Active, continual fine tuning of convolutional neural networks for reducing annotation efforts

Zhou, Zongwei; Shin, Jae Y.; Gurudu, Suryakanth R.; Gotway, Michael B.; Liang, Jianming

doi:10.1016/j.media.2021.101997

Cited by 32 publications

(16 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notably, at small shot numbers, different shot data can have very large impacts on the fine-tuning process, whereas we observed that as the shot number increases variance becomes substantially smaller. In the future, active learning (38) on cell instance segmentation promises to refine shot data selection for finetuning.…”

Section: Discussionmentioning

confidence: 99%

Scellseg: a style-aware cell instance segmentation tool with pre-training and contrastive fine-tuning

Xun

Chen

Zhou

et al. 2021

Preprint

View full text Add to dashboard Cite

Deep learning-based cell segmentation is increasingly utilized in cell biology and molecular pathology, due to massive accumulation of diverse large-scale datasets and excellent performance in cell representation. However, the development of specialized algorithms has long been hampered by a paucity of annotated training data, whereas the performance of generalist algorithm was limited without experiment-specific calibration. Here, we present a deep learning-based tool called Scellseg consisted of novel pre-trained network architecture and contrastive fine-tuning strategy. In comparison to four commonly used algorithms, Scellseg outperformed in average precision on three diverse datasets with no need for dataset-specific configuration. Interestingly, we found that eight images are sufficient for model tuning to achieve satisfied performance based on a shot data scale experiment. We also developed a graphical user interface integrated with functions of annotation, fine-tuning and inference, that allows biologists to easily specialize their own segmentation model and analyze data at the single-cell level.

show abstract

Section: Discussionmentioning

confidence: 99%

Scellseg: a style-aware cell instance segmentation tool with pre-training and contrastive fine-tuning

Xun

Chen

Zhou

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In addition to model transfer, TL can also be used to reduce the difficulty and costs of data annotation. Zhou et al [51] uses the technology of active learning and TL to implement medical data labeling, which reduces labeling costs by at least half compared with the state-of-the-art methods. In medical US image analysis, TL is frequently used to pre-train neural networks [3], [41], [52].…”

Section: Medical Ultrasound Image Preprocessingmentioning

confidence: 99%

Deep Learning in Medical Ultrasound Image Analysis: A Review

Wang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Ultrasound (US) is one of the most widely used imaging modalities in medical diagnosis. It has the advantages of real-time, low cost, noninvasive nature, and easy to operate. However, it also has the unique disadvantages of strong artifacts and noise and high dependence on the experience of doctors. In order to overcome the shortcomings of ultrasound diagnosis and help doctor improve the accuracy and efficiency of diagnosis, many computer aided diagnosis (CAD) systems have been developed. In recent years, deep learning has achieved great success in computer vision with its unique advantages. In the aspect of medical US image analysis, deep learning has also been exploited for its great potential and more and more researchers apply it to CAD systems. In this paper, we first introduce the deep learning models commonly used in medical US image analysis; Second, we review the data preprocessing methods of medical US images, including data augmentation, denoising, and enhancement; Finally, we analyze the applications of deep learning in medical US imaging tasks (such as image classification, object detection, and image reconstruction). INDEX TERMSDeep learning, medical ultrasound image analysis, ultrasound image preprocessing.

show abstract

“…Minimizing the number of annotated samples requires that the labeled samples be distinct from one another. Therefore, uncertainty and diversity are two natural metrics for informativeness and representativeness [1], [2], upon which the two articles featured in this Special Issue present two methods.…”

Section: A Active Learningmentioning

confidence: 99%

“…A NNOTATION-EFFICIENT deep learning refers to methods and practices that yield high-performance deep learning models without the use of massive carefully labeled training datasets. This paradigm has recently attracted attention from the medical imaging research community because (1) it is difficult to collect large, representative medical imaging datasets given the diversity of imaging protocols, imaging devices, and patient populations, (2) it is expensive to acquire accurate annotations from medical experts even for moderately sized medical imaging datasets, and (3) it is infeasible to adapt data-hungry deep learning models to detect and diagnose rare diseases whose low prevalence hinders data collection.…”

Section: Guest Editorial Annotation-efficient Deep Learning: the Holy Grail Of Medical Imaging I Introductionmentioning

confidence: 99%

Guest Editorial Annotation-Efficient Deep Learning: The Holy Grail of Medical Imaging

Tajbakhsh¹,

Roth

Terzopoulos

et al. 2021

IEEE Trans. Med. Imaging

Self Cite

View full text Add to dashboard Cite

Active, continual fine tuning of convolutional neural networks for reducing annotation efforts

Cited by 32 publications

References 40 publications

Scellseg: a style-aware cell instance segmentation tool with pre-training and contrastive fine-tuning

Scellseg: a style-aware cell instance segmentation tool with pre-training and contrastive fine-tuning

Deep Learning in Medical Ultrasound Image Analysis: A Review

Guest Editorial Annotation-Efficient Deep Learning: The Holy Grail of Medical Imaging

Contact Info

Product

Resources

About