Table 3.
Similarity of deep learning models for cancer determining
| Researcher | Area characterization | DL illustrate | Information set |
Outcome |
|---|---|---|---|---|
| [26] | Advanced Breast Tomosynthesis vs. Computerized Mammography | Pretrained VGG16 | Breast Screen Norway screening program | The rate of breast cancer detected by screening is comparable between computerized breast tomosynthesis and stepwise mammography in a population-based screening program |
| [27] | Precise aspiratory nodule discovery | Convolutional Neural Systems (CNNs) | LIDC-IDRI dataset | Affectability of 92.7% with 1 untrue positive per filter and affectability of 94.2% with 2 wrong positives per check for lung knob discovery on 888 checks. Utilization of thick Most extreme Concentrated Projection (MIP) images makes a difference distinguish little aspiratory knobs (3 mm-10 mm) and diminishes wrong positives |
| [32] | Pathogenesis of Oral Cancer | Not applicable (no deep learning model mentioned) | Not applicable (no dataset mentioned) | Audit and talk of key atomic concepts and chosen biomarkers embroiled in verbal carcinogenesis, particularly in verbal squamous cell carcinoma, with a center on deregulation amid diverse stages of verbal cancer advancement and movement |
| [33] | Liquid Biopsies for BC | Not applicable | Meta-analysis of 69 studies | ctDNA mutation rates for TP53, PIK3CA, and ESR1: 38%, 27%, and 32% respectively |
| [34] | Assessment of smartphone-based Employing Visual Review of the Cervix with Acidic Corrosive in helpful settings | Not appropriate | Information collected from 4,247 patients who experienced cervical cancer screening in rustic Eswatini from September 1, 2016, to December 31, 2018 | Introductory Using inspiration rate expanded from 16% to 25.1% standard preparing, at that point dropped to a normal of 9.7 term refresher preparing, expanded once more to a normal of 9.6 before the beginning of mentorship, and dropped to a normal of 8.3% in 2018 |
| [35] | Healthcare and Deep Learning | Deep Learning (Artificial Neural Network) |
Electronic Health Data—8000 |
Improved predictive performance and applications in various healthcare areas, Accuracy- 97.5% |
| [36] | Computer-Aided Diagnosis (CAD) in Gastric Cancer | Not specified in the provided text | Histopathological images of gastric cancer (GHIA) | Summarizes image preprocessing, feature extraction, segmentation, and classification techniques for future researchers |
| [37] | Tumor organization of non-small cell lung cancer (NSCLC) with detailed insights | Two-step deep learning shows autoencoder and CNN) for NSCLC arranging | Preparing (n = 90), Approval (n = 8), Test cohorts (n = 37, n = 26) from open space (CPTAC and TCGA) |
CPTAC Test Cohort: Precision:0.8649 Affectability:0.8000 Specificity:0.9412 AUC:0.8206 TCGA Test Cohort: Exactness:0.8077 Affectability:0.7692 Specificity:0.8462 AUC:0.8343 |
| [38] | Precise location and classification of breast cancer | Pa-DBN-BC (Deep Conviction Arrange) | The entire slide histopathology image dataset from four information cohorts | 86% accuracy |
| [39] | Skin Cancer Diagnosis | U-Net and VGG19 | ISIC 2016, ISIC 2017, ISIC 2018 | Palatable comes about compared to state-of-the-art |
| [40] | Rectal Adenocarcinoma Survival Prediction | DeepSurv model (seven-layer neural network) | Patients with rectal adenocarcinoma from the Soothsayer database |
C index: 0.824 (preparation cohort) and 0.821 (test cohort) Factors influencing survival: age, gender, marital status, tumor evaluation, surgical status, and chemotherapy status. High consistency between test and cohort predictions |
| [41] | Prostate Cancer Diagnosis and Gleason Grading | Deep Residual Convolutional Neural Network | 85 prostate core biopsy specimens digitized and annotated | Coarse-level accuracy: 91.5%, Fine-level accuracy: 85.4% |
| [42] | Tree-based BrT Multiclassification Demonstrate for Breast Cancer | Outfit tree-based deep learning demonstrates | BreakHis dataset (pretraining), BCBH dataset |
Classification accuracy of 87. 50% to 100% for the four subtypes of BrT The proposed show is beyond the state of the art |
| [43] | Breast Cancer (BC) | Transfer Learning (TL) | MIAS dataset |
80–20 strategy: Precision: 98.96D44 Affectability: 97.83D44 Specificity: 99.13D44 Accuracy: 97.35D44F-score: 97.66D44 AUC: 0.995 tenfold cross-validation strategy: Exactness: 98.87D44 Affectability: 97.27D44 Specificity: 98.2D44 Accuracy: 98.84D44 F-score: 98.04D44 AUC: 0.993 |
| [44] | Screening for breast cancer with mammography | Deep learning and convolutional neural systems | Different datasets in advanced mammography and advanced breast tomosynthesis | AI calculations appearing guarantee in review information sets, AUC 0.91, advance considers required for real-world screening effect |
| [45] | Breast Cancer Diagnosis | Statistical ML and Deep Learning | Various breast imaging datasets |
Recommendations for future work Accuracy 97% |
| [46] | Dermoscopic Expert | Crossbreed Convolutional, Neural Organize (hybrid-CNN) | ISIC-2016, ISIC-2017, ISIC-2018 AUC of 0.96, 0.95, 0.97 Advanced | AUC by 10.0% and 2.0% for ISIC-2016 and ISIC-2017 datasets, 3.0% higher balanced precision for ISIC-2018 dataset |
| [47] | Breast Cancer Classification | ResNet-50 pre-trained model | Histopathological images from Jimma College Therapeutic Center, 'BreakHis,' and 'zendo' online datasets | 96.75 accuracy for twofold classification, 96.7 accuracy for generous sub-type classification, 95.78 accuracy for threatening sub-type classification, and 93.86 accuracy for review recognizable proof |
| [48] | Cancer-Net SCa | Custom deep neural organize plans | Universal Skin Imaging Collaboration (ISIC) | Made strides in precision compared to ResNet-50, decreased complexity, solid skin cancer discovery execution, empowered open-source utilization and improvement |
| [49] | Automating Medical Diagnosis |
Transfer Learning, Image Classification, Object Detection, Segmentation, Multi-task Learning |
Medical image data, Skin lesion data, Pressure ulcer, Segmentation data, | Cervical cancer: Sensitivity + 5.4%, Skin lesion: Accuracy + 8.7%, Precision + 28.3%, Sensitivity + 39.7%, Pressure ulcer: Accuracy + 1.2%, IoU + 16.9%, Dice similarity + 3.5% |
| [50] |
Symptomatic Precision of CNN for Gastric Cancer Anticipating Attack Profundity of Gastric Cancer |
Convolutional Neural Network (CNN) | 17 studies, 51,446 images, 174 videos, 5539 patients |
Sensitivity: 89%, Specificity: 93%, LR + : 13.4, LR–: 11, AUC: 0.94 Sensitivity: 82%, Specificity: 90%, LR + : 8.4, LR–: 20, AUC: 0.90 |
| [51] | Image Quality Control for Cervical Precancer Screening | Deep learning gathering system | 87,420 images from 14,183 patients with numerous cervical cancers think about | Accomplished higher execution than standard approaches |
| [52] | Breast Cancer Determination Utilizing Deep Neural Systems | Convolutional Neural Systems (CNN) | Mammography and histopathologic images | Moved forward BC conclusion with DL, utilized open and private datasets, pre-processing procedures, neural arrange models, and distinguished inquire about challenges for future advancements |
| [53] | HPV Status Prediction in OPC, Survival Prediction in OPC | Ensemble Model | 492 OPC Patient Database |
AUC: 0.83, Accuracy: 78.7% AUC: 0.91, Accuracy: 87.7% |
| [54] | Pathology Detection Algorithm | YOLOv5 with an improved attention mechanism | Gastric cancer slice dataset | F1_score: 0.616, mAP: 0.611; Decision support for clinical judgment |
| [55] | Cervical Cancer (CC) | HSIC, RNN, LSTM, AFSA | Not mentioned | Risk scores for recurrence CC patients using the AFSA algorithm |
| [56] | Hepatocellular carcinoma (HCC) | Inception V3 | Genomic Data Commons Databases H&E images | Matthews’s correlation coefficient, 96.0 accuracy for benign/malignant classification, and 89.6 accuracy for tumor separation. Anticipated ten most common changed qualities (CTNNB1, FMN2, TP53, ZFX4) with AUCs from 0.71 to 0.89 |