Deep Learning and Semi-Supervised and Transfer Learning Algorithms for Medical Imaging

Mohanasundaram, R.; Malhotra, Ankit Sandeep; Arun, R.; Periasamy, P.S.

doi:10.1016/b978-0-12-816718-2.00015-4

Cited by 11 publications

(7 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The utility of ImageNet pre-training (henceforth "ImageNet weights") has been demonstrated in various medical-imaging learning tasks 7,12,14,15,[60][61][62] . That said, transfer learning between unrelated domains remains fairly controversial 18,[63][64][65] . Moreover, commonalities across data modalities may be counterintuitive.…”

Section: The Utility Of 2d B-scan Oct In Pre-trainingmentioning

confidence: 99%

SLIViT: a general AI framework for clinical-feature diagnosis from limited 3D biomedical-imaging data

Avram*,

Durmus*,

Rakocz

et al. 2023

Preprint

View full text Add to dashboard Cite

We present SLIViT, a deep-learning framework that accurately measures disease-related risk factors in volumetric biomedical imaging, such as magnetic resonance imaging (MRI) scans, optical coherence tomography (OCT) scans, and ultrasound videos. To evaluate SLIViT, we applied it to five different datasets of these three different data modalities tackling seven learning tasks (including both classification and regression) and found that it consistently and significantly outperforms domain-specific state-of-the-art models, typically improving performance (ROC AUC or correlation) by 0.1-0.4. Notably, compared to existing approaches, SLIViT can be applied even when only a small number of annotated training samples is available, which is often a constraint in medical applications. When trained on less than 700 annotated volumes, SLIViT obtained accuracy comparable to trained clinical specialists while reducing annotation time by a factor of 5,000 demonstrating its utility to automate and expedite ongoing research and other practical clinical scenarios. *Oren Avram and Berkin Durmus equally contributed to this work. **Srinivas R. Sadda and Eran Halperin jointly supervised this study.

show abstract

Section: The Utility Of 2d B-scan Oct In Pre-trainingmentioning

confidence: 99%

SLIViT: a general AI framework for clinical-feature diagnosis from limited 3D biomedical-imaging data

Avram*,

Durmus*,

Rakocz

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Associated acquisition and processing costs contribute to the paucity of clinician-labelled data. Pre-training (an architecture trained on a separate image database) and transfer learning (taking features learned on one problem and using them for a new problem) could be exploited to overcome this lack of training data [ 18 ] [ 19 ]. Transfer learning can be approached with either fine tuning or fixed representations [ 20 ].…”

Section: Introductionmentioning

confidence: 99%

“…Mustafa et al . [ 19 ] showed network performance could be improved by increasing size of both the model architecture, and the natural image pre-training dataset. ImageNet-21k (the full ImageNet dataset classified into 21000 classes) obtained superior performance over ImageNet (the subset of ImageNet classified into 1000 classes).…”

Section: Introductionmentioning

confidence: 99%

Pre-Training, Transfer Learning and Pretext Learning for a Convolutional Neural Network Applied to Automated Assessment of Clinical PET Image Quality

Hopson¹,

Neji

Dunn

et al. 2023

IEEE Trans. Radiat. Plasma Med. Sci.

View full text Add to dashboard Cite

show abstract

“…COVID-19 detection and diagnosis methods using deep learning-based algorithms are precise and effective. The advantages of supervised DL algorithms in medical imaging tasks have been demonstrated in numerous applications (21). These DL algorithms need many data to create an accurate model.…”

Section: Introductionmentioning

confidence: 99%

A deep transfer learning approach for COVID-19 detection and exploring a sense of belonging with Diabetes

Ahmad,

Merla,

Ali

et al. 2023

Front. Public Health

View full text Add to dashboard Cite

COVID-19 is an epidemic disease that results in death and significantly affects the older adult and those afflicted with chronic medical conditions. Diabetes medication and high blood glucose levels are significant predictors of COVID-19-related death or disease severity. Diabetic individuals, particularly those with preexisting comorbidities or geriatric patients, are at a higher risk of COVID-19 infection, including hospitalization, ICU admission, and death, than those without Diabetes. Everyone’s lives have been significantly changed due to the COVID-19 outbreak. Identifying patients infected with COVID-19 in a timely manner is critical to overcoming this challenge. The Real-Time Polymerase Chain Reaction (RT-PCR) diagnostic assay is currently the gold standard for COVID-19 detection. However, RT-PCR is a time-consuming and costly technique requiring a lab kit that is difficult to get in crises and epidemics. This work suggests the CIDICXR-Net50 model, a ResNet-50-based Transfer Learning (TL) method for COVID-19 detection via Chest X-ray (CXR) image classification. The presented model is developed by substituting the final ResNet-50 classifier layer with a new classification head. The model is trained on 3,923 chest X-ray images comprising a substantial dataset of 1,360 viral pneumonia, 1,363 normal, and 1,200 COVID-19 CXR images. The proposed model’s performance is evaluated in contrast to the results of six other innovative pre-trained models. The proposed CIDICXR-Net50 model attained 99.11% accuracy on the provided dataset while maintaining 99.15% precision and recall. This study also explores potential relationships between COVID-19 and Diabetes.

show abstract

Deep Learning and Semi-Supervised and Transfer Learning Algorithms for Medical Imaging

Cited by 11 publications

References 4 publications

SLIViT: a general AI framework for clinical-feature diagnosis from limited 3D biomedical-imaging data

SLIViT: a general AI framework for clinical-feature diagnosis from limited 3D biomedical-imaging data

Pre-Training, Transfer Learning and Pretext Learning for a Convolutional Neural Network Applied to Automated Assessment of Clinical PET Image Quality

A deep transfer learning approach for COVID-19 detection and exploring a sense of belonging with Diabetes

Contact Info

Product

Resources

About