article · IEEE Access
Deep-learning architectures can identify and classify eight primary cancer types and 26 subtypes from medical images. Using a secondary dataset containing over 130,000 images, hybrid computational models combine pre-trained convolutional neural networks, long short-term memory networks, and machine learning classifiers such as support vector machines and k-nearest neighbours. Two novel architectures, named Vception and Vmobilnet, merge distinct convolutional backbones with recurrent layers to process diagnostic imagery. The evaluation examined simultaneous classification alongside a two-step hierarchical method where primary classes are determined prior to identifying subtypes. Incorporating an exclusive-OR logic gate to fuse post-prediction outputs from the hybrid networks reduced misclassifications, achieving an accuracy of 99.95 percent for primary cancer classes and 99.13 percent for subtypes. Additionally, k-nearest neighbours paired with principal component analysis demonstrated strong standalone performance on lymphoma cases.
Accurate identification of specific cancer types and subtypes at early stages is essential for selecting appropriate therapies and improving survival rates. Automated image classification tools that achieve high precision across dozens of subcategories could assist clinical teams in making rapid, reliable diagnoses, minimising diagnostic errors and supporting timely medical intervention.
The methodology points towards software tools for automated cancer screening and diagnostic support in pathology or oncology departments. Because the models were trained and evaluated exclusively on a secondary open dataset from Kaggle without reported clinical validation or regulatory testing, the technology is currently at an early research stage and requires substantial clinical trials before practical deployment.
AI-generated from the published abstract. Always read the original work before citing.
Cancer is a disease where abnormal cells grow uncontrollably and spread to other body parts. It can originate anywhere in the human body, which consists of trillions of cells. These cells continually divide, replenishing the body’s needs. As cells age or sustain damage, they naturally undergo apoptosis, allowing new cells to take their place. Our research uses a secondary dataset from Kaggle, comprising over 130,000 images representing various cancer types. We have developed a novel Deep-learning model capable of detecting and classifying cancer at early stages with remarkable accuracy. The model classifies eight primary cancer types and 26 subtypes, each represented by 5,000 images. Our approach combines various computational tools, including pre-trained Convolutional Neural Networks, Machine learning, and Deep learning classifiers such as KNN and SVM, and innovative multimodal architectures of merged CNN-LSTM hybrids. We applied two distinct classification strategies. In our first approach, the main class and subclass are classified together. In the second approach, the model first predicts the main eight classes and then 26 subclasses concerning the main class classification, where the KNN model achieved higher accuracy for the Lymphoma class than CNNs. Finally, the X-OR gate-based fusion technique applied after prediction significantly reduces misclassifications and enhances the certainty of cancer types. Our findings reveal great accuracy levels of 99.25% for primary cancer classifications and 97.80% for subclass classifications. The introduction of novel models, Vception (VGG + Inception) and Vmobilnet (VGG + MobileNet), integrated with LSTM, further advances diagnostic capabilities. Again, By utilizing an X-OR gate post-prediction from Vmobilenet and Vception models, we achieved a main class accuracy of 99.95% and a subclass accuracy of 99.13%, significantly boosting model confidence. Moreover, individually, KNN achieved 97.14% accuracy for the Lymphoma class using PCA. This study not only sets a new benchmark in cancer detection but also promises to improve patient care and treatment outcomes significantly.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/access.2024.3422313
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
