# bu-cisl/computational-miniature-mesoscope-cm2 architecture

> Architecture diagram of the GitHub repository bu-cisl/computational-miniature-mesoscope-cm2, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-05-13). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/bu-cisl/computational-miniature-mesoscope-cm2
- Repository: https://github.com/bu-cisl/computational-miniature-mesoscope-cm2

## Overview

##### Main System Components
1.1 Hardware Design (CAD & 3D Printing)
- CAD_models/CM2_V1 and CM2_V2 (LED housing, MLA housing, freeform illuminator, assembly files)
- 3D-printer (lab tabletop)
1.2 Optical Simulation Environment
- Zemax_models (ZOS, CFG files, spectra and coating profiles)
- Zemax ray-tracing engine
1.3 Data Acquisition & Storage
- Physical CM² device (sensor + LED array + MLA)
- Raw measurements (.tif, .mat)
- PSF libraries and sample data (downloaded or pre-rendered)
1.4 Reconstruction Pipelines
a) Model-Based 3D Deconvolution (MATLAB)
- Algorithm/model_based_3D_deconvolution_CM2_V1/cm2_related_code.m
- Utilities (ADMM_LSI_deconv_3D.m, bg_removal.m, etc.)
b) Deep-Learning CM²Net (Python/TensorFlow)
- Algorithm/cm2net/cm2_models.py
- Algorithm/cm2net/pred_cm2net.py
- Pretrained weights, sample measurement & ground truth (external drive)

##### Relationships & Data Flows
- Feed **Zemax Models** into two paths:
- Validate/design optics → Produce PSF/response data → Stored in PSF library
- Inform CAD tweaks (iterative design loop)
- **Physical Device** generates raw fluorescence measurements → Stored as .mat/.tif
- **Reconstruction** splits into two parallel pipelines:
- MATLAB Deconvolution: uses PSF library + raw data → 3D volume output
- CM²Net Inference: uses pretrained TensorFlow model + raw data → 3D volume output
- Both outputs feed a **Visualization/Analysis** block.

##### Architectural Patterns & Design Principles
- Modular, layered architecture: separate hardware, simulation, acquisition, and reconstruction.
- Two parallel algorithmic back-ends—model-based vs. data-driven—to allow comparison/benchmarking.
- Extensibility: new algorithms or hardware versions can plug into the same pipeline.

##### Call Out Key Technologies & Frameworks
- CAD: STL, OBJ, MTL (3D printing)
- Optical Simulation: Zemax (ZOS, CFG, spectra/coat profiles)
- Data Processing: MATLAB (R2020+, ADMM solver)
- Deep Learning: Python 3.7, TensorFlow 2.3

##### Detailed Layer Breakdown
- Layer 1: Hardware & CAD
- CAD_models (V1, V2) → 3D Printer → CM² Device
- Layer 2: Optical Simulation
- Zemax_models → PSF/response outputs → PSF Library
- Layer 3: Data Acquisition
- CM² Device captures fluorescence → Raw Data Store
- Layer 4: Reconstruction Engines (parallel)
- Model-Based: MATLAB scripts + PSF Library → Deconv Output
- Data-Driven: TensorFlow model + Raw Data → CM²Net Output
- Layer 5: Visualization & Downstream Analysis

## Diagram (Mermaid)

```mermaid
flowchart TD
    %% Layer 1: Hardware & CAD
    subgraph "Layer 1: Hardware & CAD"
        direction TB
        CAD_V1["CAD_models/CM2_V1"]:::hardware
        CAD_V2["CAD_models/CM2_V2"]:::hardware
        Printer["3D Printer"]:::hardware
        Device["CM² Physical Device"]:::hardware
    end

    CAD_V1 -->|".stl, .obj"| Printer
    CAD_V2 -->|".stl, .obj"| Printer
    Printer -->|"assembled CM²"| Device

    %% Layer 2: Optical Simulation
    subgraph "Layer 2: Optical Simulation"
        direction TB
        Zemax_V1["Zemax_models/CM2_V1"]:::simulation
        Zemax_V2["Zemax_models/CM2_V2"]:::simulation
        Zemax_Util["Zemax_models/utilities"]:::simulation
        PSF_Lib["PSF Library"]:::datastore
    end

    Zemax_V1 -->|"PSF volumes"| PSF_Lib
    Zemax_V2 -->|"PSF volumes"| PSF_Lib
    Zemax_Util -->|"config & coatings"| Zemax_V1
    Zemax_Util -->|"config & coatings"| Zemax_V2
    Zemax_V1 -->|"design feedback"| CAD_V1
    Zemax_V2 -->|"design feedback"| CAD_V2

    %% Layer 3: Data Acquisition
    subgraph "Layer 3: Data Acquisition"
        direction TB
        Device -->|"raw measurements (.tif, .mat)"| RawData["Raw Data Store"]:::datastore
    end

    %% Layer 4: Reconstruction Engines
    subgraph "Layer 4: Reconstruction Engines"
        direction TB
        subgraph "Model-Based 3D Deconvolution (MATLAB)"
            direction TB
            MB_Pipeline["Algorithm/model_based_3D_deconvolution_CM2_V1"]:::algorithm
            MB_Core["cm2_related_code.m"]:::algorithm
            MB_Utils["utilities/*.m"]:::algorithm
            MB_Sample["sample_experimental_measurement.mat"]:::datastore
        end
        subgraph "Deep-Learning CM²Net (TensorFlow)"
            direction TB
            DL_Pipeline["Algorithm/cm2net"]:::algorithm
            DL_Model["cm2_models.py"]:::algorithm
            DL_Predict["pred_cm2net.py"]:::algorithm
        end
        RawData -->|".mat raw"| MB_Pipeline
        PSF_Lib -->|"PSF volumes"| MB_Pipeline
        RawData -->|".tif raw"| DL_Pipeline
    end

    MB_Pipeline -->|"3D volume output"| Visual["Visualization & Analysis"]:::external
    DL_Pipeline -->|"3D volume output"| Visual

    %% Layer 5: Visualization
    subgraph "Layer 5: Visualization & Analysis"
        direction TB
        Visual["Visualization & Analysis"]:::external
    end

    %% Click Events
    click CAD_V1 "https://github.com/bu-cisl/computational-miniature-mesoscope-cm2/tree/main/CAD_models/CM2_V1"
    click CAD_V2 "https://github.com/bu-cisl/computational-miniature-mesoscope-cm2/tree/main/CAD_models/CM2_V2"
    click Zemax_V1 "https://github.com/bu-cisl/computational-miniature-mesoscope-cm2/tree/main/Zemax_models/CM2_V1"
    click Zemax_V2 "https://github.com/bu-cisl/computational-miniature-mesoscope-cm2/tree/main/Zemax_models/CM2_V2"
    click Zemax_Util "https://github.com/bu-cisl/computational-miniature-mesoscope-cm2/tree/main/Zemax_models/utilities"
    click MB_Pipeline "https://github.com/bu-cisl/computational-miniature-mesoscope-cm2/tree/main/Algorithm/model_based_3D_deconvolution_CM2_V1"
    click MB_Core "https://github.com/bu-cisl/computational-miniature-mesoscope-cm2/blob/main/Algorithm/model_based_3D_deconvolution_CM2_V1/cm2_related_code.m"
    click MB_Utils "https://github.com/bu-cisl/computational-miniature-mesoscope-cm2/tree/main/Algorithm/model_based_3D_deconvolution_CM2_V1/utilities"
    click MB_Sample "https://github.com/bu-cisl/computational-miniature-mesoscope-cm2/blob/main/Algorithm/model_based_3D_deconvolution_CM2_V1/sample_experimental_measurement.mat"
    click DL_Pipeline "https://github.com/bu-cisl/computational-miniature-mesoscope-cm2/tree/main/Algorithm/cm2net"
    click DL_Model "https://github.com/bu-cisl/computational-miniature-mesoscope-cm2/blob/main/Algorithm/cm2net/cm2_models.py"
    click DL_Predict "https://github.com/bu-cisl/computational-miniature-mesoscope-cm2/blob/main/Algorithm/cm2net/pred_cm2net.py"

    %% Styles
    classDef hardware fill:#D0E6FF,stroke:#4682B4,stroke-width:2px;
    classDef simulation fill:#E0FFE0,stroke:#228B22,stroke-width:2px,stroke-dasharray: 5 5;
    classDef datastore fill:#FFE4B5,stroke:#CD8500,stroke-width:2px;
    classDef algorithm fill:#E6E6FA,stroke:#9370DB,stroke-width:2px;
    classDef external fill:#F0F0F0,stroke:#A9A9A9,stroke-width:2px,stroke-dasharray: 2 2;
```
