Submit to Cancers Review for Cancers Propose a Special Issue

Journal Browser

Cancer: Updates on Imaging and Machine Learning

Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Cancers (ISSN 2072-6694). This special issue belongs to the section "Cancer Causes, Screening and Diagnosis".

Deadline for manuscript submissions: closed (20 March 2023) | Viewed by 11657

Share This Special Issue

Special Issue Editors

Dr. Constantin Lapa

E-Mail Website
Guest Editor

Nuclear Medicine, Faculty of Medicine, University of Augsburg, Augsburg, Germany
Interests: theranostics; novel radioligand therapies
Special Issues, Collections and Topics in MDPI journals

Dr. Johannes Tran-Gia

E-Mail Website
Guest Editor

Department of Nuclear Medicine, University Hospital Würzburg, Würzburg, Germany
Interests: dosimetry of radiopharmaceutical therapies; molecular imaging (SPECT/CT, PET/CT); 3D printing; artificial intelligence

Special Issue Information

Dear Colleagues,

Artificial intelligence (AI) has changed the face of nuclear medicine and molecular imaging. Its potential for improvement has already been demonstrated in many areas of nuclear medicine, such as instrumentation, image acquisition and reconstruction, attenuation/scatter correction, and dosimetry. In addition to the optimization of clinical workflows and an increase in overall efficiency, this will also result in more personalized medicine. Of note, the introduction of total body scanners, which will cause an enormous increase in the amount of data that need to be processed, could be managed through the dedicated use of AI.

In this Special Issue, we would like to present the potential applications of AI in the field of nuclear medicine from a technical (e.g., instrumentation, image reconstruction, data analysis, and radiomics) and clinical (e.g., neurology, cardiology, oncology) perspective. In addition, we want to gain insight into the concept of explainable AI to make clinical decisions, which may in future be supported by AI, more comprehensible, and thus potentially more ethically sustainable for nuclear physicians.

Finally, future challenges in the reliable adoption of AI in nuclear medicine and molecular imaging are addressed to ensure that its potential is fully exploited.

Dr. Constantin Lapa
Dr. Johannes Tran-Gia
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. Cancers 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 2900 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

artificial intelligence
convolutional neural networks
radiomics
nuclear medicine
machine learning
molecular imaging

Published Papers (7 papers)

Download All Papers

Research

Jump to: Review

12 pages, 3105 KiB

Open AccessArticle

Assessment of Variabilities in Lung-Contouring Methods on CBCT Preclinical Radiomics Outputs

by Kathryn H. Brown, Jacob Illyuk, Mihaela Ghita, Gerard M. Walls, Conor K. McGarry and Karl T. Butterworth

Cancers 2023, 15(10), 2677; https://doi.org/10.3390/cancers15102677 - 09 May 2023

Cited by 3 | Viewed by 1290

Abstract

Radiomics image analysis has the potential to uncover disease characteristics for the development of predictive signatures and personalised radiotherapy treatment. Inter-observer and inter-software delineation variabilities are known to have downstream effects on radiomics features, reducing the reliability of the analysis. The purpose of this study was to investigate the impact of these variabilities on radiomics outputs from preclinical cone-beam computed tomography (CBCT) scans. Inter-observer variabilities were assessed using manual and semi-automated contours of mouse lungs (n = 16). Inter-software variabilities were determined between two tools (3D Slicer and ITK-SNAP). The contours were compared using Dice similarity coefficient (DSC) scores and the 95th percentile of the Hausdorff distance (HD_95p) metrics. The good reliability of the radiomics outputs was defined using intraclass correlation coefficients (ICC) and their 95% confidence intervals. The median DSC scores were high (0.82–0.94), and the HD_95p metrics were within the submillimetre range for all comparisons. the shape and NGTDM features were impacted the most. Manual contours had the most reliable features (73%), followed by semi-automated (66%) and inter-software (51%) variabilities. From a total of 842 features, 314 robust features overlapped across all contouring methodologies. In addition, our results have a 70% overlap with features identified from clinical inter-observer studies. Full article

(This article belongs to the Special Issue Cancer: Updates on Imaging and Machine Learning)

► Show Figures

Figure 1

13 pages, 515 KiB

Open AccessArticle

Integration of Radiomics and Tumor Biomarkers in Interpretable Machine Learning Models

by Lennart Brocki and Neo Christopher Chung

Cancers 2023, 15(9), 2459; https://doi.org/10.3390/cancers15092459 - 25 Apr 2023

Cited by 1 | Viewed by 1670

Abstract

Despite the unprecedented performance of deep neural networks (DNNs) in computer vision, their clinical application in the diagnosis and prognosis of cancer using medical imaging has been limited. One of the critical challenges for integrating diagnostic DNNs into radiological and oncological applications is their lack of interpretability, preventing clinicians from understanding the model predictions. Therefore, we studied and propose the integration of expert-derived radiomics and DNN-predicted biomarkers in interpretable classifiers, which we refer to as ConRad, for computerized tomography (CT) scans of lung cancer. Importantly, the tumor biomarkers can be predicted from a concept bottleneck model (CBM) such that once trained, our ConRad models do not require labor-intensive and time-consuming biomarkers. In our evaluation and practical application, the only input to ConRad is a segmented CT scan. The proposed model was compared to convolutional neural networks (CNNs) which act as a black box classifier. We further investigated and evaluated all combinations of radiomics, predicted biomarkers and CNN features in five different classifiers. We found the ConRad models using nonlinear SVM and the logistic regression with the Lasso outperformed the others in five-fold cross-validation, with the interpretability of ConRad being its primary advantage. The Lasso is used for feature selection, which substantially reduces the number of nonzero weights while increasing the accuracy. Overall, the proposed ConRad model combines CBM-derived biomarkers and radiomics features in an interpretable ML model which demonstrates excellent performance for lung nodule malignancy classification. Full article

(This article belongs to the Special Issue Cancer: Updates on Imaging and Machine Learning)

► Show Figures

Figure 1

18 pages, 781 KiB

Open AccessArticle

A Hybrid Algorithm of ML and XAI to Prevent Breast Cancer: A Strategy to Support Decision Making

by Fabián Silva-Aravena, Hugo Núñez Delafuente, Jimmy H. Gutiérrez-Bahamondes and Jenny Morales

Cancers 2023, 15(9), 2443; https://doi.org/10.3390/cancers15092443 - 25 Apr 2023

Cited by 5 | Viewed by 2105

Abstract

Worldwide, the coronavirus has intensified the management problems of health services, significantly harming patients. Some of the most affected processes have been cancer patients’ prevention, diagnosis, and treatment. Breast cancer is the most affected, with more than 20 million cases and at least 10 million deaths by 2020. Various studies have been carried out to support the management of this disease globally. This paper presents a decision support strategy for health teams based on machine learning (ML) tools and explainability algorithms (XAI). The main methodological contributions are: first, the evaluation of different ML algorithms that allow classifying patients with and without cancer from the available dataset; and second, an ML methodology mixed with an XAI algorithm, which makes it possible to predict the disease and interpret the variables and how they affect the health of patients. The results show that first, the XGBoost Algorithm has a better predictive capacity, with an accuracy of 0.813 for the train data and 0.81 for the test data; and second, with the SHAP algorithm, it is possible to know the relevant variables and their level of significance in the prediction, and to quantify the impact on the clinical condition of the patients, which will allow health teams to offer early and personalized alerts for each patient. Full article

(This article belongs to the Special Issue Cancer: Updates on Imaging and Machine Learning)

► Show Figures

Figure 1

19 pages, 4215 KiB

Open AccessArticle

Predicting Microenvironment in CXCR4- and FAP-Positive Solid Tumors—A Pan-Cancer Machine Learning Workflow for Theranostic Target Structures

by André Marquardt, Philipp Hartrampf, Philip Kollmannsberger, Antonio G. Solimando, Svenja Meierjohann, Hubert Kübler, Ralf Bargou, Bastian Schilling, Sebastian E. Serfling, Andreas Buck, Rudolf A. Werner, Constantin Lapa and Markus Krebs

Cancers 2023, 15(2), 392; https://doi.org/10.3390/cancers15020392 - 06 Jan 2023

Cited by 1 | Viewed by 1950

Abstract

(1) Background: C-X-C Motif Chemokine Receptor 4 (CXCR4) and Fibroblast Activation Protein Alpha (FAP) are promising theranostic targets. However, it is unclear whether CXCR4 and FAP positivity mark distinct microenvironments, especially in solid tumors. (2) Methods: Using Random Forest (RF) analysis, we searched for entity-independent mRNA and microRNA signatures related to CXCR4 and FAP overexpression in our pan-cancer cohort from The Cancer Genome Atlas (TCGA) database—representing n = 9242 specimens from 29 tumor entities. CXCR4- and FAP-positive samples were assessed via StringDB cluster analysis, EnrichR, Metascape, and Gene Set Enrichment Analysis (GSEA). Findings were validated via correlation analyses in n = 1541 tumor samples. TIMER2.0 analyzed the association of CXCR4 / FAP expression and infiltration levels of immune-related cells. (3) Results: We identified entity-independent CXCR4 and FAP gene signatures representative for the majority of solid cancers. While CXCR4 positivity marked an immune-related microenvironment, FAP overexpression highlighted an angiogenesis-associated niche. TIMER2.0 analysis confirmed characteristic infiltration levels of CD8+ cells for CXCR4-positive tumors and endothelial cells for FAP-positive tumors. (4) Conclusions: CXCR4- and FAP-directed PET imaging could provide a non-invasive decision aid for entity-agnostic treatment of microenvironment in solid malignancies. Moreover, this machine learning workflow can easily be transferred towards other theranostic targets. Full article

(This article belongs to the Special Issue Cancer: Updates on Imaging and Machine Learning)

► Show Figures

Figure 1

8 pages, 344 KiB

Open AccessArticle

Is Regular Radiographic Upper Urinary Tract Imaging for Surveillance of Non-Muscle Invasive Bladder Cancer Justified?

by Uwe Bieri, Benedikt Kranzbühler, Burkhardt Seifert, Birgit Maria Helmchen, Alexander Gu, Basil Kaufmann, Dejan Lavrek, Thomas Scherer, Marian S. Wettstein, Cédric Poyet and Thomas Hermanns

Cancers 2022, 14(22), 5586; https://doi.org/10.3390/cancers14225586 - 14 Nov 2022

Viewed by 1214

Abstract

Patients with non-muscle invasive (NMI) urothelial bladder cancer (BC) are at increased risk for the development of a secondary upper-urinary-tract urothelial carcinoma (UTUC). We aimed to assess the usefulness of routine upper-tract imaging surveillance during NMIBC follow-up in a patient cohort of a tertiary academic center. All routine upper-tract-imaging scans using computerized tomography urography (CTU) between 2003 and 2016 were assessed for UTUC detection. A total of 315 patients were analyzed. Initial tumor stage was Ta in 207 patients (65.7%), T1 in 98 patients (31.1%) and pure CIS in 10 patients (3.2%). A total of 149 (47.3%) presented with low-grade (LG), and 166 (52.7%) with high-grade (HG) disease. Median follow-up was 48 months (IQR: 55). Four patients (1.2%) were diagnosed with UTUC during follow-up. All four patients presented with initial Ta HG BC. Two of the patients (50%) were diagnosed by routine upper tract imaging. The other two patients were diagnosed after development of symptoms. The 5- and 10-year UTUC-free survival was 98.5% (standard error (SE) 0.9) and 97.6% (SE 1.3), respectively. UTUCs were detected exclusively in patients with initial HG disease, indicating that upper-tract surveillance might only be necessary in these patients. Full article

(This article belongs to the Special Issue Cancer: Updates on Imaging and Machine Learning)

► Show Figures

Figure 1

10 pages, 1320 KiB

Open AccessArticle

Can Radiomics Provide Additional Information in [¹⁸F]FET-Negative Gliomas?

by Katharina von Rohr, Marcus Unterrainer, Adrien Holzgreve, Maximilian A. Kirchner, Zhicong Li, Lena M. Unterrainer, Bogdana Suchorska, Matthias Brendel, Joerg-Christian Tonn, Peter Bartenstein, Sibylle Ziegler, Nathalie L. Albert and Lena Kaiser

Cancers 2022, 14(19), 4860; https://doi.org/10.3390/cancers14194860 - 05 Oct 2022

Cited by 2 | Viewed by 1439

Abstract

The purpose of this study was to evaluate the possibility of extracting relevant information from radiomic features even in apparently [¹⁸F]FET-negative gliomas. A total of 46 patients with a newly diagnosed, histologically verified glioma that was visually classified as [¹⁸F]FET-negative were included. Tumor volumes were defined using routine T2/FLAIR MRI data and applied to extract information from dynamic [¹⁸F]FET PET data, i.e., early and late tumor-to-background (TBR_5–15, TBR_20–40) and time-to-peak (TTP) images. Radiomic features of healthy background were calculated from the tumor volume of interest mirrored in the contralateral hemisphere. The ability to distinguish tumors from healthy tissue was assessed using the Wilcoxon test and logistic regression. A total of 5, 15, and 69% of features derived from TBR_20–40, TBR_5–15, and TTP images, respectively, were significantly different. A high number of significantly different TTP features was even found in isometabolic gliomas (after exclusion of photopenic gliomas) with visually normal [¹⁸F]FET uptake in static images. However, the differences did not reach satisfactory predictability for machine-learning-based identification of tumor tissue. In conclusion, radiomic features derived from dynamic [¹⁸F]FET PET data may extract additional information even in [¹⁸F]FET-negative gliomas, which should be investigated in larger cohorts and correlated with histological and outcome features in future studies. Full article

(This article belongs to the Special Issue Cancer: Updates on Imaging and Machine Learning)

► Show Figures

Figure 1

Review

Jump to: Research

32 pages, 6038 KiB

Open AccessReview

Image-Guided Precision Medicine in the Diagnosis and Treatment of Pheochromocytomas and Paragangliomas

by Gildas Gabiache, Charline Zadro, Laura Rozenblum, Delphine Vezzosi, Céline Mouly, Matthieu Thoulouzan, Rosine Guimbaud, Philippe Otal, Lawrence Dierickx, Hervé Rousseau, Christopher Trepanier, Laurent Dercle and Fatima-Zohra Mokrane

Cancers 2023, 15(18), 4666; https://doi.org/10.3390/cancers15184666 - 21 Sep 2023

Cited by 2 | Viewed by 1353

Abstract

In this comprehensive review, we aimed to discuss the current state-of-the-art medical imaging for pheochromocytomas and paragangliomas (PPGLs) diagnosis and treatment. Despite major medical improvements, PPGLs, as with other neuroendocrine tumors (NETs), leave clinicians facing several challenges; their inherent particularities and their diagnosis and treatment pose several challenges for clinicians due to their inherent complexity, and they require management by multidisciplinary teams. The conventional concepts of medical imaging are currently undergoing a paradigm shift, thanks to developments in radiomic and metabolic imaging. However, despite active research, clinical relevance of these new parameters remains unclear, and further multicentric studies are needed in order to validate and increase widespread use and integration in clinical routine. Use of AI in PPGLs may detect changes in tumor phenotype that precede classical medical imaging biomarkers, such as shape, texture, and size. Since PPGLs are rare, slow-growing, and heterogeneous, multicentric collaboration will be necessary to have enough data in order to develop new PPGL biomarkers. In this nonsystematic review, our aim is to present an exhaustive pedagogical tool based on real-world cases, dedicated to physicians dealing with PPGLs, augmented by perspectives of artificial intelligence and big data. Full article

(This article belongs to the Special Issue Cancer: Updates on Imaging and Machine Learning)

► Show Figures