Skip to main content

This algorithm is designed for cell segmentation post processing to find nucleus and cytoplasm, and evaluation of the segmentation algorithm based on ground truth images

Project description

Cellcyto: A Comprehensive Tool for Autofluorescence Image Segmentation Cellcyto is a dedicated algorithm suite tailored for researchers and scientists engaged in cell segmentation endeavors, particularly within the realm of autofluorescence imaging. This tool simplifies the intricate task of segmenting NAD(P)H images, allowing for a more nuanced understanding of cellular processes.

Key Features: Autofluorescence Image Segmentation: Cellcyto introduces the Cytoplasmic Post-Processing Algorithm (CPPA) designed specifically for the segmentation of NAD(P)H images. CPPA effectively tackles challenges commonly encountered in autofluorescence image segmentation, such as low signal-to-noise ratios, irregular cell shapes, and the occurrence of cell clusters.

Multiple Thresholding Techniques: With a choice of six robust thresholding methods - Isodata, Li, Mean, Otsu, Triangle, and Yen - users can optimize segmentation performance across varied NAD(P)H images. These methods have been meticulously tested across distinct cell populations like quiescent T cells, activated T cells, and MCF7 cells, ensuring versatile utility.

Interactive GUI with Dual Functions:

Segmentation Assessment: Rapidly evaluate segmentation algorithms by juxtaposing the ground truth image against segmentation outcomes, encompassing the segmentation of cell, cytoplasm, and nucleus masks. Direct Application of CPPA: Users can seamlessly identify cytoplasm and nucleus masks via CPPA within the interface itself. Optimized Segmentation with GUI: Through the GUI, users can choose their preferred thresholding technique under the "Models" section and fine-tune the "k value" to enhance segmentation performance. Additionally, when provided with ground truth images, users can activate the "find best (cytoplasm)" and "find best (nucleus)" functions. These automatically determine the most accurate thresholding strategy by pinpointing the method with the top F-measure value, as evaluated by POSEA (entire image) for all available thresholding techniques.

Comparative Evaluation: The efficiency of CPPA is juxtaposed with CellProfiler-segmentation outcomes using the per-object segmentation evaluation algorithm, POSEA.

Repository & Further Information: For those keen on delving deeper, the algorithm code along with the GUI is accessible on GitHub.

Note on CPPA: Recognizing the significance of differentiating the cytoplasm region - a hub of metabolic information - from non-metabolizing nucleus regions in autofluorescence images, Cellcyto integrates CellPose for cell segmentation with the pioneering CPPA for detailed cytoplasm segmentation. This fusion ensures precision even in challenging scenarios presented by autofluorescence images.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

Cellcyto-1.8.1.tar.gz (12.0 kB view details)

Uploaded Source

Built Distribution

Cellcyto-1.8.1-py3-none-any.whl (12.8 kB view details)

Uploaded Python 3

File details

Details for the file Cellcyto-1.8.1.tar.gz.

File metadata

  • Download URL: Cellcyto-1.8.1.tar.gz
  • Upload date:
  • Size: 12.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.13

File hashes

Hashes for Cellcyto-1.8.1.tar.gz
Algorithm Hash digest
SHA256 666cd28ea505814814e484970c5cfef2a697d572768df176024237811ad9d2c0
MD5 1a9f0302369f1ea6457fa0d2aea64f6c
BLAKE2b-256 ac90c36a5926b8ec723d5d4590f810d255d00015fff7a82ea4827e90ebd1cec2

See more details on using hashes here.

File details

Details for the file Cellcyto-1.8.1-py3-none-any.whl.

File metadata

  • Download URL: Cellcyto-1.8.1-py3-none-any.whl
  • Upload date:
  • Size: 12.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.13

File hashes

Hashes for Cellcyto-1.8.1-py3-none-any.whl
Algorithm Hash digest
SHA256 da312a216bea851be64c5cf4170b5985ec34cae178106e8de04d9bcfcfd6c6af
MD5 512552997f770583fc2acca0c80a8c06
BLAKE2b-256 e50ecd9f1281ec69ffe5fcbbbb9d661793083104905d490eae97232c9734a7d3

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page