Histo-CADx: duo cascaded fusion stages for breast cancer diagnosis from histopathological images

PeerJ Computer Science, Journal Year: 2021, Volume and Issue: 7, P. e493 - e493

Published: April 27, 2021

Breast cancer (BC) is one of the most common types that affects females worldwide. It may lead to irreversible complications and even death due late diagnosis treatment. The pathological analysis considered gold standard for BC detection, but it a challenging task. Automatic could reduce rates, by creating computer aided (CADx) system capable accurately identifying at an early stage decreasing time consumed pathologists during examinations. This paper proposes novel CADx named Histo-CADx automatic BC. Most related studies were based on individual deep learning methods. Also, did not examine influence fusing features from multiple CNNs handcrafted features. In addition, investigate best combination fused performance CADx. Therefore, two stages fusion. first fusion involves investigation impact several (DL) techniques with feature extraction methods using auto-encoder DL method. also examines searches suitable set improve Histo-CADx. second constructs classifier (MCS) outputs three classifiers, further accuracy proposed evaluated public datasets; specifically, BreakHis ICIAR 2018 datasets. results both datasets verified successfully improved compared constructed Furthermore, process has reduced computation cost system. Moreover, after confirmed reliable capacity classifying more other latest studies. Consequently, can be used help them in accurate decrease effort needed medical experts examination.

Language: Английский

---

A computer-aided diagnostic framework for coronavirus diagnosis using texture-based radiomics images

Digital Health, Journal Year: 2022, Volume and Issue: 8, P. 205520762210925 - 205520762210925

Published: Jan. 1, 2022

The accurate and rapid detection of the novel coronavirus infection, is very important to prevent fast spread such disease. Thus, reducing negative effects that influenced many industrial sectors, especially healthcare. Artificial intelligence techniques in particular deep learning could help precise diagnosis from computed tomography images. Most artificial intelligence-based studies used original images build their models; however, integration texture-based radiomics improve diagnostic accuracy diseases. This study proposes a computer-assisted framework based on multiple approaches. It first trains three Residual Networks (ResNets) with two including discrete wavelet transform gray-level covariance matrix instead Then, it fuses features sets extracted each using cosine transform. Thereafter, further combines fused obtained convolutional neural networks. Finally, support vector machine classifiers are utilized for classification procedure. proposed method validated experimentally benchmark severe respiratory syndrome 2 image dataset. accuracies attained indicate (gray-level matrix, transform) training ResNet-18 (83.22%, 74.9%), ResNet-50 (80.94%, 78.39%), ResNet-101 (80.54%, 77.99%) better than (70.34%, 76.51%, 73.42%) ResNet-18, ResNet-50, ResNet-101, respectively. Furthermore, sensitivity, specificity, accuracy, precision, F1-score achieved after fusion steps 99.47%, 99.72%, 99.60%, 99.60% which proves combining ResNets has boosted its performance. fusing mined several networks only one type approach single network. performance allows be by radiologists attaining diagnosis.

Language: Английский

---

A wavelet-based deep learning pipeline for efficient COVID-19 diagnosis via CT slices

Applied Soft Computing, Journal Year: 2022, Volume and Issue: 128, P. 109401 - 109401

Published: July 30, 2022

Language: Английский

---

A deep learning-based diagnostic tool for identifying various diseases via facial images

Digital Health, Journal Year: 2022, Volume and Issue: 8, P. 205520762211244 - 205520762211244

Published: Jan. 1, 2022

With the current health crisis caused by COVID-19 pandemic, patients have become more anxious about infection, so they prefer not to direct contact with doctors or clinicians. Lately, medical scientists confirmed that several diseases exhibit corresponding specific features on face face. Recent studies indicated computer-aided facial diagnosis can be a promising tool for automatic and screening of from images. However, few these used deep learning (DL) techniques. Most them focused detecting single disease, using handcrafted feature extraction methods conventional machine techniques based individual classifiers trained small private datasets images taken controlled environment. This study proposes novel system called FaceDisNet uses new public dataset an unconstrained environment could employed forthcoming comparisons. It detects multiple diseases. is constructed integrating spatial convolutional neural networks various architectures. does depend only but also extracts spatial-spectral features. searches fused set has greatest impact classification. employs two selection reduce large dimension resulting fusion. Finally, it builds ensemble classifier stacking perform The performance verifies its ability diagnose achieved maximum accuracy 98.57% 98% after classification steps binary multiclass categories. These results prove reliable avoid difficulties complications manual diagnosis. Also, help physicians achieve accurate diagnoses without need physical patients.

Language: Английский

---

MonDiaL-CAD: Monkeypox diagnosis via selected hybrid CNNs unified with feature selection and ensemble learning

Digital Health, Journal Year: 2023, Volume and Issue: 9

Published: Jan. 1, 2023

Recently, monkeypox virus is slowly evolving and there are fears it will spread as COVID-19. Computer-aided diagnosis (CAD) based on deep learning approaches especially convolutional neural network (CNN) can assist in the rapid determination of reported incidents. The current CADs were mostly an individual CNN. Few employed multiple CNNs but did not investigate which combination has a greater impact performance. Furthermore, they relied only spatial information features to train their models. This study aims construct CAD tool named "Monkey-CAD" that address previous limitations automatically diagnose rapidly accurately.Monkey-CAD extracts from eight then examines best possible influence classification. It employs discrete wavelet transform (DWT) merge diminishes fused features' size provides time-frequency demonstration. These sizes further reduced via entropy-based feature selection approach. finally used deliver better representation input feed three ensemble classifiers.Two freely accessible datasets called Monkeypox skin image (MSID) lesion (MSLD) this study. Monkey-CAD could discriminate among cases with without achieving accuracy 97.1% for MSID 98.7% MSLD respectively.Such promising results demonstrate be health practitioners. They also verify fusing selected boost

Language: Английский

---

Wireless Capsule Endoscopy Image Classification: An Explainable AI Approach

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 105262 - 105280

Published: Jan. 1, 2023

Deep Learning has contributed significantly to the advances made in fields of Medical Imaging and Computer Aided Diagnosis (CAD). Although a variety (DL) models exist for purposes image classification medical domain, more analysis needs be conducted on their decision-making processes. For this reason, several novel Explainable AI (XAI) techniques have been proposed recent years better understand DL models. Currently, professionals rely visual inspections diagnose potential diseases endoscopic imaging preliminary stages. However, we believe that use automated systems can enhance both efficiency such diagnoses. The aim study is increase reliability model predictions within field by implementing transfer learning balanced subset Kvasir-capsule, Wireless Capsule Endoscopy dataset. This includes top 9 classes dataset training testing. results obtained were an F1-score 97%±1% Vision Transformer model, although other as MobileNetv3Large ResNet152v2 also able achieve F1-scores over 90%. These are currently highest-reported metrics data, improving upon prior studies done same heatmaps XAI techniques, including GradCAM, GradCAM++, LayersCAM, LIME, SHAP presented form evaluated according highlighted regions importance. effort decisions top-performing look beyond black-box nature.

Language: Английский

---

GIEnsemformerCADx: A hybrid ensemble learning approach for enhanced gastrointestinal cancer recognition

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: 83(15), P. 46283 - 46323

Published: Feb. 22, 2024

Language: Английский

---

Comprehensive review of publicly available colonoscopic imaging databases for artificial intelligence research: availability, accessibility, and usability

Gastrointestinal Endoscopy, Journal Year: 2022, Volume and Issue: 97(2), P. 184 - 199.e16

Published: Sept. 7, 2022

Background and AimsPublicly available databases containing colonoscopic imaging data are valuable resources for artificial intelligence (AI) research. Currently, little is known regarding the number content of these databases. This review aimed to describe availability, accessibility, usability publicly databases, focusing on polyp detection, characterization, quality colonoscopy.MethodsA systematic literature search was performed in MEDLINE Embase identify AI studies describing published after 2010. Second, a targeted using Google's Dataset Search, Google GitHub, Figshare done directly. Databases were included if they contained about or colonoscopy. To assess accessibility following categories defined: open access, access with barriers, regulated access. potential essential details each database extracted checklist derived from Checklist Artificial Intelligence Medical Imaging.ResultsWe identified 22 3 15 The 19,463 images 952 videos. Nineteen focused localization, and/or segmentation; 6 Only half have been used by other researcher develop, train, benchmark their system. Although technical general well reported, important such as patient demographics annotation process under-reported almost all databases.ConclusionsThis provides greater insight public availability Incomplete reporting limits ability researchers current Publicly A Imaging. We

Language: Английский

---

Intelligent Dermatologist Tool for Classifying Multiple Skin Cancer Subtypes by Incorporating Manifold Radiomics Features Categories

Contrast Media & Molecular Imaging, Journal Year: 2021, Volume and Issue: 2021, P. 1 - 14

Published: Sept. 15, 2021

The rates of skin cancer (SC) are rising every year and becoming a critical health issue worldwide. SC’s early accurate diagnosis is the key procedure to reduce these improve survivability. However, manual exhausting, complicated, expensive, prone diagnostic error, highly dependent on dermatologist’s experience abilities. Thus, there vital need create automated dermatologist tools that capable accurately classifying SC subclasses. Recently, artificial intelligence (AI) techniques including machine learning (ML) deep (DL) have verified success computer-assisted in automatic detection diseases. Previous AI-based based features which either high-level DL methods or low-level handcrafted operations. Most them were constructed for binary classification SC. This study proposes an intelligent tool diagnose multiple lesions automatically. incorporates manifold radiomics categories involving such as ResNet-50, DenseNet-201, DarkNet-53 discrete wavelet transform (DWT) local pattern (LBP). results proposed prove merging different has high influence accuracy. Moreover, superior those obtained by other related tools. Therefore, can be used dermatologists help subcategory. It also overcome limitations, infection, enhance survival rates.

Language: Английский

---

Medivision: Empowering Colorectal Cancer Diagnosis and Tumor Localization Through Supervised Learning Classifications and Grad-CAM Visualization of Medical Colonoscopy Images

Cognitive Computation, Journal Year: 2025, Volume and Issue: 17(2)

Published: March 21, 2025

Language: Английский

---