AI Medicine

AI Medicine: Pioneering the Integration of Artificial Intelligence in Healthcare

Yu-Dong Yao — 2024-04-17

Editorial

AI Medicine: Pioneering the Integration of Artificial Intelligence in Healthcare

Yu-Dong Yao

Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ 07030, USA

Received: 15 April 2024; Accepted: 17 April 2024; Published: 17 April 2024

A Short Survey on Computer-Aided Diagnosis of Alzheimer's Disease: Unsupervised Learning, Transfer Learning, and Other Machine Learning Methods

Siyuan Lu — 2024-05-31

Review

A Short Survey on Computer-Aided Diagnosis of Alzheimer’s Disease: Unsupervised Learning, Transfer Learning, and Other Machine Learning Methods

Si-Yuan Lu

School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China

Received: 15 April 2024; Revised: 7 May 2024; Accepted: 14 May 2024; Published: 31 May 2024

Abstract: Alzheimer’s Disease (AD) is a neurodegenerative disorder, which is irreversible and incurable. Early diagnosis plays a significant role in controlling the progression of AD and improving the patient’s quality of life. Computer-aided diagnosis (CAD) methods have shown great potential to assist doctors in analyzing medical data, such as magnetic resonance images, positron emission tomography, and mini-mental state examination. Contributed by the advanced deep learning models, predictions of CAD methods for AD are becoming more and more accurate, which can provide a reference and verification for manual screening. In this paper, a short survey on the application of recent CAD methods in AD detection is presented. The advantages and drawbacks of these methods are discussed in detail, especially the methods based on convolutional neural networks, and the future research directions are summarized subsequently. With this survey, we hope to promote the development of CAD for early detection of AD.

A State-of-the-Art Survey of Deep Learning for Lumbar Spine Image Analysis: X-ray, CT, and MRI

Ruyi Zhang — 2024-07-17

Article

A State-of-the-Art Survey of Deep Learning for Lumbar Spine Image Analysis: X-Ray, CT, and MRI

Ruyi Zhang ^1,2,*

¹ College of Medicine and Biological Information Engineering, Northeastern University, Chuangxin Road, Shenyang, 110016, Liaoning, China; 2390160@stu.neu.edu.cn

² Research Institute for Medical and Biological Engineering, Ningbo University, Fenghua Road, Ningbo, 315211, Zhejiang, China

Received: 17 April 2024; Revised: 12 June 2024; Accepted: 22 June 2024; Published: 17 July 2024

Abstract: Lumbar spine diseases not only endanger patients' physical health but also bring about severe psychological impacts and generate substantial medical costs. Reliable lumbar spine image analysis is crucial for diagnosing and treating lumbar spine diseases. In recent years, deep learning has rapidly developed in computer vision and medical imaging, with an increasing number of researchers applying it to the field of lumbar spine imaging. This paper studies the current state of research in deep learning applications across various modalities of lumbar spine image analysis, including X-ray, CT, and MRI. We first review the public datasets available for various tasks involving lumbar spine images. Secondly, we study the different models used in various lumbar spine image modalities (X-ray, CT, and MRI) and their applications in different tasks (classification, detection, segmentation, and reconstruction). Finally, we discuss the challenges of using deep learning in lumbar spine image analysis and provide an outlook on research and development prospects.

Ultrasonic Image's Annotation Removal: A Self-supervised Noise2Noise Approach

Yuanheng Zhang — 2024-07-17

Article

Ultrasonic Image’s Annotation Removal: A Self-supervised Noise2Noise Approach

Yuanheng Zhang ¹, Nan Jiang ², Zhaoheng Xie ³, Junying Cao ²^,*, and Yueyang Teng ^1,*

¹ College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110016, China
² The Department of Ultrasound, General Hospital of Northern Theater Command, Shenyang 110169, China
³ The Institute of Medical Technology, Peking University, Beijing 100191, China
* Correspondence: shenzongchaosheng@163.com (J.C.); tengyy@bmie.neu.edu.cn (Y.T.)

Received: 11 March 2024; Revised: 25 May 2024; Accepted: 28 May 2024; Published: 17 July 2024

Abstract: Accurately annotated ultrasonic images are vital components of a high-quality medical report. Hospitals often have strict guidelines on the types of annotations that should appear on imaging results. However, manually inspecting these images can be a cumbersome task. While a neural network could potentially automate the process, training such a model typically requires a dataset of paired input and target images, which in turn involves significant human labor. This study introduces an automated approach for detecting annotations in images. This is achieved by treating the annotations as noise, creating a self-supervised pretext task and using a model trained under the Noise2Noise scheme to restore the image to a clean state. We tested a variety of model structures on the denoising task against different types of annotation, including body marker annotation, radial line annotation, etc. Our results demonstrate that most models trained under the Noise2Noise scheme outperformed their counterparts trained with noisy-clean data pairs. The costumed U-Net yielded the most optimal outcome on the body marker annotation dataset, with high scores on segmentation precision and reconstruction similarity. Our approach streamlines the laborious task of manually quality-controlling ultrasound scans, with minimal human labor involved, making the quality control process efficient and scalable.

A Comparative Study of Deep Learning in Breast Ultrasound Lesion Detection: From Two-Stage to One-Stage, from Anchor-Based to Anchor-Free

Yu Wang — 2024-09-04

Article

A Comparative Study of Deep Learning in Breast Ultrasound Lesion Detection: From Two-Stage to One-Stage, from Anchor-Based to Anchor-Free

Yu Wang ¹, Qi Zhao ¹, Baihua Zhang ², Dingcheng Tian ¹, Ruyi Zhang ¹ and Wan Zhong ^3,∗

¹ College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110024 , China

² Research Institute for Medical and Biological Engineering, Ningbo University, Ningbo 315000, China

³General Hospital of Northern Theater Command, Shenyang 110024, China

∗ Correspondence: wzhong_88@163.com

Received: 16 July 2024; Revised: 26 August 2024; Accepted: 27 August 2024; Published: 4 September 2024

Abstract: Breast cancer is one of the most common tumors among women in the world, and its early screening is crucial to improve the survival rate of patients. Breast ultrasound, with the characteristics of non radiation, real-time imaging and easy operation, has become a common method for breast cancer detection. However, this method has some problems, such as low imaging quality and strong subjectivity of diagnosis results, which affect the accurate diagnosis of breast cancer. With the ongoing advancement of deep learning technology, intelligent breast cancer detection systems have effectively overcome these challenges, enhancing diagnostic accuracy and efficiency. This study uses nine popular deep learning object detection networks (including two-stage, one-stage, anchor-based, and anchor-free networks) for the detection of breast lesions and compares the results of these methods. The experiments show that the anchor-based Single Shot MultiBox Detector (SSD) network excels in overall performance, while the anchor-free Fully Convolutional One-stage Object Detector (FCOS) exhibits the best generalization ability. Moreover, the results also indicate that, in the context of breast lesion detection, anchor-based networks generally outperform anchor-free networks.

ML-Based RNA Secondary Structure Prediction Methods: A Survey

Qi Zhao — 2024-10-29

Article

ML-Based RNA Secondary Structure Prediction Methods: A Survey

Qi Zhao ¹, Jingjing Chen ¹, Zheng Zhao ², Qian Mao ³, Haoxuan Shi ¹ and Xiaoya Fan ^4,∗

¹ School of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110000, China

² School of Artificial Intelligence, Dalian Maritime University, Dalian 116000, China

³Department of Food Science and Engineering, College of Light Industry, Liaoning University, Shenyang 110000, China

⁴School of Software, Dalian University of Technology, Key Laboratory for Ubiquitous Network and Service Software, Dalian 116000, China

∗ Correspondence: xiaoyafan@dlut.edu.cn

Received: 6 May 2024; Revised: 17 October 2024; Accepted: 22 October 2024; Published: 29 October 2024

Abstract: The secondary structure of noncoding RNAs (ncRNA) is significantly related to their functions, emphasizing the importance and value of identifying ncRNA secondary structure. Computational prediction methods have been widely used in this field. However, the performance of existing computational methods has plateaued in recent years despite various advancements. Fortunately, the emergence of machine learning, particularly deep learning, has brought new hope to this field. In this review, we present a comprehensive overview of machine learning-based methods for predicting RNA secondary structures, with a particular emphasis on deep learning approaches. Additionally, we discuss the current challenges and prospects in RNA secondary structure prediction.

Low Dose CT Image Denoising: A Comparative Study of Deep Learning Models and Training Strategies

Heng Zhao — 2024-11-05

Article

Low Dose CT Image Denoising: A Comparative Study of Deep Learning Models and Training Strategies

Heng Zhao ¹, Like Qian ¹, Yaqi Zhu ¹ and Dingcheng Tian ^1,2,∗

¹ Research Institute for Medical and Biological Engineering, Ningbo University, Ningbo 315211, China

² College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110016, China

∗ Correspondence: 2310520@stu.neu.edu.cn

Received: 8 August 2024; Revised: 10 October 2024; Accepted: 14 October 2024; Published: 5 November 2024

Abstract: Low-dose computed tomography (LDCT) denoising is an important topic in CT image research. Compared with normal-dose CT images, LDCT can reduce the radiation dose of X-rays, decreasing the radiation burden on the human body, which is beneficial to human health. However, quantum noise caused by low-dose rays will reduce the quality of CT images, thereby decreasing the accuracy of clinical diagnosis. In recent years, deep learning-based denoising methods have shown promising advantages in this field. Researchers have proposed some optimized models for low-dose CT image denoising. These methods have enhanced the application of low-dose CT image denoising from different aspects. From the perspective of experimental research, this paper investigates and evaluates some top deep learning models proposed in the field of low-dose image denoising in recent years, with the aim of determining the best models and training strategies for this task. We conducted experiments on seven deep learning models (REDCNN, EDCNN, QAE, OCTNet, UNet, WGAN, CTformer) on the AAPM dataset and the Piglet dataset. Our research shows that UNet has the best denoising effect among the models, obtaining PSNR = 33.06 (AAPM dataset) and PSNR = 31.21 (Piglet dataset), and good generalization capacity is also observed. However, UNet has a large number of parameters, and the time it takes to process an image is about 8 ms, while EDCNN takes about 4.8 ms to process an image, and its average PSNR is ranked second after UNet. EDCNN strikes a balance between denoising performance and processing efficiency, making it ideal for low-dose CT image denoising tasks.