News

Automatic segmentation of the prostate is a crucial step in the computer-aideddiagnosis of prostate cancer and in treatment planning. Current methods for prostatesegmentation primarily rely on deep learning models with neural networks. However,these models tend to be large and lack transparency, which is essential forphysicians. We proposed a new data-driven 3D prostate segmentation method onMRI named Green U-shaped Learning (GUSL). Different from deep learning basedmethods, GUSL employs a feed-forward system that utilizes successive subspacelearning (SSL).To keep enough detailed information on a dataset with a large image size, wepropose a cascading model in two stages, as shown in Figure 1: (1) segmentation ondownsampled images and (2) segmentation on the cropped patches. GUSL consistsof three main modules, as shown in Figure 2: representation learning, featurelearning, and residual correction. All modules are applied at multiple levels withvarying resolutions. We achieve fine-to-coarse unsupervised representation learning

using cascaded VoxelHop units, as well as coarse-to-fine segmentation throughfeature learning and residual correction. GUSL maintains a very competitive standingperformance-wise with other DL baseline models and keeps a smaller model sizeand less complexity, with transparency for doctors.

Nuclei Segmentation is a key step in understanding the distribution, size, and shape of nuclei in the underlying tissue. Traditionally, pathologists view histology slides under the microscope to analyze the nuclear structure. However, this process is time-consuming and is prone to inter-reader variability. An AI-based segmentation algorithm can aid pathologists in cancer detection and prognosis, and help speed up the cancer screening procedure. 

While there are several deep learning methods addressing this problem, we propose a Green Nuclei Segmentation algorithm that uses a simple, reliable, and modular approach to delineate nuclei in a histopathology slide. The Green U-shaped Learning(GUSL) is a 4 level pipeline that involves three main modules: representation learning using PixelHop, feature selection using RFT, and supervised learning using XGBoost Regressor. The different levels help look at the histopathology image at multiple resolutions, while we attempt to segment the nuclei in a coarse to fine manner. At each level, we aim to correct the previous layer’s predictions through residue correction. While this model gives good results, we can further improve the performance by refining the boundary regions to yield precise nuclei contours. 

Image denoising is a computer vision technique that removes noise from images while preserving essential structures and textures. It plays a critical role in applications such as photography enhancement, medical imaging, and remote sensing.

To address such problems, we have employed GUSL, a Green Learning-based pipeline tailored for image denoising. Noisy images are resized to multiple resolutions, and Green Learning techniques such as PixelHop, RFT, and LNT are applied at each level to extract features independently. Each level progressively refines the denoising result by correcting the residuals from the previous level. While this approach yields promising results, further refinement is needed to enhance performance in smooth and texture-rich regions.

Enhancing image feature extraction to boost image classification accuracy has been a significant research focus at the MCL lab. Initially, PixelHop++ was developed to efficiently extract image features and perform accurate image classification. Subsequently, the Least-Squares Normal Transform (LNT) was introduced to further enhance image features, improving classification results with PixelHop++ on standard image databases such as MNIST and FMNIST. Despite achieving commendable performance, further refinements remain desirable to push accuracy limits even higher.

To address this, we propose a novel pipeline of four distinct experimental setups involving different pooling strategies—absolute maximum pooling and variance pooling—at hops 1 and 2. We extract LNT features specifically from hops 1, 3, and 4 for each experiment. At hop-1, pooling (either max or variance) generates 10 LNT features per channel, resulting in a total of 250 features. Hop-3 involves transforming the (N, 3, 3, Feature) tensor to produce 90 LNT features. From hop-4, 10 additional LNT features are acquired following a DFT-based feature selection. These 350 LNT features from hops 1, 3, and 4 are concatenated alongside selected hop-4 features. Finally, features aggregated from all four experimental setups are combined, and a 10-class classifier is trained on these comprehensive feature sets, demonstrating an improvement in classification performance.

Image dehazing plays a crucial role in digital imaging by removing atmospheric distortions such as haze and fog, thereby enhancing scene clarity for applications ranging from photography to autonomous driving. Traditionally, methods like the Dark Channel Prior (DCP) have been used to estimate haze effects, leveraging the observation that most non-hazy images contain very dark pixels in at least one color channel.

In a significant advancement, researchers have now introduced a novel approach that combines the strength of DCP with the efficiency of the GUSL pipeline. In this new method, DCP serves as the foundational technique to provide an initial estimate of the haze, while the GUSL pipeline is employed to predict and correct the residual errors left by the DCP. This two-step process refines the dehazing process by capturing subtle details that DCP alone might miss.

The GUSL pipeline utilizes unsupervised representation learning for robust feature extraction, followed by supervised feature learning to enhance computational efficiency and output quality. This approach not only improves the overall dehazing performance but also maintains a lightweight design suitable for real-time applications on resource-constrained devices.

By integrating DCP with residue prediction through GUSL, the new method delivers superior image clarity with reduced computational overhead, making it an attractive solution for modern imaging challenges in mobile and edge computing environments.