Xiao Furen
2ae08ac2cd
Refactor the preprocessing and segmentation pipeline to handle AP orientation variations and improve anatomical boundary detection. Key changes include: - Implement automated AP orientation detection in `process_single_image` to handle prone scans by flipping CT and labels when necessary. - Enhance `segment_spinous_process` using a gap-based approach to identify the spinal canal, providing more stable thresholds for spinous process and vertebral body segmentation. - Improve optimization search space by using the vertebral body (VBODY) projection for x/z bounding box calculation instead of the whole bone. - Refactor `render_bone_figure` to unify 2D/3D visualization and support detailed anatomical coloring (VBODY, spinous process). - Update `cl_score_torch_xfr` with more robust penalty handling for out-of-bone and null-voxel regions. - Add `retry_robust` utility to handle transient NFS file system errors. - Update `xfr_preprocess.py` to include anatomical segmentation coloring in rotated level visualizations.
68 lines
1.9 KiB
Python
68 lines
1.9 KiB
Python
import errno
|
||
import os
|
||
import time
|
||
|
||
import numpy as np
|
||
import matplotlib.pyplot as plt
|
||
|
||
|
||
def retry_robust(fn, *args, retries=20, delay=0.5, **kwargs):
|
||
"""對 ENOENT/EEXIST 重試：NFS 上輸出樹被外部刪除（或多 worker 併發建同一
|
||
output 目錄）會有短暫的 ENOENT 窗口，重試可恢復；其他錯誤直接丟出。"""
|
||
for i in range(retries):
|
||
try:
|
||
return fn(*args, **kwargs)
|
||
except OSError as e:
|
||
if e.errno not in (errno.ENOENT, errno.EEXIST) or i == retries - 1:
|
||
raise
|
||
time.sleep(delay)
|
||
|
||
|
||
def get_unique_filepath(path: str) -> str:
|
||
"""
|
||
如果檔案已存在，自動加 _1, _2... 避免覆蓋
|
||
"""
|
||
current_path = path
|
||
count = 1
|
||
|
||
base_name, file_ext = os.path.splitext(path)
|
||
|
||
while os.path.exists(current_path):
|
||
current_path = f"{base_name}_{count}{file_ext}"
|
||
count += 1
|
||
|
||
return current_path
|
||
|
||
def save_with_unique_name(folder, label_str, way, diameter_l, length_l, diameter_r, length_r, swarm_size, max_iter):
|
||
|
||
base_name = f'{label_str}_{way}_L{diameter_l}_{length_l}_R{diameter_r}_{length_r}_{swarm_size}_{max_iter}.png'
|
||
file_path = os.path.join(folder, base_name)
|
||
|
||
count = 1
|
||
while os.path.exists(file_path):
|
||
file_name, file_ext = os.path.splitext(base_name)
|
||
file_path = os.path.join(folder, f"{file_name}_{count}{file_ext}")
|
||
count += 1
|
||
|
||
return file_path
|
||
|
||
def pad_rgb_to_shape(rgb, target_hw, pad_value=0.0):
|
||
"""Pad RGB image (H,W,3) to target (H,W), centered."""
|
||
h, w, c = rgb.shape
|
||
H, W = target_hw
|
||
assert c == 3
|
||
|
||
if h > H or w > W:
|
||
raise ValueError(f"target {target_hw} smaller than rgb {(h,w)}")
|
||
|
||
pad_h1 = (H - h) // 2
|
||
pad_h2 = H - h - pad_h1
|
||
pad_w1 = (W - w) // 2
|
||
pad_w2 = W - w - pad_w1
|
||
|
||
return np.pad(
|
||
rgb,
|
||
((pad_h1, pad_h2), (pad_w1, pad_w2), (0, 0)),
|
||
mode="constant",
|
||
constant_values=pad_value
|
||
)
|