Mammography

mammography Medical Radiographic Ray
View Benchmarks (1)

Full-field digital mammography (FFDM) produces high-resolution X-ray projection images of compressed breast tissue for cancer screening. The low-energy X-ray beam (25-32 kVp with W/Rh or Mo/Mo target-filter) maximizes soft tissue contrast. Amorphous selenium flat-panel detectors provide direct conversion with ~50 um pixel pitch. The forward model follows Beer-Lambert with energy-dependent attenuation. Primary challenges include overlapping tissue structures, microcalcification detection, and dense breast tissue masking lesions.

Forward Model

Beer Lambert Projection

Noise Model

Poisson

Default Solver

tv fista

Sensor

FLAT_PANEL_ASE

Forward-Model Signal Chain

Each primitive represents a physical operation in the measurement process. Arrows show signal flow left to right.

Pi contact Contact Projection D g, η₁ Detector
Spec Notation

Π(contact) → D(g, η₁)

Benchmark Variants & Leaderboards

Mammography

Mammography

Full Benchmark Page →
Spec Notation

Π(contact) → D(g, η₁)

Standard Leaderboard (Top 10)

# Method Score PSNR (dB) SSIM Trust Source
🥇 Score-CT 0.907 39.92 0.984 ✓ Certified Song et al., NeurIPS 2024
🥈 DiffusionCT 0.902 39.68 0.982 ✓ Certified Kazemi et al., ECCV 2024
🥉 CTFormer 0.897 39.45 0.980 ✓ Certified Li et al., ICCV 2024
4 CT-ViT 0.891 39.15 0.978 ✓ Certified Guo et al., NeurIPS 2024
5 DOLCE 0.874 38.32 0.971 ✓ Certified Liu et al., ICCV 2023
6 DuDoTrans 0.859 37.68 0.962 ✓ Certified Wang et al., MLMIR 2022
7 Learned Primal-Dual 0.831 36.42 0.947 ✓ Certified Adler & Oktem, IEEE TMI 2018
8 FBPConvNet 0.816 35.81 0.939 ✓ Certified Jin et al., IEEE TIP 2017
9 RED-CNN 0.763 33.56 0.908 ✓ Certified Chen et al., IEEE TMI 2017
10 PnP-DnCNN 0.760 33.45 0.905 ✓ Certified Zhang et al., 2017

Showing top 10 of 13 methods. View all →

Mismatch Parameters (3) click to expand
Name Symbol Description Nominal Perturbed
compression Δh Compression thickness error (mm) 0 2.0
anode_angle Δα Anode angle error (deg) 0 0.5
scatter f_s Scatter fraction error 0.3 0.35

Reconstruction Triad Diagnostics

The three diagnostic gates (G1, G2, G3) characterize how reconstruction quality degrades under different error sources. Each bar shows the relative attribution.

G1 — Forward Model Accuracy How well does the mathematical model match reality?

Model: beer lambert projection — Mismatch modes: motion blur, scatter, compression artifact, grid artifact, skin fold

G2 — Noise Characterization Is the noise model correctly specified?

Noise: poisson — Typical SNR: 20.0–40.0 dB

G3 — Calibration Quality Are instrument parameters accurately measured?

Requires: flat field, detector calibration, compression thickness, target filter combination, AEC calibration

Modality Deep Dive

Principle

Mammography uses low-energy X-rays (25-35 kVp) with specialized anode/filter combinations (Mo/Mo, Mo/Rh, W/Rh) to optimize contrast between breast tissue types (adipose, glandular, calcifications). Breast compression reduces thickness and scatter, improving contrast and reducing dose. Digital mammography uses flat-panel detectors for direct or indirect X-ray detection.

How to Build the System

A dedicated mammography unit with a compression paddle, specialized X-ray tube (Mo, Rh, or W anode), and high-resolution flat-panel detector (50-100 μm pixel size, amorphous selenium for direct conversion). Automatic optimization of target/filter and kVp based on compressed breast thickness. Regular quality assurance per ACR/MQSA requirements: phantom images, SNR measurements, artifact checks, and AEC calibration.

Common Reconstruction Algorithms

  • Contrast-limited adaptive histogram equalization (CLAHE) for display
  • Computer-aided detection (CAD) for microcalcification and mass detection
  • Digital breast tomosynthesis (DBT) reconstruction (FBP or iterative)
  • Deep-learning breast density classification (BI-RADS categories)
  • Synthetic 2D mammography from DBT volumes

Common Mistakes

  • Insufficient breast compression, increasing dose and reducing contrast
  • Positioning errors cutting off breast tissue (especially axillary tail)
  • Grid artifacts or grid cutoff from misaligned Bucky grid
  • Exposure errors from AEC sensor placed over dense tissue vs. adipose
  • Motion blur from long exposure times in thick or dense breasts

How to Avoid Mistakes

  • Apply firm, consistent compression; verify thickness readout is reasonable
  • Follow standardized positioning protocols (CC, MLO) with technologist training
  • Verify grid alignment and use reciprocating grid to eliminate grid lines
  • Position AEC sensor appropriately for breast density; adjust manually if needed
  • Use shortest possible exposure with adequate mAs; consider large-angle tomosynthesis

Forward-Model Mismatch Cases

  • The widefield fallback applies Gaussian blur, but mammography uses low-energy X-ray transmission (25-35 kVp) with tissue-specific attenuation coefficients optimized for fat/glandular tissue contrast — the physics model is fundamentally different
  • Mammographic image formation involves compression geometry, scatter grid rejection, anti-scatter grid, and detector-specific MTF — none of these are captured by a simple spatial Gaussian blur

How to Correct the Mismatch

  • Use the mammography operator implementing Beer-Lambert transmission at mammographic energies with tissue-specific attenuation: y = I_0 * exp(-mu_tissue * t) for fat, glandular, and calcification components
  • Include scatter rejection model, detector quantum efficiency (DQE), and geometric magnification for accurate forward modeling and quantitative breast density estimation

Experimental Setup

Instrument

Hologic Selenia Dimensions / Siemens MAMMOMAT Revelation

Image Size

2294x1914

Kvp

28

Target Filter

W/Rh

Mas

60

Detector

flat-panel amorphous selenium (direct conversion)

Pixel Pitch Um

70

Dataset

VinDr-Mammo, CBIS-DDSM, INbreast

Signal Chain Diagram

Experimental setup diagram for Mammography

Key References

  • VinDr-Mammo, Scientific Data 2023
  • Lee et al., 'A curated mammography dataset (CBIS-DDSM)', Scientific Data 4, 170177 (2017)

Canonical Datasets

  • VinDr-Mammo (5000 4-view exams)
  • CBIS-DDSM (curated DDSM subset)
  • INbreast (410 images, Moreira et al.)

Benchmark Pages