Linear Regression Analysis

Application of explainable artificial intelligence for healthcare: A systematic review of the last decade (2011-2022)

Influence functions approximate the effect of training samples in test-time predictions and have a wide variety of applications in machine learning interpretability and uncertainty estimation A commonly-used (first-order) influence function can be implemented efficiently as a post-hoc method requiring access only to the gradients and Hessian of the model For linear models, influence functions are well-defined due to the convexity of the underlying loss function and are generally accurate even across difficult settings where model changes are fairly large such as estimating group influences Influence functions, however, are not well-understood in the context of deep learning with non-convex loss functions In this paper, we provide a comprehensive and large-scale empirical study of successes and failures of influence functions in neural network models trained on datasets such as Iris, MNIST, CIFAR-10 and ImageNet Through our extensive experiments, we show that the network architecture, its depth and width, as well as the extent of model parameterization and regularization techniques have strong effects in the accuracy of influence functions In particular, we find that (i) influence estimates are fairly accurate for shallow networks, while for deeper networks the estimates are often erroneous; (ii) for certain network architectures and datasets, training with weight-decay regularization is important to get high-quality influence estimates; and (iii) the accuracy of influence estimates can vary significantly depending on the examined test points These results suggest that in general influence functions in deep learning are fragile and call for developing improved influence estimation methods to mitigate these issues in non-convex setups

Influence Functions in Deep Learning Are Fragile

https://hal.archives-ouvertes.fr/hal-03089370/document

Potentials and caveats of AI in hybrid imaging

One of the most promising research areas in the healthcare industry and the scientific community is focusing on the AI-based applications for real medical challenges such as the building of computer-aided diagnosis (CAD) systems for breast cancer. Transfer learning is one of the recent emerging AI-based techniques that allow rapid learning progress and improve medical imaging diagnosis performance. Although deep learning classification for breast cancer has been widely covered, certain obstacles still remain to investigate the independency among the extracted high-level deep features. This work tackles two challenges that still exist when designing effective CAD systems for breast lesion classification from mammograms. The first challenge is to enrich the input information of the deep learning models by generating pseudo-colored images instead of only using the input original grayscale images. To achieve this goal two different image preprocessing techniques are parallel used: contrast-limited adaptive histogram equalization (CLAHE) and Pixel-wise intensity adjustment. The original image is preserved in the first channel, while the other two channels receive the processed images, respectively. The generated three-channel pseudo-colored images are fed directly into the input layer of the backbone CNNs to generate more powerful high-level deep features. The second challenge is to overcome the multicollinearity problem that occurs among the high correlated deep features generated from deep learning models. A new hybrid processing technique based on Logistic Regression (LR) as well as Principal Components Analysis (PCA) is presented and called LR-PCA. Such a process helps to select the significant principal components (PCs) to further use them for the classification purpose. The proposed CAD system has been examined using two different public benchmark datasets which are INbreast and mini-MAIS. The proposed CAD system could achieve the highest performance accuracies of 98.60% and 98.80% using INbreast and mini-MAIS datasets, respectively. Such a CAD system seems to be useful and reliable for breast cancer diagnosis.

/pdf/a-hybrid-deep-transfer-learning-of-cnn-based-lr-pca-for-3cb56mc3.pdf

A Hybrid Deep Transfer Learning of CNN-Based LR-PCA for Breast Lesion Diagnosis via Medical Breast Mammograms

An overview of deep learning in medical imaging

Breast cancer causes approximately 684,996 deaths worldwide, making it the leading cause of female cancer mortality. However, these figures can be reduced with early diagnosis through mammographic imaging, allowing for the timely and effective treatment of this disease. To establish the best tools for contributing to the automatic diagnosis of breast cancer, different deep learning (DL) architectures were compared in terms of breast lesion segmentation, lesion type classification, and degree of suspicion of malignancy tests. The tasks were completed with state-of-the-art architectures and backbones. Initially, during segmentation, the base UNet, Visual Geometry Group 19 (VGG19), InceptionResNetV2, EfficientNet, MobileNetv2, ResNet, ResNeXt, MultiResUNet, linkNet-VGG19, DenseNet, SEResNet and SeResNeXt architectures were compared, where “Res” denotes a residual network. In addition, training was performed with 5 of the most advanced loss functions and validated by the Dice coefficient, sensitivity, and specificity. The proposed models achieved Dice values above 90%, with the EfficientNet architecture achieving 94.75% and 99% accuracy on the two tasks. Subsequently, classification was addressed with the ResNet50V2, VGG19, InceptionResNetV2, DenseNet121, InceptionV3, Xception and EfficientNetB7 networks. The proposed models achieved 96.97% and 97.73% accuracy through the VGG19 and ResNet50V2 networks on the lesion classification and degree of suspicion tasks, respectively. All three tasks were addressed with open-access databases, including the Digital Database for Screening Mammography (DDSM), the Mammographic Image Analysis Society (MIAS) database, and INbreast.

Comparison of Current Deep Convolutional Neural Networks for the Segmentation of Breast Masses in Mammograms

Resting state functional magnetic resonance imaging (rs-fMRI) is one of the most relevant techniques in brain exploration. However, it is susceptible to many external factors that can occlude the signal of interest. In this order of ideas, rs-fMRI images have been studied adopting different approaches, with a particular interest in artifact removal techniques through Independent Component Analysis (ICA). Such an approach is a powerful tool for blind source separation, where elements associated with noise can be eliminated. Nevertheless, such removal is subject to the identification or classification of the components provided by the ICA. In that sense, this study focuses on finding an alternative strategy to classify the independent components. The problem was addressed in two stages. In the first one, the components (3D volumes) were reduced to images by Principal Component Analysis (PCA) and by obtaining the median planes. The methods achieved a reduction of up to two orders of magnitude in the weight of the data size, and they were shown to preserve the spatial characteristics of the independent components. In the second stage, the reductions were used to train six models of convolutional neural networks. The networks analyzed in this study reached accuracies around 98 % in classification, one of them even up to 98.82 %, which reflects the high discrimination capacity of convolutional neural networks.

/pdf/redes-neuronales-convolucionales-para-la-clasificacion-de-z0wabz1ajh.pdf

Leonel Mera-Jiménez

Papers

An overview of deep learning in medical imaging

Comparison of Current Deep Convolutional Neural Networks for the Segmentation of Breast Masses in Mammograms

Redes neuronales convolucionales para la clasificación de componentes independientes de rs-fMRI