News

Magnetic Resonance Imaging(MRI) is a non-invasive, radiation-free scanning procedure generally used to obtain images of internal organs. This imaging modality is a popular screening technique for Prostate Cancer. A Prostate MRI may be used to detect prostate cancer, determine the requirement for biopsy, guide needles during targeted MRI biopsy, or detect the spreading of cancer to neighboring areas. Current standards of MRI acquisition still lead to errors, like false detections, where patients are unnecessarily sent to biopsy, or missed detections, where existing tumors remain undetected. A good quality MRI is essential to ensure that Prostate Cancer is diagnosed on time.

An MRI has several sequences, namely T2W, ADC, and DCE. For an MRI to be of diagnostic quality, atleast two of the three sequences must independently be of diagnostic quality. Errors/artifacts may be present in some or all of these sequences. Some common artifacts include motion artifacts, rectal gas, hip prosthesis, etc., that affect the quality of the MRI.

In order to assess the quality of an MRI, we train independent models for each of these sequences. While MRI images are volumetric, we treat each slice of the MRI independently. 2D Haar Wavelet Transform is applied to extract features from the LL, LH, HL, and HH bands. These features are extracted at two different resolutions. The Discriminant Feature Test(DFT) is used to reduce the feature dimension by removing features with a high DFT loss. An XGBoost Classifier is then trained using these selected features to predict whether each slice of the MRI is of satisfactory quality or not. The quality predictions from each of the three sequences are then combined to obtain the final MRI quality prediction. This approach is light-weight, efficient, and explainable, with [...]

Wavelet-based Green Learning (GreenWave) is a new image classification framework that combines the multi-scale power of wavelet transforms with the efficiency and interpretability of Green Learning principles. It avoids backpropagation and replaces traditional deep learning architectures with a transparent, feedforward pipeline.

At its core, GreenWave begins by applying a discrete wavelet transform (DWT)—typically using Haar wavelets—to each image, capturing both local and global spatial structures at multiple resolutions. It extracts features from wavelet subbands (like LL, LH, HL, HH) as well as local image patches from different regions (e.g., east, south, west, north). These features are used to construct class templates via averaging over training examples.

GreenWave operates in three rounds of classification:1. Round-1 classifies easy samples using cosine similarity between the input and class templates (one-vs-rest). It uses confidence metrics (like entropy) to decide which samples are “easy” and can exit the pipeline early.2. Round-2 focuses on semi-hard samples using updated templates and discriminant feature test (DFT) masks to emphasize class-informative coefficients. It also introduces one-vs-one templates to resolve class confusion.3. Round-3 targets the hardest samples using further refined templates and updated confusion masks, maximizing accuracy while maintaining interpretability.Throughout all stages, GreenWave uses cosine similarity as its feature-matching metric and XGBoost classifiers for decision learning, completely bypassing gradient-based training.

Overall, GreenWave demonstrates that a non-backpropagation, wavelet-template-based system can achieve near state-of-the-art performance while being highly efficient, explainable, and modular. This makes it an ideal choice for low-resource or transparent AI applications.

XGBoost is a widely used gradient-boosting framework in machine learning. Due to its low resource consumption and interpretability for sequential learning, XGBoost has gained increasing attention in green learning, where computational efficiency and model transparency are essential. However, XGBoost is not optimized in the current green learning literature. It accounts for a large part of the model parameters in a green learning system. It is desired to reduce the size of XGBoost while maintaining its high performance.

We recently have proposed a new method called Multi-stage XGBoost (MXB), a modular framework that builds a sequence of XGBoost models. MXB adopts a sequence of shallow XGBoost models, each of which defines a stage. Unlike conventional XGBoost, which is trained on the full feature set, the model at each stage of MXB is trained on a distinct feature subset. The general idea is to put more discriminant ones in earlier stages and less discriminant ones in later stages. This is motivated by the convergence curve of the XGBoost classifier and regressor. Also, the transition from one XGBoost model to the next in MXB is governed by the behavior of the gradient and Hessian, which represent the first- and second-order derivatives of the objective function, respectively. The gradient quantifies the direction and rate of change of the loss function, indicating how far the model is from optimality. The Hessian, on the other hand, measures the curvature of the loss, offering insight into the local stability of convergence.

We evaluate MXB on two datasets: MNIST and Fashion-MNIST, and compare it with standard XGBoost models of equivalent depth and model size. The training and testing curves show that MXB has smaller train–validation gaps and more stable testing loss as compared to [...]

We are very happy to welcome a new MCL member, Alek Yegazarian. Here is a quick interview with Alek:

1.  Could you briefly introduce yourself and your research interests?

My name is Alek Yegazarian, I am a recent Master of Science Electrical Engineering graduate from the University of Southern California, earning the Ming Hsieh Department of Electrical and Computer Engineering academic achievement award and the 2025 Viterbi Master’s 1 student commencement speaker honor. My research background and interests lie at the intersection of computational imaging, computer vision, and robotics. Outside of engineering and academia, I am a magician member of the Academy of Magical Arts at the Magic Castle in Hollywood, enjoy playing piano, and stay active by practicing taekwondo.2. What is your impression of MCL and USC?

I am so excited and grateful to be a part of MCL. Dr. Kuo’s passion and enthusiasm for his students and research is inspiring. I especially enjoy the lab environment, as everyone is very friendly and supportive. I am truly happy and excited every time I come to campus for research! Shout out to Wei Wang and Yixing Wu for being so welcoming, attentive, and helpful during these first few weeks working with them.

3. What is your future expectation and plan in MCL?

During this summer, I am supporting research on Green U-Shaped Learning (GUSL) for super-resolution and denoising tasks. I hope to learn and contribute as much as I can to MCL and Green Learning, while simultaneously getting to know my fellow lab members and getting a taste of life as a researcher in academia.

We are very happy to welcome a new MCL member, Kevin Lim. Here is a quick interview with Kevin:

1. Could you briefly introduce yourself and your research interests?

My name is Kevin Lim, and I am a second year master’s student studying Computer Science. I’ve explored a few subfields within the field of AI but I’m most interested in deep learning and computer vision. I found Professor Kuo’s work in green learning to be very interesting which is part of my motivation to apply for an internship at MCL.

2. What is your impression of MCL and USC?

I think USC is a place with many opportunities for ambitious people. Hard-working and passionate individuals thrive here and this serves as an inspiration for others as well. I’ve spoken to a few people at MCL already and they are very friendly, and I appreciate Professor Kuo’s leadership and guidance.

3. What is your future expectation and plan in MCL?

I hope to gain a better understanding of research trends in the image processing field, as I’ve already started to do while preparing for the Mediatek research project. I also hope to build strong connections with members of the lab.