เพิ่มตรวจจับเอียง test 001

app.py

@@ -49,6 +49,44 @@ def getMasks(landmarks, h, w):
     return RL_mask, LL_mask, H_mask
 
 
+def calculate_image_tilt(landmarks):
+    """Calculate image tilt angle based on lung symmetry"""
+    RL = landmarks[0:44]  # Right lung
+    LL = landmarks[44:94]  # Left lung
+    
+    # Find the topmost points of both lungs
+    rl_top_idx = np.argmin(RL[:, 1])
+    ll_top_idx = np.argmin(LL[:, 1])
+    
+    rl_top = RL[rl_top_idx]
+    ll_top = LL[ll_top_idx]
+    
+    # Calculate angle between the line connecting lung tops and horizontal
+    dx = ll_top[0] - rl_top[0]
+    dy = ll_top[1] - rl_top[1]
+    
+    angle_rad = np.arctan2(dy, dx)
+    angle_deg = np.degrees(angle_rad)
+    
+    return angle_deg, rl_top, ll_top
+
+def rotate_points(points, angle_deg, center):
+    """Rotate points around a center by given angle"""
+    angle_rad = np.radians(-angle_deg)  # Negative to correct the tilt
+    cos_a = np.cos(angle_rad)
+    sin_a = np.sin(angle_rad)
+    
+    # Translate to origin
+    translated = points - center
+    
+    # Rotate
+    rotated = np.zeros_like(translated)
+    rotated[:, 0] = translated[:, 0] * cos_a - translated[:, 1] * sin_a
+    rotated[:, 1] = translated[:, 0] * sin_a + translated[:, 1] * cos_a
+    
+    # Translate back
+    return rotated + center
+
 def drawOnTop(img, landmarks, original_shape):
     h, w = original_shape
     output = getDenseMask(landmarks, h, w)
@@ -62,6 +100,26 @@ def drawOnTop(img, landmarks, original_shape):
 
     RL, LL, H = landmarks[0:44], landmarks[44:94], landmarks[94:]
 
+    # Calculate image tilt and correct it for measurements
+    tilt_angle, rl_top, ll_top = calculate_image_tilt(landmarks)
+    image_center = np.array([w/2, h/2])
+    
+    # Draw tilt reference line (green)
+    image = cv2.line(image, (int(rl_top[0]), int(rl_top[1])), (int(ll_top[0]), int(ll_top[1])), (0, 1, 0), 1)
+    
+    # Add tilt angle text
+    tilt_text = f"Tilt: {tilt_angle:.1f}°"
+    cv2.putText(image, tilt_text, (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 1, 0), 2)
+    
+    # Correct landmarks for tilt
+    if abs(tilt_angle) > 2:  # Only correct if tilt is significant
+        RL_corrected = rotate_points(RL, tilt_angle, image_center)
+        LL_corrected = rotate_points(LL, tilt_angle, image_center)
+        H_corrected = rotate_points(H, tilt_angle, image_center)
+        cv2.putText(image, "Tilt Corrected", (10, 60), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (1, 1, 0), 2)
+    else:
+        RL_corrected, LL_corrected, H_corrected = RL, LL, H
+
     # Draw the landmarks as dots
     for l in RL:
         image = cv2.circle(image, (int(l[0]), int(l[1])), 5, (1, 0, 1), -1)
@@ -70,11 +128,11 @@ def drawOnTop(img, landmarks, original_shape):
     for l in H:
         image = cv2.circle(image, (int(l[0]), int(l[1])), 5, (1, 1, 0), -1)
 
-    # Draw horizontal lines for CTR calculation
-    # Heart (red line)
-    heart_xmin = int(np.min(H[:, 0]))
-    heart_xmax = int(np.max(H[:, 0]))
-    heart_y = int(np.mean([H[np.argmin(H[:, 0]), 1], H[np.argmax(H[:, 0]), 1]]))
+    # Draw horizontal lines for CTR calculation using corrected landmarks
+    # Heart (red line) - using corrected coordinates
+    heart_xmin = int(np.min(H_corrected[:, 0]))
+    heart_xmax = int(np.max(H_corrected[:, 0]))
+    heart_y = int(np.mean([H_corrected[np.argmin(H_corrected[:, 0]), 1], H_corrected[np.argmax(H_corrected[:, 0]), 1]]))
     image = cv2.line(image, (heart_xmin, heart_y), (heart_xmax, heart_y), (1, 0, 0), 2)
     
     # Add vertical lines at heart endpoints to verify widest points
@@ -82,24 +140,27 @@ def drawOnTop(img, landmarks, original_shape):
     image = cv2.line(image, (heart_xmin, heart_y - line_length), (heart_xmin, heart_y + line_length), (1, 0, 0), 2)
     image = cv2.line(image, (heart_xmax, heart_y - line_length), (heart_xmax, heart_y + line_length), (1, 0, 0), 2)
 
-    # Thorax (blue line)
-    thorax_xmin = int(min(np.min(RL[:, 0]), np.min(LL[:, 0])))
-    thorax_xmax = int(max(np.max(RL[:, 0]), np.max(LL[:, 0])))
+    # Thorax (blue line) - using corrected coordinates
+    thorax_xmin = int(min(np.min(RL_corrected[:, 0]), np.min(LL_corrected[:, 0])))
+    thorax_xmax = int(max(np.max(RL_corrected[:, 0]), np.max(LL_corrected[:, 0])))
     # Find y at leftmost and rightmost points
-    if np.min(RL[:, 0]) < np.min(LL[:, 0]):
-        thorax_ymin = RL[np.argmin(RL[:, 0]), 1]
+    if np.min(RL_corrected[:, 0]) < np.min(LL_corrected[:, 0]):
+        thorax_ymin = RL_corrected[np.argmin(RL_corrected[:, 0]), 1]
     else:
-        thorax_ymin = LL[np.argmin(LL[:, 0]), 1]
-    if np.max(RL[:, 0]) > np.max(LL[:, 0]):
-        thorax_ymax = RL[np.argmax(RL[:, 0]), 1]
+        thorax_ymin = LL_corrected[np.argmin(LL_corrected[:, 0]), 1]
+    if np.max(RL_corrected[:, 0]) > np.max(LL_corrected[:, 0]):
+        thorax_ymax = RL_corrected[np.argmax(RL_corrected[:, 0]), 1]
     else:
-        thorax_ymax = LL[np.argmax(LL[:, 0]), 1]
+        thorax_ymax = LL_corrected[np.argmax(LL_corrected[:, 0]), 1]
     thorax_y = int(np.mean([thorax_ymin, thorax_ymax]))
     image = cv2.line(image, (thorax_xmin, thorax_y), (thorax_xmax, thorax_y), (0, 0, 1), 2)
     
     # Add vertical lines at thorax endpoints to verify widest points
     image = cv2.line(image, (thorax_xmin, thorax_y - line_length), (thorax_xmin, thorax_y + line_length), (0, 0, 1), 2)
     image = cv2.line(image, (thorax_xmax, thorax_y - line_length), (thorax_xmax, thorax_y + line_length), (0, 0, 1), 2)
+    
+    # Store corrected landmarks for CTR calculation
+    return image, (RL_corrected, LL_corrected, H_corrected, tilt_angle)
 
     return image
 
@@ -186,14 +247,19 @@ def removePreprocess(output, info):
     return output
 
 
-def calculate_ctr(landmarks):
-    H = landmarks[94:]
-    RL = landmarks[0:44]
-    LL = landmarks[44:94]
+def calculate_ctr(landmarks, corrected_landmarks=None):
+    if corrected_landmarks is not None:
+        RL, LL, H, tilt_angle = corrected_landmarks
+    else:
+        H = landmarks[94:]
+        RL = landmarks[0:44]
+        LL = landmarks[44:94]
+        tilt_angle = 0
+    
     cardiac_width = np.max(H[:, 0]) - np.min(H[:, 0])
     thoracic_width = max(np.max(RL[:, 0]), np.max(LL[:, 0])) - min(np.min(RL[:, 0]), np.min(LL[:, 0]))
     ctr = cardiac_width / thoracic_width if thoracic_width > 0 else 0
-    return round(ctr, 3)
+    return round(ctr, 3), abs(tilt_angle)
 
 
 def segment(input_img):
@@ -216,22 +282,30 @@ def segment(input_img):
 
     output = output.astype('int')
 
-    outseg = drawOnTop(input_img, output, original_shape)
+    outseg, corrected_data = drawOnTop(input_img, output, original_shape)
 
     seg_to_save = (outseg.copy() * 255).astype('uint8')
     cv2.imwrite("tmp/overlap_segmentation.png", cv2.cvtColor(seg_to_save, cv2.COLOR_RGB2BGR))
 
-    ctr_value = calculate_ctr(output)
+    ctr_value, tilt_angle = calculate_ctr(output, corrected_data)
+    
+    # Add tilt warning to interpretation
+    tilt_warning = ""
+    if tilt_angle > 5:
+        tilt_warning = f" (⚠️ Image tilted {tilt_angle:.1f}° - measurement corrected)"
+    elif tilt_angle > 2:
+        tilt_warning = f" (Image tilted {tilt_angle:.1f}° - corrected)"
+    
     if ctr_value < 0.5:
-        interpretation = "Normal"
+        interpretation = f"Normal{tilt_warning}"
     elif 0.51 <= ctr_value <= 0.55:
-        interpretation = "Mild Cardiomegaly (CTR 51-55%)"
+        interpretation = f"Mild Cardiomegaly (CTR 51-55%){tilt_warning}"
     elif 0.56 <= ctr_value <= 0.60:
-        interpretation = "Moderate Cardiomegaly (CTR 56-60%)"
+        interpretation = f"Moderate Cardiomegaly (CTR 56-60%){tilt_warning}"
     elif ctr_value > 0.60:
-        interpretation = "Severe Cardiomegaly (CTR > 60%)"
+        interpretation = f"Severe Cardiomegaly (CTR > 60%){tilt_warning}"
     else:
-        interpretation = "Cardiomegaly"
+        interpretation = f"Cardiomegaly{tilt_warning}"
 
     return outseg, "tmp/overlap_segmentation.png", ctr_value, interpretation