Application of Deep Learning in Medical Ultrasound

A special issue of Diagnostics (ISSN 2075-4418). This special issue belongs to the section "Machine Learning and Artificial Intelligence in Diagnostics".

Deadline for manuscript submissions: closed (30 November 2023) | Viewed by 4778

Special Issue Editor


E-Mail Website
Guest Editor
Department of Biomedical Engineering, School of Electrical Engineering, Iran University of Science and Technology, Tehran 1684613114, Iran
Interests: ultrasound imaging; image processing; deep learning; echocardiography; high intensity focused ultrasound; compressive sensing; temporal super-resolution

Special Issue Information

Dear Colleagues,

With the development of medical imaging technology, it has found increasing use in the diagnosis of diseases. Ultrasound imaging has a particular place among imaging systems due to its special advantages, such as not using ionizing radiation, being real-time, and having a portable and cheap system. On the other hand, this type of imaging has some limitations that have drawn the attention of many researchers to try to solve these problems. The presence of noise and artifacts, the need for a lot of training and experience of users, differences of opinion between the diagnosis of different experts, or even differences in the diagnosis of an expert at different times are some of these limitations.

Deep learning as a new method has been used in many fields in recent years, including in medical imaging. The use of deep learning in ultrasound imaging and in automating diagnosis from ultrasound images is a relatively new field that promises valuable achievements in improving these systems.

The purpose of this Special Issue is to provide an environment for presenting the latest findings and ideas of researchers in the application of deep learning in improving ultrasound systems and automating the diagnosis of diseases.

Dr. Hamid Behnam
Guest Editor

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

  • deep learning
  • ultrasound
  • echocardiography
  • cancer
  • coronary artery
  • ultrasound beam forming
  • segmentation
  • classification
  • high-intensity focused ultrasound
  • tomography
  • thermometry
  • speckle noise
  • artifact
  • fetal ultrasound
  • RF signals

Published Papers (4 papers)

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

Research

Jump to: Review

17 pages, 2539 KiB  
Article
Tumor Segmentation in Colorectal Ultrasound Images Using an Ensemble Transfer Learning Model: Towards Intra-Operative Margin Assessment
by Freija Geldof, Constantijn W. A. Pruijssers, Lynn-Jade S. Jong, Dinusha Veluponnar, Theo J. M. Ruers and Behdad Dashtbozorg
Diagnostics 2023, 13(23), 3595; https://doi.org/10.3390/diagnostics13233595 - 04 Dec 2023
Cited by 1 | Viewed by 941
Abstract
Tumor boundary identification during colorectal cancer surgery can be challenging, and incomplete tumor removal occurs in approximately 10% of the patients operated for advanced rectal cancer. In this paper, a deep learning framework for automatic tumor segmentation in colorectal ultrasound images was developed, [...] Read more.
Tumor boundary identification during colorectal cancer surgery can be challenging, and incomplete tumor removal occurs in approximately 10% of the patients operated for advanced rectal cancer. In this paper, a deep learning framework for automatic tumor segmentation in colorectal ultrasound images was developed, to provide real-time guidance on resection margins using intra-operative ultrasound. A colorectal ultrasound dataset was acquired consisting of 179 images from 74 patients, with ground truth tumor annotations based on histopathology results. To address data scarcity, transfer learning techniques were used to optimize models pre-trained on breast ultrasound data for colorectal ultrasound data. A new custom gradient-based loss function (GWDice) was developed, which emphasizes the clinically relevant top margin of the tumor while training the networks. Lastly, ensemble learning methods were applied to combine tumor segmentation predictions of multiple individual models and further improve the overall tumor segmentation performance. Transfer learning outperformed training from scratch, with an average Dice coefficient over all individual networks of 0.78 compared to 0.68. The new GWDice loss function clearly decreased the average tumor margin prediction error from 1.08 mm to 0.92 mm, without compromising the segmentation of the overall tumor contour. Ensemble learning further improved the Dice coefficient to 0.84 and the tumor margin prediction error to 0.67 mm. Using transfer and ensemble learning strategies, good tumor segmentation performance was achieved despite the relatively small dataset. The developed US segmentation model may contribute to more accurate colorectal tumor resections by providing real-time intra-operative feedback on tumor margins. Full article
(This article belongs to the Special Issue Application of Deep Learning in Medical Ultrasound)
Show Figures

Figure 1

11 pages, 640 KiB  
Article
Thyroid Nodule Detection and Region Estimation in Ultrasound Images: A Comparison between Physicians and an Automated Decision Support System Approach
by Elmer Jeto Gomes Ataide, Mathews S. Jabaraj, Simone Schenke, Manuela Petersen, Sarvar Haghghi, Jan Wuestemann, Alfredo Illanes, Michael Friebe and Michael C. Kreissl
Diagnostics 2023, 13(18), 2873; https://doi.org/10.3390/diagnostics13182873 - 07 Sep 2023
Viewed by 774
Abstract
Background: Thyroid nodules are very common. In most cases, they are benign, but they can be malignant in a low percentage of cases. The accurate assessment of these nodules is critical to choosing the next diagnostic steps and potential treatment. Ultrasound (US) imaging, [...] Read more.
Background: Thyroid nodules are very common. In most cases, they are benign, but they can be malignant in a low percentage of cases. The accurate assessment of these nodules is critical to choosing the next diagnostic steps and potential treatment. Ultrasound (US) imaging, the primary modality for assessing these nodules, can lack objectivity due to varying expertise among physicians. This leads to observer variability, potentially affecting patient outcomes. Purpose: This study aims to assess the potential of a Decision Support System (DSS) in reducing these variabilities for thyroid nodule detection and region estimation using US images, particularly in lesser experienced physicians. Methods: Three physicians with varying levels of experience evaluated thyroid nodules on US images, focusing on nodule detection and estimating cystic and solid regions. The outcomes were compared to those obtained from a DSS for comparison. Metrics such as classification match percentage and variance percentage were used to quantify differences. Results: Notable disparities exist between physician evaluations and the DSS assessments: the overall classification match percentage was just 19.2%. Individually, Physicians 1, 2, and 3 had match percentages of 57.6%, 42.3%, and 46.1% with the DSS, respectively. Variances in assessments highlight the subjectivity and observer variability based on physician experience levels. Conclusions: The evident variability among physician evaluations underscores the need for supplementary decision-making tools. Given its consistency, the CAD offers potential as a reliable “second opinion” tool, minimizing human-induced variabilities in the critical diagnostic process of thyroid nodules using US images. Future integration of such systems could bolster diagnostic precision and improve patient outcomes. Full article
(This article belongs to the Special Issue Application of Deep Learning in Medical Ultrasound)
Show Figures

Figure 1

16 pages, 4035 KiB  
Article
A Deep Learning Framework for the Detection of Abnormality in Cerebral Blood Flow Velocity Using Transcranial Doppler Ultrasound
by Naima Nasrin Nisha, Kanchon Kanti Podder, Muhammad E. H. Chowdhury, Mamun Rabbani, Md. Sharjis Ibne Wadud, Somaya Al-Maadeed, Sakib Mahmud, Amith Khandakar and Susu M. Zughaier
Diagnostics 2023, 13(12), 2000; https://doi.org/10.3390/diagnostics13122000 - 08 Jun 2023
Cited by 2 | Viewed by 1452
Abstract
Transcranial doppler (TCD) ultrasound is a non-invasive imaging technique that can be used for continuous monitoring of blood flow in the brain through the major cerebral arteries by calculating the cerebral blood flow velocity (CBFV). Since the brain requires a consistent supply of [...] Read more.
Transcranial doppler (TCD) ultrasound is a non-invasive imaging technique that can be used for continuous monitoring of blood flow in the brain through the major cerebral arteries by calculating the cerebral blood flow velocity (CBFV). Since the brain requires a consistent supply of blood to function properly and meet its metabolic demand, a change in CBVF can be an indication of neurological diseases. Depending on the severity of the disease, the symptoms may appear immediately or may appear weeks later. For the early detection of neurological diseases, a classification model is proposed in this study, with the ability to distinguish healthy subjects from critically ill subjects. The TCD ultrasound database used in this study contains signals from the middle cerebral artery (MCA) of 6 healthy subjects and 12 subjects with known neurocritical diseases. The classification model works based on the maximal blood flow velocity waveforms extracted from the TCD ultrasound. Since the signal quality of the recorded TCD ultrasound is highly dependent on the operator’s skillset, a noisy and corrupted signal can exist and can add biases to the classifier. Therefore, a deep learning classifier, trained on a curated and clean biomedical signal can reliably detect neurological diseases. For signal classification, this study proposes a Self-organized Operational Neural Network (Self-ONN)-based deep learning model Self-ResAttentioNet18, which achieves classification accuracy of 96.05% with precision, recall, f1 score, and specificity of 96.06%, 96.05%, 96.06%, and 96.09%, respectively. With an area under the ROC curve of 0.99, the model proves its feasibility to confidently classify middle cerebral artery (MCA) waveforms in near real-time. Full article
(This article belongs to the Special Issue Application of Deep Learning in Medical Ultrasound)
Show Figures

Figure 1

Review

Jump to: Research

39 pages, 1903 KiB  
Review
Ultrasound Image Analysis with Vision Transformers—Review
by Majid Vafaeezadeh, Hamid Behnam and Parisa Gifani
Diagnostics 2024, 14(5), 542; https://doi.org/10.3390/diagnostics14050542 - 04 Mar 2024
Viewed by 979
Abstract
Ultrasound (US) has become a widely used imaging modality in clinical practice, characterized by its rapidly evolving technology, advantages, and unique challenges, such as a low imaging quality and high variability. There is a need to develop advanced automatic US image analysis methods [...] Read more.
Ultrasound (US) has become a widely used imaging modality in clinical practice, characterized by its rapidly evolving technology, advantages, and unique challenges, such as a low imaging quality and high variability. There is a need to develop advanced automatic US image analysis methods to enhance its diagnostic accuracy and objectivity. Vision transformers, a recent innovation in machine learning, have demonstrated significant potential in various research fields, including general image analysis and computer vision, due to their capacity to process large datasets and learn complex patterns. Their suitability for automatic US image analysis tasks, such as classification, detection, and segmentation, has been recognized. This review provides an introduction to vision transformers and discusses their applications in specific US image analysis tasks, while also addressing the open challenges and potential future trends in their application in medical US image analysis. Vision transformers have shown promise in enhancing the accuracy and efficiency of ultrasound image analysis and are expected to play an increasingly important role in the diagnosis and treatment of medical conditions using ultrasound imaging as technology progresses. Full article
(This article belongs to the Special Issue Application of Deep Learning in Medical Ultrasound)
Show Figures

Figure 1

Back to TopTop