Deep Learning in Medical Image Analysis

Zhang, Yudong; Górriz, Juan Manuel; Dong, Zhengchao

doi:10.3390/jimaging7040074

Cited by 52 publications

(21 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the majority of the last few decades, medical images have been interpreted by radiologists and other human specialists. However, academics and medical professionals are starting to use computer-assisted therapy due to the large range of disorders and potential exhaustion of human capacity [7].…”

Section: Figure 1 -Examples Of the Images From The Bach Challenge: A)...mentioning

confidence: 99%

Classification of breast cancer images using new transfer learning techniques

2023

ijcsm

View full text Add to dashboard Cite

Breast cancer is one of the most common types of cancer among women, which requires building smart systems to help doctors and early detection of cancer. Deep learning applications have emerged in many fields, especially in health care, but there are still some limitations in this technique, such as the small number of classified medical images needed to train deep learning models, to solve this problem, transfer learning technology appeared based on transferring knowledge from pre-trained models on ImageNet and setting them to the current task, but there is still a problem that the features extracted from ImageNet are not medical, so this paper aims to find a solution to this problem by using new techniques for transfer learning by taking advantage of the presence of unclassified medical images of the same disease to reduce the impact of ImageNet. The proposed approach was applied to the modified Xception model to classify the histological images of breast cancer in the ICIAR 2018 dataset into four classes: invasive carcinoma, in situ carcinoma, benign, and normal. The proposed approach has obtained 99%, 99.003%, 98.995%, 99%, 98.55%, and 99.14% for accuracy, precision, recall, F1-score, sensitivity, and specificity respectively. Our work has been compared with previous works.

show abstract

Section: Figure 1 -Examples Of the Images From The Bach Challenge: A)...mentioning

confidence: 99%

Classification of breast cancer images using new transfer learning techniques

2023

ijcsm

View full text Add to dashboard Cite

show abstract

“…Segmentation using deep learning aids in obtaining useful information by performing rib suppression in CXRs, resulting in a more accurate diagnosis [13]. Due to the growing demand for CAD, deep learning has shown significant progress in medical imaging [14,15].…”

Section: Introductionmentioning

confidence: 99%

Segmentation Performance Comparison Considering Regional Characteristics in Chest X-ray Using Deep Learning

Lee

Kim

2022

Sensors

View full text Add to dashboard Cite

Chest radiography is one of the most widely used diagnostic methods in hospitals, but it is difficult to read clearly because several human organ tissues and bones overlap. Therefore, various image processing and rib segmentation methods have been proposed to focus on the desired target. However, it is challenging to segment ribs elaborately using deep learning because they cannot reflect the characteristics of each region. Identifying which region has specific characteristics vulnerable to deep learning is an essential indicator of developing segmentation methods in medical imaging. Therefore, it is necessary to compare the deep learning performance differences based on regional characteristics. This study compares the differences in deep learning performance based on the rib region to verify whether deep learning reflects the characteristics of each part and to demonstrate why this regional performance difference has occurred. We utilized 195 normal chest X-ray datasets with data augmentation for learning and 5-fold cross-validation. To compare segmentation performance, the rib image was divided vertically and horizontally based on the spine, clavicle, heart, and lower organs, which are characteristic indicators of the baseline chest X-ray. Resultingly, we found that the deep learning model showed a 6–7% difference in the segmentation performance depending on the regional characteristics of the rib. We verified that the performance differences in each region cannot be ignored. This study will enable a more precise segmentation of the ribs and the development of practical deep learning algorithms.

show abstract

“…The most widely used techniques include data augmentation, generation of synthetic images with generative models (11), and cutting of the number of images from classes containing the highest number of pictures. (5) In intra-class classification problems, intra-class similarities, same class dissimilarities, limited color intensity distribution, and intensity similarity between cancerous lesions and surrounding tissues often occur and lead to high misclassification rate. (6) In some datasets, the size of images is unequal.…”

Section: Introductionmentioning

confidence: 99%

“…Due to the growing number of patients, it can be unmanageable for a doctor or a specialist to diagnose the disease in the early stage without any automated system. As interpretation of many medical images can lead to fatigue of clinical experts, computer-aided interventions may assist them in reducing the strain associated with high-performance interpretation ( 5 ). With the development of CNN-based applications in medical image analysis ( 6 ), clinical specialists benefit from CAD by utilizing outputs of a computerized analysis to identify lesions, evaluate the existence and extent of diseases, and improve the accuracy and reliability of diagnosis by decreasing false negative rates.…”

Section: Introductionmentioning

confidence: 99%

MNet-10: A robust shallow convolutional neural network model performing ablation study on medical images assessing the effectiveness of applying optimal data augmentation technique

et al. 2022

View full text Add to dashboard Cite

Interpretation of medical images with a computer-aided diagnosis (CAD) system is arduous because of the complex structure of cancerous lesions in different imaging modalities, high degree of resemblance between inter-classes, presence of dissimilar characteristics in intra-classes, scarcity of medical data, and presence of artifacts and noises. In this study, these challenges are addressed by developing a shallow convolutional neural network (CNN) model with optimal configuration performing ablation study by altering layer structure and hyper-parameters and utilizing a suitable augmentation technique. Eight medical datasets with different modalities are investigated where the proposed model, named MNet-10, with low computational complexity is able to yield optimal performance across all datasets. The impact of photometric and geometric augmentation techniques on different datasets is also evaluated. We selected the mammogram dataset to proceed with the ablation study for being one of the most challenging imaging modalities. Before generating the model, the dataset is augmented using the two approaches. A base CNN model is constructed first and applied to both the augmented and non-augmented mammogram datasets where the highest accuracy is obtained with the photometric dataset. Therefore, the architecture and hyper-parameters of the model are determined by performing an ablation study on the base model using the mammogram photometric dataset. Afterward, the robustness of the network and the impact of different augmentation techniques are assessed by training the model with the rest of the seven datasets. We obtain a test accuracy of 97.34% on the mammogram, 98.43% on the skin cancer, 99.54% on the brain tumor magnetic resonance imaging (MRI), 97.29% on the COVID chest X-ray, 96.31% on the tympanic membrane, 99.82% on the chest computed tomography (CT) scan, and 98.75% on the breast cancer ultrasound datasets by photometric augmentation and 96.76% on the breast cancer microscopic biopsy dataset by geometric augmentation. Moreover, some elastic deformation augmentation methods are explored with the proposed model using all the datasets to evaluate their effectiveness. Finally, VGG16, InceptionV3, and ResNet50 were trained on the best-performing augmented datasets, and their performance consistency was compared with that of the MNet-10 model. The findings may aid future researchers in medical data analysis involving ablation studies and augmentation techniques.

show abstract

Deep Learning in Medical Image Analysis

Abstract: Over recent years, deep learning (DL) has established itself as a powerful tool across a broad spectrum of domains in imaging—e [...]

Cited by 52 publications

References 23 publications

Classification of breast cancer images using new transfer learning techniques

Classification of breast cancer images using new transfer learning techniques

Segmentation Performance Comparison Considering Regional Characteristics in Chest X-ray Using Deep Learning

MNet-10: A robust shallow convolutional neural network model performing ablation study on medical images assessing the effectiveness of applying optimal data augmentation technique

Contact Info

Product

Resources

About