MyMedR

Displaying publications 21 - 40 of 120 in total

Abstract:

Sort:

Fulltext Intelligent screening systems for cervical cancer

Jusman Y, Ng SC, Abu Osman NA

ScientificWorldJournal, 2014;2014:810368.
PMID: 24955419 DOI: 10.1155/2014/810368

Advent of medical image digitalization leads to image processing and computer-aided diagnosis systems in numerous clinical applications. These technologies could be used to automatically diagnose patient or serve as second opinion to pathologists. This paper briefly reviews cervical screening techniques, advantages, and disadvantages. The digital data of the screening techniques are used as data for the computer screening system as replaced in the expert analysis. Four stages of the computer system are enhancement, features extraction, feature selection, and classification reviewed in detail. The computer system based on cytology data and electromagnetic spectra data achieved better accuracy than other data.

Matched MeSH terms: Image Processing, Computer-Assisted/methods*
Fulltext Estimating body related soft biometric traits in video frames

Arigbabu OA, Ahmad SM, Adnan WA, Yussof S, Iranmanesh V, Malallah FL

ScientificWorldJournal, 2014;2014:460973.
PMID: 25121120 DOI: 10.1155/2014/460973

Soft biometrics can be used as a prescreening filter, either by using single trait or by combining several traits to aid the performance of recognition systems in an unobtrusive way. In many practical visual surveillance scenarios, facial information becomes difficult to be effectively constructed due to several varying challenges. However, from distance the visual appearance of an object can be efficiently inferred, thereby providing the possibility of estimating body related information. This paper presents an approach for estimating body related soft biometrics; specifically we propose a new approach based on body measurement and artificial neural network for predicting body weight of subjects and incorporate the existing technique on single view metrology for height estimation in videos with low frame rate. Our evaluation on 1120 frame sets of 80 subjects from a newly compiled dataset shows that the mentioned soft biometric information of human subjects can be adequately predicted from set of frames.

Matched MeSH terms: Image Processing, Computer-Assisted/methods
Fulltext Reducing scanning electron microscope charging by using exponential contrast stretching technique on post-processing images

Sim KS, Tan YY, Lai MA, Tso CP, Lim WK

J Microsc, 2010 Apr 1;238(1):44-56.
PMID: 20384837 DOI: 10.1111/j.1365-2818.2009.03328.x

An exponential contrast stretching (ECS) technique is developed to reduce the charging effects on scanning electron microscope images. Compared to some of the conventional histogram equalization methods, such as bi-histogram equalization and recursive mean-separate histogram equalization, the proposed ECS method yields better image compensation. Diode sample chips with insulating and conductive surfaces are used as test samples to evaluate the efficiency of the developed algorithm. The algorithm is implemented in software with a frame grabber card, forming the front-end video capture element.

Matched MeSH terms: Image Processing, Computer-Assisted/methods*
A discrimination method for the detection of pneumonia using chest radiograph

Noor NM, Rijal OM, Yunus A, Abu-Bakar SA

Comput Med Imaging Graph, 2010 Mar;34(2):160-6.
PMID: 19758785 DOI: 10.1016/j.compmedimag.2009.08.005

This paper presents a statistical method for the detection of lobar pneumonia when using digitized chest X-ray films. Each region of interest was represented by a vector of wavelet texture measures which is then multiplied by the orthogonal matrix Q(2). The first two elements of the transformed vectors were shown to have a bivariate normal distribution. Misclassification probabilities were estimated using probability ellipsoids and discriminant functions. The result of this study recommends the detection of pneumonia by constructing probability ellipsoids or discriminant function using maximum energy and maximum column sum energy texture measures where misclassification probabilities were less than 0.15.

Matched MeSH terms: Image Processing, Computer-Assisted/methods*
Diabetic retinopathy: a quadtree based blood vessel detection algorithm using RGB components in fundus images

Reza AW, Eswaran C, Hati S

J Med Syst, 2008 Apr;32(2):147-55.
PMID: 18461818

Blood vessel detection in retinal images is a fundamental step for feature extraction and interpretation of image content. This paper proposes a novel computational paradigm for detection of blood vessels in fundus images based on RGB components and quadtree decomposition. The proposed algorithm employs median filtering, quadtree decomposition, post filtration of detected edges, and morphological reconstruction on retinal images. The application of preprocessing algorithm helps in enhancing the image to make it better fit for the subsequent analysis and it is a vital phase before decomposing the image. Quadtree decomposition provides information on the different types of blocks and intensities of the pixels within the blocks. The post filtration and morphological reconstruction assist in filling the edges of the blood vessels and removing the false alarms and unwanted objects from the background, while restoring the original shape of the connected vessels. The proposed method which makes use of the three color components (RGB) is tested on various images of publicly available database. The results are compared with those obtained by other known methods as well as with the results obtained by using the proposed method with the green color component only. It is shown that the proposed method can yield true positive fraction values as high as 0.77, which are comparable to or somewhat higher than the results obtained by other known methods. It is also shown that the effect of noise can be reduced if the proposed method is implemented using only the green color component.

Matched MeSH terms: Image Processing, Computer-Assisted/methods*
Model-based compression for 3D medical images stored in the DICOM format

Logeswaran R, Eswaran C

J Med Syst, 2006 Apr;30(2):133-8.
PMID: 16705998

Many medical examinations involve acquisition of a large series of slice images for 3D reconstruction of the organ of interest. With the paperless hospital concept and telemedicine, there is very heavy utilization of limited electronic storage and transmission bandwidth. This paper proposes model-based compression to reduce the load on such resources, as well as aid diagnosis through the 3D reconstruction of the structures of interest, for images acquired by various modalities, such as MRI, Ultrasound, CT, PET etc. and stored in the DICOM file format. An example implementation for the biliary track in MRCP images is illustrated in the paper. Significant compression gains may be derived from the proposed method, and a suitable mixture of the models and raw images would enhance the patient medical history archives as the models may be stored in the DICOM file format used in most medical archiving systems.

Matched MeSH terms: Image Processing, Computer-Assisted/methods*
Fulltext Semantic representation of monogenean haptoral Bar image annotation

Abu A, Susan LL, Sidhu AS, Dhillon SK

BMC Bioinformatics, 2013;14:48.
PMID: 23398696 DOI: 10.1186/1471-2105-14-48

Digitised monogenean images are usually stored in file system directories in an unstructured manner. In this paper we propose a semantic representation of these images in the form of a Monogenean Haptoral Bar Image (MHBI) ontology, which are annotated with taxonomic classification, diagnostic hard part and image properties. The data we used are basically of the monogenean species found in fish, thus we built a simple Fish ontology to demonstrate how the host (fish) ontology can be linked to the MHBI ontology. This will enable linking of information from the monogenean ontology to the host species found in the fish ontology without changing the underlying schema for either of the ontologies.

Matched MeSH terms: Image Processing, Computer-Assisted/methods*
Intelligent microscopic approach for identification and recognition of citrus deformities

Safdar A, Khan MA, Shah JH, Sharif M, Saba T, Rehman A, et al.

Microsc Res Tech, 2019 Sep;82(9):1542-1556.
PMID: 31209970 DOI: 10.1002/jemt.23320

Plant diseases are accountable for economic losses in an agricultural country. The manual process of plant diseases diagnosis is a key challenge from last one decade; therefore, researchers in this area introduced automated systems. In this research work, automated system is proposed for citrus fruit diseases recognition using computer vision technique. The proposed method incorporates five fundamental steps such as preprocessing, disease segmentation, feature extraction and reduction, fusion, and classification. The noise is being removed followed by a contrast stretching procedure in the very first phase. Later, watershed method is applied to excerpt the infectious regions. The shape, texture, and color features are subsequently computed from these infection regions. In the fourth step, reduced features are fused using serial-based approach followed by a final step of classification using multiclass support vector machine. For dimensionality reduction, principal component analysis is utilized, which is a statistical procedure that enforces an orthogonal transformation on a set of observations. Three different image data sets (Citrus Image Gallery, Plant Village, and self-collected) are combined in this research to achieving a classification accuracy of 95.5%. From the stats, it is quite clear that our proposed method outperforms several existing methods with greater precision and accuracy.

Matched MeSH terms: Image Processing, Computer-Assisted/methods*
Lung nodule classification using deep Local-Global networks

Al-Shabi M, Lan BL, Chan WY, Ng KH, Tan M

Int J Comput Assist Radiol Surg, 2019 Oct;14(10):1815-1819.
PMID: 31020576 DOI: 10.1007/s11548-019-01981-7

PURPOSE: Lung nodules have very diverse shapes and sizes, which makes classifying them as benign/malignant a challenging problem. In this paper, we propose a novel method to predict the malignancy of nodules that have the capability to analyze the shape and size of a nodule using a global feature extractor, as well as the density and structure of the nodule using a local feature extractor.
METHODS: We propose to use Residual Blocks with a 3 × 3 kernel size for local feature extraction and Non-Local Blocks to extract the global features. The Non-Local Block has the ability to extract global features without using a huge number of parameters. The key idea behind the Non-Local Block is to apply matrix multiplications between features on the same feature maps.
RESULTS: We trained and validated the proposed method on the LIDC-IDRI dataset which contains 1018 computed tomography scans. We followed a rigorous procedure for experimental setup, namely tenfold cross-validation, and ignored the nodules that had been annotated by

Matched MeSH terms: Image Processing, Computer-Assisted/methods*
Automated nuclei segmentation of malignant using level sets

Husham A, Hazim Alkawaz M, Saba T, Rehman A, Saleh Alghamdi J

Microsc Res Tech, 2016 Oct;79(10):993-997.
PMID: 27476682 DOI: 10.1002/jemt.22733

Segmentation of objects from a noisy and complex image is still a challenging task that needs to be addressed. This article proposed a new method to detect and segment nuclei to determine whether they are malignant or not (determination of the region of interest, noise removal, enhance the image, candidate detection is employed on the centroid transform to evaluate the centroid of each object, the level set [LS] is applied to segment the nuclei). The proposed method consists of three main stages: preprocessing, seed detection, and segmentation. Preprocessing stage involves the preparation of the image conditions to ensure that they meet the segmentation requirements. Seed detection detects the seed point to be used in the segmentation stage, which refers to the process of segmenting the nuclei using the LS method. In this research work, 58 H&E breast cancer images from the UCSB Bio-Segmentation Benchmark dataset are evaluated. The proposed method reveals the high performance and accuracy in comparison to the techniques reported in literature. The experimental results are also harmonized with the ground truth images.

Matched MeSH terms: Image Processing, Computer-Assisted/methods*
A comparative study between xerographic, computer-assisted overlay generation and animated-superimposition methods in bite mark analyses

Tai MW, Chong ZF, Asif MK, Rahmat RA, Nambiar P

Leg Med (Tokyo), 2016 Sep;22:42-8.
PMID: 27591538 DOI: 10.1016/j.legalmed.2016.07.009

This study was to compare the suitability and precision of xerographic and computer-assisted methods for bite mark investigations. Eleven subjects were asked to bite on their forearm and the bite marks were photographically recorded. Alginate impressions of the subjects' dentition were taken and their casts were made using dental stone. The overlays generated by xerographic method were obtained by photocopying the subjects' casts and the incisal edge outlines were then transferred on a transparent sheet. The bite mark images were imported into Adobe Photoshop® software and printed to life-size. The bite mark analyses using xerographically generated overlays were done by comparing an overlay to the corresponding printed bite mark images manually. In computer-assisted method, the subjects' casts were scanned into Adobe Photoshop®. The bite mark analyses using computer-assisted overlay generation were done by matching an overlay and the corresponding bite mark images digitally using Adobe Photoshop®. Another comparison method was superimposing the cast images with corresponding bite mark images employing the Adobe Photoshop® CS6 and GIF-Animator©. A score with a range of 0-3 was given during analysis to each precision-determining criterion and the score was increased with better matching. The Kruskal Wallis H test showed significant difference between the three sets of data (H=18.761, p<0.05). In conclusion, bite mark analysis using the computer-assisted animated-superimposition method was the most accurate, followed by the computer-assisted overlay generation and lastly the xerographic method. The superior precision contributed by digital method is discernible despite the human skin being a poor recording medium of bite marks.

Matched MeSH terms: Image Processing, Computer-Assisted/methods*
Fulltext Nuclear IHC enumeration: A digital phantom to evaluate the performance of automated algorithms in digital pathology

Niazi MKK, Abas FS, Senaras C, Pennell M, Sahiner B, Chen W, et al.

PLoS One, 2018;13(5):e0196547.
PMID: 29746503 DOI: 10.1371/journal.pone.0196547

Automatic and accurate detection of positive and negative nuclei from images of immunostained tissue biopsies is critical to the success of digital pathology. The evaluation of most nuclei detection algorithms relies on manually generated ground truth prepared by pathologists, which is unfortunately time-consuming and suffers from inter-pathologist variability. In this work, we developed a digital immunohistochemistry (IHC) phantom that can be used for evaluating computer algorithms for enumeration of IHC positive cells. Our phantom development consists of two main steps, 1) extraction of the individual as well as nuclei clumps of both positive and negative nuclei from real WSI images, and 2) systematic placement of the extracted nuclei clumps on an image canvas. The resulting images are visually similar to the original tissue images. We created a set of 42 images with different concentrations of positive and negative nuclei. These images were evaluated by four board certified pathologists in the task of estimating the ratio of positive to total number of nuclei. The resulting concordance correlation coefficients (CCC) between the pathologist and the true ratio range from 0.86 to 0.95 (point estimates). The same ratio was also computed by an automated computer algorithm, which yielded a CCC value of 0.99. Reading the phantom data with known ground truth, the human readers show substantial variability and lower average performance than the computer algorithm in terms of CCC. This shows the limitation of using a human reader panel to establish a reference standard for the evaluation of computer algorithms, thereby highlighting the usefulness of the phantom developed in this work. Using our phantom images, we further developed a function that can approximate the true ratio from the area of the positive and negative nuclei, hence avoiding the need to detect individual nuclei. The predicted ratios of 10 held-out images using the function (trained on 32 images) are within ±2.68% of the true ratio. Moreover, we also report the evaluation of a computerized image analysis method on the synthetic tissue dataset.

Matched MeSH terms: Image Processing, Computer-Assisted/methods*
In-Line Sorting of Harumanis Mango Based on External Quality Using Visible Imaging

Ibrahim MF, Ahmad Sa'ad FS, Zakaria A, Md Shakaff AY

Sensors (Basel), 2016 Oct 27;16(11).
PMID: 27801799

The conventional method of grading Harumanis mango is time-consuming, costly and affected by human bias. In this research, an in-line system was developed to classify Harumanis mango using computer vision. The system was able to identify the irregularity of mango shape and its estimated mass. A group of images of mangoes of different size and shape was used as database set. Some important features such as length, height, centroid and parameter were extracted from each image. Fourier descriptor and size-shape parameters were used to describe the mango shape while the disk method was used to estimate the mass of the mango. Four features have been selected by stepwise discriminant analysis which was effective in sorting regular and misshapen mango. The volume from water displacement method was compared with the volume estimated by image processing using paired t-test and Bland-Altman method. The result between both measurements was not significantly different (P > 0.05). The average correct classification for shape classification was 98% for a training set composed of 180 mangoes. The data was validated with another testing set consist of 140 mangoes which have the success rate of 92%. The same set was used for evaluating the performance of mass estimation. The average success rate of the classification for grading based on its mass was 94%. The results indicate that the in-line sorting system using machine vision has a great potential in automatic fruit sorting according to its shape and mass.

Matched MeSH terms: Image Processing, Computer-Assisted/methods*
Fulltext A localization strategy combined with transfer learning for image annotation

Chen Z, Rajamanickam L, Cao J, Zhao A, Hu X

PLoS One, 2021;16(12):e0260758.
PMID: 34879097 DOI: 10.1371/journal.pone.0260758

This study aims to solve the overfitting problem caused by insufficient labeled images in the automatic image annotation field. We propose a transfer learning model called CNN-2L that incorporates the label localization strategy described in this study. The model consists of an InceptionV3 network pretrained on the ImageNet dataset and a label localization algorithm. First, the pretrained InceptionV3 network extracts features from the target dataset that are used to train a specific classifier and fine-tune the entire network to obtain an optimal model. Then, the obtained model is used to derive the probabilities of the predicted labels. For this purpose, we introduce a squeeze and excitation (SE) module into the network architecture that augments the useful feature information, inhibits useless feature information, and conducts feature reweighting. Next, we perform label localization to obtain the label probabilities and determine the final label set for each image. During this process, the number of labels must be determined. The optimal K value is obtained experimentally and used to determine the number of predicted labels, thereby solving the empty label set problem that occurs when the predicted label values of images are below a fixed threshold. Experiments on the Corel5k multilabel image dataset verify that CNN-2L improves the labeling precision by 18% and 15% compared with the traditional multiple-Bernoulli relevance model (MBRM) and joint equal contribution (JEC) algorithms, respectively, and it improves the recall by 6% compared with JEC. Additionally, it improves the precision by 20% and 11% compared with the deep learning methods Weight-KNN and adaptive hypergraph learning (AHL), respectively. Although CNN-2L fails to improve the recall compared with the semantic extension model (SEM), it improves the comprehensive index of the F1 value by 1%. The experimental results reveal that the proposed transfer learning model based on a label localization strategy is effective for automatic image annotation and substantially boosts the multilabel image annotation performance.

Matched MeSH terms: Image Processing, Computer-Assisted/methods*
FPGA implementation of real-time SENSE reconstruction using pre-scan and Emaps sensitivities

Siddiqui MF, Reza AW, Shafique A, Omer H, Kanesan J

Magn Reson Imaging, 2017 12;44:82-91.
PMID: 28855113 DOI: 10.1016/j.mri.2017.08.005

Sensitivity Encoding (SENSE) is a widely used technique in Parallel Magnetic Resonance Imaging (MRI) to reduce scan time. Reconfigurable hardware based architecture for SENSE can potentially provide image reconstruction with much less computation time. Application specific hardware platform for SENSE may dramatically increase the power efficiency of the system and can decrease the execution time to obtain MR images. A new implementation of SENSE on Field Programmable Gate Array (FPGA) is presented in this study, which provides real-time SENSE reconstruction right on the receiver coil data acquisition system with no need to transfer the raw data to the MRI server, thereby minimizing the transmission noise and memory usage. The proposed SENSE architecture can reconstruct MR images using receiver coil sensitivity maps obtained using pre-scan and eigenvector (E-maps) methods. The results show that the proposed system consumes remarkably less computation time for SENSE reconstruction, i.e., 0.164ms @ 200MHz, while maintaining the quality of the reconstructed images with good mean SNR (29+ dB), less RMSE (<5×10-2) and comparable artefact power (<9×10-4) to conventional SENSE reconstruction. A comparison of the center line profiles of the reconstructed and reference images also indicates a good quality of the reconstructed images. Furthermore, the results indicate that the proposed architectural design can prove to be a significant tool for SENSE reconstruction in modern MRI scanners and its low power consumption feature can be remarkable for portable MRI scanners.

Matched MeSH terms: Image Processing, Computer-Assisted/methods*
Knee cartilage segmentation and thickness computation from ultrasound images

Faisal A, Ng SC, Goh SL, Lai KW

Med Biol Eng Comput, 2018 Apr;56(4):657-669.
PMID: 28849317 DOI: 10.1007/s11517-017-1710-2

Quantitative thickness computation of knee cartilage in ultrasound images requires segmentation of a monotonous hypoechoic band between the soft tissue-cartilage interface and the cartilage-bone interface. Speckle noise and intensity bias captured in the ultrasound images often complicates the segmentation task. This paper presents knee cartilage segmentation using locally statistical level set method (LSLSM) and thickness computation using normal distance. Comparison on several level set methods in the attempt of segmenting the knee cartilage shows that LSLSM yields a more satisfactory result. When LSLSM was applied to 80 datasets, the qualitative segmentation assessment indicates a substantial agreement with Cohen's κ coefficient of 0.73. The quantitative validation metrics of Dice similarity coefficient and Hausdorff distance have average values of 0.91 ± 0.01 and 6.21 ± 0.59 pixels, respectively. These satisfactory segmentation results are making the true thickness between two interfaces of the cartilage possible to be computed based on the segmented images. The measured cartilage thickness ranged from 1.35 to 2.42 mm with an average value of 1.97 ± 0.11 mm, reflecting the robustness of the segmentation algorithm to various cartilage thickness. These results indicate a potential application of the methods described for assessment of cartilage degeneration where changes in the cartilage thickness can be quantified over time by comparing the true thickness at a certain time interval.

Matched MeSH terms: Image Processing, Computer-Assisted/methods*
Automated diagnosis of focal liver lesions using bidirectional empirical mode decomposition features

Acharya UR, Koh JEW, Hagiwara Y, Tan JH, Gertych A, Vijayananthan A, et al.

Comput Biol Med, 2018 03 01;94:11-18.
PMID: 29353161 DOI: 10.1016/j.compbiomed.2017.12.024

Liver is the heaviest internal organ of the human body and performs many vital functions. Prolonged cirrhosis and fatty liver disease may lead to the formation of benign or malignant lesions in this organ, and an early and reliable evaluation of these conditions can improve treatment outcomes. Ultrasound imaging is a safe, non-invasive, and cost-effective way of diagnosing liver lesions. However, this technique has limited performance in determining the nature of the lesions. This study initiates a computer-aided diagnosis (CAD) system to aid radiologists in an objective and more reliable interpretation of ultrasound images of liver lesions. In this work, we have employed radon transform and bi-directional empirical mode decomposition (BEMD) to extract features from the focal liver lesions. After which, the extracted features were subjected to particle swarm optimization (PSO) technique for the selection of a set of optimized features for classification. Our automated CAD system can differentiate normal, malignant, and benign liver lesions using machine learning algorithms. It was trained using 78 normal, 26 benign and 36 malignant focal lesions of the liver. The accuracy, sensitivity, and specificity of lesion classification were 92.95%, 90.80%, and 97.44%, respectively. The proposed CAD system is fully automatic as no segmentation of region-of-interest (ROI) is required.

Matched MeSH terms: Image Processing, Computer-Assisted/methods*
Fulltext Sign language recognition using the fusion of image and hand landmarks through multi-headed convolutional neural network

Pathan RK, Biswas M, Yasmin S, Khandaker MU, Salman M, Youssef AAF

Sci Rep, 2023 Oct 09;13(1):16975.
PMID: 37813932 DOI: 10.1038/s41598-023-43852-x

Sign Language Recognition is a breakthrough for communication among deaf-mute society and has been a critical research topic for years. Although some of the previous studies have successfully recognized sign language, it requires many costly instruments including sensors, devices, and high-end processing power. However, such drawbacks can be easily overcome by employing artificial intelligence-based techniques. Since, in this modern era of advanced mobile technology, using a camera to take video or images is much easier, this study demonstrates a cost-effective technique to detect American Sign Language (ASL) using an image dataset. Here, "Finger Spelling, A" dataset has been used, with 24 letters (except j and z as they contain motion). The main reason for using this dataset is that these images have a complex background with different environments and scene colors. Two layers of image processing have been used: in the first layer, images are processed as a whole for training, and in the second layer, the hand landmarks are extracted. A multi-headed convolutional neural network (CNN) model has been proposed and tested with 30% of the dataset to train these two layers. To avoid the overfitting problem, data augmentation and dynamic learning rate reduction have been used. With the proposed model, 98.981% test accuracy has been achieved. It is expected that this study may help to develop an efficient human-machine communication system for a deaf-mute society.

Matched MeSH terms: Image Processing, Computer-Assisted/methods
Fulltext An Overview of Deep Learning Methods for Left Ventricle Segmentation

Shoaib MA, Chuah JH, Ali R, Hasikin K, Khalil A, Hum YC, et al.

Comput Intell Neurosci, 2023;2023:4208231.
PMID: 36756163 DOI: 10.1155/2023/4208231

Cardiac health diseases are one of the key causes of death around the globe. The number of heart patients has considerably increased during the pandemic. Therefore, it is crucial to assess and analyze the medical and cardiac images. Deep learning architectures, specifically convolutional neural networks have profoundly become the primary choice for the assessment of cardiac medical images. The left ventricle is a vital part of the cardiovascular system where the boundary and size perform a significant role in the evaluation of cardiac function. Due to automatic segmentation and good promising results, the left ventricle segmentation using deep learning has attracted a lot of attention. This article presents a critical review of deep learning methods used for the left ventricle segmentation from frequently used imaging modalities including magnetic resonance images, ultrasound, and computer tomography. This study also demonstrates the details of the network architecture, software, and hardware used for training along with publicly available cardiac image datasets and self-prepared dataset details incorporated. The summary of the evaluation matrices with results used by different researchers is also presented in this study. Finally, all this information is summarized and comprehended in order to assist the readers to understand the motivation and methodology of various deep learning models, as well as exploring potential solutions to future challenges in LV segmentation.

Matched MeSH terms: Image Processing, Computer-Assisted/methods
Deep learning techniques in PET/CT imaging: A comprehensive review from sinogram to image space

Fallahpoor M, Chakraborty S, Pradhan B, Faust O, Barua PD, Chegeni H, et al.

Comput Methods Programs Biomed, 2024 Jan;243:107880.
PMID: 37924769 DOI: 10.1016/j.cmpb.2023.107880

Positron emission tomography/computed tomography (PET/CT) is increasingly used in oncology, neurology, cardiology, and emerging medical fields. The success stems from the cohesive information that hybrid PET/CT imaging offers, surpassing the capabilities of individual modalities when used in isolation for different malignancies. However, manual image interpretation requires extensive disease-specific knowledge, and it is a time-consuming aspect of physicians' daily routines. Deep learning algorithms, akin to a practitioner during training, extract knowledge from images to facilitate the diagnosis process by detecting symptoms and enhancing images. This acquired knowledge aids in supporting the diagnosis process through symptom detection and image enhancement. The available review papers on PET/CT imaging have a drawback as they either included additional modalities or examined various types of AI applications. However, there has been a lack of comprehensive investigation specifically focused on the highly specific use of AI, and deep learning, on PET/CT images. This review aims to fill that gap by investigating the characteristics of approaches used in papers that employed deep learning for PET/CT imaging. Within the review, we identified 99 studies published between 2017 and 2022 that applied deep learning to PET/CT images. We also identified the best pre-processing algorithms and the most effective deep learning models reported for PET/CT while highlighting the current limitations. Our review underscores the potential of deep learning (DL) in PET/CT imaging, with successful applications in lesion detection, tumor segmentation, and disease classification in both sinogram and image spaces. Common and specific pre-processing techniques are also discussed. DL algorithms excel at extracting meaningful features, and enhancing accuracy and efficiency in diagnosis. However, limitations arise from the scarcity of annotated datasets and challenges in explainability and uncertainty. Recent DL models, such as attention-based models, generative models, multi-modal models, graph convolutional networks, and transformers, are promising for improving PET/CT studies. Additionally, radiomics has garnered attention for tumor classification and predicting patient outcomes. Ongoing research is crucial to explore new applications and improve the accuracy of DL models in this rapidly evolving field.

Matched MeSH terms: Image Processing, Computer-Assisted/methods

Filters

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links