Submit to Diagnostics Review for Diagnostics Propose a Special Issue

Journal Menu

Journal Browser

Deep Learning-Based Models for Medical Imaging Diagnosis

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 "Machine Learning and Artificial Intelligence in Diagnostics".

Deadline for manuscript submissions: closed (30 June 2023) | Viewed by 5477

Share This Special Issue

Special Issue Editor

Dr. Mohammad Khishe

E-Mail Website
Guest Editor

Department of Electronic Engineering, Imam Khomeini Marine Science University of Nowshahr, Nowshahr 16846-13114, Iran
Interests: deep learning; artificial intelligence; data mining

Special Issue Information

Dear Colleagues,

The principles of Deep Learning (DL) and its significance in medical diagnostic imaging are explained in Deep Learning Models for Medical Imaging using two distinct practical examples: (1) cytology image processing and (2) disease screening, prediction, and decision making. Both research studies used public datasets in their corresponding experimental studies; Custom CNN, OptiCNN, CovNet, ResNet, AlexNet, GoogleNet, InceptionNet, LeNet, and DenseNet are a few of the DL models that were employed. The outcomes include both "with" and "without" transfer learning, data augmentation, composite networks, and other optimization techniques. DL models for diagnostic imaging are accessible to a wide audience, from students commencing their academic careers to seasoned researchers and scientists in academia and industry. With a focus on case studies in medical information and image processing, this Special Issue aims to establish the foundation for DL applications, discuss various DL-based diagnostics applications with a focus on personalized treatments, and provide a summary of the frameworks for a wider integration of various methodologies in clinical practice.

Potential subjects could revolve around, but are not constrained to:

Data analysis techniques, frameworks, algorithms, and best practices based on DL techniques including evolved models, hybrid models, and reinforcement learning;
Techniques for evolving DL, such as hyperparameter tuning, parameter optimization, etc.;
Techniques for recognizing interactions and integrating various data modalities using DL-based models.

Dr. Mohammad Khishe
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

medical imaging diagnosis
deep convolutional neural network
deep learning
CT-scan
X-ray

Published Papers (4 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

12 pages, 2520 KiB

Open AccessArticle

Deep Learner System Based on Focal Color Retinal Fundus Images to Assist in Diagnosis

by Yanli Zou, Yujuan Wang, Xiangbin Kong, Tingting Chen, Jiangna Chen and Yiqun Li

Diagnostics 2023, 13(18), 2985; https://doi.org/10.3390/diagnostics13182985 - 18 Sep 2023

Viewed by 838

Abstract

Retinal diseases are a serious and widespread ophthalmic disease that seriously affects patients’ vision and quality of life. With the aging of the population and the change in lifestyle, the incidence rate of retinal diseases has increased year by year. However, traditional diagnostic methods often require experienced doctors to analyze and judge fundus images, which carries the risk of subjectivity and misdiagnosis. This paper will analyze an intelligent medical system based on focal retinal image-aided diagnosis and use a convolutional neural network (CNN) to recognize, classify, and detect hard exudates (HEs) in fundus images (FIs). The research results indicate that under the same other conditions, the accuracy, recall, and precision of the system in diagnosing five types of patients with pathological changes under color retinal FIs range from 86.4% to 98.6%. Under conventional retinopathy FIs, the accuracy, recall, and accuracy of the system in diagnosing five types of patients ranged from 70.1% to 85%. The results show that the application of focus color retinal FIs in the intelligent medical system has high accuracy and reliability for the early detection and diagnosis of diabetic retinopathy and has important clinical applications. Full article

(This article belongs to the Special Issue Deep Learning-Based Models for Medical Imaging Diagnosis)

► Show Figures

Figure 1

20 pages, 8165 KiB

Open AccessArticle

A Deep Learning Model Based on Capsule Networks for COVID Diagnostics through X-ray Images

by Gabriela Rangel, Juan C. Cuevas-Tello, Mariano Rivera and Octavio Renteria

Diagnostics 2023, 13(17), 2858; https://doi.org/10.3390/diagnostics13172858 - 04 Sep 2023

Cited by 1 | Viewed by 954

Abstract

X-ray diagnostics are widely used to detect various diseases, such as bone fracture, pneumonia, or intracranial hemorrhage. This method is simple and accessible in most hospitals, but requires an expert who is sometimes unavailable. Today, some diagnoses are made with the help of deep learning algorithms based on Convolutional Neural Networks (CNN), but these algorithms show limitations. Recently, Capsule Networks (CapsNet) have been proposed to overcome these problems. In our work, CapsNet is used to detect whether a chest X-ray image has disease (COVID or pneumonia) or is healthy. An improved model called DRCaps is proposed, which combines the advantage of CapsNet and the dilation rate (dr) parameter to manage images with 226 × 226 resolution. We performed experiments with 16,669 chest images, in which our model achieved an accuracy of 90%. Furthermore, the model size is 11M with a reconstruction stage, which helps to avoid overfitting. Experiments show how the reconstruction stage works and how we can avoid the max-pooling operation for networks with a stride and dilation rate to downsampling the convolution layers. In this paper, DRCaps is superior to other comparable models in terms of accuracy, parameters, and image size handling. The main idea is to keep the model as simple as possible without using data augmentation or a complex preprocessing stage. Full article

(This article belongs to the Special Issue Deep Learning-Based Models for Medical Imaging Diagnosis)

► Show Figures

Figure 1

11 pages, 3677 KiB

Open AccessArticle

Deep-Learning-Based Image Denoising in Imaging of Urolithiasis: Assessment of Image Quality and Comparison to State-of-the-Art Iterative Reconstructions

by Robert Terzis, Robert Peter Reimer, Christian Nelles, Erkan Celik, Liliana Caldeira, Axel Heidenreich, Enno Storz, David Maintz, David Zopfs and Nils Große Hokamp

Diagnostics 2023, 13(17), 2821; https://doi.org/10.3390/diagnostics13172821 - 31 Aug 2023

Viewed by 784

Abstract

This study aimed to compare the image quality and diagnostic accuracy of deep-learning-based image denoising reconstructions (DLIDs) to established iterative reconstructed algorithms in low-dose computed tomography (LDCT) of patients with suspected urolithiasis. LDCTs (CTDIvol, 2 mGy) of 76 patients (age: 40.3 ± 5.2 years, M/W: 51/25) with suspected urolithiasis were retrospectively included. Filtered-back projection (FBP), hybrid iterative and model-based iterative reconstruction (HIR/MBIR, respectively) were reconstructed. FBP images were processed using a Food and Drug Administration (FDA)-approved DLID. ROIs were placed in renal parenchyma, fat, muscle and urinary bladder. Signal- and contrast-to-noise ratios (SNR/CNR, respectively) were calculated. Two radiologists evaluated image quality on five-point Likert scales and urinary stones. The results showed a progressive decrease in image noise from FBP, HIR and DLID to MBIR with significant differences between each method (p < 0.05). SNR and CNR were comparable between MBIR and DLID, while it was significantly lower in HIR followed by FBP (e.g., SNR: 1.5 ± 0.3; 1.4 ± 0.4; 1.0 ± 0.3; 0.7 ± 0.2, p < 0.05). Subjective analysis confirmed best image quality in MBIR, followed by DLID and HIR, both being superior to FBP (p < 0.05). Diagnostic accuracy for urinary stone detection was best using MBIR (0.94), lowest using FBP (0.84) and comparable between DLID (0.90) and HIR (0.90). Stone size measurements were consistent between all reconstructions and showed excellent correlation (r² = 0.958–0.975). In conclusion, MBIR yielded the highest image quality and diagnostic accuracy, with DLID producing better results than HIR and FBP in image quality and matching HIR in diagnostic precision. Full article

(This article belongs to the Special Issue Deep Learning-Based Models for Medical Imaging Diagnosis)

► Show Figures

Figure 1

16 pages, 15235 KiB

Open AccessArticle

Automated Skeletal Bone Age Assessment with Two-Stage Convolutional Transformer Network Based on X-ray Images

by Xiongwei Mao, Qinglei Hui, Siyu Zhu, Wending Du, Chenhui Qiu, Xiaoping Ouyang and Dexing Kong

Diagnostics 2023, 13(11), 1837; https://doi.org/10.3390/diagnostics13111837 - 24 May 2023

Cited by 1 | Viewed by 1483

Abstract

Human skeletal development is continuous and staged, and different stages have various morphological characteristics. Therefore, bone age assessment (BAA) can accurately reflect the individual’s growth and development level and maturity. Clinical BAA is time consuming, highly subjective, and lacks consistency. Deep learning has made considerable progress in BAA in recent years by effectively extracting deep features. Most studies use neural networks to extract global information from input images. However, clinical radiologists are highly concerned about the ossification degree in some specific regions of the hand bones. This paper proposes a two-stage convolutional transformer network to improve the accuracy of BAA. Combined with object detection and transformer, the first stage mimics the bone age reading process of the pediatrician, extracts the hand bone region of interest (ROI) in real time using YOLOv5, and proposes hand bone posture alignment. In addition, the previous information encoding of biological sex is integrated into the feature map to replace the position token in the transformer. The second stage extracts features within the ROI by window attention, interacts between different ROIs by shifting the window attention to extract hidden feature information, and penalizes the evaluation results using a hybrid loss function to ensure its stability and accuracy. The proposed method is evaluated on the data from the Pediatric Bone Age Challenge organized by the Radiological Society of North America (RSNA). The experimental results show that the proposed method achieves a mean absolute error (MAE) of 6.22 and 4.585 months on the validation and testing sets, respectively, and the cumulative accuracy within 6 and 12 months reach 71% and 96%, respectively, which is comparable to the state of the art, markedly reducing the clinical workload and realizing rapid, automatic, and high-precision assessment. Full article

(This article belongs to the Special Issue Deep Learning-Based Models for Medical Imaging Diagnosis)

► Show Figures

Journal Menu

Journal Browser

Deep Learning-Based Models for Medical Imaging Diagnosis

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Published Papers (4 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI