HMARNET-A Hierarchical Multi-Attention Residual Network for Gleason scoring of prostate cancer

Article Engineering, Biomedical

Classification of breast cancer from histopathology images using an ensemble of deep multiscale networks

R. Karthik et al.

Summary: Manual delineation of tumours in breast histopathology images is time-consuming and laborious, and computer-aided detection systems can improve efficiency. This study proposes an ensemble of two CNN architectures integrated with Channel and Spatial attention, achieving high accuracy in breast cancer classification.

BIOCYBERNETICS AND BIOMEDICAL ENGINEERING (2022)

Add to Collection

Article Oncology

Biomarker Identification through Multiomics Data Analysis of Prostate Cancer Prognostication Using a Deep Learning Model and Similarity Network Fusion

Tzu-Hao Wang et al.

Summary: This study identified potential multiomics biomarkers for early detection of prognostic recurrence of prostate cancer patients using DL and SNF on the TCGA PRAD dataset. The constructed multiomics panels showed high predictive performance with intersected biomarkers and clinical information, providing valuable insights into cancer mechanisms and potential prognostic biomarkers for clinical decision-making.

CANCERS (2021)

Add to Collection

Proceedings Paper Computer Science, Interdisciplinary Applications

Automatic Prostate Cancer Grading Using Deep Architectures

Muhammad Mohsin et al.

Summary: Prostate cancer is the second most aggressive cancer in men over 45, with a major impact on their lives. The study focuses on deep learning models for automatically grading prostate cancer from tissue images. Utilizing UNet based architecture and four different deep learning models, the proposed framework achieved better performance compared to state of the art models.

2021 IEEE/ACS 18TH INTERNATIONAL CONFERENCE ON COMPUTER SYSTEMS AND APPLICATIONS (AICCSA) (2021)

Add to Collection

Proceedings Paper Engineering, Biomedical

Systematic comparison of deep learning strategies for weakly supervised Gleason grading

Sebastian Otalora et al.

Summary: This study compares weakly supervised strategies for classifying the five classes of GS using global diagnostic labels as the only source of supervision. Results show that DL networks and class-wise data augmentation outperform other strategies, achieving a kappa score of 0.44, which could be improved with a larger dataset or combining strong and weakly supervised models.

MEDICAL IMAGING 2020: DIGITAL PATHOLOGY (2021)

Add to Collection

Review Computer Science, Interdisciplinary Applications