Comparative assessment of CNN architectures for classification of breast FNAC images

Saikia, Amartya Ranjan; Bora, Kangkana; Mahanta, Lipi B.; Das, Anup

doi:10.1016/j.tice.2019.02.001

Cited by 62 publications

(30 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several prior studies evaluated DL architecture differences for medical images, including radiologic US examinations of the thyroid and breast. Researchers from India compared the training and performance of 4 different DL network architectures (VGG‐16, VGG‐19, ResNet‐50, and Inception‐v3) on approximately 2000 cases for analysis of pathologic breast images . The researchers found a wide range of accuracy between the CNNs: from 63% to 96%.…”

Section: Discussionmentioning

confidence: 99%

Are All Deep Learning Architectures Alike for Point‐of‐Care Ultrasound?: Evidence From a Cardiac Image Classification Model Suggests Otherwise

Blaivas

2019

J of Ultrasound Medicine

View full text Add to dashboard Cite

Objectives-Little is known about optimal deep learning (DL) approaches for point-of-care ultrasound (POCUS) applications. We compared 6 popular DL architectures for POCUS cardiac image classification to determine whether an optimal DL architecture exists for future DL algorithm development in POCUS.Methods-We trained 6 convolutional neural networks (CNNs) with a range of complexities and ages (AlexNet, VGG-16, VGG-19, ResNet50, Den-seNet201, and Inception-v4). Each CNN was trained by using images of 5 typical POCUS cardiac views. Images were extracted from 225 publicly available deidentified POCUS cardiac videos. A total of 750,018 individual images were extracted, with 90% used for model training and 10% for cross-validation. The training time and accuracy achieved were tracked. A real-world test of the algorithms was performed on a set of 125 completely new cardiac images. Descriptive statistics, Pearson R values, and κ values were calculated for each CNN.Results-Accuracy ranged from 96% to 85.6% correct for the 6 CNNs. VGG-16, one of the oldest and simplest CNNs, performed best at 96% correct with 232 minutes to train (R = 0.97; κ = 0.95; P < .00001). The worst-performing CNN was the newer DenseNet201, with 85.6% accuracy and 429 minutes to train (R = 0.92; κ = 0.82; P < .00001).Conclusions-Six common image classification DL algorithms showed considerable variability in their accuracy and training time when trained and tested on identical data, suggesting that not all will perform optimally for POCUS DL applications. Contrary to well-established accuracies for CNNs, more modern and deeper algorithms yielded poorer results.

show abstract

Section: Discussionmentioning

confidence: 99%

Are All Deep Learning Architectures Alike for Point‐of‐Care Ultrasound?: Evidence From a Cardiac Image Classification Model Suggests Otherwise

Blaivas

2019

J of Ultrasound Medicine

View full text Add to dashboard Cite

show abstract

“…Through previous literature and preliminary experiments, the VGG16 model demonstrated a balance in framework, accuracy, computational efficiency and proven performance in the medical field, and was chosen for our experiments (19)(20)(21). The model comprises 16 layers, including 13 convolutional layers with 3x3 convolution kernels and 3 fully connected layers.…”

Section: Methodsmentioning

confidence: 99%

Artificial classification of cervical squamous lesions in ThinPrep cytologic tests using a deep convolutional neural network

Liu

Wang

et al. 2020

Oncol Lett

View full text Add to dashboard Cite

The diagnosis of squamous cell carcinoma requires the accurate classification of cervical squamous lesions in the ThinPrep cytologic test (TCT). It primarily relies on a pathologist's interpretation under a microscope. Deep convolutional neural networks (DCNN) have played an increasingly important role in digital pathology. However, they have not been applied to diverse datasets and externally validated. In the present study, a DCNN model based on VGG16 and an ensemble training strategy (ETS) based on 5-fold cross-validation was employed to automatically classify normal and abnormal cervical squamous cells from a multi-center dataset. First, we collected a dataset comprising 82 TCT samples from four hospitals and fine-tuned our model twice on the dataset with and without the ETS. Then, we compared the classifications obtained from the models with those provided by two skilled pathologists to discriminate the performance of the models in terms of classification accuracy and efficiency. Finally, paired sample t-tests were used to validate the consistency between the classification provided by the proposed methods and that of the pathologists. The results showed that ETS slightly, though not significantly, improved the classification accuracy compared with that of the pathologists: P 0 = 0.387>0.05 (DCNN without ETS vs. DCNN with ETS), P 1 = 0.771>0.05 (DCNN with ETS vs. pathologist 1), P 2 = 0.489>0.05 (DCNN with ETS vs. pathologist 2). The DCNN model was almost 6-fold faster than that of the pathologists. The accuracy of our automated scheme was similar to that of the pathologists, but a higher efficiency in the accurate identification of cervical squamous lesions was provided by the scheme. This result allows for wider and more efficient screening and may provide a replacement for pathologists in the future. Future research should address the viability of the practical implementation of such DCNN models in the laboratory setting.

show abstract

“…For instance, [Shallu and Mehra 2018] compares VGG-16 and VGG-19 against ResNet50 with and without transfer learning, showing that VGGs are more efficient than the ResNet. In [Saikia et al 2019], a study on the performance of VGG16, VGG19, ResNet-50, and GoogLeNet-V3 is carried out in fine-needle aspiration cytology images, in which GoogLeNet-V3 reached the best results after a fine-tuning. Further, a novel attention-based deep learning model using VGG-16 is proposed by [Sitaula and Hossain 2020] to improve COVID-19 classification using x-ray images getting the best results.…”

Section: Related Workmentioning

confidence: 99%

Efficient Breast Cancer Classification Using Histopathological Images and a Simpler VGG

Filho

Cortes

2021

Anais Do XV Brazilian E-Science Workshop (BRESCI 2021)

View full text Add to dashboard Cite

Breast cancer is the second most deadly disease worldwide. This severe condition led 627,000 people to die in 2018. Thus, early detection is critical for improving the patients' lifetime or even cure them. In this context, we can appeal to Medicine 4.0 that exploits the machine learning capabilities to obtain a faster and more efficient diagnosis. Therefore, this work aims to apply a simpler convolutional neural network, called VGG-7, for classifying breast cancer in histopathological images. Results have shown that VGG-7 overcomes the performance of VGG-16 and VGG-19, showing an accuracy of 98%, a precision of 99%, a recall of 98%, and an F1 score of 98%.

show abstract

Comparative assessment of CNN architectures for classification of breast FNAC images

Cited by 62 publications

References 15 publications

Are All Deep Learning Architectures Alike for Point‐of‐Care Ultrasound?: Evidence From a Cardiac Image Classification Model Suggests Otherwise

Are All Deep Learning Architectures Alike for Point‐of‐Care Ultrasound?: Evidence From a Cardiac Image Classification Model Suggests Otherwise

Artificial classification of cervical squamous lesions in ThinPrep cytologic tests using a deep convolutional neural network

Efficient Breast Cancer Classification Using Histopathological Images and a Simpler VGG

Contact Info

Product

Resources

About