I am a PhD candidate in the Department of Electrical Engineering at Caltech, advised by Prof. Changhuei Yang. My current research interests include: (a) Computational microscopy with model-based methods;
(b) Physics-based neural network for microscopic image reconstruction;
(c) Vision-based learning-assisted methods with imaging system co-designs for digital pathology.
News
12/03/2024 - I am awarded Schmidt Academy for Software Engineering Graduate Research Fellowship. The support will start on Jan. 1st, 2025 for contributions to the algorithm and software development towards computational microscopy, specifically Fourier Ptychographic Microscopy. [Schmidt Academy GRA Fellows]
08/06/2024 - Our new paper titled "Investigating 3D microbial community dynamics of the rhizosphere using quantitative phase and fluorescence microscopy" is online at PNAS . [Science.org News]
05/24/2024 - I am awarded SPIE Optics and Photonics Scholarship . [Webpage] [PDF] [News]
03/06/2024 - The new paper "AI-guided histopathology predicts brain metastasis in lung cancer patients" has been featured on the Caltech homepage. News
03/04/2024 - My new paper on "AI-guided histopathology predicts brain metastasis in lung cancer patients" is online today. Check my publication list here !
02/14/2024 - I passed my candidacy exam!
11/21/2023 - My personal homepage is online!
06/30/2021 - I joined Caltech Biophotonics Lab!
Selected Publications
Full publication list here
FPM-INR: Fourier ptychographic microscopy image stack reconstruction using implicit neural representations
Haowen Zhou*, Brandon Y. Feng*, Haiyun Guo, Siyu Lin, Mingshu Liang, Christopher A. Metzler, Changhuei Yang
Optica, 2023 (BibTex) [Project Page] {Data}
Fourier ptychographic microscope images the biological samples with high-resolution and large field-of-view simultaneously. However, this microscope faces challenges with long image stack reconstruction time and huge data volumes. We designed physics-based neural signal representations to tackle these challenges and showed potential in facilitating remote diagnosis, digital pathology, and efficient clinical data packaging.
Haowen Zhou*, Brandon Y. Feng*, Haiyun Guo, Siyu Lin, Mingshu Liang, Christopher A. Metzler, Changhuei Yang
Optica, 2023 (BibTex) [Project Page] {Data}
Fourier ptychographic microscope images the biological samples with high-resolution and large field-of-view simultaneously. However, this microscope faces challenges with long image stack reconstruction time and huge data volumes. We designed physics-based neural signal representations to tackle these challenges and showed potential in facilitating remote diagnosis, digital pathology, and efficient clinical data packaging.
Single-shot volumetric fluorescence imaging with neural fields
Oumeng Zhang*, Haowen Zhou*, Brandon Y Feng, Elin M Larsson, Reinaldo E Alcalde, Siyuan Yin, Catherine Deng, Changhuei Yang
arXiv, 2024 (BibTex) [Project Page]
Single-shot volumetric fluorescence (SVF) imaging captures biological processes with high temporal resolution and a large field of view, unlike traditional methods requiring multiple axial plane scans. Existing SVF methods often face limitations due to large, complex point spread functions (PSFs), affecting signal-to-noise ratio, resolution, and field of view. The paper introduces the QuadraPol PSF combined with neural fields, using a compact custom polarizer and a polarization camera to detect fluorescence and encode the 3D scene within a compact PSF without depth ambiguity. This approach, coupled with a novel reconstruction algorithm, significantly reduces acquisition time by approximately 20 times and captures a 100 mm³ volume in one shot, demonstrated through imaging bacterial colonies and plant root morphology.
Oumeng Zhang*, Haowen Zhou*, Brandon Y Feng, Elin M Larsson, Reinaldo E Alcalde, Siyuan Yin, Catherine Deng, Changhuei Yang
arXiv, 2024 (BibTex) [Project Page]
Single-shot volumetric fluorescence (SVF) imaging captures biological processes with high temporal resolution and a large field of view, unlike traditional methods requiring multiple axial plane scans. Existing SVF methods often face limitations due to large, complex point spread functions (PSFs), affecting signal-to-noise ratio, resolution, and field of view. The paper introduces the QuadraPol PSF combined with neural fields, using a compact custom polarizer and a polarization camera to detect fluorescence and encode the 3D scene within a compact PSF without depth ambiguity. This approach, coupled with a novel reconstruction algorithm, significantly reduces acquisition time by approximately 20 times and captures a 100 mm³ volume in one shot, demonstrated through imaging bacterial colonies and plant root morphology.
