Comparing the performance of various filters on stoned kidney images

Mondal, Paramita; Khatun, Mst. Maklina; Akter, Umme Hadia

doi:10.9790/0661-1804057378

Cited by 1 publication

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Noise removal techniques can aid to identify details and characteristics of images that are not obvious. This is an important task in biomedical image analysis as the medical images require reliable techniques to get accurate results [ 34 ]. The performance of neural networks heavily depends on edge information and noise filtering techniques [ 35 ].…”

Section: Proposed Methodologymentioning

confidence: 99%

A shallow deep learning approach to classify skin cancer using down-scaling method to minimize time and space complexity

et al. 2022

View full text Add to dashboard Cite

The complex feature characteristics and low contrast of cancer lesions, a high degree of inter-class resemblance between malignant and benign lesions, and the presence of various artifacts including hairs make automated melanoma recognition in dermoscopy images quite challenging. To date, various computer-aided solutions have been proposed to identify and classify skin cancer. In this paper, a deep learning model with a shallow architecture is proposed to classify the lesions into benign and malignant. To achieve effective training while limiting overfitting problems due to limited training data, image preprocessing and data augmentation processes are introduced. After this, the ‘box blur’ down-scaling method is employed, which adds efficiency to our study by reducing the overall training time and space complexity significantly. Our proposed shallow convolutional neural network (SCNN_12) model is trained and evaluated on the Kaggle skin cancer data ISIC archive which was augmented to 16485 images by implementing different augmentation techniques. The model was able to achieve an accuracy of 98.87% with optimizer Adam and a learning rate of 0.001. In this regard, parameter and hyper-parameters of the model are determined by performing ablation studies. To assert no occurrence of overfitting, experiments are carried out exploring k-fold cross-validation and different dataset split ratios. Furthermore, to affirm the robustness the model is evaluated on noisy data to examine the performance when the image quality gets corrupted.This research corroborates that effective training for medical image analysis, addressing training time and space complexity, is possible even with a lightweighted network using a limited amount of training data.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%