[CCoE Notice] Dissertation Announcement: Lin Bai, "Annotation-Free Large-Scale Overlapping Nuclear Segmentation on Multiplexed Fluorescence Images Using Foundation Model and Weak to Strong Learning"

[Greenwell, Stephen J]

[Dissertation Defense Announcement at the Cullen College of Engineering]
Annotation-Free Large-Scale Overlapping Nuclear Segmentation on Multiplexed Fluorescence Images Using Foundation Model and Weak to Strong Learning
Lin Bai
April 18, 2025, 11 a.m. to 1 p.m. (CST)
Location: Room N202 Bldg. 1
Zoom: Join the meeting<https://urldefense.com/v3/__https://uh-edu-cougarnet.zoom.us/j/84778001715?pwd=cE6pmEMQGmekjLpQViH8Nd6XxDO6DJ.1__;!!LkSTlj0I!DeWsTsNxnMEaKsSsqFQZqPmQY_OTptBdveU-8n7V2-uB7Hlzugq5u9FdRf40y-_KYxDhGW5maIRdd2FWhXem3KU5kZc$ >
Committee Chair:
Badri Roysam, Ph.D.
Committee Members:
Saurabh Prasad, Ph.D. | Hien Van Nguyen, Ph.D. | David Mayerich, Ph.D. |
Dragan Maric, Ph.D.
Abstract
We present a weak to strong generalization methodology for fully automated training of a multi-head extension of the Mask-RCNN method with efficient channel attention for reliable segmentation of overlapping cell nuclei in multiplex cyclic immunofluorescent (IHC) whole-slide images (WSI), and present evidence for pseudo-label correction and coverage expansion, the key phenomena underlying weak to strong generalization. This method can learn to segment de novo a new class of images resulting from a new instrument and/or a new protocol without the need for human annotations. We present metrics for automated self-diagnosis of segmentation quality in production environments, where human visual proofreading of massive WSI images is unaffordable. The proposed method was benchmarked against five current widely used methods and showed a significant improvement. We extend our study by adapting and applying the framework to two additional datasets to evaluate its generalizability across different imaging domains. The code, sample WSI images, and high-resolution segmentation results are provided in open form for community adoption and adaptation to other image analysis tasks.
[Engineered For What's Next]


-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://Bug.EGR.UH.EDU/pipermail/engi-dist/attachments/20250331/38315fa9/attachment-0001.html 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.png
Type: image/png
Size: 28058 bytes
Desc: image001.png
Url : http://Bug.EGR.UH.EDU/pipermail/engi-dist/attachments/20250331/38315fa9/attachment-0002.png 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image002.png
Type: image/png
Size: 5699 bytes
Desc: image002.png
Url : http://Bug.EGR.UH.EDU/pipermail/engi-dist/attachments/20250331/38315fa9/attachment-0003.png