Table 8 Benchmarking of deep learning models for cancer detection
Study | Field description | DL model | Dataset | Results |
|---|---|---|---|---|
[27] | Exact aspiratory knob discovery | Convolutional Neural Networks (CNNs) | LIDC-IDRI dataset | 92.7% distribution probability with 1 bad positive per filter and 94.2% distribution probability with 2 bad positives per filter for lung nodules over 888 examinations in the LIDC-IDRI dataset. The use of MIP imaging increases the likelihood of indication and reduces the number of false positive results when locating pulmonary lymph nodes programmed into the CT interface |
[39] | Pa-DBN-BC | Deep Belief Network (DBN) | The slide histopathology image dataset from four distinct cohorts achieved | 86% accuracies in breast cancer location and classification, surpassing previous deep learning strategies |
[56] | Hepatocellular carcinoma (HCC) | Inception V3 | Genomic Data Commons Databases | 96.0 accuracy for kind and dangerous classification—89.6 accuracy for tumor separation (well, direct, and destitute)—Expectation of 10 most common changed qualities in HCC—Outside AUCs for 4 qualities (CTNNB1, FMN2, TP53, ZFX4) extending from 0.71 to 0.89—Utilize of convolutional neural systems to help pathologists in classification and quality transformation discovery in liver cancer |
[46] | Dermo Expert | Hybrid-CNN | ISIC-2016, ISIC-2017, ISIC-2018 | AUC: 0.96, 0.95, 0.97; Improved AUC by 10.0% (ISIC-2016) and 2.0% (ISIC-2017); Outperformed by 3.0% in balanced accuracy (ISIC-2018) |
[64] | Learning Algorithm for Adaptive Signal Processing | Fractional Backpropagation MLP | Leukemia cancer classification | Outperformed BP-MLP in convergence rate and test accuracy |
[65] | Breast Cancer Discovery and Classification | Modified Entropy Whale Optimization Algorithm (MEWOA) | In the breast, MIAS, CBIS-DDSM | IN breast: 99.7%, MIAS: 99.8%, CBIS-DDSM: 93.8% |
Current Study | Adenocarcinoma, Expansive Cell Carcinoma, Squamous Cell Carcinoma, Typical | Adenocarcinoma, expanding cell carcinoma, squamous cell carcinoma | 1000 images from the Kaggle lung cancer dataset | Best accuracy for humans (EfficientNet 93%) Accuracy 99.44% synthetic accuracy |