A comparison of deep learning and hand crafted features in medical image modality classification

Khan, Sameer; Yong, Suet-Peng

doi:10.1109/iccoins.2016.7783289

Cited by 26 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The training data of a small size is considered as the main reason for the limited performance of deep learning. Khan and Yong [ 49 ] reported that the hand-crafted features outperformed the deep learned features in medical image modality classification with small datasets. Cho et al [ 50 ] presented a study on determining how much training dataset is necessary to achieve high classification accuracy.…”

Section: Deep Learning In Cancer Classificationmentioning

confidence: 99%

Application of Deep Learning in Automated Analysis of Molecular Images in Cancer: A Survey

Xue

Chen

Qin

et al. 2017

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

Molecular imaging enables the visualization and quantitative analysis of the alterations of biological procedures at molecular and/or cellular level, which is of great significance for early detection of cancer. In recent years, deep leaning has been widely used in medical imaging analysis, as it overcomes the limitations of visual assessment and traditional machine learning techniques by extracting hierarchical features with powerful representation capability. Research on cancer molecular images using deep learning techniques is also increasing dynamically. Hence, in this paper, we review the applications of deep learning in molecular imaging in terms of tumor lesion segmentation, tumor classification, and survival prediction. We also outline some future directions in which researchers may develop more powerful deep learning models for better performance in the applications in cancer molecular imaging.

show abstract

Section: Deep Learning In Cancer Classificationmentioning

confidence: 99%

Application of Deep Learning in Automated Analysis of Molecular Images in Cancer: A Survey

Xue

Chen

Qin

et al. 2017

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

show abstract

“…Meanwhile, Yong, 2016 andSong, et al, 2016 indicate that the hand-crafted features outperform the deep learned features in their studies. Therefore, how to effectively use features for a HAR task is still challenging.…”

Section: Research Problemsmentioning

confidence: 97%

“…The results inKashif, et al, 2016 have shown that adding hand-crafted features to the raw data can help improve the detection accuracy of deep convolutional neural networks for tumour cells in histology images. Meanwhile, there are some other studies giving certain interesting findings in similar fields, e.g., the experimental results inKhan & Yong, 2016 indicate that the hand-crafted features outperform the deep learned features in medical images.…”

mentioning

confidence: 95%

A survey on wearable sensor modality centred human activity recognition in health care

Wang

Cang

2019

Expert Systems with Applications

271

127

View full text Add to dashboard Cite

Increased life expectancy coupled with declining birth rates leads to an aging population structure. Agingcaused changes, such as physical or cognitive decline, could affect people's quality of life, resulting in injuries, mental health or the lack of physical activity. Sensor-based human activity recognition (HAR) is one of the most promising assistive technologies to support older people's daily life, which has enabled enormous potential in human-centred applications. Recent surveys either focus on the deep learning approaches or one specific sensor modality in HAR. This survey aims to provide a comprehensive introduction for newcomers to HAR, including the conventional approaches and the deep learning methods. It specifically puts more emphasis on wearable sensor-based HAR systems. We first describe the state-of-art sensor modalities. We then detail each step of the wearable sensor-based HAR. In the feature learning section, we concentrate both hand-crafted features and deep learned features in HAR. We also present the ambient-sensor-based HAR, including camera-based systems, and the systems which combine the wearable and ambient sensors. Finally, we identify certain challenges in HAR to pose research problems for further improvement in HAR.

show abstract

“…). Both methods have pros and cons; DL usually (not always ) outperforms the hand‐crafted algorithm; however, it requires a far greater amount of learning material. One limitation of DL is its black‐box nature; the DL algorithm cannot apply reason to the machine‐generated decision, which can confuse endoscopists who are familiar with diagnostics that have been accumulated by many endoscopists.…”

Section: What Is Deep Learning?mentioning

confidence: 99%

Artificial intelligence and upper gastrointestinal endoscopy: Current status and future perspective

Mori

Kudo

Mohmed

et al. 2019

Digestive Endoscopy

109

View full text Add to dashboard Cite

With recent breakthroughs in artificial intelligence, computer‐aided diagnosis (CAD) for upper gastrointestinal endoscopy is gaining increasing attention. Main research focuses in this field include automated identification of dysplasia in Barrett's esophagus and detection of early gastric cancers. By helping endoscopists avoid missing and mischaracterizing neoplastic change in both the esophagus and the stomach, these technologies potentially contribute to solving current limitations of gastroscopy. Currently, optical diagnosis of early‐stage dysplasia related to Barrett's esophagus can be precisely achieved only by endoscopists proficient in advanced endoscopic imaging, and the false‐negative rate for detecting gastric cancer is approximately 10%. Ideally, these novel technologies should work during real‐time gastroscopy to provide on‐site decision support for endoscopists regardless of their skill; however, previous studies of these topics remain ex vivo and experimental in design. Therefore, the feasibility, effectiveness, and safety of CAD for upper gastrointestinal endoscopy in clinical practice remain unknown, although a considerable number of pilot studies have been conducted by both engineers and medical doctors with excellent results. This review summarizes current publications relating to CAD for upper gastrointestinal endoscopy from the perspective of endoscopists and aims to indicate what is required for future research and implementation in clinical practice.

show abstract

A comparison of deep learning and hand crafted features in medical image modality classification

Cited by 26 publications

References 16 publications

Application of Deep Learning in Automated Analysis of Molecular Images in Cancer: A Survey

Application of Deep Learning in Automated Analysis of Molecular Images in Cancer: A Survey

A survey on wearable sensor modality centred human activity recognition in health care

Artificial intelligence and upper gastrointestinal endoscopy: Current status and future perspective

Contact Info

Product

Resources

About