Optimization of CNN Model With Hyper Parameter Tuning for Enhancing Sturdiness in Classification of Histopathological Images

Johny, Anil; Nallikuzhy, Tom J

doi:10.2139/ssrn.3735831

Cited by 6 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In task-specific applications, there barely exists a definite method to find the number of layers or amount of neurons required in each layer for training the model. The selection of few parameters is based on our previous work in [ 49 ], and we found that the training to test the ratio of the dataset is fixed to 80 : 20 for a batch size of 32 with 500 epochs throughout the experiment. Initialization of the network weights is done using the Gaussian distribution with a low standard deviation for all the layers.…”

Section: Methodsmentioning

confidence: 99%

“…Here, the training starts with a high learning rate, and towards the end of training epochs, LR decays monotonically till the last epoch in both methods. Towards the end of training, for small learning rates, the gradient enters local minima and never escapes [ 49 ]. Table 4 shows the obtained values of performance metrics corresponding to the conventional learning strategies mentioned in Section 1 .…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Learning Rate in Deep CNN Model for Metastasis Detection and Classification of Histopathology Images

Johny

2021

Computational and Mathematical Methods in Medicine

Self Cite

View full text Add to dashboard Cite

Diagnosis of different breast cancer stages using histopathology whole slide images (WSI) is the gold standard in determining the grade of tissue metastasis. Computer-aided diagnosis (CAD) assists medical experts as a second opinion tool in early detection to prevent further proliferation. The field of pathology has advanced so rapidly that it is possible to obtain high-quality images from glass slides. Patches from the region of interest in histopathology images are extracted and trained using artificial neural network models. The trained model primarily analyzes and predicts the histology images for the benign or malignant class to which it belongs. Classification of medical images focuses on the training of models with layers of abstraction to distinguish between these two classes with less false-positive rates. The learning rate is the crucial hyperparameter used during the training of deep convolutional neural networks (DCNN) to improve model accuracy. This work emphasizes the relevance of the dynamic learning rate than the fixed learning rate during the training of networks. The dynamic learning rate varies with preset conditions between the lower and upper boundaries and repeats at different iterations. The performance of the model thus improves and attains comparatively high accuracy with fewer iterations.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Dynamic Learning Rate in Deep CNN Model for Metastasis Detection and Classification of Histopathology Images

Johny

2021

Computational and Mathematical Methods in Medicine

Self Cite

View full text Add to dashboard Cite

show abstract

“…histopathology [62] and with biomedical imaging [63]. SIENNA demonstrates on average accuracy on clinical DICOM MRI data across 3 tasks of 92% (Non-Tumor, SD=5.5%), 91% (GBM, SD = 3.2%), and 93% (MET, SD = 2.6%), with the distribution of accuracies skewed higher to 100% and a lower bound at 75%.…”

Section: Introductionmentioning

confidence: 99%

“…SIENNA’s ability to identify meaningful patterns and attributes is further enriched by adversarial training, [57,58] using images with subtle parameter distortion to exploit the model’s vulnerabilities and decision boundaries for re-optimization. Finally, we apply hyperparameter tuning [59,60] to SIENNA for robustness in diagnostic output, as has been demonstrated for CNN analysis applied in genetics [59], vision [61], histopathology [62] and with biomedical imaging [63]. SIENNA demonstrates on average accuracy on clinical DICOM MRI data across 3 tasks of 92% (Non-Tumor, SD=5.5%), 91% (GBM, SD = 3.2%), and 93% (MET, SD = 2.6%), with the distribution of accuracies skewed higher to 100% and a lower bound at 75%.…”

Section: Introductionmentioning

confidence: 99%

SIENNA: Generalizable Lightweight Machine Learning Platform for Brain Tumor Diagnostics

Sunil,

Rajeev,

Chatterjee

et al. 2024

Preprint

View full text Add to dashboard Cite

The transformative integration of Machine Learning (ML) for Artificial General Intelligence (AGI)-enhanced clinical imaging diagnostics, is itself in development. In brain tumor pathologies, magnetic resonance imaging (MRI) is a critical step that impacts the decision for invasive surgery, yet expert MRI tumor typing is inconsistent and misdiagnosis can reach levels as high as 85%. Current state-of-the-art (SOTA) ML brain tumor models struggle with data overfitting and susceptibility to shortcut learning, further exacerbated in large-sized models with many tunable parameters. In a comparison with multiple SOTA models, our deep ML brain tumor diagnostics model, SIENNA, surpassed limitations in four key areas of prioritized minimal data preprocessing, an optimized architecture that reduces shortcut learning and overfitting, integrated inductive cross-validation method for generalizability, and smaller neural architecture. SIENNA is applicable across MRI machines and 1.5 and 3.0 Tesla, and achieves high average accuracies on clinical DICOM MRI data across three-way classification: 92% (non-tumor), 91% (GBM), and 93% (MET) with retained high F1 and AUROC values for limited false positives/negatives. SIENNA is a lightweight clinical-ready AGI framework compatible with future multimodal expanded data integration.

show abstract

“…In most studies conducted in the field of classification systems for histopathological images of colorectal cancer [7,8], the use of deep-learning systems usually involves the use of standard parameters without a detailed analysis of the influence of the parameters, hyperparameters, and preprocessing stages of histopathological images on the behavior of the system. In this paper, we present a novel and comprehensive study on the influence on the classification performance of a classification system (Deep Learning-VGG19) for classifying histopathological images of colorectal cancer and show how an appropriate choice of these parameters can have an important impact on the accuracy of the classifier.…”

Section: Introductionmentioning

confidence: 99%

Computer Aided Classifier of Colorectal Cancer on Histopatological Whole Slide Images Analyzing Deep Learning Architecture Parameters

et al. 2023

View full text Add to dashboard Cite

The diagnosis of different pathologies and stages of cancer using whole histopathology slide images (WSI) is the gold standard for determining the degree of tissue metastasis. The use of deep learning systems in the field of medical images, especially histopathology images, is becoming increasingly important. The training and optimization of deep neural network models involve fine-tuning parameters and hyperparameters such as learning rate, batch size (BS), and boost to improve the performance of the model in task-specific applications. Tuning hyperparameters is a major challenge in designing deep neural network models, having a large impact on the performance. This paper analyzes how the parameters and hyperparameters of a deep learning architecture affect the classification of colorectal cancer (CRC) histopathology images using the well-known VGG19 model. This paper also discusses the pre-processing of these images, such as the use of color normalization and stretching transformations on the data set. Among these hyperparameters, the most important neural network hyperparameter is the learning rate (LR). In this paper, different strategies for the optimization of LR are analyzed (both static and dynamic) and a new experiment based on the variation of LR is proposed (the relevance of dynamic strategies over fixed LR is highlighted), after each layer of the neural network together with decreasing variations according to the epochs. The results obtained are very remarkable, obtaining in the simulation an accurate system that achieves 96.4% accuracy on test images (for nine different tissue classes) using the triangular-cyclic learning rate.

show abstract

Optimization of CNN Model With Hyper Parameter Tuning for Enhancing Sturdiness in Classification of Histopathological Images

Cited by 6 publications

References 0 publications

Dynamic Learning Rate in Deep CNN Model for Metastasis Detection and Classification of Histopathology Images

Dynamic Learning Rate in Deep CNN Model for Metastasis Detection and Classification of Histopathology Images

SIENNA: Generalizable Lightweight Machine Learning Platform for Brain Tumor Diagnostics

Computer Aided Classifier of Colorectal Cancer on Histopatological Whole Slide Images Analyzing Deep Learning Architecture Parameters

Contact Info

Product

Resources

About