Machine Learning Driven Dashboard for Chronic Myeloid Leukemia Prediction using Protein Sequences DOI Open Access
Waqar Ahmad, Tahani Jaser Alahmadi,

Muhammad Awais Amin

et al.

Published: June 26, 2024

In Southeast Asia, the incidence of Leukemia, a malignant blood cancer originating from hema-topoietic progenitor cells, is on rise, marked by concerning 54% mortality rate. This study focuses enhancing early-stage prediction to improve patient recovery prospects significantly. Leveraging Machine Learning and Data Science, we employ protein sequential data frequently mutated genes such as BCL2, HSP90, PARP, RB predict Chronic Myeloid Leukemia (CML). Our approach relies robust feature extraction techniques, namely Di-peptide Composition (DPC), Amino Acid (AAC), Pseudo amino acid composition (Pse-AAC), with prior attention addressing outliers validating selection through Pearson Corre-lation Coefficient. augmentation ensures well-rounded dataset for analysis. Employing range models, including Support Vector (SVM), XGBoost, Random Forest (RF), K Nearest Neighbor (KNN), Decision Tree (DT), Logistic Regression (LR), achieve accuracy rates spanning 66% 94%. These classifiers undergo comprehensive as-sessment using performance metrics accuracy, sensitivity, specificity, F1-score, confusion matrix. proposed solution, encompassing user-friendly web application dashboard, presents an invaluable tool early CML diagnosis profound implications practitioners, offering deploy-able asset within healthcare institutions hospitals.

Language: Английский

Blood cancer prediction model based on deep learning technique DOI Creative Commons
Ahmed Shehta,

Mona Nasr,

Alaa El Din M. El Ghazali

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 13, 2025

Abstract Blood cancer is among the critical health concerns people around world and normally emanates from genetic environmental issues. Early detection becomes essential, as rate of death associated with it high, to ensure that treatment success up, mortality reduced. This paper focuses on improving blood diagnosis using advanced deep learning techniques like ResNetRS50, RegNetX016, AlexNet, Convnext, EfficientNet, Inception_V3, Xception, VGG19. Among models assessed, ResNetRS50 had better accuracy speed minimal error rates compared other state-of-the-arts. work will exploit power in contributing early reducing bad outcomes for patients. currently one deadliest diseases worldwide, resulting a combination non-genetic factors. It stands leading cause cancer-related deaths both developed developing nations. pivotal rates, increases likelihood successful potential cure. The objective decrease through cancer, thus offering individuals chance survival this disease.

Language: Английский

Citations

3
RNA-Seq analysis for breast cancer detection: a study on paired tissue samples using hybrid optimization and deep learning techniques DOI Creative Commons
Abrar Yaqoob, Navneet Kumar Verma, Rabia Musheer Aziz

et al.

Journal of Cancer Research and Clinical Oncology, Journal Year: 2024, Volume and Issue: 150(10)

Published: Oct. 10, 2024

Breast cancer is a leading global health issue, contributing to high mortality rates among women. The challenge of early detection exacerbated by the dimensionality and complexity gene expression data, which complicates classification process.

Language: Английский

Citations

13
Integrated Diagnostics of Thyroid Nodules DOI Open Access
Luca Giovanella, Alfredo Campennì, Murat Tuncel

et al.

Cancers, Journal Year: 2024, Volume and Issue: 16(2), P. 311 - 311

Published: Jan. 11, 2024

Thyroid nodules are common findings, particularly in iodine-deficient regions. Our paper aims to revise different diagnostic tools available clinical thyroidology and propose their rational integration. We will elaborate on the pros cons of thyroid ultrasound (US) its scoring systems, scintigraphy, fine-needle aspiration cytology (FNAC), molecular imaging, artificial intelligence (AI). Ultrasonographic systems can help differentiate between benign malignant nodules. Depending constellation or number suspicious features, a FNAC is recommended. However, hyperfunctioning presumed exclude malignancy with very high negative predictive value (NPV). Particularly regions where iodine supply low, most seen patients normal thyroid-stimulating hormone (TSH) levels. scintigraphy essential for detection these Among non-toxic nodules, careful application US risk stratification pivotal inappropriate guide procedure ones. almost one-third examinations rendered as indeterminate, requiring “diagnostic surgery” provide definitive diagnosis. 99mTc-methoxy-isobutyl-isonitrile ([99mTc]Tc-MIBI) [18F]fluoro-deoxy-glucose ([18F]FDG) imaging spare those from unnecessary surgeries. The AI evaluation needs be determined.

Language: Английский

Citations

11
Exploring the Molecular Terrain: A Survey of Analytical Methods for Biological Network Analysis DOI Open Access
Trong-The Nguyen, Thi-Kien Dao, Duc-Tinh Pham

et al.

Symmetry, Journal Year: 2024, Volume and Issue: 16(4), P. 462 - 462

Published: April 10, 2024

Biological systems, characterized by their complex interplay of symmetry and asymmetry, operate through intricate networks interacting molecules, weaving the elaborate tapestry life. The exploration these networks, aptly termed “molecular terrain”, is pivotal for unlocking mysteries biological processes spearheading development innovative therapeutic strategies. This review embarks on a comprehensive survey analytical methods employed in network analysis, focusing elucidating roles asymmetry within networks. By highlighting strengths, limitations, potential applications, we delve into reconstruction, topological analysis with an emphasis detection, examination dynamics, which together reveal nuanced balance between stable, symmetrical configurations dynamic, asymmetrical shifts that underpin functionality. equips researchers multifaceted toolbox designed to navigate decipher networks’ intricate, balanced landscape, thereby advancing our understanding manipulation systems. Through this detailed exploration, aim foster significant advancements paving way novel interventions deeper comprehension molecular underpinnings

Language: Английский

Citations

7
Brain tumor detection and classification in MRI using hybrid ViT and GRU model with explainable AI in Southern Bangladesh DOI Creative Commons

Md. Mahfuz Ahmed,

Md. Maruf Hossain, Md. Rakibul Islam

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Oct. 1, 2024

Language: Английский

Citations

7
Application of 3D, 4D, 5D, and 6D bioprinting in cancer research: what does the future look like? DOI
Danial Khorsandi,

Dorsa Rezayat,

Serap Sezen

et al.

Journal of Materials Chemistry B, Journal Year: 2024, Volume and Issue: 12(19), P. 4584 - 4612

Published: Jan. 1, 2024

Recent advancements pertaining to the application of 3D, 4D, 5D, and 6D bioprinting in cancer research are discussed, focusing on important challenges future perspectives.

Language: Английский

Citations

5
Integrating cat boost algorithm with triangulating feature importance to predict survival outcome in recurrent cervical cancer DOI Creative Commons

S. Geeitha,

K. Ravishankar,

Jaehyuk Cho

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Aug. 27, 2024

Cervical cancer is one of the most dangerous malignancies in women. Prolonged survival times are made possible by breakthroughs early recognition and efficient treatment a disease.The existing methods lagging on finding important attributes to predict outcome. The main objective this study find individuals with cervical who at greater risk death from recurrence predicting survival.A novel approach proposed technique Triangulating feature importance factors through which may vary improve outcome.Five algorithms Support vector machine, Naive Bayes, supervised logistic regression, decision tree algorithm, Gradient boosting, random forest used build concept. Conventional attribute selection like information gain (IG), FCBF, ReliefFare employed. recommended classifier evaluated for Precision, Recall, F1, Mathews Correlation Coefficient (MCC), Classification Accuracy (CA), Area under curve (AUC) using various methods. boosting algorithm (CAT BOOST) attains highest accuracy value 0.99 outcome patients. research identify patients improved.

Language: Английский

Citations

4
Optimising ovarian tumor classification using a novel CT sequence selection algorithm DOI Creative Commons

K V Bhuvaneshwari,

Husam Lahza,

B. R. Sreenivasa

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Oct. 23, 2024

Gynaecological cancers, especially ovarian cancer, remain a critical public health issue, particularly in regions like India, where there are challenges related to cancer awareness, variable pathology, and limited access screening facilities. These often lead the diagnosis of at advanced stages, resulting poorer outcomes for patients. The goal this study is enhance accuracy classifying tumours, with focus on distinguishing between malignant early-stage cases, by applying deep learning methods. In our approach, we utilized three pre-trained models-Xception, ResNet50V2, ResNet50V2FPN-to classify tumors using publicly available Computed Tomography (CT) scan data. To further improve model's performance, developed novel CT Sequence Selection Algorithm, which optimises use images more precise classification tumours. models were trained evaluated selected TIFF images, comparing performance ResNet50V2FPN model without Algorithm. Our experimental results show Comparative evaluation against ResNet50V2 FPN model, both demonstrates superiority proposed algorithm over existing state-of-the-art This research presents promising approach improving early detection management gynecological potential benefits patient outcomes, areas healthcare resources.

Language: Английский

Citations

4
Optimized deep learning model for comprehensive medical image analysis across multiple modalities DOI
Saif Ur Rehman Khan,

Sohaib Asif,

Ming Zhao

et al.

Neurocomputing, Journal Year: 2024, Volume and Issue: 619, P. 129182 - 129182

Published: Dec. 12, 2024

Language: Английский

Citations

4
Effective BCDNet-based breast cancer classification model using hybrid deep learning with VGG16-based optimal feature extraction DOI Creative Commons

M. P.,

Ali Muna,

Yasser A. Ali

et al.

BMC Medical Imaging, Journal Year: 2025, Volume and Issue: 25(1)

Published: Jan. 8, 2025

Abstract Problem Breast cancer is a leading cause of death among women, and early detection crucial for improving survival rates. The manual breast diagnosis utilizes more time subjective. Also, the previous CAD models mostly depend on manmade visual details that are complex to generalize across ultrasound images utilizing distinct techniques. Distinct imaging tools have been utilized in works such as mammography MRI. However, these costly less portable than imaging. non-invasive method commonly used screening. Hence, paper presents novel deep learning model, BCDNet, classifying tumors benign or malignant using images. Aim primary aim study design an effective model can accurately classify their stages, thus reducing mortality aims optimize weight parameters RPAOSM-ESO algorithm enhance accuracy minimize false negative Methods BCDNet transfer from pre-trained VGG16 network feature extraction employs AHDNAM classification approach, which includes ASPP, DTCN, 1DCNN, attention mechanism. fine-tune weights parameters. Results RPAOSM-ESO-BCDNet-based provided 94.5 This value relatively higher DTCN (88.2), 1DCNN (89.6), MobileNet (91.3), ASPP-DTC-1DCNN-AM (93.8). it guaranteed designed RPAOSM-ESO-BCDNet produces accurate solutions models. Conclusion with its sophisticated techniques optimized by algorithm, shows promise suggests could be valuable tool cancer, potentially saving lives burden healthcare systems.

Language: Английский

Citations

0