Submit to Diagnostics Review for Diagnostics Propose a Special Issue

Journal Browser

Novel Approaches in Oncologic Imaging

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Diagnostics (ISSN 2075-4418). This special issue belongs to the section "Medical Imaging and Theranostics".

Deadline for manuscript submissions: closed (31 January 2022) | Viewed by 32849

Share This Special Issue

Special Issue Editors

Dr. Thomas Geyer

E-Mail Website
Guest Editor

Department of Radiology, University Hospital, LMU Munich, 81377 Munich, Germany
Interests: contrast-enhanced ultrasound; cancer imaging; CT and MRI; hybrid imaging; PET/CT; vascularization and microperfusion; liver cancer; economic aspects in medical imaging

Dr. Saif Afat

E-Mail Website
Guest Editor

Department for Diagnostic and Interventional Radiology, Eberhard Karls University Tuebingen, University Hospital Tuebingen, 72076 Tuebingen, Germany
Interests: deep learning; MRI; AI; oncology; computed tomography; COVID-19

Special Issue Information

Dear colleagues,

The early and accurate detection of malignant lesions is essential for a modern targeted therapy in oncology. Modern radiology offers various diagnostic procedures for detecting cancer and monitoring patients during therapy. Recent developments in radiology, including the use of artificial intelligence and imaging biomarkers, as well as the widespread use of hybrid imaging techniques, have already shown promising results for improving oncologic imaging and individualizing patient management. Novel insights are needed in order to accelerate the implementation of these techniques into clinical routine. Furthermore, the economic aspects of these modern approaches are becoming increasingly important.

The aim of this Special Issue is to present recent developments and novel approaches in diagnostic oncologic imaging, covering insights from recent technical developments, including artificial intelligence and imaging biomarkers, to specific imaging techniques, thus adding value for clinical and economic oncology patient management.

Dr. Thomas Geyer
Dr. Saif Afat
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Diagnostics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

oncologic imaging
CT and MRI
hybrid imaging
imaging biomarkers
ultrasound
vascularization and microperfusion
liver cancer
economic aspects in medical imaging
artificial intelligence

Published Papers (13 papers)

Download All Papers

Research

11 pages, 5406 KiB

Open AccessArticle

Detection of Splenic Tissue Using ^99mTc-Labelled Denatured Red Blood Cells Scintigraphy—A Quantitative Single Center Analysis

by Adrien Holzgreve, Friederike Völter, Astrid Delker, Wolfgang G. Kunz, Matthias P. Fabritius, Matthias Brendel, Nathalie L. Albert, Peter Bartenstein, Marcus Unterrainer and Lena M. Unterrainer

Diagnostics 2022, 12(2), 486; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics12020486 - 14 Feb 2022

Cited by 4 | Viewed by 3508

Abstract

Background: Red blood cells (RBC) scintigraphy can be used not only for detection of bleeding sites, but also of spleen tissue. However, there is no established quantitative readout. Therefore, we investigated uptake in suspected splenic lesions in direct quantitative correlation to sites of physiologic uptake in order to objectify the readout. Methods: 20 patients with Tc-99m-labelled RBC scintigraphy and SPECT/low-dose CT for assessment of suspected splenic tissue were included. Lesions were rated as vital splenic or non-splenic tissue, and uptake and physiologic uptake of bone marrow, pancreas, and spleen were then quantified using a volume-of-interest based approach. Hepatic uptake served as a reference. Results: The median uptake ratio was significantly higher in splenic (2.82 (range, 0.58–24.10), n = 47) compared to other lesions (0.49 (0.01–0.83), n = 7), p < 0.001, and 5 lesions were newly discovered. The median pancreatic uptake was 0.09 (range 0.03–0.67), bone marrow 0.17 (0.03–0.45), and orthotopic spleen 14.45 (3.04–29.82). Compared to orthotopic spleens, the pancreas showed lowest uptake (0.09 vs. 14.45, p = 0.004). Based on pancreatic uptake we defined a cutoff (0.75) to distinguish splenic from other tissues. Conclusion: As the uptake in extra-splenic regions is invariably low compared to splenules, it can be used as comparator for evaluating suspected splenic tissues. Full article

(This article belongs to the Special Issue Novel Approaches in Oncologic Imaging)

► Show Figures

Figure 1

14 pages, 3879 KiB

Open AccessArticle

AI Denoising Significantly Improves Image Quality in Whole-Body Low-Dose Computed Tomography Staging

by Andreas S. Brendlin, David Plajer, Maryanna Chaika, Robin Wrazidlo, Arne Estler, Ilias Tsiflikas, Christoph P. Artzner, Saif Afat and Malte N. Bongers

Diagnostics 2022, 12(1), 225; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics12010225 - 17 Jan 2022

Cited by 13 | Viewed by 2343

Abstract

(1) Background: To evaluate the effects of an AI-based denoising post-processing software solution in low-dose whole-body computer tomography (WBCT) stagings; (2) Methods: From 1 January 2019 to 1 January 2021, we retrospectively included biometrically matching melanoma patients with clinically indicated WBCT staging from two scanners. The scans were reconstructed using weighted filtered back-projection (wFBP) and Advanced Modeled Iterative Reconstruction strength 2 (ADMIRE 2) at 100% and simulated 50%, 40%, and 30% radiation doses. Each dataset was post-processed using a novel denoising software solution. Five blinded radiologists independently scored subjective image quality twice with 6 weeks between readings. Inter-rater agreement and intra-rater reliability were determined with an intraclass correlation coefficient (ICC). An adequately corrected mixed-effects analysis was used to compare objective and subjective image quality. Multiple linear regression measured the contribution of “Radiation Dose”, “Scanner”, “Mode”, “Rater”, and “Timepoint” to image quality. Consistent regions of interest (ROI) measured noise for objective image quality; (3) Results: With good–excellent inter-rater agreement and intra-rater reliability (Timepoint 1: ICC ≥ 0.82, 95% CI 0.74–0.88; Timepoint 2: ICC ≥ 0.86, 95% CI 0.80–0.91; Timepoint 1 vs. 2: ICC ≥ 0.84, 95% CI 0.78–0.90; all p ≤ 0.001), subjective image quality deteriorated significantly below 100% for wFBP and ADMIRE 2 but remained good–excellent for the post-processed images, regardless of input (p ≤ 0.002). In regression analysis, significant increases in subjective image quality were only observed for higher radiation doses (≥0.78, 95%CI 0.63–0.93; p < 0.001), as well as for the post-processed images (≥2.88, 95%CI 2.72–3.03, p < 0.001). All post-processed images had significantly lower image noise than their standard counterparts (p < 0.001), with no differences between the post-processed images themselves. (4) Conclusions: The investigated AI post-processing software solution produces diagnostic images as low as 30% of the initial radiation dose (3.13 ± 0.75 mSv), regardless of scanner type or reconstruction method. Therefore, it might help limit patient radiation exposure, especially in the setting of repeated whole-body staging examinations. Full article

(This article belongs to the Special Issue Novel Approaches in Oncologic Imaging)

► Show Figures

Figure 1

12 pages, 3125 KiB

Open AccessArticle

Incorporating the Breast Imaging Reporting and Data System Lexicon with a Fully Convolutional Network for Malignancy Detection on Breast Ultrasound

by Yung-Hsien Hsieh, Fang-Rong Hsu, Seng-Tong Dai, Hsin-Ya Huang, Dar-Ren Chen and Wei-Chung Shia

Diagnostics 2022, 12(1), 66; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics12010066 - 28 Dec 2021

Cited by 4 | Viewed by 1672

Abstract

In this study, we applied semantic segmentation using a fully convolutional deep learning network to identify characteristics of the Breast Imaging Reporting and Data System (BI-RADS) lexicon from breast ultrasound images to facilitate clinical malignancy tumor classification. Among 378 images (204 benign and 174 malignant images) from 189 patients (102 benign breast tumor patients and 87 malignant patients), we identified seven malignant characteristics related to the BI-RADS lexicon in breast ultrasound. The mean accuracy and mean IU of the semantic segmentation were 32.82% and 28.88, respectively. The weighted intersection over union was 85.35%, and the area under the curve was 89.47%, showing better performance than similar semantic segmentation networks, SegNet and U-Net, in the same dataset. Our results suggest that the utilization of a deep learning network in combination with the BI-RADS lexicon can be an important supplemental tool when using ultrasound to diagnose breast malignancy. Full article

(This article belongs to the Special Issue Novel Approaches in Oncologic Imaging)

► Show Figures

Figure 1

9 pages, 1353 KiB

Open AccessArticle

Clinical Evaluation of an Abbreviated Contrast-Enhanced Whole-Body MRI for Oncologic Follow-Up Imaging

by Judith Herrmann, Saif Afat, Andreas Brendlin, Maryanna Chaika, Andreas Lingg and Ahmed E. Othman

Diagnostics 2021, 11(12), 2368; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics11122368 - 16 Dec 2021

Cited by 4 | Viewed by 2202

Abstract

Over the last decades, overall survival for most cancer types has increased due to earlier diagnosis and more effective treatments. Simultaneously, whole-body MRI-(WB-MRI) has gained importance as a radiation free staging alternative to computed tomography. The aim of this study was to evaluate the diagnostic confidence and reproducibility of a novel abbreviated 20-min WB-MRI for oncologic follow-up imaging in patients with melanoma. In total, 24 patients with melanoma were retrospectively included in this institutional review board-approved study. All patients underwent three consecutive staging examinations via WB-MRI in a clinical 3 T MR scanner with an abbreviated 20-min protocol. Three radiologists independently evaluated the images in a blinded, random order regarding image quality (overall image quality, organ-based image quality, sharpness, noise, and artifacts) and regarding its diagnostic confidence on a 5-point-Likert-Scale (5 = excellent). Inter-reader agreement and reproducibility were assessed. Overall image quality and diagnostic confidence were rated to be excellent (median 5, interquartile range [IQR] 5–5). The sharpness of anatomic structures, and the extent of noise and artifacts, as well as the assessment of lymph nodes, liver, bone, and the cutaneous system were rated to be excellent (median 5, IQR 4–5). The image quality of the lung was rated to be good (median 4, IQR 4–5). Therefore, our study demonstrated that the novel accelerated 20-min WB-MRI protocol is feasible, providing high image quality and diagnostic confidence with reliable reproducibility for oncologic follow-up imaging. Full article

(This article belongs to the Special Issue Novel Approaches in Oncologic Imaging)

► Show Figures

Figure 1

9 pages, 2046 KiB

Open AccessArticle

Deep Learning-Based Body Composition Analysis Predicts Outcome in Melanoma Patients Treated with Immune Checkpoint Inhibitors

by Anton Faron, Nikola S. Opheys, Sebastian Nowak, Alois M. Sprinkart, Alexander Isaak, Maike Theis, Narine Mesropyan, Christoph Endler, Judith Sirokay, Claus C. Pieper, Daniel Kuetting, Ulrike Attenberger, Jennifer Landsberg and Julian A. Luetkens

Diagnostics 2021, 11(12), 2314; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics11122314 - 09 Dec 2021

Cited by 13 | Viewed by 2388

Abstract

Previous studies suggest an impact of body composition on outcome in melanoma patients. We aimed to determine the prognostic value of CT-based body composition assessment in patients receiving immune checkpoint inhibitor therapy for treatment of metastatic disease using a deep learning approach. One hundred seven patients with staging CT examinations prior to initiation of checkpoint inhibition between January 2013 and August 2019 were retrospectively evaluated. Using an automated deep learning-based body composition analysis pipeline, parameters for estimation of skeletal muscle mass (skeletal muscle index, SMI) and adipose tissue compartments (visceral adipose tissue index, VAI; subcutaneous adipose tissue index, SAI) were derived from staging CT. The cohort was binarized according to gender-specific median cut-off values. Patients below the median were defined as having low SMI, VAI, or SAI, respectively. The impact on outcome was assessed using the Kaplan–Meier method with log-rank tests. A multivariable logistic regression model was built to test the impact of body composition parameters on 3-year mortality. Patients with low SMI displayed significantly increased 1-year (25% versus 9%, p = 0.035), 2-year (32% versus 13%, p = 0.017), and 3-year mortality (38% versus 19%, p = 0.016). No significant differences with regard to adipose tissue compartments were observed (3-year mortality: VAI, p = 0.448; SAI, p = 0.731). On multivariable analysis, low SMI (hazard ratio (HR), 2.245; 95% confidence interval (CI), 1.005–5.017; p = 0.049), neutrophil-to-lymphocyte ratio (HR, 1.170; 95% CI, 1.076–1.273; p < 0.001), and Karnofsky index (HR, 0.965; 95% CI, 0.945–0.985; p = 0.001) remained as significant predictors of 3-year mortality. Lowered skeletal muscle index as an indicator of sarcopenia was associated with worse outcome in patients with metastatic melanoma receiving immune checkpoint inhibitor therapy. Full article

(This article belongs to the Special Issue Novel Approaches in Oncologic Imaging)

► Show Figures

Figure 1

12 pages, 8699 KiB

Open AccessArticle

A Predictive Clinical-Radiomics Nomogram for Survival Prediction of Glioblastoma Using MRI

by Samy Ammari, Raoul Sallé de Chou, Corinne Balleyguier, Emilie Chouzenoux, Mehdi Touat, Arnaud Quillent, Sarah Dumont, Sophie Bockel, Gabriel C. T. E. Garcia, Mickael Elhaik, Bidault Francois, Valentin Borget, Nathalie Lassau, Mohamed Khettab and Tarek Assi

Diagnostics 2021, 11(11), 2043; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics11112043 - 04 Nov 2021

Cited by 12 | Viewed by 2638

Abstract

Glioblastoma (GBM) is the most common and aggressive primary brain tumor in adult patients with a median survival of around one year. Prediction of survival outcomes in GBM patients could represent a huge step in treatment personalization. The objective of this study was to develop machine learning (ML) algorithms for survival prediction of GBM patient. We identified a radiomic signature on a training-set composed of data from the 2019 BraTS challenge (210 patients) from MRI retrieved at diagnosis. Then, using this signature along with the age of the patients for training classification models, we obtained on test-sets AUCs of 0.85, 0.74 and 0.58 (0.92, 0.88 and 0.75 on the training-sets) for survival at 9-, 12- and 15-months, respectively. This signature was then validated on an independent cohort of 116 GBM patients with confirmed disease relapse for the prediction of patients surviving less or more than the median OS of 22 months. Our model insured an AUC of 0.71 (0.65 on train). The Kaplan–Meier method showed significant OS difference between groups (log-rank p = 0.05). These results suggest that radiomic signatures may improve survival outcome predictions in GBM thus creating a solid clinical tool for tailoring therapy in this population. Full article

(This article belongs to the Special Issue Novel Approaches in Oncologic Imaging)

► Show Figures

Figure 1

13 pages, 3061 KiB

Open AccessArticle

A Radiomics Approach to Predict the Emergence of New Hepatocellular Carcinoma in Computed Tomography for High-Risk Patients with Liver Cirrhosis

by Eric Tietz, Daniel Truhn, Gustav Müller-Franzes, Marie-Luise Berres, Karim Hamesch, Sven Arke Lang, Christiane Katharina Kuhl, Philipp Bruners and Maximilian Schulze-Hagen

Diagnostics 2021, 11(9), 1650; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics11091650 - 09 Sep 2021

Cited by 2 | Viewed by 1859

Abstract

Liver cirrhosis poses a major risk for the development of hepatocellular carcinoma (HCC). This retrospective study investigated to what extent radiomic features allow the prediction of emerging HCC in patients with cirrhosis in contrast-enhanced computed tomography (CECT). A total of 51 patients with liver cirrhosis and newly detected HCC lesions (n = 82) during follow-up (FU-CT) after local tumor therapy were included. These lesions were not to have been detected by the radiologist in the chronologically prior CECT (PRE-CT). For training purposes, segmentations of 22 patients with liver cirrhosis but without HCC-recurrence were added. A total of 186 areas (82 HCCs and 104 cirrhotic liver areas without HCC) were analyzed. Using univariate analysis, four independent features were identified, and a multivariate logistic regression model was trained to classify the outlined regions as “HCC probable” or “HCC improbable”. In total, 60/82 (73%) of segmentations with later detected HCC and 84/104 (81%) segmentations without HCC were classified correctly (AUC of 81%, 95% CI 74–87%), yielding a sensitivity of 72% (95% CI 57–83%) and a specificity of 86% (95% CI 76–96%). In conclusion, the model predicted the occurrence of new HCCs within segmented areas with an acceptable sensitivity and specificity in cirrhotic liver tissue in CECT. Full article

(This article belongs to the Special Issue Novel Approaches in Oncologic Imaging)

► Show Figures

Figure 1

13 pages, 2439 KiB

Open AccessArticle

Diagnostic Value of Contrast-Enhanced Ultrasound for Evaluation of Transjugular Intrahepatic Portosystemic Shunt Perfusion

by Constantin A. Marschner, Thomas Geyer, Matthias F. Froelich, Johannes Rübenthaler, Vincent Schwarze and Dirk-André Clevert

Diagnostics 2021, 11(9), 1593; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics11091593 - 01 Sep 2021

Cited by 3 | Viewed by 2026

Abstract

Background: In patients with liver cirrhosis, transjugular intrahepatic portosystemic shunt (TIPS) displays an effective method for treating portal hypertension. Main indications include refractory ascites and secondary prevention of esophageal bleeding. Color Doppler ultrasound (CDUS) plays a leading role in the follow-up management, whereas contrast-enhanced ultrasound (CEUS) is not routinely considered. We compared the efficacy of CEUS to CDUS and highlighted differences compared to findings of corresponding computed tomography (CT) and magnetic resonance imaging (MRI). (2) Methods: On a retrospective basis, 106 patients with CEUS examination after TIPS were included. The enrollment period was 12 years (between 2008 and 2020) and the age group ranged from 23.3 to 82.1 years. In addition, 92 CDUS, 43 CT and 58 MRI scans were evaluated for intermodal comparison. (3) Results: Intermodal analysis and comparison revealed a high level of concordance between CDUS, CT and MRI in the vast majority of cases. In comparison to CDUS, the correlation of the relevant findings was 92.5%, 95.3% for CT and 87.9% for MRI. In some cases, however, additional information was provided by CEUS (4) Conclusions: CEUS depicts a safe and effective imaging modality for follow-up after TIPS. In addition to CDUS, CEUS enables specific assessment of stent pathologies and stent dysfunction due to its capacity to dynamically visualize single microbubbles at high spatial and temporal resolution. Due to the low number of adverse events regarding the application of contrast agents, CEUS can be administered to a very broad patient population, thus avoiding additional radiation exposure compared to CT angiography in cases with divergent findings during follow-up. Full article

(This article belongs to the Special Issue Novel Approaches in Oncologic Imaging)

► Show Figures

Figure 1

16 pages, 5550 KiB

Open AccessArticle

Stability and Reproducibility of Radiomic Features Based Various Segmentation Technique on MR Images of Hepatocellular Carcinoma (HCC)

by Nurin Syazwina Mohd Haniff, Muhammad Khalis Abdul Karim, Nurul Huda Osman, M Iqbal Saripan, Iza Nurzawani Che Isa and Mohammad Johari Ibahim

Diagnostics 2021, 11(9), 1573; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics11091573 - 30 Aug 2021

Cited by 13 | Viewed by 2366

Abstract

Hepatocellular carcinoma (HCC) is considered as a complex liver disease and ranked as the eighth-highest mortality rate with a prevalence of 2.4% in Malaysia. Magnetic resonance imaging (MRI) has been acknowledged for its advantages, a gold technique for diagnosing HCC, and yet the false-negative diagnosis from the examinations is inevitable. In this study, 30 MR images from patients diagnosed with HCC is used to evaluate the robustness of semi-automatic segmentation using the flood fill algorithm for quantitative features extraction. The relevant features were extracted from the segmented MR images of HCC. Four types of features extraction were used for this study, which are tumour intensity, shape feature, textural feature and wavelet feature. A total of 662 radiomic features were extracted from manual and semi-automatic segmentation and compared using intra-class relation coefficient (ICC). Radiomic features extracted using semi-automatic segmentation utilized flood filling algorithm from 3D-slicer had significantly higher reproducibility (average ICC = 0.952 ± 0.009, p < 0.05) compared with features extracted from manual segmentation (average ICC = 0.897 ± 0.011, p > 0.05). Moreover, features extracted from semi-automatic segmentation were more robust compared to manual segmentation. This study shows that semi-automatic segmentation from 3D-Slicer is a better alternative to the manual segmentation, as they can produce more robust and reproducible radiomic features. Full article

(This article belongs to the Special Issue Novel Approaches in Oncologic Imaging)

► Show Figures

Figure 1

13 pages, 1888 KiB

Open AccessArticle

Computed Tomography-Navigation™ Electromagnetic System Compared to Conventional Computed Tomography Guidance for Percutaneous Lung Biopsy: A Single-Center Experience

by Morgane Lanouzière, Olivier Varbédian, Olivier Chevallier, Loïc Griviau, Kévin Guillen, Romain Popoff, Serge-Ludwig Aho-Glélé and Romaric Loffroy

Diagnostics 2021, 11(9), 1532; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics11091532 - 25 Aug 2021

Cited by 9 | Viewed by 2987

Abstract

The aim of our study was to assess the efficacy of a computed tomography (CT)-Navigation™ electromagnetic system compared to conventional CT methods for percutaneous lung biopsies (PLB). In this single-center retrospective study, data of a CT-Navigation™ system guided PLB (NAV-group) and conventional CT PLB (CT-group) performed between January 2017 and February 2020 were reviewed. The primary endpoint was the diagnostic success. Secondary endpoints were technical success, total procedure duration, number of CT acquisitions and the dose length product (DLP) during step ∆1 (from planning to initial needle placement), step ∆2 (progression to target), and the entire intervention (from planning to final control) and complications. Additional parameters were recorded, such as the lesion’s size and trajectory angles. Sixty patients were included in each group. The lesions median size and median values of the two trajectory angles were significantly lower (20 vs. 29.5 mm, p = 0.006) and higher in the NAV-group (15.5° and 10° vs. 6° and 1°; p < 0.01), respectively. Technical and diagnostic success rates were similar in both groups, respectively 95% and 93.3% in the NAV-group, and 93.3% and 91.6% in the CT-group. There was no significant difference in total procedure duration (p = 0.487) and total number of CT acquisitions (p = 0.066), but the DLP was significantly lower in the NAV-group (p < 0.01). There was no significant difference in complication rate. For PLB, CT-Navigation™ system is efficient and safe as compared to the conventional CT method. Full article

(This article belongs to the Special Issue Novel Approaches in Oncologic Imaging)

► Show Figures

Figure 1

14 pages, 3996 KiB

Open AccessArticle

Dynamic Contrast-Enhanced and Intravoxel Incoherent Motion MRI Biomarkers Are Correlated to Survival Outcome in Advanced Hepatocellular Carcinoma

by Bang-Bin Chen, Yu-Yun Shao, Zhong-Zhe Lin, Chih-Hung Hsu, Ann-Lii Cheng, Chiun Hsu, Po-Chin Liang and Tiffany Ting-Fang Shih

Diagnostics 2021, 11(8), 1340; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics11081340 - 26 Jul 2021

Cited by 7 | Viewed by 2113

Abstract

Objective: This study assessed dynamic contrast-enhanced (DCE)-MRI and intravoxel incoherent motion diffusion-weighted imaging (IVIM DWI) parameters to prospectively predict survival outcomes in participants with advanced hepatocellular carcinoma (HCC) who received lenalidomide, a dual antiangiogenic and immunomodulatory agent, as second-line therapy in a Phase II clinical trial. Materials and methods: Forty-four participants with advanced HCC who had progression after sorafenib as first-line treatment were prospectively enrolled. Pretreatment MRI parameters—obtained from DCE-MRI (peak, slope, AUC, K^trans, K_ep, and V_e), apparent diffusion coefficient (ADC), and IVIM DWI (pure diffusion coefficient (D), pseudodiffusion coefficient (D*), and perfusion fraction (f))—were derived from the largest hepatic tumor. The Cox model was used to investigate the associations of the parameters with progression-free survival (PFS) and overall survival (OS). Results: Median PFS and OS were 2.3 and 8.0 months, respectively. Univariate analysis showed that participants with a high slope (p = 0.024), K_ep (p < 0.001), and ADC (p = 0.018) values had longer PFS than those with low values; participants with a small tumor size (p = 0.006), high slope (p = 0.01), ADC (p = 0.015), and f (p = 0.012) values had longer OS than those with low values did. Cox multivariable analysis revealed that K_ep (p < 0.001) and ADC (p = 0.009) remained independent predictors of PFS; slope (p = 0.003) and ADC (p = 0.009) remained independent predictors of OS. Moreover, K_ep and slope were still significant after Bonferroni correction was performed (p < 0.005). Conclusion: Both pretreatment DCE-MRI and IVIM DWI parameters, especially slope and ADC, may predict PFS and OS in participants with HCC receiving lenalidomide as second-line therapy. Full article

(This article belongs to the Special Issue Novel Approaches in Oncologic Imaging)

► Show Figures

Figure 1

14 pages, 9976 KiB

Open AccessArticle

Machine-Learning-Based Radiomics MRI Model for Survival Prediction of Recurrent Glioblastomas Treated with Bevacizumab

by Samy Ammari, Raoul Sallé de Chou, Tarek Assi, Mehdi Touat, Emilie Chouzenoux, Arnaud Quillent, Elaine Limkin, Laurent Dercle, Joya Hadchiti, Mickael Elhaik, Salma Moalla, Mohamed Khettab, Corinne Balleyguier, Nathalie Lassau, Sarah Dumont and Cristina Smolenschi

Diagnostics 2021, 11(7), 1263; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics11071263 - 14 Jul 2021

Cited by 7 | Viewed by 2592

Abstract

Anti-angiogenic therapy with bevacizumab is a widely used therapeutic option for recurrent glioblastoma (GBM). Nevertheless, the therapeutic response remains highly heterogeneous among GBM patients with discordant outcomes. Recent data have shown that radiomics, an advanced recent imaging analysis method, can help to predict both prognosis and therapy in a multitude of solid tumours. The objective of this study was to identify novel biomarkers, extracted from MRI and clinical data, which could predict overall survival (OS) and progression-free survival (PFS) in GBM patients treated with bevacizumab using machine-learning algorithms. In a cohort of 194 recurrent GBM patients (age range 18–80), radiomics data from pre-treatment T2 FLAIR and gadolinium-injected MRI images along with clinical features were analysed. Binary classification models for OS at 9, 12, and 15 months were evaluated. Our classification models successfully stratified the OS. The AUCs were equal to 0.78, 0.85, and 0.76 on the test sets (0.79, 0.82, and 0.87 on the training sets) for the 9-, 12-, and 15-month endpoints, respectively. Regressions yielded a C-index of 0.64 (0.74) for OS and 0.57 (0.69) for PFS. These results suggest that radiomics could assist in the elaboration of a predictive model for treatment selection in recurrent GBM patients. Full article

(This article belongs to the Special Issue Novel Approaches in Oncologic Imaging)

► Show Figures

Figure 1

14 pages, 6271 KiB

Open AccessArticle

Applying MRI Intensity Normalization on Non-Bone Tissues to Facilitate Pseudo-CT Synthesis from MRI

by Kuei-Yuan Hou, Hao-Yuan Lu and Ching-Ching Yang

Diagnostics 2021, 11(5), 816; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics11050816 - 30 Apr 2021

Cited by 2 | Viewed by 2384

Abstract

This study aimed to facilitate pseudo-CT synthesis from MRI by normalizing MRI intensity of the same tissue type to a similar intensity level. MRI intensity normalization was conducted through dividing MRI by a shading map, which is a smoothed ratio image between MRI and a three-intensity mask. Regarding pseudo-CT synthesis from MRI, a conversion model based on a three-layer convolutional neural network was trained and validated. Before MRI intensity normalization, the mean value ± standard deviation of fat tissue in 0.35 T chest MRI was 297 ± 73 (coefficient of variation (CV) = 24.58%), which was 533 ± 91 (CV = 17.07%) in 1.5 T abdominal MRI. The corresponding results were 149 ± 32 (CV = 21.48%) and 148 ± 28 (CV = 18.92%) after intensity normalization. With regards to pseudo-CT synthesis from MRI, the differences in mean values between pseudo-CT and real CT were 3, 15, and 12 HU for soft tissue, fat, and lung/air in 0.35 T chest imaging, respectively, while the corresponding results were 3, 14, and 15 HU in 1.5 T abdominal imaging. Overall, the proposed workflow is reliable in pseudo-CT synthesis from MRI and is more practicable in clinical routine practice compared with deep learning methods, which demand a high level of resources for building a conversion model. Full article

(This article belongs to the Special Issue Novel Approaches in Oncologic Imaging)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Novel Approaches in Oncologic Imaging

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (13 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI