3D brain tumor segmentation with MONAI

!python -c "import monai" || pip install -q -U "monai[nibabel, tqdm]"
!python -c "import wandb" || pip install -q -U wandb

import os

import numpy as np
from tqdm.auto import tqdm
import wandb

from monai.apps import DecathlonDataset
from monai.data import DataLoader, decollate_batch
from monai.losses import DiceLoss
from monai.inferers import sliding_window_inference
from monai.metrics import DiceMetric
from monai.networks.nets import SegResNet
from monai.transforms import (
    Activations,
    AsDiscrete,
    Compose,
    LoadImaged,
    MapTransform,
    NormalizeIntensityd,
    Orientationd,
    RandFlipd,
    RandScaleIntensityd,
    RandShiftIntensityd,
    RandSpatialCropd,
    Spacingd,
    EnsureTyped,
    EnsureChannelFirstd,
)
from monai.utils import set_determinism

import torch

wandb.login()

wandb.init(project="monai-brain-tumor-segmentation")

config = wandb.config
config.seed = 0
config.roi_size = [224, 224, 144]
config.batch_size = 1
config.num_workers = 4
config.max_train_images_visualized = 20
config.max_val_images_visualized = 20
config.dice_loss_smoothen_numerator = 0
config.dice_loss_smoothen_denominator = 1e-5
config.dice_loss_squared_prediction = True
config.dice_loss_target_onehot = False
config.dice_loss_apply_sigmoid = True
config.initial_learning_rate = 1e-4
config.weight_decay = 1e-5
config.max_train_epochs = 50
config.validation_intervals = 1
config.dataset_dir = "./dataset/"
config.checkpoint_dir = "./checkpoints"
config.inference_roi_size = (128, 128, 64)
config.max_prediction_images_visualized = 20

set_determinism(seed=config.seed)

# 디렉토리 생성
os.makedirs(config.dataset_dir, exist_ok=True)
os.makedirs(config.checkpoint_dir, exist_ok=True)

class ConvertToMultiChannelBasedOnBratsClassesd(MapTransform):
    """
    brats 클래스를 기반으로 레이블을 다중 채널로 변환합니다:
    레이블 1은 종양 주위 부종입니다.
    레이블 2는 GD-강화 종양입니다.
    레이블 3은 괴사성 및 비강화 종양 코어입니다.
    가능한 클래스는 TC(종양 코어), WT(전체 종양) 및 ET(강화 종양)입니다.

    참조: https://github.com/Project-MONAI/tutorials/blob/main/3d_segmentation/brats_segmentation_3d.ipynb

    """

    def __call__(self, data):
        d = dict(data)
        for key in self.keys:
            result = []
            # 레이블 2와 레이블 3을 병합하여 TC를 구성합니다.
            result.append(torch.logical_or(d[key] == 2, d[key] == 3))
            # 레이블 1, 2 및 3을 병합하여 WT를 구성합니다.
            result.append(
                torch.logical_or(
                    torch.logical_or(d[key] == 2, d[key] == 3), d[key] == 1
                )
            )
            # 레이블 2는 ET입니다.
            result.append(d[key] == 2)
            d[key] = torch.stack(result, axis=0).float()
        return d

train_transform = Compose(
    [
        # 4개의 Nifti 이미지를 로드하고 함께 쌓습니다.
        LoadImaged(keys=["image", "label"]),
        EnsureChannelFirstd(keys="image"),
        EnsureTyped(keys=["image", "label"]),
        ConvertToMultiChannelBasedOnBratsClassesd(keys="label"),
        Orientationd(keys=["image", "label"], axcodes="RAS"),
        Spacingd(
            keys=["image", "label"],
            pixdim=(1.0, 1.0, 1.0),
            mode=("bilinear", "nearest"),
        ),
        RandSpatialCropd(
            keys=["image", "label"], roi_size=config.roi_size, random_size=False
        ),
        RandFlipd(keys=["image", "label"], prob=0.5, spatial_axis=0),
        RandFlipd(keys=["image", "label"], prob=0.5, spatial_axis=1),
        RandFlipd(keys=["image", "label"], prob=0.5, spatial_axis=2),
        NormalizeIntensityd(keys="image", nonzero=True, channel_wise=True),
        RandScaleIntensityd(keys="image", factors=0.1, prob=1.0),
        RandShiftIntensityd(keys="image", offsets=0.1, prob=1.0),
    ]
)
val_transform = Compose(
    [
        LoadImaged(keys=["image", "label"]),
        EnsureChannelFirstd(keys="image"),
        EnsureTyped(keys=["image", "label"]),
        ConvertToMultiChannelBasedOnBratsClassesd(keys="label"),
        Orientationd(keys=["image", "label"], axcodes="RAS"),
        Spacingd(
            keys=["image", "label"],
            pixdim=(1.0, 1.0, 1.0),
            mode=("bilinear", "nearest"),
        ),
        NormalizeIntensityd(keys="image", nonzero=True, channel_wise=True),
    ]
)

train_dataset = DecathlonDataset(
    root_dir=config.dataset_dir,
    task="Task01_BrainTumour",
    transform=val_transform,
    section="training",
    download=True,
    cache_rate=0.0,
    num_workers=4,
)
val_dataset = DecathlonDataset(
    root_dir=config.dataset_dir,
    task="Task01_BrainTumour",
    transform=val_transform,
    section="validation",
    download=False,
    cache_rate=0.0,
    num_workers=4,
)

table = wandb.Table(columns=["ID", "Image"])

for id, img, label in zip(ids, images, labels):
    mask_img = wandb.Image(
        img,
        masks={
            "prediction": {"mask_data": label, "class_labels": class_labels}
            # ...
        },
    )

    table.add_data(id, img)

wandb.log({"Table": table})

def log_data_samples_into_tables(
    sample_image: np.array,
    sample_label: np.array,
    split: str = None,
    data_idx: int = None,
    table: wandb.Table = None,
):
    num_channels, _, _, num_slices = sample_image.shape
    with tqdm(total=num_slices, leave=False) as progress_bar:
        for slice_idx in range(num_slices):
            ground_truth_wandb_images = []
            for channel_idx in range(num_channels):
                ground_truth_wandb_images.append(
                    masks = {
                        "ground-truth/Tumor-Core": {
                            "mask_data": sample_label[0, :, :, slice_idx],
                            "class_labels": {0: "background", 1: "Tumor Core"},
                        },
                        "ground-truth/Whole-Tumor": {
                            "mask_data": sample_label[1, :, :, slice_idx] * 2,
                            "class_labels": {0: "background", 2: "Whole Tumor"},
                        },
                        "ground-truth/Enhancing-Tumor": {
                            "mask_data": sample_label[2, :, :, slice_idx] * 3,
                            "class_labels": {0: "background", 3: "Enhancing Tumor"},
                        },
                    }
                    wandb.Image(
                        sample_image[channel_idx, :, :, slice_idx],
                        masks=masks,
                    )
                )
            table.add_data(split, data_idx, slice_idx, *ground_truth_wandb_images)
            progress_bar.update(1)
    return table

table = wandb.Table(
    columns=[
        "Split",
        "Data Index",
        "Slice Index",
        "Image-Channel-0",
        "Image-Channel-1",
        "Image-Channel-2",
        "Image-Channel-3",
    ]
)

# train_dataset에 대한 시각화 생성
max_samples = (
    min(config.max_train_images_visualized, len(train_dataset))
    if config.max_train_images_visualized > 0
    else len(train_dataset)
)
progress_bar = tqdm(
    enumerate(train_dataset[:max_samples]),
    total=max_samples,
    desc="Generating Train Dataset Visualizations:",
)
for data_idx, sample in progress_bar:
    sample_image = sample["image"].detach().cpu().numpy()
    sample_label = sample["label"].detach().cpu().numpy()
    table = log_data_samples_into_tables(
        sample_image,
        sample_label,
        split="train",
        data_idx=data_idx,
        table=table,
    )

# val_dataset에 대한 시각화 생성
max_samples = (
    min(config.max_val_images_visualized, len(val_dataset))
    if config.max_val_images_visualized > 0
    else len(val_dataset)
)
progress_bar = tqdm(
    enumerate(val_dataset[:max_samples]),
    total=max_samples,
    desc="Generating Validation Dataset Visualizations:",
)
for data_idx, sample in progress_bar:
    sample_image = sample["image"].detach().cpu().numpy()
    sample_label = sample["label"].detach().cpu().numpy()
    table = log_data_samples_into_tables(
        sample_image,
        sample_label,
        split="val",
        data_idx=data_idx,
        table=table,
    )

# 테이블을 대시보드에 기록
wandb.log({"Tumor-Segmentation-Data": table})

# 트레이닝 데이터셋에 train_transforms 적용
train_dataset.transform = train_transform

# train_loader 생성
train_loader = DataLoader(
    train_dataset,
    batch_size=config.batch_size,
    shuffle=True,
    num_workers=config.num_workers,
)

# val_loader 생성
val_loader = DataLoader(
    val_dataset,
    batch_size=config.batch_size,
    shuffle=False,
    num_workers=config.num_workers,
)

device = torch.device("cuda:0")

# 모델 생성
model = SegResNet(
    blocks_down=[1, 2, 2, 4],
    blocks_up=[1, 1, 1],
    init_filters=16,
    in_channels=4,
    out_channels=3,
    dropout_prob=0.2,
).to(device)

# 옵티마이저 생성
optimizer = torch.optim.Adam(
    model.parameters(),
    config.initial_learning_rate,
    weight_decay=config.weight_decay,
)

# 학습률 스케줄러 생성
lr_scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(
    optimizer, T_max=config.max_train_epochs
)

loss_function = DiceLoss(
    smooth_nr=config.dice_loss_smoothen_numerator,
    smooth_dr=config.dice_loss_smoothen_denominator,
    squared_pred=config.dice_loss_squared_prediction,
    to_onehot_y=config.dice_loss_target_onehot,
    sigmoid=config.dice_loss_apply_sigmoid,
)

dice_metric = DiceMetric(include_background=True, reduction="mean")
dice_metric_batch = DiceMetric(include_background=True, reduction="mean_batch")
post_trans = Compose([Activations(sigmoid=True), AsDiscrete(threshold=0.5)])

# 자동 혼합 정밀도를 사용하여 트레이닝 가속화
scaler = torch.cuda.amp.GradScaler()
torch.backends.cudnn.benchmark = True

def inference(model, input):
    def _compute(input):
        return sliding_window_inference(
            inputs=input,
            roi_size=(240, 240, 160),
            sw_batch_size=1,
            predictor=model,
            overlap=0.5,
        )

    with torch.cuda.amp.autocast():
        return _compute(input)

wandb.define_metric("epoch/epoch_step")
wandb.define_metric("epoch/*", step_metric="epoch/epoch_step")
wandb.define_metric("batch/batch_step")
wandb.define_metric("batch/*", step_metric="batch/batch_step")
wandb.define_metric("validation/validation_step")
wandb.define_metric("validation/*", step_metric="validation/validation_step")

batch_step = 0
validation_step = 0
metric_values = []
metric_values_tumor_core = []
metric_values_whole_tumor = []
metric_values_enhanced_tumor = []

# W&B Artifact 오브젝트 정의
artifact = wandb.Artifact(
    name=f"{wandb.run.id}-checkpoint", type="model"
)

epoch_progress_bar = tqdm(range(config.max_train_epochs), desc="Training:")

for epoch in epoch_progress_bar:
    model.train()
    epoch_loss = 0

    total_batch_steps = len(train_dataset) // train_loader.batch_size
    batch_progress_bar = tqdm(train_loader, total=total_batch_steps, leave=False)
    
    # 트레이닝 단계
    for batch_data in batch_progress_bar:
        inputs, labels = (
            batch_data["image"].to(device),
            batch_data["label"].to(device),
        )
        optimizer.zero_grad()
        with torch.cuda.amp.autocast():
            outputs = model(inputs)
            loss = loss_function(outputs, labels)
        scaler.scale(loss).backward()
        scaler.step(optimizer)
        scaler.update()
        epoch_loss += loss.item()
        batch_progress_bar.set_description(f"train_loss: {loss.item():.4f}:")
        ## 배치별 트레이닝 손실을 W&B에 기록
        wandb.log({"batch/batch_step": batch_step, "batch/train_loss": loss.item()})
        batch_step += 1

    lr_scheduler.step()
    epoch_loss /= total_batch_steps
    ## 배치별 트레이닝 손실과 학습률을 W&B에 기록
    wandb.log(
        {
            "epoch/epoch_step": epoch,
            "epoch/mean_train_loss": epoch_loss,
            "epoch/learning_rate": lr_scheduler.get_last_lr()[0],
        }
    )
    epoch_progress_bar.set_description(f"Training: train_loss: {epoch_loss:.4f}:")

    # 유효성 검사 및 모델 체크포인트 단계
    if (epoch + 1) % config.validation_intervals == 0:
        model.eval()
        with torch.no_grad():
            for val_data in val_loader:
                val_inputs, val_labels = (
                    val_data["image"].to(device),
                    val_data["label"].to(device),
                )
                val_outputs = inference(model, val_inputs)
                val_outputs = [post_trans(i) for i in decollate_batch(val_outputs)]
                dice_metric(y_pred=val_outputs, y=val_labels)
                dice_metric_batch(y_pred=val_outputs, y=val_labels)

            metric_values.append(dice_metric.aggregate().item())
            metric_batch = dice_metric_batch.aggregate()
            metric_values_tumor_core.append(metric_batch[0].item())
            metric_values_whole_tumor.append(metric_batch[1].item())
            metric_values_enhanced_tumor.append(metric_batch[2].item())
            dice_metric.reset()
            dice_metric_batch.reset()

            checkpoint_path = os.path.join(config.checkpoint_dir, "model.pth")
            torch.save(model.state_dict(), checkpoint_path)
            
            # W&B Artifacts를 사용하여 모델 체크포인트를 기록하고 버전 관리합니다.
            artifact.add_file(local_path=checkpoint_path)
            wandb.log_artifact(artifact, aliases=[f"epoch_{epoch}"])

            # 유효성 검사 메트릭을 W&B 대시보드에 기록합니다.
            wandb.log(
                {
                    "validation/validation_step": validation_step,
                    "validation/mean_dice": metric_values[-1],
                    "validation/mean_dice_tumor_core": metric_values_tumor_core[-1],
                    "validation/mean_dice_whole_tumor": metric_values_whole_tumor[-1],
                    "validation/mean_dice_enhanced_tumor": metric_values_enhanced_tumor[-1],
                }
            )
            validation_step += 1


# 이 Artifact가 기록을 마칠 때까지 기다립니다.
artifact.wait()

model_artifact = wandb.use_artifact(
    "geekyrakshit/monai-brain-tumor-segmentation/d5ex6n4a-checkpoint:v49",
    type="model",
)
model_artifact_dir = model_artifact.download()
model.load_state_dict(torch.load(os.path.join(model_artifact_dir, "model.pth")))
model.eval()

def log_predictions_into_tables(
    sample_image: np.array,
    sample_label: np.array,
    predicted_label: np.array,
    split: str = None,
    data_idx: int = None,
    table: wandb.Table = None,
):
    num_channels, _, _, num_slices = sample_image.shape
    with tqdm(total=num_slices, leave=False) as progress_bar:
        for slice_idx in range(num_slices):
            wandb_images = []
            for channel_idx in range(num_channels):
                wandb_images += [
                    wandb.Image(
                        sample_image[channel_idx, :, :, slice_idx],
                        masks={
                            "ground-truth/Tumor-Core": {
                                "mask_data": sample_label[0, :, :, slice_idx],
                                "class_labels": {0: "background", 1: "Tumor Core"},
                            },
                            "prediction/Tumor-Core": {
                                "mask_data": predicted_label[0, :, :, slice_idx] * 2,
                                "class_labels": {0: "background", 2: "Tumor Core"},
                            },
                        },
                    ),
                    wandb.Image(
                        sample_image[channel_idx, :, :, slice_idx],
                        masks={
                            "ground-truth/Whole-Tumor": {
                                "mask_data": sample_label[1, :, :, slice_idx],
                                "class_labels": {0: "background", 1: "Whole Tumor"},
                            },
                            "prediction/Whole-Tumor": {
                                "mask_data": predicted_label[1, :, :, slice_idx] * 2,
                                "class_labels": {0: "background", 2: "Whole Tumor"},
                            },
                        },
                    ),
                    wandb.Image(
                        sample_image[channel_idx, :, :, slice_idx],
                        masks={
                            "ground-truth/Enhancing-Tumor": {
                                "mask_data": sample_label[2, :, :, slice_idx],
                                "class_labels": {0: "background", 1: "Enhancing Tumor"},
                            },
                            "prediction/Enhancing-Tumor": {
                                "mask_data": predicted_label[2, :, :, slice_idx] * 2,
                                "class_labels": {0: "background", 2: "Enhancing Tumor"},
                            },
                        },
                    ),
                ]
            table.add_data(split, data_idx, slice_idx, *wandb_images)
            progress_bar.update(1)
    return table

# 예측 테이블 생성
prediction_table = wandb.Table(
    columns=[
        "Split",
        "Data Index",
        "Slice Index",
        "Image-Channel-0/Tumor-Core",
        "Image-Channel-1/Tumor-Core",
        "Image-Channel-2/Tumor-Core",
        "Image-Channel-3/Tumor-Core",
        "Image-Channel-0/Whole-Tumor",
        "Image-Channel-1/Whole-Tumor",
        "Image-Channel-2/Whole-Tumor",
        "Image-Channel-3/Whole-Tumor",
        "Image-Channel-0/Enhancing-Tumor",
        "Image-Channel-1/Enhancing-Tumor",
        "Image-Channel-2/Enhancing-Tumor",
        "Image-Channel-3/Enhancing-Tumor",
    ]
)

# 추론 및 시각화 수행
with torch.no_grad():
    config.max_prediction_images_visualized
    max_samples = (
        min(config.max_prediction_images_visualized, len(val_dataset))
        if config.max_prediction_images_visualized > 0
        else len(val_dataset)
    )
    progress_bar = tqdm(
        enumerate(val_dataset[:max_samples]),
        total=max_samples,
        desc="Generating Predictions:",
    )
    for data_idx, sample in progress_bar:
        val_input = sample["image"].unsqueeze(0).to(device)
        val_output = inference(model, val_input)
        val_output = post_trans(val_output[0])
        prediction_table = log_predictions_into_tables(
            sample_image=sample["image"].cpu().numpy(),
            sample_label=sample["label"].cpu().numpy(),
            predicted_label=val_output.cpu().numpy(),
            data_idx=data_idx,
            split="validation",
            table=prediction_table,
        )

    wandb.log({"Predictions/Tumor-Segmentation-Data": prediction_table})


# 실험 종료
wandb.finish()