Region Extraction and Classification of Skin Cancer: A Heterogeneous framework of Deep CNN Features Fusion and Reduction

Saba, Tanzila; Khan, Muhammad Attique; Rehman, Amjad; Marie-Sainte, Souad Larabi

doi:10.1007/s10916-019-1413-3

Cited by 193 publications

(107 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Our work was assessed on three well-established publicly available datasets PH2, ISBI 2017 Skin Lesion Challenge (SLC) and ISIC 2019 (SLC). We evaluated our proposed segmentation method against segmentation frameworks based on deep convolutional neural network (DCNN) [ 57 ], approaches with U-nets followed by histogram equalization and C-means clustering [ 58 ], segmentation done by crowdsourcing from ISIC 2017 challenge results [ 59 ], simultaneous segmentation and classification using bootstrapping deep convolutional neural network model [ 60 ], segmentation using contrast stretching and mean deviation [ 61 ] and semantic segmentation method for automatic segmentation [ 62 ]. In addition, we also drew inspiration from few of the most successful lesion segmentation methods introduced in the recent years like segmentation by means of FCN networks, multi stage fully convolution network (FCN) with parallel integration (mFCN-PI) [ 63 , 64 ], FrCN method involving simultaneous segmentation and classification, a fully-convolutional residual networks (FCRN), which was an amendment and extension of FCN architecture [ 65 , 66 , 67 ], a deep fully convolutional-deconvolutional neural network (CDNN) performing automatic segmentation [ 68 ] and lastly with the semi automatic Grab cut algorithm [ 69 ].…”

Section: Discussionmentioning

confidence: 99%

Melanoma Diagnosis Using Deep Learning and Fuzzy Logic

Banerjee¹,

Singh²,

Chakraborty³

et al. 2020

Diagnostics

View full text Add to dashboard Cite

Melanoma or malignant melanoma is a type of skin cancer that develops when melanocyte cells, damaged by excessive exposure to harmful UV radiations, start to grow out of control. Though less common than some other kinds of skin cancers, it is more dangerous because it rapidly metastasizes if not diagnosed and treated at an early stage. The distinction between benign and melanocytic lesions could at times be perplexing, but the manifestations of the disease could fairly be distinguished by a skilled study of its histopathological and clinical features. In recent years, deep convolutional neural networks (DCNNs) have succeeded in achieving more encouraging results yet faster and computationally effective systems for detection of the fatal disease are the need of the hour. This paper presents a deep learning-based ‘You Only Look Once (YOLO)’ algorithm, which is based on the application of DCNNs to detect melanoma from dermoscopic and digital images and offer faster and more precise output as compared to conventional CNNs. In terms with the location of the identified object in the cell, this network predicts the bounding box of the detected object and the class confidence score. The highlight of the paper, however, lies in its infusion of certain resourceful concepts like two phase segmentation done by a combination of the graph theory using minimal spanning tree concept and L-type fuzzy number based approximations and mathematical extraction of the actual affected area of the lesion region during feature extraction process. Experimented on a total of 20250 images from three publicly accessible datasets—PH2, International Symposium on Biomedical Imaging (ISBI) 2017 and The International Skin Imaging Collaboration (ISIC) 2019, encouraging results have been obtained. It achieved a Jac score of 79.84% on ISIC 2019 dataset and 86.99% and 88.64% on ISBI 2017 and PH2 datasets, respectively. Upon comparison of the pre-defined parameters with recent works in this area yielded comparatively superior output in most cases.

show abstract

Section: Discussionmentioning

confidence: 99%

Melanoma Diagnosis Using Deep Learning and Fuzzy Logic

Banerjee¹,

Singh²,

Chakraborty³

et al. 2020

Diagnostics

View full text Add to dashboard Cite

show abstract

“…Horie et al [24] demonstrated the diagnostic capability of deep learning techniques like CNN for esophageal cancer, which included squamous cell carcinoma and adenocarcinoma with a sensitivity of 98%. [25] Saba, Tanzila, et al proposed an automated cascaded design for skin lesion detection, which consisted of three significant steps, namely, contrast stretching and boundary extraction using CNN, and finally extracting depth features using transferred learning. Sekaran, Kaushik, et al [26] proposed a model deployed using a convolutional neural network to isolate infected images from healthy ones.…”

Section: Related Workmentioning

confidence: 99%

Automatic Detection of White Blood Cancer From Bone Marrow Microscopic Images Using Convolutional Neural Networks

et al. 2020

View full text Add to dashboard Cite

Leukocytes, produced in the bone marrow, make up around one percent of all blood cells. Uncontrolled growth of these white blood cells leads to the birth of blood cancer. Out of the three different types of cancers, the proposed study provides a robust mechanism for the classification of Acute Lymphoblastic Leukemia (ALL) and Multiple Myeloma (MM) using the SN-AM dataset. Acute lymphoblastic leukemia (ALL) is a type of cancer where the bone marrow forms too many lymphocytes. On the other hand, Multiple myeloma (MM), a different kind of cancer, causes cancer cells to accumulate in the bone marrow rather than releasing them into the bloodstream. Therefore, they crowd out and prevent the production of healthy blood cells. Conventionally, the process was carried out manually by a skilled professional in a considerable amount of time. The proposed model eradicates the probability of errors in the manual process by employing deep learning techniques, namely convolutional neural networks. The model, trained on cells' images, first pre-processes the images and extracts the best features. This is followed by training the model with the optimized Dense Convolutional neural network framework (termed DCNN here) and finally predicting the type of cancer present in the cells. The model was able to reproduce all the measurements correctly while it recollected the samples exactly 94 times out of 100. The overall accuracy was recorded to be 97.2%, which is better than the conventional machine learning methods like Support Vector Machine (SVMs), Decision Trees, Random Forests, Naive Bayes, etc. This study indicates that the DCNN model's performance is close to that of the established CNN architectures with far fewer parameters and computation time tested on the retrieved dataset. Thus, the model can be used effectively as a tool for determining the type of cancer in the bone marrow.

show abstract

“…The pre-trained model parameters are updated based on the customized (new) dataset. Researches are using TL concept along with fine-tuning of existing CNN models for medical image classification and disease detection 43 , 44 .…”

Section: Related Workmentioning

confidence: 99%

Developing intelligent medical image modality classification system using deep transfer learning and LDA

Hassan

Ali²,

Alquhayz

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Rapid advancement in imaging technology generates an enormous amount of heterogeneous medical data for disease diagnosis and rehabilitation process. Radiologists may require related clinical cases from medical archives for analysis and disease diagnosis. It is challenging to retrieve the associated clinical cases automatically, efficiently and accurately from the substantial medical image archive due to diversity in diseases and imaging modalities. We proposed an efficient and accurate approach for medical image modality classification that can used for retrieval of clinical cases from large medical repositories. The proposed approach is developed using transfer learning concept with pre-trained ResNet50 Deep learning model for optimized features extraction followed by linear discriminant analysis classification (TLRN-LDA). Extensive experiments are performed on challenging standard benchmark ImageCLEF-2012 dataset of 31 classes. The developed approach yields improved average classification accuracy of 87.91%, which is higher up-to 10% compared to the state-of-the-art approaches on the same dataset. Moreover, hand-crafted features are extracted for comparison. Performance of TLRN-LDA system demonstrates the effectiveness over state-of-the-art systems. The developed approach may be deployed to diagnostic centers to assist the practitioners for accurate and efficient clinical case retrieval and disease diagnosis.

show abstract

Region Extraction and Classification of Skin Cancer: A Heterogeneous framework of Deep CNN Features Fusion and Reduction

Cited by 193 publications

References 61 publications

Melanoma Diagnosis Using Deep Learning and Fuzzy Logic

Melanoma Diagnosis Using Deep Learning and Fuzzy Logic

Automatic Detection of White Blood Cancer From Bone Marrow Microscopic Images Using Convolutional Neural Networks

Developing intelligent medical image modality classification system using deep transfer learning and LDA

Contact Info

Product

Resources

About