Automated and real-time segmentation of suspicious breast masses using convolutional neural network

Kumar, Viksit; Webb, Jeremy; Gregory, Adriana; Denis, Max; Meixner, Duane D.; Bayat, Mahdi; Whaley, Dana H.; Fatemi, Mostafa; Alizad, Azra

doi:10.1371/journal.pone.0195816

Cited by 92 publications

(47 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To perform the segmentation task, we chose a U-net-like architecture implemented in the fast.ai library 6 . U-net was developed specifically for semantic segmentation and has been successfully applied to complex biomedical images such as electron microscopy of neuronal structures and MRI or ultrasound images in breast cancer screening 9,12,13 . We trained the U-net network using 492 plate images and corresponding Ilastik-generated masks, with 20% kept aside for validation (see Implementation for full training parameters).…”

Section: Resultsmentioning

confidence: 99%

A fully automated deep learning pipeline for high-throughput colony segmentation and classification

Carl

Duempelmann

Shimada

et al. 2019

Preprint

View full text Add to dashboard Cite

Background: Adenine auxotrophy is a commonly used non-selective genetic marker in yeast research.It allows investigators to easily visualize and quantify various genetic and epigenetic events by simply reading out colony color. However, manual counting of large numbers of colonies is extremely timeconsuming, difficult to reproduce and possibly inaccurate.Results: Using cutting-edge neural networks, we have developed a fully automated pipeline for colony segmentation and classification, which speeds up white/red colony quantification 100-fold over manual counting by an experienced researcher. Conclusions: Our approach uses readily available training data and can be smoothly integrated intoexisting protocols, vastly speeding up screening assays and increasing the statistical power of experiments that employ adenine auxotrophy. KeywordsDeep learning, neural networks, adenine auxotrophy, yeast, growth assay BackgroundAuxotrophy is the inability of an organism to synthesize a particular organic compound required for its growth. For example, yeasts with mutations in the adenine biosynthetic pathway cannot grow on media lacking adenine. When grown under adenine-limiting conditions, adenine auxotrophs grow but accumulate a cell-limited red pigment in their vacuoles, whereas wild type cells grow white. This red/white colony color assay has been widely used over the last decades for the investigation of many biological processes, such as recombination, copy number, chromosome loss, plasmid stability, prion propagation, or epigenetic gene regulation in both budding and fission yeasts. However, adapting this assay to quantitative high-throughput applications has proven challenging, as it requires extensive scoring of colony phenotypes by eye. In addition to being time-consuming and tedious, manual colony scoring may suffer from inaccuracy and irreproducibility. Nonetheless, up to now manual scoring is a common practice in the yeast community. Modern machine-learning techniques such as deep learning have made huge strides in automated image classification in recent years and are beginning to be applied to previously intractable problems in the biomedical imaging domain. We set out to leverage these recent developments to build a computational pipeline that would enable fully automated high-throughput adenine auxotrophy-based screening and quantification.Typically, red/white colony color assays start with plating individual yeast cells on limiting adenine indicator plates and allowing them to grow until they form colonies large enough to be inspected by eye.Each plate may represent an independent condition or genotype, the penetrance of which can be assessed by quantifying the percentage of non-white colonies per plate. In order to create a pipeline that would fit into existing protocols as seamlessly as possible, we considered our input to be images of plates and our desired output to be percentages of white and non-white colonies per plate. Two major tasks are required to generate this output: separating the colonies from th...

show abstract

Section: Resultsmentioning

confidence: 99%

A fully automated deep learning pipeline for high-throughput colony segmentation and classification

Carl

Duempelmann

Shimada

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Rodrigues et al [20] took the advantage of pixel-wise classification and achieved a DSC of 0.824. Kumar et al [21] proposed convolutional neural network approaches for breast ultrasound lesion segmentation and their algorithms effectively segmented the breast masses, achieving a mean DSC of 0.82.…”

Section: Fig 1 a Malignant Lesion In Breast Ultrasoundmentioning

confidence: 99%

Lesion Segmentation in Ultrasound Using Semi-Pixel-Wise Cycle Generative Adversarial Nets

Xing

Wang

et al. 2021

IEEE/ACM Trans. Comput. Biol. and Bioinf.

View full text Add to dashboard Cite

Breast cancer is the most common invasive cancer with the highest cancer occurrence in females. Handheld ultrasound is one of the most efficient ways to identify and diagnose the breast cancer. The area and the shape information of a lesion is very helpful for clinicians to make diagnostic decisions. In this study we propose a new deep-learning scheme, semi-pixel-wise cycle generative adversarial net (SPCGAN) for segmenting the lesion in 2D ultrasound. The method takes the advantage of a fully convolutional neural network (FCN) and a generative adversarial net to segment a lesion by using prior knowledge. We compared the proposed method to a fully connected neural network and the level set segmentation method on a test dataset consisting of 32 malignant lesions and 109 benign lesions. Our proposed method achieved a Dice similarity coefficient (DSC) of 0.92 while FCN and the level set achieved 0.90 and 0.79 respectively. Particularly, for malignant lesions, our method increases the DSC (0.90) of the fully connected neural network to 0.93 significantly (p <0.001). The results show that our SPCGAN can obtain robust segmentation results. The framework of SPCGAN is particularly effective when sufficient training samples are not available compared to FCN. Our proposed method may be used to relieve the radiologists' burden for annotation.

show abstract

“…This model achieved a similar sensitivity, positive predictive value, negative predictive value, and accuracy for the diagnosis of malignant thyroid tumors with higher specificity compared to those corresponding to experienced radiologists ( 12 , 13 ). For the detection of breast cancer, Kumar et al reported a real-time segmentation model of breast tumors using a CNN ( 14 ). This system can reportedly segment tumor images in real-time, suggesting its potential for clinical applications.…”

Section: History and Recent Progress Of Ai In Medical Imagingmentioning

confidence: 99%

Artificial Intelligence in Medical Imaging and Its Application in Sonography for the Management of Liver Tumor

Nishida

Kudo

2020

Front. Oncol.

View full text Add to dashboard Cite

Recent advancement in artificial intelligence (AI) facilitate the development of AI-powered medical imaging including ultrasonography (US). However, overlooking or misdiagnosis of malignant lesions may result in serious consequences; the introduction of AI to the imaging modalities may be an ideal solution to prevent human error. For the development of AI for medical imaging, it is necessary to understand the characteristics of modalities on the context of task setting, required data sets, suitable AI algorism, and expected performance with clinical impact. Regarding the AI-aided US diagnosis, several attempts have been made to construct an image database and develop an AI-aided diagnosis system in the field of oncology. Regarding the diagnosis of liver tumors using US images, 4- or 5-class classifications, including the discrimination of hepatocellular carcinoma (HCC), metastatic tumors, hemangiomas, liver cysts, and focal nodular hyperplasia, have been reported using AI. Combination of radiomic approach with AI is also becoming a powerful tool for predicting the outcome in patients with HCC after treatment, indicating the potential of AI for applying personalized medical care. However, US images show high heterogeneity because of differences in conditions during the examination, and a variety of imaging parameters may affect the quality of images; such conditions may hamper the development of US-based AI. In this review, we summarized the development of AI in medical images with challenges to task setting, data curation, and focus on the application of AI for the managements of liver tumor, especially for US diagnosis.

show abstract

Automated and real-time segmentation of suspicious breast masses using convolutional neural network

Cited by 92 publications

References 27 publications

A fully automated deep learning pipeline for high-throughput colony segmentation and classification

A fully automated deep learning pipeline for high-throughput colony segmentation and classification

Lesion Segmentation in Ultrasound Using Semi-Pixel-Wise Cycle Generative Adversarial Nets

Artificial Intelligence in Medical Imaging and Its Application in Sonography for the Management of Liver Tumor

Contact Info

Product

Resources

About