IEEE Transactions on Pattern Analysis and Machine Intelligence

In this paper, we first describe the basics of the field of cancer diagnosis, which includes steps of cancer diagnosis followed by the typical classification methods used by doctors, providing a historical idea of cancer classification techniques to the readers. These methods include Asymmetry, Border, Color and Diameter (ABCD) method, seven-point detection method, Menzies method, and pattern analysis. They are used regularly by doctors for cancer diagnosis, although they are not considered very efficient for obtaining better performance. Moreover, considering all types of audience, the basic evaluation criteria are also discussed. The criteria include the receiver operating characteristic curve (ROC curve), Area under the ROC curve (AUC), F1 score, accuracy, specificity, sensitivity, precision, dice-coefficient, average accuracy, and Jaccard index. Previously used methods are considered inefficient, asking for better and smarter methods for cancer diagnosis. Artificial intelligence and cancer diagnosis are gaining attention as a way to define better diagnostic tools. In particular, deep neural networks can be successfully used for intelligent image analysis. The basic framework of how this machine learning works on medical imaging is provided in this study, i.e., pre-processing, image segmentation and post-processing. The second part of this manuscript describes the different deep learning techniques, such as convolutional neural networks (CNNs), generative adversarial models (GANs), deep autoencoders (DANs), restricted Boltzmann’s machine (RBM), stacked autoencoders (SAE), convolutional autoencoders (CAE), recurrent neural networks (RNNs), long short-term memory (LTSM), multi-scale convolutional neural network (M-CNN), multi-instance learning convolutional neural network (MIL-CNN). For each technique, we provide Python codes, to allow interested readers to experiment with the cited algorithms on their own diagnostic problems. The third part of this manuscript compiles the successfully applied deep learning models for different types of cancers. Considering the length of the manuscript, we restrict ourselves to the discussion of breast cancer, lung cancer, brain cancer, and skin cancer. The purpose of this bibliographic review is to provide researchers opting to work in implementing deep learning and artificial neural networks for cancer diagnosis a knowledge from scratch of the state-of-the-art achievements.

https://www.mdpi.com/2072-6694/11/9/1235/pdf

Cancer Diagnosis Using Deep Learning: A Bibliographic Review.

Skin cancer is one of most deadly diseases in humans. According to the high similarity between melanoma and nevus lesions, physicians take much more time to investigate these lesions. The automated classification of skin lesions will save effort, time and human life. The purpose of this paper is to present an automatic skin lesions classification system with higher classification rate using the theory of transfer learning and the pre-trained deep neural network. The transfer learning has been applied to the Alex-net in different ways, including fine-tuning the weights of the architecture, replacing the classification layer with a softmax layer that works with two or three kinds of skin lesions, and augmenting dataset by fixed and random rotation angles. The new softmax layer has the ability to classify the segmented color image lesions into melanoma and nevus or into melanoma, seborrheic keratosis, and nevus. The three well-known datasets, MED-NODE, Derm (IS & Quest) and ISIC, are used in testing and verifying the proposed method. The proposed DCNN weights have been fine-tuned using the training and testing dataset from ISIC in addition to 10-fold cross validation for MED-NODE and DermIS—DermQuest. The accuracy, sensitivity, specificity, and precision measures are used to evaluate the performance of the proposed method and the existing methods. For the datasets, MED-NODE, Derm (IS & Quest) and ISIC, the proposed method has achieved accuracy percentages of 96.86%, 97.70%, and 95.91% respectively. The performance of the proposed method has outperformed the performance of the existing classification methods of skin cancer.

/pdf/classification-of-skin-lesions-using-transfer-learning-and-5bzjqitwxi.pdf

Classification of skin lesions using transfer learning and augmentation with Alex-net

Artificial intelligence-based image classification methods for diagnosis of skin cancer: Challenges and opportunities.

This is the first part of a large survey paper in which we analyze recent literature on Formal Concept Analysis (FCA) and some closely related disciplines using FCA. We collected 1072 papers published between 2003 and 2011 mentioning terms related to Formal Concept Analysis in the title, abstract and keywords. We developed a knowledge browsing environment to support our literature analysis process. We use the visualization capabilities of FCA to explore the literature, to discover and conceptually represent the main research topics in the FCA community. In this first part, we zoom in on and give an extensive overview of the papers published between 2003 and 2011 on developing FCA-based methods for knowledge processing. We also give an overview of the literature on FCA extensions such as pattern structures, logical concept analysis, relational concept analysis, power context families, fuzzy FCA, rough FCA, temporal and triadic concept analysis and discuss scalability issues.

https://publications.hse.ru/mirror/pubs/share/folder/hgte0pjz18/direct/114480023.pdf

Review: Formal Concept Analysis in knowledge processing: A survey on models and techniques

Deep CNN techniques have dramatically become the state of the art in image classification. However, applying high-capacity Deep CNN in medical image analysis has been impeded because of scarcity of labeled data. This study has two primary contributions: first, we propose a classification model to improve performance of classification of skin lesion using Deep CNN and Data Augmentation. Second, we demonstrate the use of image data augmentation for overcoming the problem of data limitation and examine the influence of different number of augmented samples on the performance of different classifiers. The proposed classification system is evaluated using the largest public skin lesion testing dataset, containing 600 testing images, and 6,162 training images. New state-of-the-art performance result is archived with AUC (89.2% vs. 87.4%), AP (73.9% vs. 71.5%), and ACC (89.0% vs. 87.2%). In additional, we explore the influence of each image augmentation on the three classifiers and observe that performance of each classifier is influenced differently by each augmentation and has better results comparing with traditional methods. Thus, it is suggested that the performance of skin cancer classification and medial image classification could be improved further by applying data augmentation.

Deep CNN and Data Augmentation for Skin Lesion Classification

Digital collections are increasingly used for a variety of purposes. In Europe only, we can conservatively estimate that tens of thousands of users consult digital libraries daily. The usages are often motivated by qualitative and quantitative research. However, caution must be advised as most digitized documents are indexed through their OCRed version, which is far from perfect, especially for ancient documents. In this paper, we aim to estimate the impact of OCR errors on the use of a major online platform: The Gallica digital library from the National Library of France. It accounts for more than 100M OCRed documents and receives 80M search queries every year. In this context, we introduce two main contributions. First, an original corpus of OCRed documents composed of 12M characters along with the corresponding gold standard is presented and provided, with an equal share of English- and French-written documents. Next, statistics on OCR errors have been computed thanks to a novel alignment method introduced in this paper. Making use of all the user queries submitted to the Gallica portal over 4 months, we take advantage of our error model to propose an indicator for predicting the relative risk that queried terms mismatch targeted resources due to OCR errors, underlining the critical extent to which OCR quality impacts on digital library access.

https://hal.archives-ouvertes.fr/hal-03025508/document

Impact of OCR errors on the use of digital libraries: towards a better access to information

Most digital libraries that provide user-friendly interfaces, enabling quick and intuitive access to their resources, are based on Document Image Analysis and Recognition (DIAR) methods. Such DIAR methods need ground-truthed document images to be evaluated/compared and, in some cases, trained. Especially with the advent of deep learning-based approaches, the required size of annotated document datasets seems to be ever-growing. Manually annotating real documents has many drawbacks, which often leads to small reliably annotated datasets. In order to circumvent those drawbacks and enable the generation of massive ground-truthed data with high variability, we present DocCreator, a multi-platform and open-source software able to create many synthetic image documents with controlled ground truth. DocCreator has been used in various experiments, showing the interest of using such synthetic images to enrich the training stage of DIAR tools.

DocCreator: A New Software for Creating Synthetic Ground-Truthed Document Images

Document image segmentation is crucial to OCR and other digitization processes. In this paper, we present a learning-based approach for text and non-text separation in document images. The training features are extracted at the level of connected components, a mid-level between the slow noise-sensitive pixel level, and the segmentation-dependent zone level. Given all types, shapes and sizes of connected components, we extract a powerful set of features based on size, shape, stroke width and position of each connected component. Adaboosting with Decision trees is used for labeling connected components. Finally, the classification of connected components into text and non-text is corrected based on classification probabilities and size as well as stroke width analysis of the nearest neighbors of a connected component. The performance of our approach has been evaluated on the two standard datasets: UW-III and ICDAR-2009 competition for document layout analysis. Our results demonstrate that the proposed approach achieves competitive performance for segmenting text and non-text in document images of variable content and degradation.

Text and non-text segmentation based on connected component features

Recently, benefiting from the advances of the deep convolution neural networks (CNNs), significant progress has been made in the field of the face verification and face recognition. Specially, the performance of the FaceNet has overpassed the human level performance in terms of the accuracy on the datasets "Labeled Faces in the Wild (LFW)" and "Youtube Faces in the Wild (YTF)". The triplet loss used in the FaceNet has proved its effectiveness for face verification. However, the number of the possible triplets is explosive when using a large scale dataset to train the model. In this paper, we propose a simple class-wise triplet loss based on the intra/inter-class distance metric learning which can largely reduce the number of the possible triplets to be learned. However the simplification of the classic triplet loss function has not degraded the performance of the proposed approach. The experimental evaluations on the most widely used benchmarks LFW and YTF show that the model with the proposed class-wise simple triplet loss can reach the state-of-the-art performance. And the visualization of the distribution of the learned features based on the MNIST dataset has also shown the effectiveness of the proposed method to better separate the classes and make the features more discriminative in comparison with the other state-of-the-art loss function.

Muriel Visani

Papers

Deep CNN and Data Augmentation for Skin Lesion Classification

Impact of OCR errors on the use of digital libraries: towards a better access to information

DocCreator: A New Software for Creating Synthetic Ground-Truthed Document Images

Text and non-text segmentation based on connected component features

Simple Triplet Loss Based on Intra/Inter-Class Metric Learning for Face Verification