---
title: 'ACDC: Automated Cardiac Diagnosis Challenge'
url: https://www.emergentmind.com/topics/automated-cardiac-diagnosis-challenge-acdc
type: topic
---

# ACDC: Automated Cardiac Diagnosis Challenge

Searching arXiv for foundational and recent papers on the Automated Cardiac Diagnosis Challenge (ACDC).
The **Automated Cardiac Diagnosis Challenge (ACDC)** is a public benchmark for **automatic segmentation** of key cardiac structures in cine MRI and **automatic diagnosis** of cardiac disease from those images. Across the works that use it as a central benchmark, ACDC is consistently defined around **2D short-axis cine cardiac MRI**, with annotations for the **left ventricle cavity (LV)**, **right ventricle cavity (RV)**, and **myocardium (MYO)**, and with patient-level diagnostic labels spanning five categories: **NOR**, **DCM**, **HCM**, **MINF**, and **RV/ARV/RVA** depending on paper-specific naming conventions [1708.01141], [1801.05173], [2103.08590]. It functions both as a segmentation benchmark and as a substrate for end-to-end or staged automated diagnosis pipelines, including feature-based classifiers, radiomics systems, motion- and biomechanics-based methods, multi-task learning systems, and interpretability studies [1707.00587], [1810.10117], [1909.11854], [2507.05783].

## 1. Benchmark definition and dataset composition

In the ACDC challenge setting, the modality is **4D cine cardiac MRI** or, equivalently, **2D short-axis slices over time**, with emphasis on **end-diastole (ED)** and **end-systole (ES)** for annotation and evaluation [1708.01141], [1707.00587]. The training labels comprise manual segmentations of **LV cavity**, **RV cavity**, and **myocardium**, typically only at **ED** and **ES**, plus a patient-level diagnosis label [1708.01141], [1707.00587], [1810.10117].

Several papers restate the canonical cohort structure. One formulation gives **150 exams (150 patients)** split into **100 training cases** and **50 test cases**, with **five equally sized groups**: **NOR**, **MINF**, **DCM**, **HCM**, and **ARV** [1801.05173]. Another formulation describes **150 patients in total**, with **100 in the official ACDC training set** and **50 in the test set**, adopting exactly that split for training and testing [2507.05783]. A more restricted use appears in interpretability work that focuses on the **100 labeled cases** and the challenge’s **70/30 training/development** partition rather than the hidden test set [2103.08590].

The imaging protocol is repeatedly described in compatible terms: **short-axis cine MR**, **SSFP** or steady-state free precession, **28–40 time frames per cardiac cycle**, **slice thickness 5–8 mm** or **5–10 mm**, and **in-plane resolution 1.37–1.68 mm²/pixel** [2103.08590], [1801.05173], [1708.01141]. Some descriptions also note acquisition on **1.5 T Siemens Avanto** and **3.0 T Siemens Trio Tim** scanners [2103.08590].

The five diagnostic groups are tied to clinically defined criteria involving ventricular volumes, ejection fraction, wall motion, myocardial mass, or myocardial thickness [1801.05173]. A plausible implication is that ACDC was designed not merely as a segmentation leaderboard, but as a benchmark linking anatomy, function, and diagnosis.

## 2. Core tasks: segmentation and diagnosis

ACDC defines two primary tasks: **segmentation** of **LV**, **RV**, and **MYO** at **ED** and **ES**, and **cardiac diagnosis** into one of the five disease classes [2103.08590]. The segmentation task is commonly formalized as a pixel-wise or voxel-wise labeling problem. One explicit 2D formulation is:

\[
X \in \mathbb{R}^{n \times n}, \qquad
Y \in \{LV, RV, MYO, bg\}^{n \times n}
\]

so that each pixel is assigned to one of the three anatomical structures or background [2103.08590].

Most ACDC diagnosis pipelines are structured as a sequence: segment the cardiac structures, compute clinical indices such as **volumes**, **ejection fraction**, **mass**, or **wall thickness**, and then classify the patient into **NOR**, **DCM**, **HCM**, **MINF**, or **RV/ARV/RVA** [2103.08590], [1708.01141], [1707.00587]. This staged design is explicit in works that derive **LV volume at ED and ES**, **RV volume at ED and ES**, **myocardial volume**, **ejection fraction**, and multiple volume ratios from segmentation masks [1708.01141], [1707.00587].

Several papers give the standard ejection fraction formula:

\[
EF = \frac{EDV - ESV}{EDV}
\]

or its percent form [1708.01141], [1707.00587], [2505.03838]. In feature-driven ACDC systems, these quantities are then fed to classifiers such as **Random Forest**, **SVM**, **MLP**, **Logistic Regression**, or ensembles thereof [1708.01141], [1707.00587], [1801.05173], [2507.05783].

A recurrent misconception is that ACDC is only a segmentation dataset. The literature repeatedly treats diagnosis as equally central: the challenge is explicitly about **combined segmentation plus diagnosis**, and many methods are evaluated on both tasks [1708.01141], [1801.05173], [2505.03838].

## 3. Segmentation methodologies developed on ACDC

ACDC has served as a testbed for a wide range of segmentation architectures. Early and influential approaches include **2D fully convolutional networks**, **U-Net-inspired models**, **DenseNet-derived FCNs**, and **dilated CNNs** [1708.01141], [1801.05173], [1708.01141]. A later wave includes **directional feature map modules**, **residual 3D U-Nets**, **temporal ConvLSTM decoders**, **foundation-model hybrids**, and **state-space-model architectures** [2007.11349], [2505.03838], [2012.14564], [2505.16304].

One ACDC challenge solution employs a **2D fully convolutional network** called **DFCN-C**, combining DenseNet connectivity, residual shortcuts in the decoder, and an Inception-style multi-scale first layer, with about **371k parameters** and overall challenge rank **second place for segmentation** [1801.05173]. Another ACDC pipeline uses a **dilated convolutional network** with a **131 × 131** receptive field and eight output channels jointly predicting ED and ES classes for LV, RV, MYO, and background [1708.01141].

Temporal structure has also been exploited. A myocardial sequence-segmentation framework combines **Res U-net** and **ConvLSTM**, reporting that temporal modeling can improve Dice by **up to 2%** on ACDC [2012.14564]. A different line of work introduces **directional feature maps**, learning for each pixel a vector pointing from the nearest boundary into the structure interior, and reports improvement from mean Dice **0.886** to **0.916** and mean Hausdorff distance from **23.009 mm** to **6.693 mm** on an ACDC train/validation split [2007.11349].

More recent methods incorporate larger pretrained or long-range modeling components. **SAMba-UNet** integrates **SAM2**, **VMamba**, and **UNet**, reporting **Dice coefficient of 0.9103** and **HD95 boundary error of 1.0859 mm** on ACDC, with particular gains for **RV** and **MYO** [2505.16304]. A plausible implication is that ACDC continues to function as a comparative platform across successive architectural paradigms, from compact FCNs to hybrid foundation-model systems.

## 4. Diagnosis pipelines and clinically derived features

A dominant ACDC design pattern is to convert segmentations into a patient-level feature vector reflecting routine cardiology measurements. Repeated feature families include **LV/RV volumes at ED and ES**, **ejection fractions**, **myocardial volume or mass**, **volume ratios**, and **myocardial wall thickness statistics** [1708.01141], [1707.00587], [2505.03838].

One feature-based system computes 14 features: patient **height** and **weight**, six volumes, two ejection fractions, and four ratios such as \(V_{RV}^{ED} / V_{LV}^{ED}\) and \(V_{Myo}^{ES} / V_{LV}^{ES}\) [1708.01141]. Another ACDC solution uses **20 features** including **volumes at ED and ES**, **LV and RV ejection fractions**, **LV/RV** and **Myo/LV** volume ratios, and multiple statistics of **myocardial wall thickness** across slices and phases [2505.03838]. The DenseNet-based challenge-winning diagnosis method also derives **myocardial wall thickness variation profile** features at ED and ES and explicitly uses them in a second-stage expert classifier for **MINF vs DCM** [1801.05173].

Radiomics-based diagnosis extends beyond these conventional descriptors. A radiomics study extracts **567 features** from ACDC: **3 patient/global features** plus **188 features per structure** across LV, MYO, and RV, spanning **shape-based**, **first-order intensity**, **GLCM**, **GLRLM**, and **GLSZM** categories [1909.11854]. Sequential forward selection identifies a 10-feature subset that yields **100% accuracy** under leave-one-out cross-validation on the 100 ACDC training cases [1909.11854]. This suggests that ACDC supports not only morphology-function pipelines but also higher-dimensional feature engineering.

End-to-end learning has also been attempted. A multi-task DenseNet/U-Net model jointly learns diagnosis and segmentation from ACDC, reducing classification error from **32%** to **22%** compared with a diagnosis-only baseline [1810.10117]. This suggests that segmentation supervision can regularize diagnosis learning when the dataset is relatively small.

## 5. Reported performance across representative ACDC systems

The literature reports performance using both segmentation metrics and patient-level diagnostic accuracy. For segmentation, the most common overlap metric is the **Dice coefficient**:

\[
\text{Dice}(A,B) = \frac{2|A \cap B|}{|A| + |B|}
\]

as stated in multiple ACDC works [2103.08590], [2507.05783], [2007.11349]. Many studies also report **Hausdorff distance**, **HD95**, **IoU**, or boundary distances [1801.05173], [2505.16304], [2011.07025].

The table below summarizes representative concrete results reported on ACDC.

| Work | Segmentation result | Diagnosis result |
|---|---|---|
| “Automatic Segmentation and Disease Classification Using Cardiac Cine MR Images” [1708.01141] | Average Dice scores **0.94** (LV), **0.88** (RV), **0.87** (myocardium) | **91%** correct disease category |
| “Automatic Cardiac Disease Assessment on cine-MRI via Time-Series Segmentation and Domain Specific Features” [1707.00587] | Test Dice **0.950** (LVC), **0.923** (RVC), **0.911** (LVM) | **92%** on test set |
| “Fully Convolutional Multi-scale Residual DenseNets...” [1801.05173] | **second place for segmentation** in ACDC-2017 | **first place** with **100%** accuracy |
| “Biomechanics-Informed Neural Network for Explainable Cardiovascular Disease Identification” [2507.05783] | Dice **0.945** (LV), **0.908** (RV), **0.905** (MYO) | **98%** train, **100%** test |
| “IntelliCardiac” [2505.03838] | Average Dice **92.56%** | **98%** accuracy |
| “SAMba-UNet” [2505.16304] | Dice **0.9103**, HD95 **1.0859 mm** | Not a diagnosis classifier |

These results are not directly interchangeable because protocols differ. Some studies use the official **100/50** ACDC split [2507.05783], [2505.03838]; some use internal **cross-validation** on the 100 labeled cases [1708.01141], [1707.00587], [1909.11854]; and some focus only on the **70/30** training/development partition or the public training set [2103.08590], [2011.07025]. A plausible implication is that direct leaderboard-style ranking from paper tables alone can be misleading unless the evaluation protocol is matched.

## 6. Interpretability, robustness, and methodological extensions

A significant later development in ACDC research is the shift from pure performance reporting to explainability, quality control, and physically informed modeling. One interpretability study trains a **2D U-Net** for LV/RV/MYO segmentation on ACDC and probes it using **D-TCAV**, a concept-based method that automatically discovers latent concepts from super-pixels and assigns **TCAV scores** per pathology class [2103.08590]. The core finding is that concepts learned by a segmentation-only model are mostly **anatomical**, not pathology-specific, with average maximum–minimum pathology difference across clusters of **3.4%** and a notable outlier in **cluster 56** [2103.08590]. This suggests that anatomy-trained representations do not automatically become disease-discriminative.

Another line of work combines segmentation with **uncertainty estimation** and **local failure detection**. Using ACDC, one study trains Bayesian versions of **DN**, **DRN**, and **U-net**, derives uncertainty maps using **entropy** and **MC-dropout**, and then trains a second CNN to identify local segmentation failures [2011.07025]. Simulated manual correction of detected failure regions yields statistically significant improvements in Dice and Hausdorff distance, and reduces editing time from about **20 minutes** to **less than 2 minutes per patient** in a manual-correction experiment [2011.07025]. This suggests that ACDC can support not just automatic segmentation, but semi-automatic reliability-aware workflows.

Biomechanics-informed approaches move beyond static anatomy. A 2025 method builds a **cascaded CNN-based 3D registration framework** with **Neo-Hookean** regularization on ACDC, estimates local deformation, and derives mechanical features such as voxelwise effective **\(\mu(p)\)** and **\(\kappa(p)\)** for diagnosis [2507.05783]. This explicitly links cardiac motion and tissue mechanics to ACDC disease classes. A plausible implication is that ACDC has become a benchmark for integrating image analysis with physical modeling, not only for segmentation accuracy.

## 7. Role of ACDC in the cardiac MRI research landscape

Across the cited literature, ACDC serves several distinct functions. First, it is a **segmentation benchmark** for LV, RV, and MYO in cine MRI, supporting comparisons across CNNs, transformers, state-space models, and hybrid systems [1801.05173], [2007.11349], [2505.16304]. Second, it is an **automated diagnosis benchmark** in which segmentation-derived features, radiomics, or learned representations are mapped to the five canonical classes [1708.01141], [1707.00587], [1909.11854], [1810.10117]. Third, it is a **methodological sandbox** for interpretability, uncertainty estimation, motion extraction, registration, and biomechanics [2103.08590], [2011.07025], [2103.16695], [2507.05783].

A recurring theme is that ACDC’s disease taxonomy is sufficiently structured to reward clinically motivated features. Many high-performing methods rely on measurements that directly reflect the class definitions: ventricular dilatation for **DCM**, myocardial thickening for **HCM**, regional thinning or altered thickness heterogeneity for **MINF**, and RV enlargement or dysfunction for **ARV/RVA** [1708.01141], [1801.05173], [2505.03838]. This has preserved the relevance of interpretable, feature-driven pipelines even as end-to-end models have become more capable.

At the same time, several works note limitations. Some approaches are developed and validated on **ACDC only** and explicitly identify external validation and domain generalization as future work [2505.03838], [2407.20387]. Some are constrained by the fact that only **ED** and **ES** are manually annotated, even though the underlying data are full cine sequences [1707.00587], [1810.10117]. Others note that ACDC leaderboard-style metrics do not capture interpretability, reliability, or clinical workflow integration [2103.08590], [2011.07025].

Taken together, the corpus suggests that ACDC occupies a foundational place in automated cardiac MRI analysis: it anchors research on segmentation, diagnosis, explainability, and functional modeling within a single, shared benchmark. A plausible implication is that its enduring value lies not only in its leaderboard history but in the way it has structured an entire research program around the relationship between cardiac anatomy, function, pathology, and algorithmic transparency.

Source: https://www.emergentmind.com/topics/automated-cardiac-diagnosis-challenge-acdc