English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Colorectal and prostate cancers are the most common types of cancer in menworldwide. To diagnose colorectal and prostate cancer, a pathologist performs ahistological analysis on needle biopsy samples. This manual process istime-consuming and error-prone, resulting in high intra and interobservervariability, which affects diagnosis reliability. This study aims to develop anautomatic computerized system for diagnosing colorectal and prostate tumors byusing images of biopsy samples to reduce time and diagnosis error ratesassociated with human analysis. We propose a CNN model for classifyingcolorectal and prostate tumors from multispectral images of biopsy samples. Thekey idea was to remove the last block of the convolutional layers and halve thenumber of filters per layer. Our results showed excellent performance, with anaverage test accuracy of 99.8% and 99.5% for the prostate and colorectal datasets, respectively. The system showed excellent performance when compared withpretrained CNNs and other classification methods, as it avoids thepreprocessing phase while using a single CNN model for classification. Overall,the proposed CNN architecture was globally the best-performing system forclassifying colorectal and prostate tumor images. The proposed CNN was detailedand compared with previously trained network models used as feature extractors.These CNNs were also compared with other classification techniques. As opposedto pretrained CNNs and other classification approaches, the proposed CNNyielded excellent results. The computational complexity of the CNNs was alsoinvestigated, it was shown that the proposed CNN is better at classifyingimages than pretrained networks because it does not require preprocessing.Thus, the overall analysis was that the proposed CNN architecture was globallythe best-performing system for classifying colorectal and prostate tumorimages.

jmir bioinformatics and biotechnology

Convolutional Neural Network-Based Automatic Classification of  Colorectal and Prostate Tumor Biopsies Using Multispectral Imagery: System  Development Study