Improving liver lesions classification on CT/MRI images based on Hounsfield Units attenuation and deep learning

Article Oncology

Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries

Hyuna Sung et al.

Summary: The global cancer burden in 2020 saw an estimated 19.3 million new cancer cases and almost 10.0 million cancer deaths. Female breast cancer surpassed lung cancer as the most commonly diagnosed cancer, while lung cancer remained the leading cause of cancer death. These trends are expected to rise in 2040, with transitioning countries experiencing a larger increase compared to transitioned countries due to demographic changes and risk factors associated with globalization and a growing economy. Efforts to improve cancer prevention measures and provision of cancer care in transitioning countries will be crucial for global cancer control.

CA-A CANCER JOURNAL FOR CLINICIANS (2021)

添加到收藏夹

Article Oncology

Automatic Detection and Classification of Focal Liver Lesions Based on Deep Convolutional Neural Networks: A Preliminary Study

Jiarong Zhou et al.

Summary: This study proposed a deep learning-based framework for automatic detection and classification of liver lesions in CT images. The model showed superior performance in detecting and classifying FLLs, outperforming other CNN models and physicians, thereby aiding inexperienced physicians in reaching accurate diagnoses in clinical practices.

FRONTIERS IN ONCOLOGY (2021)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

Joint segmentation and classification of hepatic lesions in ultrasound images using deep learning

Hwaseong Ryu et al.

Summary: The study developed a convolutional neural network system for segmenting and classifying hepatic lesions in ultrasound images. Jointly conducting segmentation and classification led to performance improvements, particularly in classification accuracy and sensitivity.

EUROPEAN RADIOLOGY (2021)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

Saliency-based 3D convolutional neural network for categorising common focal liver lesions on multisequence MRI

Shu-Hui Wang et al.

Summary: An interpretable deep learning model was developed for the classification of focal liver lesions (FLLs) on multisequence MRI, showing high diagnostic performance. The model outperformed radiology residents and general radiologists but was slightly lower than academic radiologists in accuracy.

INSIGHTS INTO IMAGING (2021)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging

Classification of focal liver lesions in CT images using convolutional neural networks with lesion information augmented patches and synthetic data augmentation

Hansang Lee et al.

Summary: The study introduces a deep learning method for classifying focal liver lesions using synthetic data augmentation and LINA patches. Results show improvements in data diversity and class imbalance, as well as enhanced learning efficiency for small lesions.

MEDICAL PHYSICS (2021)

添加到收藏夹

Article Oncology