arXiv subjects

Jackie Ma

Publications and source records attributed to Jackie Ma.

29 records · Page 2Linked to original sources

arXiv2024

Synthetic Generation of Dermatoscopic Images with GAN and Closed-Form Factorization

In the realm of dermatological diagnoses, where the analysis of dermatoscopic and microscopic skin lesion images is pivotal for the accurate and early detection of various medical conditions, the costs associated with creating diverse and high-quality annotated datasets have hampered the accuracy and generalizability of machine learning models. We propose an innovative unsupervised augmentation solution that harnesses Generative Adversarial Network (GAN) based models and associated techniques over their latent space to generate controlled semiautomatically-discovered semantic variations in dermatoscopic images. We created synthetic images to incorporate the semantic variations and augmented the training data with these images. With this approach, we were able to increase the performance of machine learning models and set a new benchmark amongst non-ensemble based models in skin lesion classification on the HAM10000 dataset; and used the observed analytics and generated models for detailed studies on model explainability, affirming the effectiveness of our solution.

cs.CV↗

arXiv2023

From Modern CNNs to Vision Transformers: Assessing the Performance, Robustness, and Classification Strategies of Deep Learning Models in Histopathology

While machine learning is currently transforming the field of histopathology, the domain lacks a comprehensive evaluation of state-of-the-art models based on essential but complementary quality requirements beyond a mere classification accuracy. In order to fill this gap, we developed a new methodology to extensively evaluate a wide range of classification models, including recent vision transformers, and convolutional neural networks such as: ConvNeXt, ResNet (BiT), Inception, ViT and Swin transformer, with and without supervised or self-supervised pretraining. We thoroughly tested the models on five widely used histopathology datasets containing whole slide images of breast, gastric, and colorectal cancer and developed a novel approach using an image-to-image translation model to assess the robustness of a cancer classification model against stain variations. Further, we extended existing interpretability methods to previously unstudied models and systematically reveal insights of the models' classifications strategies that can be transferred to future model architectures.

eess.IV↗

arXiv2021

On the Robustness of Pretraining and Self-Supervision for a Deep Learning-based Analysis of Diabetic Retinopathy

There is an increasing number of medical use-cases where classification algorithms based on deep neural networks reach performance levels that are competitive with human medical experts. To alleviate the challenges of small dataset sizes, these systems often rely on pretraining. In this work, we aim to assess the broader implications of these approaches. For diabetic retinopathy grading as exemplary use case, we compare the impact of different training procedures including recently established self-supervised pretraining methods based on contrastive learning. To this end, we investigate different aspects such as quantitative performance, statistics of the learned feature representations, interpretability and robustness to image distortions. Our results indicate that models initialized from ImageNet pretraining report a significant increase in performance, generalization and robustness to image distortions. In particular, self-supervised models show further benefits to supervised models. Self-supervised models with initialization from ImageNet pretraining not only report higher performance, they also reduce overfitting to large lesions along with improvements in taking into account minute lesions indicative of the progression of the disease. Understanding the effects of pretraining in a broader sense that goes beyond simple performance comparisons is of crucial importance for the broader medical imaging community beyond the use-case considered in this work.

cs.CV↗

arXiv2020

Risk Estimation of SARS-CoV-2 Transmission from Bluetooth Low Energy Measurements

Digital contact tracing approaches based on Bluetooth low energy (BLE) have the potential to efficiently contain and delay outbreaks of infectious diseases such as the ongoing SARS-CoV-2 pandemic. In this work we propose a novel machine learning based approach to reliably detect subjects that have spent enough time in close proximity to be at risk of being infected. Our study is an important proof of concept that will aid the battery of epidemiological policies aiming to slow down the rapid spread of COVID-19.

q-bio.QM↗

arXiv2017

Anisotropic Multiscale Systems on Bounded Domains

We provide a construction of multiscale systems on a bounded domain $Ω\subset \mathbb{R}^2$ coined boundary shearlet systems, which satisfy several properties advantageous for applications to imaging science and the numerical analysis of partial differential equations. More precisely, we construct boundary shearlet systems that form frames for the Sobolev spaces $H^s(Ω),s\in \mathbb{N} \cup \{0\},$ with controllable frame bounds and admit optimally sparse approximations for functions, which are smooth apart from a curve-like discontinuity. We show that the constructed systems allow incorporating boundary conditions. Furthermore, for $s \geq 0$ and $f\in H^s(Ω)$ we prove that weighted $\ell^2$ norms of the $L^2-$analysis coefficients of $f$ are equivalent to its $H^s(Ω)$ norm. This yields in particular, that the reweighted systems are frames also for $H^{-s}(Ω)$. Moreover, we demonstrate numerically, that the associated $L^2-$synthesis operator is also stable as a map to $H^s(Ω)$ which, in combination with the previous result, strongly indicates that these systems constitute so-called Gelfand frames for $(H^s(Ω), L^2(Ω), H^{-s}(Ω))$.

math.FA↗

arXiv2017

A multilevel based reweighting algorithm with joint regularizers for sparse recovery

Sparsity is one of the key concepts that allows the recovery of signals that are subsampled at a rate significantly lower than required by the Nyquist-Shannon sampling theorem. Our proposed framework uses arbitrary multiscale transforms, such as those build upon wavelets or shearlets, as a sparsity promoting prior which allow to decompose the image into different scales such that image features can be optimally extracted. In order to further exploit the sparsity of the recovered signal we combine the method of reweighted $\ell^1$, introduced by Candès et al., with iteratively updated weights accounting for the multilevel structure of the signal. This is done by directly incorporating this approach into a split Bregman based algorithmic framework. Furthermore, we add total generalized variation (TGV) as a second regularizer into the split Bregman algorithm. The resulting algorithm is then applied to a classical and widely considered task in signal- and image processing which is the reconstruction of images from their Fourier measurements. Our numerical experiments show a highly improved performance at relatively low computational costs compared to many other well established methods and strongly suggest that sparsity is better exploited by our method.

math.OC↗

arXiv2017

Shearlet-based compressed sensing for fast 3D cardiac MR imaging using iterative reweighting

High-resolution three-dimensional (3D) cardiovascular magnetic resonance (CMR) is a valuable medical imaging technique, but its widespread application in clinical practice is hampered by long acquisition times. Here we present a novel compressed sensing (CS) reconstruction approach using shearlets as a sparsifying transform allowing for fast 3D CMR (3DShearCS). Shearlets are mathematically optimal for a simplified model of natural images and have been proven to be more efficient than classical systems such as wavelets. Data is acquired with a 3D Radial Phase Encoding (RPE) trajectory and an iterative reweighting scheme is used during image reconstruction to ensure fast convergence and high image quality. In our in-vivo cardiac MRI experiments we show that the proposed method 3DShearCS has lower relative errors and higher structural similarity compared to the other reconstruction techniques especially for high undersampling factors, i.e. short scan times. In this paper, we further show that 3DShearCS provides improved depiction of cardiac anatomy (measured by assessing the sharpness of coronary arteries) and two clinical experts qualitatively analyzed the image quality.

cs.CV↗

arXiv2016

Stable reconstructions for the analysis formulation of $\ell^p$-minimization using redundant systems

In compressed sensing sparse solutions are usually obtained by solving an $\ell^1$-minimization problem. Furthermore, the sparsity of the signal does need not be directly given. In fact, it is sufficient to have a signal that is sparse after an application of a suitable transform. In this paper we consider the stability of solutions obtained from $\ell^p$-minimization for arbitrary $0<p \leq1$. Further we suppose that the signals are sparse with respect to general redundant transforms associated to not necessarily tight frames. Since we are considering general frames the role of the dual frame has to be additionally discussed. For our stability analysis we will introduce a new concept of so-called \emph{frames with identifiable duals}. Further, we numerically highlight a gap between the theory and the applications of compressed sensing for some specific redundant transforms.

cs.IT↗

arXiv2015

Generalized sampling reconstruction from Fourier measurements using compactly supported shearlets

In this paper we study the general reconstruction of a compactly supported function from its Fourier coefficients using compactly supported shearlet systems. We assume that only finitely many Fourier samples of the function are accessible and based on this finite collection of measurements an approximation is sought in a finite dimensional shearlet reconstruction space. We analyse this sampling and reconstruction process by a recently introduced method called generalized sampling. In particular by studying the stable sampling rate of generalized sampling we then show stable recovery of the signal is possible using an almost linear rate. Furthermore, we compare the result to the previously obtained rates for wavelets.

math.FA↗

arXiv2015

Linear independence of compactly supported separable shearlet systems

This paper examines linear independence of shearlet systems. This property has already been studied for wavelets and other systems such as, for instance, for Gabor systems. In fact, for Gabor systems this problem is commonly known as the HRT conjecture. In this paper we present a proof of linear independence of compactly supported separable shearlet systems. For this, we employ a sampling strategy to utilize the structure of an implicitly given underlying oversampled wavelet system as well as the shape of the supports of the shearlet elements.

math.FA↗

arXiv2014

Linear Stable Sampling Rate: Optimality of 2D Wavelet Reconstructions from Fourier Measurements

In this paper we analyze two-dimensional wavelet reconstructions from Fourier samples within the framework of generalized sampling. For this, we consider both separable compactly-supported wavelets and boundary wavelets. We prove that the number of samples that must be acquired to ensure a stable and accurate reconstruction scales linearly with the number of reconstructing wavelet functions. We also provide numerical experiments that corroborate our theoretical results.

math.FA↗