GU Radiologists vs AI in Detection of Prostate Cancer on MRI

We validated our previously developed algorithm for prostate cancer detection using an independent patient cohort who went through radical prostatectomy and compared with genitourinary radiologists under the same setting.

Algorithmic self-calibration for optimized 3D differential phase contrast microscopy

We developed a rapid, stage-free phase tomography by hand spinning the defocus knob while updating illumination patterns and taking measurements at a high frame rate, and the defocus trajectory can be inferred with the algorithm.

Joint Prostate Cancer Detection and Histological Score Prediction on MRI

We proposed a multi-class CNN to jointly detect prostate cancer lesions and characterizes their histopathological aggressiveness by fully utilizing distinctive knowledge from multi-parametric MRI.

Interpreting CNN Knowledge via an Explanatory Graph

We proposed to automatically discover object parts in an unsupervised manner, which disentangles feature components of object parts from feature representations of each convolutional filter.

Mining Object Parts from CNNs via Active Question-Answering

We used active question-answering to weakly-supervised semanticize neural patterns in conv-layers of the CNN and mine part concepts.