Machine Learning for Imaging-Based Cancer Diagnostics

A special issue of Current Oncology (ISSN 1718-7729).

Deadline for manuscript submissions: closed (22 February 2023) | Viewed by 5379

Special Issue Editors

National Library of Medicine, National Institutes of Health, Bethesda, MD 20894, USA
Interests: cancers; machine learning; artificial intelligence; image processing; computer vision; biomedical informatics; data science
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
National Library of Medicine, National Institutes of Health, Bethesda, MD 20894, USA
Interests: machine learning; artificial intelligence; medical image analysis; image informatics; multimodal data analysis; data science; NCI (cervical cancer)
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Medical imaging has been ubiquitously used in clinical point-of-care and plays an important role in cancer screening, diagnosis, and treatment. There are many types of medical imaging modalities, for example, MRI, CT, X-ray, PET, mammography, ultrasound, colposcopy, microscopy, endoscopy, and fluoroscopy. Innovations in machine learning and computer-aided techniques to medical imaging in combination with various omics applications can provide valuable information to clinicians to aid in decision-making as well as improve the quality and efficiency of medical care. Although promising results have been demonstrated in the literature, especially with deep learning techniques, a great deal of work and effort remain to further advance this research field. Progress has been limited by the lack of sufficiently large and diverse datasets —especially those enriched by multiple expert annotations, relatively high intra- and inter-observer variance in annotations, inadequately defined truth standards, poor correlation in annotations among data collected at different sources, and noisy labels. Further, advances are also limited by poor image quality control, insufficiently meaningful and usable AI model explanations that adversely impact clinical interpretation of machine predictions, inadequate integration with non-imaging biomarkers, and data imbalance due to the varying prevalence of cases, among others. Through this Special Issue, we aim to highlight advances in machine learning and artificial intelligence methods that address or overcome some of the listed challenges and limitations toward improving the state of the art in image-based cancer diagnostics, treatment, and predictive risk assessment.

We are pleased to invite you to submit your related original research articles and reviews to this Special Issue, “Machine Learning for Imaging-Based Cancer Diagnostics”, of the open-access MDPI journal Current Oncology (impact factor: 3.109). This Special Issue aims to promote and advance machine learning techniques in medical applications, especially regarding the use of intelligent medical imaging to aid the diagnostics, therapeutics, and predictive risk assessment of cancers of various organs. Research areas may include (but are not limited to) the following:

  • Computer-aided diagnosis;
  • Medical image analysis;
  • Medical image reconstruction;
  • Medical image registration;
  • Medical image enhancement;
  • Medical image segmentation;
  • Medical image classification;
  • Medical image fusion;
  • Medical image retrieval;
  • Image-guided interventions and surgery;
  • Network interpretability and explainability for medical applications;
  • Visualization in medical imaging;
  • Automatic medical data cleaning;
  • Statistical pattern analysis for medical applications;
  • Multi-model medical data analysis;
  • Medical data bias mitigation;
  • Multiomics with imaging applications for cancer diagnostics and therapeutics.

We look forward to receiving your contributions.

You may choose our Joint Special Issue in Cancers.

Dr. Zhiyun Xue
Dr. Sameer Antani
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. Current Oncology is an international peer-reviewed open access monthly 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 2200 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

  • machine learning
  • deep learning
  • cancer diagnosis
  • medical image analysis
  • enhancement
  • segmentation
  • registration
  • classification
  • network explanation

Published Papers (2 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

9 pages, 1026 KiB  
Article
CT Texture Analysis of Adrenal Pheochromocytomas: A Pilot Study
by Filippo Crimì, Elena Agostini, Alessandro Toniolo, Francesca Torresan, Maurizio Iacobone, Irene Tizianel, Carla Scaroni, Emilio Quaia, Cristina Campi and Filippo Ceccato
Curr. Oncol. 2023, 30(2), 2169-2177; https://doi.org/10.3390/curroncol30020167 - 9 Feb 2023
Cited by 6 | Viewed by 2014
Abstract
Radiomics is a promising research field that combines big data analysis (from tissue texture analysis) with clinical questions. We studied the application of CT texture analysis in adrenal pheochromocytomas (PCCs) to define the correlation between the extracted features and the secretory pattern, the [...] Read more.
Radiomics is a promising research field that combines big data analysis (from tissue texture analysis) with clinical questions. We studied the application of CT texture analysis in adrenal pheochromocytomas (PCCs) to define the correlation between the extracted features and the secretory pattern, the histopathological data, and the natural history of the disease. A total of 17 patients affected by surgically removed PCCs were retrospectively enrolled. Before surgery, all patients underwent contrast-enhanced CT and complete endocrine evaluation (catecholamine secretion and genetic evaluation). The pheochromocytoma adrenal gland scaled score (PASS) was determined upon histopathological examination. After a resampling of all CT images, the PCCs were delineated using LifeX software in all three phases (unenhanced, arterial, and venous), and 58 texture parameters were extracted for each volume of interest. Using the Mann–Whitney test, the correlations between the hormonal hypersecretion, the malignancy score of the lesion (PASS > 4), and texture parameters were studied. The parameters DISCRETIZED_HUpeak and GLZLM_GLNU in the unenhanced phase and GLZLM_SZE, CONVENTIONAL_HUmean, CONVENTIONAL_HUQ3, DISCRETIZED_HUmean, DISCRETIZED_AUC_CSH, GLRLM_HGRE, and GLZLM_SZHGE in the venous phase were able to differentiate secreting PCCs (p < 0.01), and the parameters GLZLM_GLNU in the unenhanced phase and GLRLM_GLNU and GLRLM_RLNU in the venous differentiated tumors with low and high PASS. CT texture analysis of adrenal PCCs can be a useful tool for the early identification of secreting or malignant tumors. Full article
(This article belongs to the Special Issue Machine Learning for Imaging-Based Cancer Diagnostics)
Show Figures

Figure 1

16 pages, 4836 KiB  
Article
A Deep Learning Workflow for Mass-Forming Intrahepatic Cholangiocarcinoma and Hepatocellular Carcinoma Classification Based on MRI
by Yangling Liu, Bin Wang, Xiao Mo, Kang Tang, Jianfeng He and Jingang Hao
Curr. Oncol. 2023, 30(1), 529-544; https://doi.org/10.3390/curroncol30010042 - 30 Dec 2022
Cited by 4 | Viewed by 2339
Abstract
Objective: Precise classification of mass-forming intrahepatic cholangiocarcinoma (MF-ICC) and hepatocellular carcinoma (HCC) based on magnetic resonance imaging (MRI) is crucial for personalized treatment strategy. The purpose of the present study was to differentiate MF-ICC from HCC applying a novel deep-learning-based workflow with stronger [...] Read more.
Objective: Precise classification of mass-forming intrahepatic cholangiocarcinoma (MF-ICC) and hepatocellular carcinoma (HCC) based on magnetic resonance imaging (MRI) is crucial for personalized treatment strategy. The purpose of the present study was to differentiate MF-ICC from HCC applying a novel deep-learning-based workflow with stronger feature extraction ability and fusion capability to improve the classification performance of deep learning on small datasets. Methods: To retain more effective lesion features, we propose a preprocessing method called semi-segmented preprocessing (Semi-SP) to select the region of interest (ROI). Then, the ROIs were sent to the strided feature fusion residual network (SFFNet) for training and classification. The SFFNet model is composed of three parts: the multilayer feature fusion module (MFF) was proposed to extract discriminative features of MF-ICC/HCC and integrate features of different levels; a new stationary residual block (SRB) was proposed to solve the problem of information loss and network instability during training; the attention mechanism convolutional block attention module (CBAM) was adopted in the middle layer of the network to extract the correlation of multi-spatial feature information, so as to filter the irrelevant feature information in pixels. Results: The SFFNet model achieved an overall accuracy of 92.26% and an AUC of 0.9680, with high sensitivity (86.21%) and specificity (94.70%) for MF-ICC. Conclusion: In this paper, we proposed a specifically designed Semi-SP method and SFFNet model to differentiate MF-ICC from HCC. This workflow achieves good MF-ICC/HCC classification performance due to stronger feature extraction and fusion capabilities, which provide complementary information for personalized treatment strategy. Full article
(This article belongs to the Special Issue Machine Learning for Imaging-Based Cancer Diagnostics)
Show Figures

Figure 1

Back to TopTop