Al-Biruni Earth Radius Optimization with Transfer Learning Based Histopathological Image Analysis for Lung and Colon Cancer Detection

Cancers, Journal Year: 2023, Volume and Issue: 15(13), P. 3300 - 3300

Published: June 23, 2023

An early diagnosis of lung and colon cancer (LCC) is critical for improved patient outcomes effective treatment. Histopathological image (HSI) analysis has emerged as a robust tool diagnosis. HSI LCC includes the examination tissue samples attained from to recognize lesions or cancerous cells. It significant role in staging this tumor, which aids prognosis treatment planning, but manual subject human error also time-consuming. Therefore, computer-aided approach needed detection using HSI. Transfer learning (TL) leverages pretrained deep (DL) algorithms that have been trained on larger dataset extracting related features HIS, are then used training classifier tumor This manuscript offers design Al-Biruni Earth Radius Optimization with Learning-based Image Analysis Lung Colon Cancer Detection (BERTL-HIALCCD) technique. The purpose study detect effectually histopathological images. To execute this, BERTL-HIALCCD method follows concepts computer vision (CV) transfer accurate detection. When technique, an ShuffleNet model applied feature extraction process, its hyperparameters chosen by BER system. For effectual recognition LCC, convolutional recurrent neural network (DCRNN) applied. Finally, coati optimization algorithm (COA) exploited parameter choice DCRNN approach. examining efficacy comprehensive group experiments was conducted large experimental demonstrate combination AER COA attain performance over compared models.

Language: Английский

---

Hybrid firefly particle swarm optimisation algorithm for feature selection problems

Expert Systems, Journal Year: 2023, Volume and Issue: 41(7)

Published: June 1, 2023

Abstract Feature selection techniques play a vital role in the processes that deal with enormous amounts of data. These have become extremely crucial and necessary for data mining machine learning problems. Researchers always been race to develop provide libraries frameworks standardise this procedure. In work, we propose hybrid meta‐heuristic algorithm facilitate problem feature classification problems learning. It is python based, lucid efficient geared towards optimising striking balance between number features selected accuracy. The proposed work binary existing algorithms, particle swarm optimisation (PSO) algorithm, firefly (FA) such it blends best each an optimised way solving said problem. suggested approach assessed against six datasets from different domains are publicly available at UCI repository demonstrate its validity. Breast cancer, Iris, WBC, Mushroom, Glass ID, Abalone. This has also evaluated similar, evolutionary‐based approaches prove superiority. Various metrics as accuracy, precision, recall, f1 score, features, run time analysed, measured, compared. found be suitable

Language: Английский

---

Grad-CAM: Understanding AI Models

Computers, materials & continua/Computers, materials & continua (Print), Journal Year: 2023, Volume and Issue: 76(2), P. 1321 - 1324

Published: Jan. 1, 2023

Artificial intelligence; Grad-CAM; deep learning; convolutional neural networks; classification; location; explainable

---

Exploiting histopathological imaging for early detection of lung and colon cancer via ensemble deep learning model

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

Published: Sept. 3, 2024

Cancer seems to have a vast number of deaths due its heterogeneity, aggressiveness, and significant propensity for metastasis. The predominant categories cancer that may affect males females occur worldwide are colon lung cancer. A precise on-time analysis this can increase the survival rate improve appropriate treatment characteristics. An efficient effective method speedy accurate recognition tumours in areas is provided as an alternative methods. Earlier diagnosis disease on front drastically reduces chance death. Machine learning (ML) deep (DL) approaches accelerate diagnosis, facilitating researcher workers study majority patients limited period at low cost. This research presents Histopathological Imaging Early Detection Lung Colon via Ensemble DL (HIELCC-EDL) model. HIELCC-EDL technique utilizes histopathological images identify (LCC). To achieve this, uses Wiener filtering (WF) noise elimination. In addition, model channel attention Residual Network (CA-ResNet50) complex feature patterns. Moreover, hyperparameter selection CA-ResNet50 performed using tuna swarm optimization (TSO) technique. Finally, detection LCC achieved by ensemble three classifiers such extreme machine (ELM), competitive neural networks (CNNs), long short-term memory (LSTM). illustrate promising performance model, complete set experimentations was benchmark dataset. experimental validation portrayed superior accuracy value 99.60% over recent approaches.

Language: Английский

---

MMCAF: A Survival Status Prediction Method Based on Cross‐Attention Fusion of Multimodal Colorectal Cancer Data

International Journal of Imaging Systems and Technology, Journal Year: 2025, Volume and Issue: 35(2)

Published: Feb. 14, 2025

ABSTRACT The employment of artificial intelligence methods in computer‐assisted diagnosis systems is critical for colorectal cancer survival analysis and prognosis. However, due to the low prediction accuracy single‐modal data research complexity multimodal fusion methods, current study's effect on minimal. To address this issue, authors offer a cross attention (MMCAF) technique predicting status. First, feature engineering used create sets every mode heterogeneity data. Second, three‐mode allocate weight single‐mode features via channels cross‐attention processes. Lastly, cross‐entropy loss function minimized order estimate classification survival. experimental results reveal that MMCAF approach predicts states with 97.73% an area under receiver operating characteristic curve (AUC) 0.99. When compared best outcome other algorithms (feature concatenation), increases by about 6 percentage points, while AUC 7 points. This finding thoroughly demonstrates MMCAF's efficacy

Language: Английский

---

A Comprehensive Review of the Tunicate Swarm Algorithm: Variations, Applications, and Results

Archives of Computational Methods in Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: March 12, 2025

Language: Английский

---

Recent Versions and Applications of Tunicate Swarm Algorithm

Archives of Computational Methods in Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: April 14, 2025

Language: Английский

---

Mathematical modeling of a Hybrid Mutated Tunicate Swarm Algorithm for Feature Selection and Global Optimization

AIMS Mathematics, Journal Year: 2024, Volume and Issue: 9(9), P. 24336 - 24358

Published: Jan. 1, 2024

<p>The latest advances in engineering, science, and technology have contributed to an enormous generation of datasets. This vast dataset contains irrelevant, redundant, noisy features that adversely impact classification performance data mining machine learning (ML) techniques. Feature selection (FS) is a preprocessing stage minimize the dimensionality by choosing most prominent feature while improving performance. Since size produced are often extensive dimension, this enhances complexity search space, where maximal number potential solutions 2nd for n As becomes large, it computationally impossible compute feature. Therefore, there need effective FS techniques large-scale problems classification. Many metaheuristic approaches were utilized resolve challenges heuristic-based approaches. Recently, swarm algorithm has been suggested demonstrated perform effectively tasks. I developed Hybrid Mutated Tunicate Swarm Algorithm Global Optimization (HMTSA-FSGO) technique. The proposed HMTSA-FSGO model mainly aims eradicate unwanted choose relevant ones highly classifier results. In model, HMTSA derived integrating standard TSA with two concepts: A dynamic s-best mutation operator optimal trade-off between exploration exploitation directional rule enhanced space exploration. also includes bidirectional long short-term memory (BiLSTM) examine process. rat optimizer (RSO) can hyperparameters boost BiLSTM network simulation analysis technique tested using series experiments. investigational validation showed superior outcome 93.01%, 97.39%, 61.59%, 99.15%, 67.81% over diverse datasets.</p>

Language: Английский

---

Identification of Anomalies in Lung and Colon Cancer Using Computer Vision-Based Swin Transformer with Ensemble Model on Histopathological Images

Bioengineering, Journal Year: 2024, Volume and Issue: 11(10), P. 978 - 978

Published: Sept. 28, 2024

Lung and colon cancer (LCC) is a dominant life-threatening disease that needs timely attention precise diagnosis for efficient treatment. The conventional diagnostic techniques LCC regularly encounter constraints in terms of efficiency accuracy, thus causing challenges primary recognition Early the can immensely reduce probability death. In medical practice, histopathological study tissue samples generally uses classical model. Still, automated devices exploit artificial intelligence (AI) produce results diagnosis. histopathology, both machine learning (ML) deep (DL) approaches be deployed owing to their latent ability analyzing predicting physically accurate molecular phenotypes microsatellite uncertainty. this background, presents novel technique called Colon Cancer using Swin Transformer with an Ensemble Model on Histopathological Images (LCCST-EMHI). proposed LCCST-EMHI method focuses designing DL model classification images (HI). order achieve this, utilizes bilateral filtering (BF) get rid noise. Further, (ST) also employed purpose feature extraction. For detection process, ensemble classifier used three techniques: bidirectional long short-term memory multi-head (BiLSTM-MHA), Double Deep Q-Network (DDQN), sparse stacked autoencoder (SSAE). Eventually, hyperparameter selection models implemented utilizing walrus optimization algorithm (WaOA) method. illustrate promising performance approach, extensive range simulation analyses was conducted benchmark dataset. experimentation demonstrated approach over other recent methods.

Language: Английский

---

Cultivating diagnostic clarity: The importance of reporting artificial intelligence confidence levels in radiologic diagnoses

Clinical Imaging, Journal Year: 2024, Volume and Issue: 117, P. 110356 - 110356

Published: Nov. 13, 2024

Language: Английский

---