News • Deep learning refinement

Colorectal cancer: AI tool improves diagnostic accuracy

Researchers from the University of Jyväskylä in collaboration with the Institute of Biomedicine University of Turku and Nova Central Finland have developed an artificial intelligence tool for automatic colorectal cancer tissue analysis.

Photo
Each dot represents an image piece from a cancer microscope slide. The AI system has automatically arranged them by similarity.

Image source: Prezja et al., Scientific Reports 2023 (CC BY 4.0)

The refined neural network outperformed all previous solutions in the task. The neural network offers a faster, more precise method for classifying colorectal cancer tissue images from microscope slides. This could significantly reduce the workload of histopathologists, leading to quicker insights, prognoses, and diagnoses. The research article is available in Nature Scientific Reports

In a significant nod to open science and cooperative growth, the researchers are making the trained neural network tool available to the public. This gesture is intended to spur further advancements by inviting scientists, researchers, and developers globally to refine its capabilities and investigate new applications. “By granting universal access, the aim is to fast-track breakthroughs in colorectal cancer research”, adds Fabi Prezja, who was responsible for the design of the method.

While the results are promising, it's crucial to adopt AI in clinical settings judiciously. The calibre and diversity of medical data are central to the success of AI-driven methods. As these AI solutions inch closer to routine clinical implementation, it's imperative they undergo stringent clinical validation to ensure their outcomes consistently align with clinical standards.


Source: University of Jyväskylä

25.10.2023

Related articles

Photo

News • Biomarker-based predictions

AI drives precision oncology for colorectal cancer

For the first time, researchers show that AI-based predictions can deliver comparable results to clinical tests on biopsies of patients with colorectal cancer (CRC).

Photo

News • WSI-based analysis

AI-driven classification of diffuse gliomas skips molecular testing

Research from Shenzhen proposes an integrated diagnosis model for automatic classification of adult-type diffuse gliomas directly from annotation-free standard whole-slide pathological images.

Photo

News • AI approach to colorectal tumors

Deep learning identifies molecular patterns of cancer

A new AI platform can analyze genomic data extremely quickly, picking out key patterns to classify different types of colorectal tumors and improve the drug discovery process.

Related products

Subscribe to Newsletter