Localization of lung abnormalities on chest X-rays using self-supervised equivariant attention

D'souza, G. I.; Reddy, Navyasri; Manjunath, K.

doi:10.1007/s13534-022-00249-5

Cited by 5 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We identified five major categories of disease localization methods in studies, including (1) self-training, (2) graphical models, (3) multiple-instance learning, (4) weak localization by extraction of visualization from classification task, and (5) seeding-based weakly supervised segmentation. The studies in [ 44 , 64 , 69 , 105 , 107 , 110 , 112 ] proposed approaches that are clear, robust, and efficient in detecting tuberculosis-consistent regions. These methods utilize bounding boxes to improve their performance and present their results using the intersection over the bounding box (IoBB) metric over the ChestX-ray8 and ChestX-ray14 datasets.…”

Section: Discusionmentioning

confidence: 99%

Weak Localization of Radiographic Manifestations in Pulmonary Tuberculosis from Chest X-ray: A Systematic Review

Feyisa,

Ayano,

Debelee

et al. 2023

Sensors

View full text Add to dashboard Cite

Pulmonary tuberculosis (PTB) is a bacterial infection that affects the lung. PTB remains one of the infectious diseases with the highest global mortalities. Chest radiography is a technique that is often employed in the diagnosis of PTB. Radiologists identify the severity and stage of PTB by inspecting radiographic features in the patient’s chest X-ray (CXR). The most common radiographic features seen on CXRs include cavitation, consolidation, masses, pleural effusion, calcification, and nodules. Identifying these CXR features will help physicians in diagnosing a patient. However, identifying these radiographic features for intricate disorders is challenging, and the accuracy depends on the radiologist’s experience and level of expertise. So, researchers have proposed deep learning (DL) techniques to detect and mark areas of tuberculosis infection in CXRs. DL models have been proposed in the literature because of their inherent capacity to detect diseases and segment the manifestation regions from medical images. However, fully supervised semantic segmentation requires several pixel-by-pixel labeled images. The annotation of such a large amount of data by trained physicians has some challenges. First, the annotation requires a significant amount of time. Second, the cost of hiring trained physicians is expensive. In addition, the subjectivity of medical data poses a difficulty in having standardized annotation. As a result, there is increasing interest in weak localization techniques. Therefore, in this review, we identify methods employed in the weakly supervised segmentation and localization of radiographic manifestations of pulmonary tuberculosis from chest X-rays. First, we identify the most commonly used public chest X-ray datasets for tuberculosis identification. Following that, we discuss the approaches for weakly localizing tuberculosis radiographic manifestations in chest X-rays. The weakly supervised localization of PTB can highlight the region of the chest X-ray image that contributed the most to the DL model’s classification output and help pinpoint the diseased area. Finally, we discuss the limitations and challenges of weakly supervised techniques in localizing TB manifestations regions in chest X-ray images.

show abstract

Section: Discusionmentioning

confidence: 99%

Weak Localization of Radiographic Manifestations in Pulmonary Tuberculosis from Chest X-ray: A Systematic Review

Feyisa,

Ayano,

Debelee

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The authors attempt to compensate for the lack of coloured images by applying transfer learning [7] knowledge from domains where the information collected from coloured data is abundant. The goal is to use existing deep neural network architectures like ResNet [8]. These architectures have been pre-trained on one of the most famous and diverse image datasets, ImageNet [9].…”

Section: Introductionmentioning

confidence: 99%

Colorizing Multi-Modal Medical Data: An Autoencoder-based Approach for Enhanced Anatomical Information in X-ray Images

Saini,

Venkatesh,

Ganesh

et al. 2024

EAI Endorsed Trans Perv Health Tech

View full text Add to dashboard Cite

Colourisation is the process of synthesising colours in black and white images without altering the image’s structural content and semantics. The authors explore the concept of colourisation, aiming to colourise the multi-modal medical data through X-rays. Colourized X-ray images have a better potential to portray anatomical information than their conventional monochromatic counterparts. These images contain precious anatomical information that, when colourised, will become very valuable and potentially display more information for clinical diagnosis. This will help improve understanding of these X-rays and significantly contribute to the arena of medical image analysis. The authors have implemented three models, a basic auto-encoder architecture, and two combined learnings of the autoencoder module with transfer learning of pre-trained neural networks. The unique feature of this proposed framework is that it can colourise any medical modality in the medical imaging domain. The framework’s performance is evaluated on a chest x-ray image dataset, and it has produced benchmark results enabling high-quality colourisation. The biggest challenge is the need for a correct solution for the mapping between intensity and colour. This makes human interaction and external information from medical professionals crucial for interpreting the results.

show abstract

Clinical Performance Evaluation of an Artificial Intelligence-Powered Amyloid Brain PET Quantification Method

Kang,

Heo,

Chung

et al. 2024

Nucl Med Mol Imaging

View full text Add to dashboard Cite

Purpose This study assesses the clinical performance of BTXBrain-Amyloid, an artificial intelligence-powered software for quantifying amyloid uptake in brain PET images. Methods 150 amyloid brain PET images were visually assessed by experts and categorized as negative and positive. Standardized uptake value ratio (SUVR) was calculated with cerebellum grey matter as the reference region, and receiver operating characteristic (ROC) and precision-recall (PR) analysis for BTXBrain-Amyloid were conducted. For comparison, same image processing and analysis was performed using Statistical Parametric Mapping (SPM) program. In addition, to evaluate the spatial normalization (SN) performance, mutual information (MI) between MRI template and spatially normalized PET images was calculated and SPM group analysis was conducted. Results Both BTXBrain and SPM methods discriminated between negative and positive groups. However, BTXBrain exhibited lower SUVR standard deviation (0.06 and 0.21 for negative and positive, respectively) than SPM method (0.11 and 0.25). In ROC analysis, BTXBrain had an AUC of 0.979, compared to 0.959 for SPM, while PR curves showed an AUC of 0.983 for BTXBrain and 0.949 for SPM. At the optimal cut-off, the sensitivity and specificity were 0.983 and 0.921 for BTXBrain and 0.917 and 0.921 for SPM12, respectively. MI evaluation also favored BTXBrain (0.848 vs. 0.823), indicating improved SN. In SPM group analysis, BTXBrain exhibited higher sensitivity in detecting basal ganglia differences between negative and positive groups. Conclusion BTXBrain-Amyloid outperformed SPM in clinical performance evaluation, also demonstrating superior SN and improved detection of deep brain differences. These results suggest the potential of BTXBrain-Amyloid as a valuable tool for clinical amyloid PET image evaluation.

show abstract

Localization of lung abnormalities on chest X-rays using self-supervised equivariant attention

Cited by 5 publications

References 16 publications

Weak Localization of Radiographic Manifestations in Pulmonary Tuberculosis from Chest X-ray: A Systematic Review

Weak Localization of Radiographic Manifestations in Pulmonary Tuberculosis from Chest X-ray: A Systematic Review

Colorizing Multi-Modal Medical Data: An Autoencoder-based Approach for Enhanced Anatomical Information in X-ray Images

Clinical Performance Evaluation of an Artificial Intelligence-Powered Amyloid Brain PET Quantification Method

Contact Info

Product

Resources

About