Kaiqiang Ma

Bio: Kaiqiang Ma is an academic researcher from Hangzhou Dianzi University. The author has contributed to research in topics: Digital pathology & Contextual image classification. The author has an hindex of 2, co-authored 3 publications receiving 226 citations.

Breast Cancer Microscope Image Classification Based on CNN with Image Deformation

Abstract: In recent years, digital pathology, computational storage and computing capabilities have been evolved rapidly. Computer software provides a possibility to automatically identify tissue types of high-resolution microscopic images, thus greatly improving the accuracy of physician diagnosis and reducing the workload of physicians. In this paper, the convolution neural network (CNN) and hybrid CNN model such as CNN + SVM are adopted to classify the breast cancer microscope images on ICIAR2018 dataset. Part A of the challenge is to automatically classify H&E-stained breast histological microscopy into four categories: normal, benign, carcinoma in situ and invasive carcinoma. In case that the data set is too small, VGG16 network and transfer learning are used, together with a variety of data augmentation methods. In addition to the traditional method of natural image augmentation, this study introduces a deformation to the microscope image and then uses a multi-model vote to achieve a 92.5% accuracy on 80 validation sets, an ACC of 91.7% on the test set of [7]. This approach yielded test set ACC’s of 0.83 on the first task of the Grand Challenge on Breast Cancer Histology Images.

Classification of blood cancer images using a convolutional neural networks ensemble

Abstract: This paper presents the method of our submission to the ISBI 2019 Challenge for the task of classification of normal versus malignant cells in B-ALL white blood cancer microscopic images. We aimed to combine convolutional neural networks with several state-of-the-art techniques. Specifically, we fine-tuned pretrained deep learning networks including ResNet and DenseNet for this task. Overfitting is one of the major problems for this challenge. We solve overfitting by using the gradient norm clipping and the cosine annealing learning rate schedule with restarts, which have a significant impact on the performance of our deep neural network. More importantly, adaptive pooling layer is used in our models. With this modification, models are able to adapt to images of any size. An ensemble of deep models achieved a 0.8570 weighted-f1 score on the preliminary test set reported by the test server.

Translational AI and Deep Learning in Diagnostic Pathology

Abstract: There has been an exponential growth in the application of AI in health and in pathology. This is resulting in the innovation of deep learning technologies that are specifically aimed at cellular imaging and practical applications that could transform diagnostic pathology. This paper reviews the different approaches to deep learning in pathology, the public grand challenges that have driven this innovation and a range of emerging applications in pathology. The translation of AI into clinical practice will require applications to be embedded seamlessly within digital pathology workflows, driving an integrated approach to diagnostics and providing pathologists with new tools that accelerate workflow and improve diagnostic consistency and reduce errors. The clearance of digital pathology for primary diagnosis in the US by some manufacturers provides the platform on which to deliver practical AI. AI and computational pathology will continue to mature as researchers, clinicians, industry, regulatory organizations and patient advocacy groups work together to innovate and deliver new technologies to health care providers: technologies which are better, faster, cheaper, more precise, and safe.

Deep Learning for Whole Slide Image Analysis: An Overview.

Abstract: The widespread adoption of whole slide imaging has increased the demand for effective and efficient gigapixel image analysis. Deep learning is at the forefront of computer vision, showcasing significant improvements over previous methodologies on visual understanding. However, whole slide images have billions of pixels and suffer from high morphological heterogeneity as well as from different types of artifacts. Collectively, these impede the conventional use of deep learning. For the clinical translation of deep learning solutions to become a reality, these challenges need to be addressed. In this paper, we review work on the interdisciplinary attempt of training deep neural networks using whole slide images, and highlight the different ideas underlying these methodologies.