Confidence Aware Neural Networks for Skin Cancer Detection

Deep learning (DL) models have received particular attention in medical imaging due to their promising pattern recognition capabilities. However, Deep Neural Networks (DNNs) require a huge amount of data, and because of the lack of sufficient data in this field, transfer learning can be a great solution. DNNs used for disease diagnosis meticulously concentrate on improving the accuracy of predictions without providing a figure about their confidence of predictions. Knowing how much a DNN model is confident in a computer-aided diagnosis model is necessary for gaining clinicians' confidence and trust in DL-based solutions. To address this issue, this work presents three different methods for quantifying uncertainties for skin cancer detection from images. It also comprehensively evaluates and compares performance of these DNNs using novel uncertainty-related metrics. The obtained results reveal that the predictive uncertainty estimation methods are capable of flagging risky and erroneous predictions with a high uncertainty estimate. We also demonstrate that ensemble approaches are more reliable in capturing uncertainties through inference.

Evaluating Post-hoc Interpretability with Intrinsic Interpretability

Despite Convolutional Neural Networks having reached human-level performance in some medical tasks, their clinical use has been hindered by their lack of interpretability. Two major interpretability strategies have been proposed to tackle this problem: post-hoc methods and intrinsic methods. Although there are several post-hoc methods to interpret DL models, there is significant variation between the explanations provided by each method, and it a difficult to validate them due to the lack of ground-truth. To address this challenge, we adapted the intrinsical interpretable ProtoPNet for the context of histopathology imaging and compared the attribution maps produced by it and the saliency maps made by post-hoc methods. To evaluate the similarity between saliency map methods and attribution maps we adapted 10 saliency metrics from the saliency model literature, and used the breast cancer metastases detection dataset PatchCamelyon with 327,680 patches of histopathological images of sentinel lymph node sections to validate the proposed approach. Overall, SmoothGrad and Occlusion were found to have a statistically bigger overlap with ProtoPNet while Deconvolution and Lime have been found to have the least.

Federated Learning with Research Prototypes for Multi-Center MRI-based Detection of Prostate Cancer with Diverse Histopathology

Early prostate cancer detection and staging from MRI are extremely challenging tasks for both radiologists and deep learning algorithms, but the potential to learn from large and diverse datasets remains a promising avenue to increase their generalization capability both within- and across clinics. To enable this for prototype-stage algorithms, where the majority of existing research remains, in this paper we introduce a flexible federated learning framework for cross-site training, validation, and evaluation of deep prostate cancer detection algorithms. Our approach utilizes an abstracted representation of the model architecture and data, which allows unpolished prototype deep learning models to be trained without modification using the NVFlare federated learning framework. Our results show increases in prostate cancer detection and classification accuracy using a specialized neural network model and diverse prostate biopsy data collected at two University of California research hospitals, demonstrating the efficacy of our approach in adapting to different datasets and improving MR-biomarker discovery. We open-source our FLtools system, which can be easily adapted to other deep learning projects for medical imaging.

Deep Multiple Instance Learning with Distance-Aware Self-Attention

Traditional supervised learning tasks require a label for every instance in the training set, but in many real-world applications, labels are only available for collections (bags) of instances. This problem setting, known as multiple instance learning (MIL), is particularly relevant in the medical domain, where high-resolution images are split into smaller patches, but labels apply to the image as a whole. Recent MIL models are able to capture correspondences between patches by employing self-attention, allowing them to weigh each patch differently based on all other patches in the bag. However, these approaches still do not consider the relative spatial relationships between patches within the larger image, which is especially important in computational pathology. To this end, we introduce a novel MIL model with distance-aware self-attention (DAS-MIL), which explicitly takes into account relative spatial information when modelling the interactions between patches. Unlike existing relative position representations for self-attention which are discrete, our approach introduces continuous distance-dependent terms into the computation of the attention weights, and is the first to apply relative position representations in the context of MIL. We evaluate our model on a custom MNIST-based MIL dataset that requires the consideration of relative spatial information, as well as on CAMELYON16, a publicly available cancer metastasis detection dataset, where we achieve a test AUROC score of 0.91. On both datasets, our model outperforms existing MIL approaches that employ absolute positional encodings, as well as existing relative position representation schemes applied to MIL. Our code is available at https://anonymous.4open.science/r/das-mil.

Artificial Intelligence For Breast Cancer Detection: Trends & Directions

In the last decade, researchers working in the domain of computer vision and Artificial Intelligence (AI) have beefed up their efforts to come up with the automated framework that not only detects but also identifies stage of breast cancer. The reason for this surge in research activities in this direction are mainly due to advent of robust AI algorithms (deep learning), availability of hardware that can train those robust and complex AI algorithms and accessibility of large enough dataset required for training AI algorithms. Different imaging modalities that have been exploited by researchers to automate the task of breast cancer detection are mammograms, ultrasound, magnetic resonance imaging, histopathological images or any combination of them. This article analyzes these imaging modalities and presents their strengths, limitations and enlists resources from where their datasets can be accessed for research purpose. This article then summarizes AI and computer vision based state-of-the-art methods proposed in the last decade, to detect breast cancer using various imaging modalities. Generally, in this article we have focused on to review frameworks that have reported results using mammograms as it is most widely used breast imaging modality that serves as first test that medical practitioners usually prescribe for the detection of breast cancer. Second reason of focusing on mammogram imaging modalities is the availability of its labeled datasets. Datasets availability is one of the most important aspect for the development of AI based frameworks as such algorithms are data hungry and generally quality of dataset affects performance of AI based algorithms. In a nutshell, this research article will act as a primary resource for the research community working in the field of automated breast imaging analysis.

Perfusion imaging in deep prostate cancer detection from mp-MRI: can we take advantage of it?

To our knowledge, all deep computer-aided detection and diagnosis (CAD) systems for prostate cancer (PCa) detection consider bi-parametric magnetic resonance imaging (bp-MRI) only, including T2w and ADC sequences while excluding the 4D perfusion sequence,which is however part of standard clinical protocols for this diagnostic task. In this paper, we question strategies to integrate information from perfusion imaging in deep neural architectures. To do so, we evaluate several ways to encode the perfusion information in a U-Net like architecture, also considering early versus mid fusion strategies. We compare performance of multiparametric MRI (mp-MRI) models with the baseline bp-MRI model based on a private dataset of 219 mp-MRI exams. Perfusion maps derived from dynamic contrast enhanced MR exams are shown to positively impact segmentation and grading performance of PCa lesions, especially the 3D MR volume corresponding to the maximum slope of the wash-in curve as well as Tmax perfusion maps. The latter mp-MRI models indeed outperform the bp-MRI one whatever the fusion strategy, with Cohen's kappa score of 0.318$\pm$0.019 for the bp-MRI model and 0.378 $\pm$ 0.033 for the model including the maximum slope with a mid fusion strategy, also achieving competitive Cohen's kappa score compared to state of the art.

Multi-class Skin Cancer Classification Architecture Based on Deep Convolutional Neural Network

Skin cancer detection is challenging since different types of skin lesions share high similarities. This paper proposes a computer-based deep learning approach that will accurately identify different kinds of skin lesions. Deep learning approaches can detect skin cancer very accurately since the models learn each pixel of an image. Sometimes humans can get confused by the similarities of the skin lesions, which we can minimize by involving the machine. However, not all deep learning approaches can give better predictions. Some deep learning models have limitations, leading the model to a false-positive result. We have introduced several deep learning models to classify skin lesions to distinguish skin cancer from different types of skin lesions. Before classifying the skin lesions, data preprocessing and data augmentation methods are used. Finally, a Convolutional Neural Network (CNN) model and six transfer learning models such as Resnet-50, VGG-16, Densenet, Mobilenet, Inceptionv3, and Xception are applied to the publically available benchmark HAM10000 dataset to classify seven classes of skin lesions and to conduct a comparative analysis. The models will detect skin cancer by differentiating the cancerous cell from the non-cancerous ones. The models performance is measured using performance metrics such as precision, recall, f1 score, and accuracy. We receive accuracy of 90, 88, 88, 87, 82, and 77 percent for inceptionv3, Xception, Densenet, Mobilenet, Resnet, CNN, and VGG16, respectively. Furthermore, we develop five different stacking models such as inceptionv3-inceptionv3, Densenet-mobilenet, inceptionv3-Xception, Resnet50-Vgg16, and stack-six for classifying the skin lesions and found that the stacking models perform poorly. We achieve the highest accuracy of 78 percent among all the stacking models.

Siamese Neural Networks for Skin Cancer Classification and New Class Detection using Clinical and Dermoscopic Image Datasets

Skin cancer is the most common malignancy in the world. Automated skin cancer detection would significantly improve early detection rates and prevent deaths. To help with this aim, a number of datasets have been released which can be used to train Deep Learning systems - these have produced impressive results for classification. However, this only works for the classes they are trained on whilst they are incapable of identifying skin lesions from previously unseen classes, making them unconducive for clinical use. We could look to massively increase the datasets by including all possible skin lesions, though this would always leave out some classes. Instead, we evaluate Siamese Neural Networks (SNNs), which not only allows us to classify images of skin lesions, but also allow us to identify those images which are different from the trained classes - allowing us to determine that an image is not an example of our training classes. We evaluate SNNs on both dermoscopic and clinical images of skin lesions. We obtain top-1 classification accuracy levels of 74.33% and 85.61% on clinical and dermoscopic datasets, respectively. Although this is slightly lower than the state-of-the-art results, the SNN approach has the advantage that it can detect out-of-class examples. Our results highlight the potential of an SNN approach as well as pathways towards future clinical deployment.

Applied Deep Learning to Identify and Localize Polyps from Endoscopic Images

Deep learning based neural networks have gained popularity for a variety of biomedical imaging applications. In the last few years several works have shown the use of these methods for colon cancer detection and the early results have been promising. These methods can potentially be utilized to assist doctor's and may help in identifying the number of lesions or abnormalities in a diagnosis session. From our literature survey we found out that there is a lack of publicly available labeled data. Thus, as part of this work, we have aimed at open sourcing a dataset which contains annotations of polyps and ulcers. This is the first dataset that's coming from India containing polyp and ulcer images. The dataset can be used for detection and classification tasks. We also evaluated our dataset with several popular deep learning object detection models that's trained on large publicly available datasets and found out empirically that the model trained on one dataset works well on our dataset that has data being captured in a different acquisition device.

Improving Precancerous Case Characterization via Transformer-based Ensemble Learning

The application of natural language processing (NLP) to cancer pathology reports has been focused on detecting cancer cases, largely ignoring precancerous cases. Improving the characterization of precancerous adenomas assists in developing diagnostic tests for early cancer detection and prevention, especially for colorectal cancer (CRC). Here we developed transformer-based deep neural network NLP models to perform the CRC phenotyping, with the goal of extracting precancerous lesion attributes and distinguishing cancer and precancerous cases. We achieved 0.914 macro-F1 scores for classifying patients into negative, non-advanced adenoma, advanced adenoma and CRC. We further improved the performance to 0.923 using an ensemble of classifiers for cancer status classification and lesion size named entity recognition (NER). Our results demonstrated the potential of using NLP to leverage real-world health record data to facilitate the development of diagnostic tests for early cancer prevention.