. · The heterogeneous biology of tumor cells can lead to a mixed therapeutic response and should be addressed in diagnostics and the therapeutic regime.. · Quantitative image diagnostics can be enhanced using AI, improved histopathological methods, and liquid profiling in the future..

Advanced Diffusion-Weighted MRI for Cancer Microstructure Assessment in Body Imaging, and Its Relationship With Histology

Diffusion-weighted magnetic resonance imaging (DW-MRI) aims to disentangle multiple biological signal sources in each imaging voxel, enabling the computation of innovative maps of tissue microstructure. DW-MRI model development has been dominated by brain applications. More recently, advanced methods with high fidelity to histology are gaining momentum in other contexts, for example, in oncological applications of body imaging, where new biomarkers are urgently needed. The objective of this article is to review the state-of-the-art of DW-MRI in body imaging (ie, not including the nervous system) in oncology, and to analyze its value as compared to reference colocalized histology measurements, given that demonstrating the histological validity of any new DW-MRI method is essential. In this article, we review the current landscape of DW-MRI techniques that extend standard apparent diffusion coefficient (ADC), describing their acquisition protocols, signal models, fitting settings, microstructural parameters, and relationship with histology. Preclinical, clinical, and in/ex vivo studies were included. The most used techniques were intravoxel incoherent motion (IVIM; 36.3% of used techniques), diffusion kurtosis imaging (DKI; 16.7%), vascular, extracellular, and restricted diffusion for cytometry in tumors (VERDICT; 13.3%), and imaging microstructural parameters using limited spectrally edited diffusion (IMPULSED; 11.7%). Another notable category of techniques relates to innovative b-tensor diffusion encoding or joint diffusion-relaxometry. The reviewed approaches provide histologically meaningful indices of cancer microstructure (eg, vascularization/cellularity) which, while not necessarily accurate numerically, may still provide useful sensitivity to microscopic pathological processes. Future work of the community should focus on improving the inter-/intra-scanner robustness, and on assessing histological validity in broader contexts. LEVEL OF EVIDENCE: NA TECHNICAL EFFICACY: Stage 2.

Nuclei segmentation with point annotations from pathology images via self-supervised learning and co-training

Nuclei segmentation is a crucial task for whole slide image analysis in digital pathology. Generally, the segmentation performance of fully-supervised learning heavily depends on the amount and quality of the annotated data. However, it is time-consuming and expensive for professional pathologists to provide accurate pixel-level ground truth, while it is much easier to get coarse labels such as point annotations. In this paper, we propose a weakly-supervised learning method for nuclei segmentation that only requires point annotations for training. First, coarse pixel-level labels are derived from the point annotations based on the Voronoi diagram and the k-means clustering method to avoid overfitting. Second, a co-training strategy with an exponential moving average method is designed to refine the incomplete supervision of the coarse labels. Third, a self-supervised visual representation learning method is tailored for nuclei segmentation of pathology images that transforms the hematoxylin component images into the H&E stained images to gain better understanding of the relationship between the nuclei and cytoplasm. We comprehensively evaluate the proposed method using two public datasets. Both visual and quantitative results demonstrate the superiority of our method to the state-of-the-art methods, and its competitive performance compared to the fully-supervised methods. Codes are available at https://github.com/hust-linyi/SC-Net.

Multi-classification approach for lung nodule detection and classification with proposed texture feature in X-ray images

Lung cancer is a widespread type of cancer around the world. It is, moreover, a lethal type of tumor. Nevertheless, analysis signifies that earlier recognition of lung cancer considerably develops the possibilities of survival. By deploying X-rays and Computed Tomography (CT) scans, radiologists could identify hazardous nodules at an earlier period. However, when more citizens adopt these diagnoses, the workload rises for radiologists. Computer Assisted Diagnosis (CAD)-based detection systems can identify these nodules automatically and could assist radiologists in reducing their workloads. However, they result in lower sensitivity and a higher count of false positives. The proposed work introduces a new approach for Lung Nodule (LN) detection. At first, Histogram Equalization (HE) is done during pre-processing. As the next step, improved Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH) based segmentation is done. Then, the characteristics, including "Gray Level Run-Length Matrix (GLRM), Gray Level Co-Occurrence Matrix (GLCM), and the proposed Local Vector Pattern (LVP)," are retrieved. These features are then categorized utilizing an optimized Convolutional Neural Network (CNN) and itdetectsnodule or non-nodule images. Subsequently, Long Short-Term Memory (LSTM) is deployed to categorize nodule types (benign, malignant, or normal). The CNN weights are fine-tuned by the Chaotic Population-based Beetle Swarm Algorithm (CP-BSA). Finally, the superiority of the proposed approach is confirmed across various measures. The developed approach has exhibited a high precision value of 0.9575 for the best case scenario, and high sensitivity value of 0.9646 for the mean case scenario. The superiority of the proposed approach is confirmed across various measures.

Suspicious lung lesions for malignancy: the lesion-to-spinal cord signal intensity ratio in T2WI and DWI–MRI versus PET/CT; a prospective pathologic correlated study with accuracy and ROC analyses

Background

The multi-detector computed tomography (MDCT) and tissue biopsy are the gold standards for the evaluation of lung malignancies. However, there is a wide range of pulmonary indeterminate lesions that could mimic lung cancer. Furthermore, the diagnosis of malignancy could be challenging if the lesion is small and early presenting by a part-solid or ground-glass nodule or if surrounded by parenchymal lung reaction with consolidation and atelectasis. The previous literature focused on the role of diffusion-weighted image–magnetic resonance imaging (DWI) and the apparent diffusion coefficient (ADC) mapping in the evaluation of lung malignancy. A novel quantitative T2 assessment is provided and tested in this study. Aim of the work: To evaluate the accuracy of specific non-invasive quantitative magnetic resonance imaging (MRI) parameters in the characterization of suspicious lung lesions and the discrimination between the malignant and benign nature. They included the lesion-to-spinal cord signal intensity ratio in T2-WI and DWI as well as the mean and minimum apparent diffusion coefficient (ADC) values. This is performed using a prospective pathologic correlated study with receiver-operating characteristics (ROC) analysis and comparison with positron emission tomography (PET-CT) accuracy results.

Results

This study was prospectively performed during the period between June/2021 and June/2022. It was conducted on 43 suspicious lung lesions detected by MDCT. MRI and PET/CT examinations were performed for all patients, and the results were compared to the final diagnosis obtained after biopsy and pathological assessment, using the statistical tests of significance and P-value. Cutoff values were automatically calculated, and then, accuracy tests and ROC analyses were performed. Five expert radiologists and a single consulting pulmonologist participated in this study. The inter-rater reliability ranges between good and excellent with the intra-class correlation coefficient (ICC) ranging between 0.85 and 0.94. In T2-WI: The lesion-to-spinal cord signal intensity ratio was higher in the malignant group (1.35 ± 0.29) than in the benign group (0.88 ± 0.40), (P < 0.001). At the estimated cutoff value (> 1), the sensitivity was 96.43%, the specificity was 80.00%, and AUC = 0.86. In b500-DWI: The lesion-to-spinal cord signal intensity ratio was higher in the malignant group (0.70–1.35) than in the benign group (0.20–0.70) (P < 0.001). At the estimated cutoff value (> 0.7), the sensitivity was 71.43%, the specificity was 86.67%, and AUC = 0.86. The mean and minimum ADC values were lower in the malignant group (0.6–1.3 and 0.3–1.1 × 10–3 mm2/s) than the benign group (1–1.6 and 0.7–1.4 × 10–3 mm2/s), (P < 0.01 and < 0.001, respectively). At their estimated cutoff values (≤ 1.2 and ≤ 0.9 × 10–3 mm2/s, respectively), the sensitivity was (71.4 and 85.7%), specificity was (83.3 and 66.7%), respectively, and AUC = 0.77 for both. PET/CT had 96.4% sensitivity, 92.3% specificity, and AUC = 0.94.

Conclusions

PET-CT remains the most specific and sensitive tool for the differentiation between benign and malignant lesions. The lesion-to-cord signal intensity ratios in T2WI and DWI-MRI and to a minor extent the mean and minimum ADC values are also considered good parameters for this differentiation based on their accurate statistical results, particularly if PET/CT was not available or feasible. The study added to the previous literature a novel quantitative T2WI assessment which proved a high sensitivity equal to PET/CT with a lower but a good specificity. The availability, expertise, time factor, and patients' tolerance remain challenging factors for MRI.

Lung Nodule Detection via Optimized Convolutional Neural Network: Impact of Improved Moth Flame Algorithm

Lung cancer is a high-risk disease that affects people all over the world, and lung nodules are the most common sign of early lung cancer. Since early identification of lung cancer can considerably improve a lung scanner patient's chances of survival, an accurate and efficient nodule detection system can be essential. Automatic lung nodule recognition decreases radiologists' effort, as well as the risk of misdiagnosis and missed diagnoses. Hence, this article developed a new lung nodule detection model with four stages like "Image pre-processing, segmentation, feature extraction and classification". In this processes, pre-processing is the first step, in which the input image is subjected to a series of operations. Then, the "Otsu Thresholding model" is used to segment the pre-processed pictures. Then in the third stage, the LBP features are retrieved that is then classified via optimized Convolutional Neural Network (CNN). In this, the activation function and convolutional layer count of CNN is optimally tuned via a proposed algorithm known as Improved Moth Flame Optimization (IMFO). At the end, the betterment of the scheme is validated by carrying out analysis in terms of certain measures. Especially, the accuracy of the proposed work is 6.85%, 2.91%, 1.75%, 0.73%, 1.83%, as well as 4.05% superior to the extant SVM, KNN, CNN, MFO, WTEEB as well as GWO + FRVM methods respectively.

Deep learning characterization of brain tumours with diffusion weighted imaging

Glioblastoma multiforme (GBM) is one of the most deadly forms of cancer. Methods of characterizing these tumours are valuable for improving predictions of their progression and response to treatment. A mathematical model called the proliferation-invasion (PI) model has been used extensively in the literature to model the growth of these tumours, though it relies on known values of two key parameters: the tumour cell diffusivity and proliferation rate. Unfortunately, these parameters are difficult to estimate in a patient-specific manner, making personalized tumour forecasting challenging. In this paper, we develop and apply a deep learning model capable of making accurate estimates of these key GBM-characterizing parameters while simultaneously producing a full prediction of the tumour progression curve. Our method uses two sets of multi sequence MRI in order to produce estimations and relies on a preprocessing pipeline which includes brain tumour segmentation and conversion to tumour cellularity. We first apply our deep learning model to synthetic tumours to showcase the model's capabilities and identify situations where prediction errors are likely to occur. We then apply our model to a clinical dataset consisting of five patients diagnosed with GBM. For all patients, we derive evidence-based estimates for each of the PI model parameters and predictions for the future progression of the tumour, along with estimates of the parameter uncertainties. Our work provides a new, easily generalizable method for the estimation of patient-specific tumour parameters, which can be built upon to aid physicians in designing personalized treatments.

Whole-lesion histogram analysis of multiple diffusion metrics for differentiating lung cancer from inflammatory lesions

Background

Whole-lesion histogram analysis can provide comprehensive assessment of tissues by calculating additional quantitative metrics such as skewness and kurtosis; however, few studies have evaluated its value in the differential diagnosis of lung lesions.

Purpose

To compare the diagnostic performance of conventional diffusion-weighted imaging (DWI), intravoxel incoherent motion (IVIM) magnetic resonance imaging (MRI) and diffusion kurtosis imaging (DKI) in differentiating lung cancer from focal inflammatory lesions, based on whole-lesion volume histogram analysis.

Methods

Fifty-nine patients with solitary pulmonary lesions underwent multiple b-values DWIs, which were then postprocessed using mono-exponential, bi-exponential and DKI models. Histogram parameters of the apparent diffusion coefficient (ADC), true diffusivity (D), pseudo-diffusion coefficient (D*), and perfusion fraction (f), apparent diffusional kurtosis (K_app) and kurtosis-corrected diffusion coefficient (D_app) were calculated and compared between the lung cancer and inflammatory lesion groups. Receiver operating characteristic (ROC) curves were constructed to evaluate the diagnostic performance.

Results

The ADC^mean, ADC^median, D ^mean and D ^median values of lung cancer were significantly lower than those of inflammatory lesions, while the ADC^skewness, K_app ^mean, K_app ^median, K_app ^SD, K_app ^kurtosis and D_app ^skewness values of lung cancer were significantly higher than those of inflammatory lesions (all p < 0.05). ADC^skewness (p = 0.019) and D ^median (p = 0.031) were identified as independent predictors of lung cancer. D ^median showed the best performance for differentiating lung cancer from inflammatory lesions, with an area under the ROC curve of 0.777. Using a D ^median of 1.091 × 10^-3 mm²/s as the optimal cut-off value, the sensitivity, specificity, positive predictive value and negative predictive value were 69.23%, 85.00%, 90.00% and 58.62%, respectively.

Conclusions

Whole-lesion histogram analysis of DWI, IVIM and DKI parameters is a promising approach for differentiating lung cancer from inflammatory lesions, and D ^median shows the best performance in the differential diagnosis of solitary pulmonary lesions.

A proof-of-concept pipeline to guide evaluation of tumor tissue perfusion by dynamic contrast-agent imaging: Direct simulation and inverse tracer-kinetic procedures

Dynamic contrast-enhanced (DCE) perfusion imaging has shown great potential to non-invasively assess cancer development and its treatment by their characteristic tissue signatures. Different tracer kinetics models are being applied to estimate tissue and tumor perfusion parameters from DCE perfusion imaging. The goal of this work is to provide an in silico model-based pipeline to evaluate how these DCE imaging parameters may relate to the true tissue parameters. As histology data provides detailed microstructural but not functional parameters, this work can also help to better interpret such data. To this aim in silico vasculatures are constructed and the spread of contrast agent in the tissue is simulated. As a proof of principle we show the evaluation procedure of two tracer kinetic models from in silico contrast-agent perfusion data after a bolus injection. Representative microvascular arterial and venous trees are constructed in silico. Blood flow is computed in the different vessels. Contrast-agent input in the feeding artery, intra-vascular transport, intra-extravascular exchange and diffusion within the interstitial space are modeled. From this spatiotemporal model, intensity maps are computed leading to in silico dynamic perfusion images. Various tumor vascularizations (architecture and function) are studied and show spatiotemporal contrast imaging dynamics characteristic of in vivo tumor morphotypes. The Brix II also called 2CXM, and extended Tofts tracer-kinetics models common in DCE imaging are then applied to recover perfusion parameters that are compared with the ground truth parameters of the in silico spatiotemporal models. The results show that tumor features can be well identified for a certain permeability range. The simulation results in this work indicate that taking into account space explicitly to estimate perfusion parameters may lead to significant improvements in the perfusion interpretation of the current tracer-kinetics models.

Correlation between PD-L1 Expression of Non-Small Cell Lung Cancer and Data from IVIM-DWI Acquired during Magnetic Resonance of the Thorax: Preliminary Results

This study aims to investigate the correlation between intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) parameters in magnetic resonance imaging (MRI) and programmed death-ligand 1 (PD-L1) expression in non-small cell lung cancer (NSCLC). Twenty-one patients diagnosed with stage III NSCLC from April 2021 to April 2022 were included. The tumors were distinguished into two groups: no PD-L1 expression (<1%), and positive PD-L1 expression (≥1%). Conventional MRI and IVIM-DWI sequences were acquired with a 1.5-T system. Both fixed-size ROIs and freehand segmentations of the tumors were evaluated, and the data were analyzed through a software using four different algorithms. The diffusion (D), pseudodiffusion (D*), and perfusion fraction (pf) were obtained. The correlation between IVIM parameters and PD-L1 expression was studied with Pearson correlation coefficient. The Wilcoxon−Mann−Whitney test was used to study IVIM parameter distributions in the two groups. Twelve patients (57%) had PD-L1 ≥1%, and 9 (43%) <1%. There was a statistically significant correlation between D* values and PD-L1 expression in images analyzed with algorithm 0, for fixed-size ROIs (189.2 ± 65.709 µm²/s × 104 in no PD-L1 expression vs. 122.0 ± 31.306 µm²/s × 104 in positive PD-L1 expression, p = 0.008). The values obtained with algorithms 1, 2, and 3 were not significantly different between the groups. The IVIM-DWI MRI parameter D* can reflect PD-L1 expression in NSCLC.

A comparison study of monoexponential and fractional order calculus diffusion models and 18F-FDG PET in differentiating benign and malignant solitary pulmonary lesions and their pathological types

Objective

To evaluate the application value of monoexponential, fractional order calculus (FROC) diffusion models and PET imaging to distinguish between benign and malignant solitary pulmonary lesions (SPLs) and malignant SPLs with different pathological types and explore the correlation between each parameter and Ki67 expression.

Methods

A total of 112 patients were enrolled in this study. Prior to treatment, all patients underwent a dedicated thoracic ¹⁸F-FDG PET/MR examination. Five parameters [including apparent diffusion coefficient (ADC) derived from the monoexponential model; diffusion coefficient (D), a microstructural quantity (μ), and fractional order parameter (β) derived from the FROC model and maximum standardized uptake value (SUVmax) derived from PET] were compared between benign and malignant SPLs and different pathological types of malignant SPLs. Independent sample t test, Mann-Whitney U test, DeLong test and receiver operating characteristic (ROC) curve analysis were used for statistical evaluation. Pearson correlation analysis was used to calculate the correlations between Ki-67 and ADC, D, μ, β, and SUVmax.

Results

The ADC and D values were significantly higher and the μ and SUVmax values were significantly lower in the benign group [1.57 (1.37, 2.05) μm²/ms, 1.59 (1.52, 1.72) μm²/ms, 5.06 (3.76, 5.66) μm, 5.15 ± 2.60] than in the malignant group [1.32 (1.03, 1.51) μm²/ms, 1.43 (1.29, 1.52) μm²/ms, 7.06 (5.87, 9.45) μm, 9.85 ± 4.95]. The ADC, D and β values were significantly lower and the μ and SUVmax values were significantly higher in the squamous cell carcinoma (SCC) group [1.29 (0.66, 1.42) μm²/ms, 1.32 (1.02, 1.42) μm²/ms, 0.63 ± 0.10, 9.40 (7.76, 15.38) μm, 11.70 ± 5.98] than in the adenocarcinoma (AC) group [1.40 (1.28, 1.67) μm²/ms, 1.52 (1.44, 1.64) μm²/ms, 0.70 ± 0.10, 5.99 (4.54, 6.87) μm, 8.76 ± 4.18]. ROC curve analysis showed that for a single parameter, μ exhibited the best AUC value in discriminating between benign and malignant SPLs groups and AC and SCC groups (AUC = 0.824 and 0.911, respectively). Importantly, the combination of monoexponential, FROC models and PET imaging can further improve diagnostic performance (AUC = 0.872 and 0.922, respectively). The Pearson correlation analysis showed that Ki67 was positively correlated with μ value and negatively correlated with ADC and D values (r = 0.402, -0.346, -0.450, respectively).

Conclusion

The parameters D and μ derived from the FROC model were superior to ADC and SUVmax in distinguishing benign from malignant SPLs and adenocarcinoma from squamous cell carcinoma, in addition, the combination of multiple parameters can further improve diagnostic performance. The non-Gaussian FROC diffusion model is expected to become a noninvasive quantitative imaging technique for identifying SPLs.

Value of IVIM in Differential Diagnoses between Benign and Malignant Solitary Lung Nodules and Masses: A Meta-analysis

Purpose

This study aims to evaluate the accuracy of intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) in distinguishing malignant and benign solitary pulmonary nodules and masses.

Methods

Studies investigating the diagnostic accuracy of IVIM-DWI in lung lesions published through December 2020 were searched. The standardized mean differences (SMDs) of the apparent diffusion coefficient (ADC), tissue diffusivity (D), pseudo-diffusivity (D*), and perfusion fraction (f) were calculated. The sensitivity, specificity, area under the curve (AUC), publication bias, and heterogeneity were then summarized, and the source of heterogeneity and the reliability of combined results were explored by meta-regression and sensitivity analysis.

Results

A total of 16 studies including 714 malignant and 355 benign lesions were included. Significantly lower ADC, D, and f values were found in malignant pulmonary lesions compared to those in benign lesions. The D value showed the best diagnostic performance (sensitivity = 0.90, specificity = 0.71, AUC = 0.91), followed by ADC (sensitivity = 0.84, specificity = 0.75, AUC = 0.88), f (sensitivity = 0.70, specificity = 0.62, AUC = 0.71), and D^* (sensitivity = 0.67, specificity = 0.61, AUC = 0.67). There was an inconspicuous publication bias in ADC, D, D* and f values, moderate heterogeneity in ADC, and high heterogeneity in D, D*, and f values. Subgroup analysis suggested that both ADC and D values had a significant higher sensitivity in “nodules or masses” than that in “nodules.”

Conclusions

The parameters derived from IVIM-DWI, especially the D value, could further improve the differential diagnosis between malignant and benign solitary pulmonary nodules and masses.

Systematic Review Registration:https://www.crd.york.ac.uk/PROSPERO/#myprospero, identifier: CRD42021226664

Volumetric analysis of intravoxel incoherent motion diffusion-weighted imaging in preoperative assessment of non-small cell lung cancer

PURPOSE

To evaluate the potential of intravoxel incoherent motion (IVIM) and apparent diffusion coefficient (ADC) in the prediction of tumor grade, lymph node metastasis and pleural invasion of non-small cell lung cancer (NSCLC) before surgery.

MATERIALS AND METHODS

65 patients diagnosed with NSCLC by surgery were enrolled. IVIM-DWI (10 b-values, 0-1000 s/mm²) was performed before surgery. The mean and minimum ADC (ADC_mean, ADC_min) and IVIM parameters D, D* and f were independently measured and calculated by 2 radiologists by drawing regions of interest (ROIs) including the solid component of the whole tumor. Intraclass correlation coefficients (ICCs) were analysed. Spearman analysis was used to determine the correlation between IVIM parameters and tumor differentiation. Independent sample t-tests (normal distribution) or Mann-Whitney U tests (non-normal distribution) were used to compare the differences between the parameters in moderately-well and poorly differentiated groups, with and without lymph node metastasis and pleural invasion groups. Receiver operating characteristic (ROC) curves were generated.

RESULTS

The ADC_mean, ADC_min, D and f values were negatively correlated with the pathological grades of tumor (P < 0.05). The ADC_mean and D values of patients with poor differentiation and lymph node metastasis were significantly lower than that of patients with moderately-well differentiation and without lymph node metastasis (P < 0.001-0.012). The D value was significantly lower and f value was significantly higher among patients with pleural invasion than those without (P =   0.033 and < 0.001). ROC analysis showed that the area under the ROC curve (AUC) was larger for D in predicting the degree of differentiation (0.832) and lymph node metastasis (0.806), and higher for f in predicting pleural invasion (0.832).

CONCLUSIONS

IVIM is useful for predicting the tumor differentiation, lymph node metastasis and pleural invasion in NSCLC patients before surgery.

Whole-lesion histogram analysis of mono-exponential and bi-exponential diffusion-weighted imaging in differentiating lung cancer from benign pulmonary lesions using 3 T MRI

AIM

To investigate whether whole-lesion histogram analysis of apparent diffusion coefficient (ADC) values derived from mono-exponential and bi-exponential diffusion-weighted imaging (DWI) can differentiate lung cancer from benign pulmonary lesions.

MATERIALS AND METHODS

Thirty-two patients with lung cancer and 17 patients with benign pulmonary lesions were included retrospectively. All patients underwent DWI before surgery or biopsy. ADC histogram parameters, including mean, percentile values (10^th and 90^th), kurtosis, and skewness, were calculated independently by two radiologists. The histogram parameters were compared between patients with lung cancer and benign lesions. Receiver operating characteristic curves were constructed to evaluate the diagnostic performance.

RESULTS

The ADC_Mean, ADC_10th, D_Mean, D_10th were significantly lower in lung cancer (1.187 ± 0.144 × 10^-3; 0.440 ± 0.062 × 10^-3; 1.068 ± 0.108 × 10^-3; and 0.422 ± 0.049 × 10^-3 mm/s) compared to benign lesions (1.418 ± 0.274 × 10^-3; 0.555 ± 0.113 × 10^-3; 1.216 ± 0.149 × 10^-3; and 0.490 ± 0.044 × 10^-3 mm/s; p<0.05). The ADC_Skewness and D_Skewness were significantly different between lung cancer (2.35 ± 0.72; 2.58 ± 1.14) and benign lesions (1.85 ± 0.54; 1.59 ± 1.47; p<0.05). D_10th was robust in differentiating lung cancer from benign lesions. Using 0.453 × 10^-3 mm/s as the optimal threshold, the sensitivity, specificity, and accuracy of D_10th were 78.12%, 82.35%, and 79.6%, respectively.

CONCLUSION

Whole-lesion histogram analysis of ADC values derived by mono-exponential and bi-exponential DWI using 3 T magnetic resonance imaging helps distinguish lung cancer from benign pulmonary lesions.

Biomarkers for site-specific response to neoadjuvant chemotherapy in epithelial ovarian cancer: relating MRI changes to tumour cell load and necrosis

BACKGROUND

Diffusion-weighted magnetic resonance imaging (DW-MRI) potentially interrogates site-specific response to neoadjuvant chemotherapy (NAC) in epithelial ovarian cancer (EOC).

METHODS

Participants with newly diagnosed EOC due for platinum-based chemotherapy and interval debulking surgery were recruited prospectively in a multicentre study (n = 47 participants). Apparent diffusion coefficient (ADC) and solid tumour volume (up to 10 lesions per participant) were obtained from DW-MRI before and after NAC (including double-baseline for repeatability assessment in n = 19). Anatomically matched lesions were analysed after surgical excision (65 lesions obtained from 25 participants). A trained algorithm determined tumour cell fraction, percentage tumour and percentage necrosis on histology. Whole-lesion post-NAC ADC and pre/post-NAC ADC changes were compared with histological metrics (residual tumour/necrosis) for each tumour site (ovarian, omental, peritoneal, lymph node).

RESULTS

Tumour volume reduced at all sites after NAC. ADC increased between pre- and post-NAC measurements. Post-NAC ADC correlated negatively with tumour cell fraction. Pre/post-NAC changes in ADC correlated positively with percentage necrosis. Significant correlations were driven by peritoneal lesions.

CONCLUSIONS

Following NAC in EOC, the ADC (measured using DW-MRI) increases differentially at disease sites despite similar tumour shrinkage, making its utility site-specific. After NAC, ADC correlates negatively with tumour cell fraction; change in ADC correlates positively with percentage necrosis.

CLINICAL TRIAL REGISTRATION

ClinicalTrials.gov NCT01505829.

Free-breathing radial volumetric interpolated breath-hold examination sequence and dynamic contrast-enhanced MRI combined with diffusion-weighted imaging for assessment of solitary pulmonary nodules

OBJECTIVE

To test the performance of free-breathing Dynamic Contrast-Enhanced MRI (DCE-MRI) using a radial volumetric interpolated breath-hold examination (VIBE) sequence combined with diffusion-weighted imaging (DWI) for quantitative solitary pulmonary nodule (SPN) assessment.

METHODS

A total of 67 SPN cases receiving routine MRI routine scans, DWI, and dynamic-enhanced MRI in our hospital from May 2017 to November 2018 were collected. These cases were divided into a malignant group and a benign group according to the characteristics of the SPNs. The quantitative DCE-MRI parameters (K^trans, K_ep, V_e) and apparent diffusion coefficient (ADC) values of the nodules were measured.

RESULTS

The K^trans and K_ep values in the malignant group were higher than those in the benign group, while the ADC values in the malignant group were lower than those in the benign group. Furthermore, the K^trans value of adenocarcinoma was higher than that of squamous cell carcinoma and small cell carcinoma (P < 0.05). The V_e value was significantly different between non-small cell carcinoma and small cell carcinoma (P < 0.05). With an ADC value of 0.98 × 10^-3 mm²/s as the threshold, the specificity and sensitivity to diagnose benign and malignant nodules was 90.6% and 80%, respectively.

CONCLUSION

High-temporal-resolution DCE-MRI using the r-VIBE technique in combination with DWI could contribute to pulmonary nodule analysis and possibly serve as a potential alternative to distinguish malignant from benign nodules as well as differentiate different types of malignancies.

Spatial heterogeneity of nanomedicine investigated by multiscale imaging of the drug, the nanoparticle and the tumour environment

Genetic and phenotypic tumour heterogeneity is an important cause of therapy resistance. Moreover, non-uniform spatial drug distribution in cancer treatment may cause pseudo-resistance, meaning that a treatment is ineffective because the drug does not reach its target at sufficient concentrations. Together with tumour heterogeneity, non-uniform drug distribution causes “therapy heterogeneity”: a spatially heterogeneous treatment effect. Spatial heterogeneity in drug distribution occurs on all scales ranging from interpatient differences to intratumour differences on tissue or cellular scale. Nanomedicine aims to improve the balance between efficacy and safety of drugs by targeting drug-loaded nanoparticles specifically to tumours. Spatial heterogeneity in nanoparticle and payload distribution could be an important factor that limits their efficacy in patients. Therefore, imaging spatial nanoparticle distribution and imaging the tumour environment giving rise to this distribution could help understand (lack of) clinical success of nanomedicine. Imaging the nanoparticle, drug and tumour environment can lead to improvements of new nanotherapies, increase understanding of underlying mechanisms of heterogeneous distribution, facilitate patient selection for nanotherapies and help assess the effect of treatments that aim to reduce heterogeneity in nanoparticle distribution.

In this review, we discuss three groups of imaging modalities applied in nanomedicine research: non-invasive clinical imaging methods (nuclear imaging, MRI, CT, ultrasound), optical imaging and mass spectrometry imaging. Because each imaging modality provides information at a different scale and has its own strengths and weaknesses, choosing wisely and combining modalities will lead to a wealth of information that will help bring nanomedicine forward.

The Continuing Evolution of Molecular Functional Imaging in Clinical Oncology: The Road to Precision Medicine and Radiogenomics (Part II)

The present era of precision medicine sees "cancer" as a consequence of molecular derangements occurring at the commencement of the disease process, with morphological changes happening much later in the process of tumourigenesis. Conventional imaging techniques, such as computed tomography (CT), ultrasound (US) and magnetic resonance imaging (MRI) play an integral role in the detection of disease at the macroscopic level. However, molecular functional imaging (MFI) techniques entail the visualisation and quantification of biochemical and physiological processes occurring during tumourigenesis. MFI has the potential to play a key role in heralding the transition from the concept of "one-size-fits-all" treatment to "precision medicine". Integration of MFI with other fields of tumour biology such as genomics has spawned a novel concept called "radiogenomics", which could serve as an indispensable tool in translational cancer research. With recent advances in medical image processing, such as texture analysis, deep learning and artificial intelligence, the future seems promising; however, their clinical utility remains unproven at present. Despite the emergence of novel imaging biomarkers, the majority of these require validation before clinical translation is possible. In this two part review, we discuss the systematic collaboration across structural, anatomical and molecular imaging techniques that constitute MFI. Part I reviews positron emission tomography, radiogenomics, AI, and optical imaging, while part II reviews MRI, CT and ultrasound, their current status, and recent advances in the field of precision oncology.

Histopathological Image Segmentation Using Modified Kernel-Based Fuzzy C-Means and Edge Bridge and Fill Technique

Histopathological lung cancer segmentation using region of interest is one of the emerging research area in the field of health monitoring system. In this paper, the histopathological images were collected from the database Stanford Tissue Microarray Database (TMAD). After image collection, pre-processing was performed using a normalization technique, which enhances the quality of the histopathological image by eliminating unwanted noise. After pre-processing, segmentation was carried out using the modified kernel-based fuzzy c-means clustering (KFCM) approach along with the edge bridge and fill technique (EBFT). It was a flexible high-level machine learning technique to localize the object in a complex template. The experimental result shows that the proposed approach segments the normal and abnormal cancer regions by means of precision, recall, specificity, accuracy, and Jaccard coefficient. The proposed methodology improved the classification accuracy in lung cancer segmentation up to 2.5–5% compared to the existing methods deep convolutional neural network (DCNN) and diffusion-weighted approach.

Comparison of Various Parameters of DWI in Distinguishing Solitary Pulmonary Nodules

In order to prospectively assess various parameters of diffusion weighted imaging (DWI) in differential diagnosis of benign and malignant solitary pulmonary nodules (SPNs), 58 patients (40 men and 18 women, and mean age of 48.1±10.4 years old) with SPNs undergoing conventional MR, DWI using b=500 s/mm² on a 1.5T MR scanner, were studied. Various DWI parameters [apparent diffusion coefficient (ADC), lesion-tospinal cord signal intensity ratio (LSR), signal intensity (SI) score] were calculated and compared between malignant and benign SPNs groups. A receiver operating characteristic (ROC) curve analysis was employed to compare the diagnostic capabilities of all the parameters for discrimination between benign and malignant SPNs. The results showed that there were 42 malignant and 16 benign SPNs. The ADC was significantly lower in malignant SPNs (1.40±0.44)×10^-3 mm²/s than in benign SPNs (1.81±0.58)×10^-3 mm²/s. The LSR and SI scores were significantly increased in malignant SPNs (0.90±0.37 and 2.8±1.2) as compared with those in benign SPNs (0.68±0.39 and 2.2±1.2). The area under the ROC curves (AUC) of all parameters was not significantly different between malignant SPNs and benign SPNs. It was suggested that as three reported parameters for DWI, ADC, LSR and SI scores are all feasible for discrimination of malignant and benign SPNs. The three parameters have equal diagnostic performance.

Prognostic value of metabolic tumour volume and total lesion glycolysis measured by 18F-fluorodeoxyglucose positron emission tomography/computed tomography in small cell lung cancer: A systematic review and meta-analysis

The aim of this study was to evaluate the prognostic value of metabolic tumour volume (MTV) and total lesion glycolysis (TLG) for small cell lung cancer (SCLC). MEDLINE, EMBASE and Cochrane Library databases were systematically searched. The pooled hazard ratio (HR) was used to measure the influence of MTV and TLG on survival. The subgroup analysis according to VALSG stage and the measured extent of MTV was performed. Patients with high MTV values experienced a significantly poorer prognosis with a HR of 2.42 (95% CI 1.46-4.03) for overall survival (OS) and a HR of 2.78 (95% CI 1.39-5.53) for progression-free survival (PFS) from the random effect model, and the pooled HR from the fixed effect model was 2.10 (95% CI 1.77-2.50) for OS and 2.27 (95% CI 1.83-2.81) for PFS. Patients with high TLG experienced a poorer prognosis with a HR of 1.61 (95% CI: 1.24-2.07) for OS from the random effect model, and the pooled HR from the fixed effect model was 1.64 (95% CI 1.37-1.96). Heterogeneity among studies was high for MTV in both OS and PFS meta-analyses (I²  = 87% and 88% respectively). After removing one outlier study the heterogeneity was substantially reduced (I²  = 0%) and the pooled HR for the effect of MTV on OS was 1.80 (1.51-2.16, P < 0.00001), and on PFS it was 1.86 (1.49-2.33, P < 0.00001), using either the fixed or random effects model. High MTV is associated with a significantly poorer prognosis OS and PFS, and high TLG is associated with a significantly poorer prognosis regarding OS for SCLC.

Automated pixel-wise brain tissue segmentation of diffusion-weighted images via machine learning

The diffusion-weighted (DW) MR signal sampled over a wide range of b-values potentially allows for tissue differentiation in terms of cellularity, microstructure, perfusion, and T₂ relaxivity. This study aimed to implement a machine learning algorithm for automatic brain tissue segmentation from DW-MRI datasets, and to determine the optimal sub-set of features for accurate segmentation. DWI was performed at 3 T in eight healthy volunteers using 15 b-values and 20 diffusion-encoding directions. The pixel-wise signal attenuation, as well as the trace and fractional anisotropy (FA) of the diffusion tensor, were used as features to train a support vector machine classifier for gray matter, white matter, and cerebrospinal fluid classes. The datasets of two volunteers were used for validation. For each subject, tissue classification was also performed on 3D T₁ -weighted data sets with a probabilistic framework. Confusion matrices were generated for quantitative assessment of image classification accuracy in comparison with the reference method. DWI-based tissue segmentation resulted in an accuracy of 82.1% on the validation dataset and of 82.2% on the training dataset, excluding relevant model over-fitting. A mean Dice coefficient (DSC) of 0.79 ± 0.08 was found. About 50% of the classification performance was attributable to five features (i.e. signal measured at b-values of 5/10/500/1200 s/mm² and the FA). This reduced set of features led to almost identical performances for the validation (82.2%) and the training (81.4%) datasets (DSC = 0.79 ± 0.08). Machine learning techniques applied to DWI data allow for accurate brain tissue segmentation based on both morphological and functional information.