International Journal of Advanced Research in Computer and Communication Engineering, 2024
: Skin cancer is a growing public health concern; while some types of skin cancer are deadly, suc... more : Skin cancer is a growing public health concern; while some types of skin cancer are deadly, such as Melanoma, early detection is crucial for effective treatment and improving patient survival rates [1,2,3,4]. In fact, Malignant melanoma accounts for only 2.3% of all skin cancers yet is responsible for more than 75% of skin cancer-related deaths. However, if it is detected at an early stage, it is highly curable; the 10-year survival rate is between 90% and 97% when the tumour thickness is less than 1 mm. Also, the treatment for an early detected cancerous mole is as simple as excision of the lesion, which can prevent metastasis and spread of cancer to other organs. In this research study, we introduce an approach for skin cancer classification using a state-of-the-art deep learning architecture that has demonstrated exceptional performance in diverse image analysis tasks. We have used two publicly available benchmark data sets for training and validating our results: HAM10000 and ISIC2018 datasets. These datasets consist of dermoscopic images captured using Dermatoscopes and carefully annotated by expert dermatologists. Preprocessing techniques, such as normalization and augmentation, are applied to enhance the robustness and generalization of the model. The proposed approach demonstrated the efficacy of extracting relevant features for accurate classification by leveraging Deep Object Detection models to identify the location of the Lesion, then using the Segment Anything Model (SAM) and MedSAM for extracting the border of the lesions, then finally using various pre-trained states-of-the-art Deep Convolution Networks for Classification. Comprehensive experiments and evaluations are performed in this research; the results demonstrate the effectiveness of using Zero-Shot Segmentation methods over traditional deep learning architectures in skin cancer classification.
World Journal of Advanced Research and Reviews, 2024
Brain tumors pose a significant health challenge by putting pressure on healthy parts of the brai... more Brain tumors pose a significant health challenge by putting pressure on healthy parts of the brain or spreading into other areas and blocking the flow of fluid around the brain. Thus, identifying and categorizing the tumor is crucial for delivering effective treatment, especially if detected early. This means the tumor is smaller, and treatment is more effective, less invasive, and has fewer side effects. In recent years, many researchers have developed computer vision, and more specifically, deep learning methods, to automate the analysis of brain MRI scans. These methods enable efficient processing and improve the accuracy of detecting small tumors. This paper aims to propose a deep-learning method for classifying brain tumors. In this work, the input image goes through two subprocesses: first, object detection to identify the tumor's location. Then, a fine-tuned Segment Anything Model (SAM) was applied to extract the lesion from the background. Finally, deep learning Convolution Neural Network (CNN), is applied to the cropped image for classification. This method will help doctors and researchers detect tumors at the initial stages
Advanced techniques in machine learning combined with scalable "cloud" computing infrastructure a... more Advanced techniques in machine learning combined with scalable "cloud" computing infrastructure are driving the creation of new and innovative health diagnostic applications. We describe a service and application for performing image training and recognition, tailored to dermatology and melanoma identification. The system implements new machine learning approaches to provide a feedback-driven training loop. This training sequence enhances classification performance by incrementally retraining the classifier model from expert responses. To easily provide this application and associated web service to clinical practices, we also describe a scalable cloud infrastructure, deployable in public cloud infrastructure and private, on-premise systems.
Asymmetry is one of key characteristics for early diagnosis of melanoma according to medical algo... more Asymmetry is one of key characteristics for early diagnosis of melanoma according to medical algorithms such as (ABCD, CASH etc.). Besides shape information, cues such as irregular distribution of colors and structures within the lesion area are assessed by dermatologists to determine lesion asymmetry. Motivated by the clinical practices, we have used Kullback-Leibler divergence of color histogram and Structural Similarity metric as a measures of these irregularities. We have presented performance of several classifiers using these features on publicly available PH2 dataset. The obtained result shows better asymmetry classification than available literature. Besides being a new benchmark, the proposed technique can be used for early diagnosis of melanoma by both clinical experts and other automated diagnosis systems.
This paper presents a robust segmentation method based on multi-scale classification to identify ... more This paper presents a robust segmentation method based on multi-scale classification to identify the lesion boundary in dermoscopic images. Our proposed method leverages a collection of classifiers which are trained at various resolutions to categorize each pixel as "lesion" or…
Detection of dermoscopic patterns, such as typical network and regular globules, is an important ... more Detection of dermoscopic patterns, such as typical network and regular globules, is an important step in the skin lesion analysis. This is one of the steps, required to compute the ABCD-score, commonly used for lesion type classification. In this article, we investigate the possibility of automatically detect dermoscopic patterns using deep convolutional neural networks and other image classification algorithms. For the evaluation, we employ the dataset obtained through collaboration with the International Skin Imaging Collaboration (ISIC), including 211 lesions manually annotated by domain experts, generating over 2000 samples of each class (network and globules). Experimental results demonstrates that we can correctly classify 88% of network examples, and 83% of globules example. The best results are achieved by a convolutional neural network with 8 layers.
This paper proposes an unsupervised skin lesion segmentation method for dermoscopy images by expl... more This paper proposes an unsupervised skin lesion segmentation method for dermoscopy images by exploiting the contextual information of skin image at the superpixel level. In particular, a Laplacian sparse coding is presented to evaluate the probabilities of the skin image pixels to delineate lesion border. Moreover, a new rule-based smoothing strategy is proposed as the lesion segmentation refinement procedure. Finally, a multi-scale superpixel segmentation of the skin image is provided to handle size variation of the lesion in order to improve the accuracy of the detected border. Experiments conducted on two datasets show the superiority of our proposed method over several state-of-the-art skin segmentation methods.
2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)
Accurate skin lesion segmentation is an important yet challenging problem for medical image analy... more Accurate skin lesion segmentation is an important yet challenging problem for medical image analysis. The skin lesion segmentation is subject to variety of challenges such as the significant pattern and colour diversity found within the lesions, presence of various artifacts, etc. In this paper, we present two fully convolutional networks with several side outputs to take advantage of discriminative capability of features learned at intermediate layers with varying resolutions and scales for the lesion segmentation. More specifically, we integrate fine and coarse prediction scores of the side-layers which allows our framework to not only output accurate probability map for the lesion, but also extract fine lesion boundary details such as the fuzzy border, which further improves the lesion segmentation. Quantitative evaluation is performed on the 2016 International Symposium on Biomedical Imaging (ISBI 2016) dataset, which shows our proposed approach compares favorably with state-of-the-art skin segmentation methods.
International Journal of Advanced Research in Computer and Communication Engineering, 2024
: Skin cancer is a growing public health concern; while some types of skin cancer are deadly, suc... more : Skin cancer is a growing public health concern; while some types of skin cancer are deadly, such as Melanoma, early detection is crucial for effective treatment and improving patient survival rates [1,2,3,4]. In fact, Malignant melanoma accounts for only 2.3% of all skin cancers yet is responsible for more than 75% of skin cancer-related deaths. However, if it is detected at an early stage, it is highly curable; the 10-year survival rate is between 90% and 97% when the tumour thickness is less than 1 mm. Also, the treatment for an early detected cancerous mole is as simple as excision of the lesion, which can prevent metastasis and spread of cancer to other organs. In this research study, we introduce an approach for skin cancer classification using a state-of-the-art deep learning architecture that has demonstrated exceptional performance in diverse image analysis tasks. We have used two publicly available benchmark data sets for training and validating our results: HAM10000 and ISIC2018 datasets. These datasets consist of dermoscopic images captured using Dermatoscopes and carefully annotated by expert dermatologists. Preprocessing techniques, such as normalization and augmentation, are applied to enhance the robustness and generalization of the model. The proposed approach demonstrated the efficacy of extracting relevant features for accurate classification by leveraging Deep Object Detection models to identify the location of the Lesion, then using the Segment Anything Model (SAM) and MedSAM for extracting the border of the lesions, then finally using various pre-trained states-of-the-art Deep Convolution Networks for Classification. Comprehensive experiments and evaluations are performed in this research; the results demonstrate the effectiveness of using Zero-Shot Segmentation methods over traditional deep learning architectures in skin cancer classification.
World Journal of Advanced Research and Reviews, 2024
Brain tumors pose a significant health challenge by putting pressure on healthy parts of the brai... more Brain tumors pose a significant health challenge by putting pressure on healthy parts of the brain or spreading into other areas and blocking the flow of fluid around the brain. Thus, identifying and categorizing the tumor is crucial for delivering effective treatment, especially if detected early. This means the tumor is smaller, and treatment is more effective, less invasive, and has fewer side effects. In recent years, many researchers have developed computer vision, and more specifically, deep learning methods, to automate the analysis of brain MRI scans. These methods enable efficient processing and improve the accuracy of detecting small tumors. This paper aims to propose a deep-learning method for classifying brain tumors. In this work, the input image goes through two subprocesses: first, object detection to identify the tumor's location. Then, a fine-tuned Segment Anything Model (SAM) was applied to extract the lesion from the background. Finally, deep learning Convolution Neural Network (CNN), is applied to the cropped image for classification. This method will help doctors and researchers detect tumors at the initial stages
Advanced techniques in machine learning combined with scalable "cloud" computing infrastructure a... more Advanced techniques in machine learning combined with scalable "cloud" computing infrastructure are driving the creation of new and innovative health diagnostic applications. We describe a service and application for performing image training and recognition, tailored to dermatology and melanoma identification. The system implements new machine learning approaches to provide a feedback-driven training loop. This training sequence enhances classification performance by incrementally retraining the classifier model from expert responses. To easily provide this application and associated web service to clinical practices, we also describe a scalable cloud infrastructure, deployable in public cloud infrastructure and private, on-premise systems.
Asymmetry is one of key characteristics for early diagnosis of melanoma according to medical algo... more Asymmetry is one of key characteristics for early diagnosis of melanoma according to medical algorithms such as (ABCD, CASH etc.). Besides shape information, cues such as irregular distribution of colors and structures within the lesion area are assessed by dermatologists to determine lesion asymmetry. Motivated by the clinical practices, we have used Kullback-Leibler divergence of color histogram and Structural Similarity metric as a measures of these irregularities. We have presented performance of several classifiers using these features on publicly available PH2 dataset. The obtained result shows better asymmetry classification than available literature. Besides being a new benchmark, the proposed technique can be used for early diagnosis of melanoma by both clinical experts and other automated diagnosis systems.
This paper presents a robust segmentation method based on multi-scale classification to identify ... more This paper presents a robust segmentation method based on multi-scale classification to identify the lesion boundary in dermoscopic images. Our proposed method leverages a collection of classifiers which are trained at various resolutions to categorize each pixel as "lesion" or…
Detection of dermoscopic patterns, such as typical network and regular globules, is an important ... more Detection of dermoscopic patterns, such as typical network and regular globules, is an important step in the skin lesion analysis. This is one of the steps, required to compute the ABCD-score, commonly used for lesion type classification. In this article, we investigate the possibility of automatically detect dermoscopic patterns using deep convolutional neural networks and other image classification algorithms. For the evaluation, we employ the dataset obtained through collaboration with the International Skin Imaging Collaboration (ISIC), including 211 lesions manually annotated by domain experts, generating over 2000 samples of each class (network and globules). Experimental results demonstrates that we can correctly classify 88% of network examples, and 83% of globules example. The best results are achieved by a convolutional neural network with 8 layers.
This paper proposes an unsupervised skin lesion segmentation method for dermoscopy images by expl... more This paper proposes an unsupervised skin lesion segmentation method for dermoscopy images by exploiting the contextual information of skin image at the superpixel level. In particular, a Laplacian sparse coding is presented to evaluate the probabilities of the skin image pixels to delineate lesion border. Moreover, a new rule-based smoothing strategy is proposed as the lesion segmentation refinement procedure. Finally, a multi-scale superpixel segmentation of the skin image is provided to handle size variation of the lesion in order to improve the accuracy of the detected border. Experiments conducted on two datasets show the superiority of our proposed method over several state-of-the-art skin segmentation methods.
2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)
Accurate skin lesion segmentation is an important yet challenging problem for medical image analy... more Accurate skin lesion segmentation is an important yet challenging problem for medical image analysis. The skin lesion segmentation is subject to variety of challenges such as the significant pattern and colour diversity found within the lesions, presence of various artifacts, etc. In this paper, we present two fully convolutional networks with several side outputs to take advantage of discriminative capability of features learned at intermediate layers with varying resolutions and scales for the lesion segmentation. More specifically, we integrate fine and coarse prediction scores of the side-layers which allows our framework to not only output accurate probability map for the lesion, but also extract fine lesion boundary details such as the fuzzy border, which further improves the lesion segmentation. Quantitative evaluation is performed on the 2016 International Symposium on Biomedical Imaging (ISBI 2016) dataset, which shows our proposed approach compares favorably with state-of-the-art skin segmentation methods.
Uploads
Papers by Mani Abedini
early detection is crucial for effective treatment and improving patient survival rates [1,2,3,4]. In fact, Malignant
melanoma accounts for only 2.3% of all skin cancers yet is responsible for more than 75% of skin cancer-related deaths.
However, if it is detected at an early stage, it is highly curable; the 10-year survival rate is between 90% and 97% when
the tumour thickness is less than 1 mm. Also, the treatment for an early detected cancerous mole is as simple as excision
of the lesion, which can prevent metastasis and spread of cancer to other organs. In this research study, we introduce an
approach for skin cancer classification using a state-of-the-art deep learning architecture that has demonstrated
exceptional performance in diverse image analysis tasks. We have used two publicly available benchmark data sets for
training and validating our results: HAM10000 and ISIC2018 datasets. These datasets consist of dermoscopic images
captured using Dermatoscopes and carefully annotated by expert dermatologists. Preprocessing techniques, such as
normalization and augmentation, are applied to enhance the robustness and generalization of the model. The proposed
approach demonstrated the efficacy of extracting relevant features for accurate classification by leveraging Deep Object
Detection models to identify the location of the Lesion, then using the Segment Anything Model (SAM) and MedSAM
for extracting the border of the lesions, then finally using various pre-trained states-of-the-art Deep Convolution
Networks for Classification. Comprehensive experiments and evaluations are performed in this research; the results
demonstrate the effectiveness of using Zero-Shot Segmentation methods over traditional deep learning architectures in
skin cancer classification.
early detection is crucial for effective treatment and improving patient survival rates [1,2,3,4]. In fact, Malignant
melanoma accounts for only 2.3% of all skin cancers yet is responsible for more than 75% of skin cancer-related deaths.
However, if it is detected at an early stage, it is highly curable; the 10-year survival rate is between 90% and 97% when
the tumour thickness is less than 1 mm. Also, the treatment for an early detected cancerous mole is as simple as excision
of the lesion, which can prevent metastasis and spread of cancer to other organs. In this research study, we introduce an
approach for skin cancer classification using a state-of-the-art deep learning architecture that has demonstrated
exceptional performance in diverse image analysis tasks. We have used two publicly available benchmark data sets for
training and validating our results: HAM10000 and ISIC2018 datasets. These datasets consist of dermoscopic images
captured using Dermatoscopes and carefully annotated by expert dermatologists. Preprocessing techniques, such as
normalization and augmentation, are applied to enhance the robustness and generalization of the model. The proposed
approach demonstrated the efficacy of extracting relevant features for accurate classification by leveraging Deep Object
Detection models to identify the location of the Lesion, then using the Segment Anything Model (SAM) and MedSAM
for extracting the border of the lesions, then finally using various pre-trained states-of-the-art Deep Convolution
Networks for Classification. Comprehensive experiments and evaluations are performed in this research; the results
demonstrate the effectiveness of using Zero-Shot Segmentation methods over traditional deep learning architectures in
skin cancer classification.