Spaces:
Sleeping
Sleeping
File size: 5,974 Bytes
a8e4c2f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 |
import numpy as np
import pandas as pd
from scipy.signal import resample
from sklearn.preprocessing import scale
import soundfile as sf
from gemini import query_gemini_rest
import librosa
import tempfile
EXPECTED_LEN = 256
STEP = 128
PCG_LABELS = [
"Normal",
"Aortic Stenosis",
"Mitral Stenosis",
"Mitral Valve Prolapse",
"Pericardial Murmurs"
]
LABELS_EMG = ["healthy", "myopathy", "neuropathy"]
def load_uploaded_file(file, signal_type="ECG") -> np.ndarray:
name = file.name.lower()
if signal_type in ("ECG", "EMG"):
text = file.read().decode("utf-8").strip()
if "," in text:
vals = [float(x) for x in text.split(",") if x.strip()]
else:
vals = [float(x) for x in text.splitlines() if x.strip()]
return np.array(vals, dtype=np.float32)
if signal_type == "VAG":
if name.endswith(".csv"):
df = pd.read_csv(file)
features = [
"rms_amplitude",
"peak_frequency",
"spectral_entropy",
"zero_crossing_rate",
"mean_frequency",
]
return df[features].iloc[0].values.astype(np.float32)
elif name.endswith(".npy"):
return np.load(file)
elif name.endswith(".wav"):
data, _ = sf.read(file)
return data.astype(np.float32)
raise ValueError("Unsupported VAG file format.")
if signal_type == "PCG" and name.endswith((".wav", ".flac", ".mp3")):
data, _ = sf.read(file)
if data.ndim > 1:
data = data[:, 0]
return data.astype(np.float32)
raise ValueError("Unsupported file format.")
def preprocess_signal(x: np.ndarray) -> np.ndarray:
if x.size != EXPECTED_LEN:
x = resample(x, EXPECTED_LEN)
return scale(x).astype(np.float32)
def segment_signal(raw: np.ndarray) -> np.ndarray:
raw = preprocess_signal(raw)
seg = raw.reshape(EXPECTED_LEN, 1)
return seg[np.newaxis, ...]
PCG_INPUT_LEN = 995
def preprocess_pcg_waveform(wave: np.ndarray) -> np.ndarray:
if wave.ndim > 1:
wave = wave.mean(axis=1)
if len(wave) < PCG_INPUT_LEN:
wave = np.pad(wave, (0, PCG_INPUT_LEN - len(wave)))
else:
wave = wave[:PCG_INPUT_LEN]
wave = (wave - np.mean(wave)) / (np.std(wave) + 1e-8)
return wave.astype(np.float32)
def analyze_pcg_signal(file, model, gemini_key=None):
signal, _ = sf.read(file)
signal = preprocess_pcg_waveform(signal)
input_data = signal.reshape(1, PCG_INPUT_LEN, 1)
preds = model.predict(input_data, verbose=0)[0]
labels = [
"Normal",
"Aortic Stenosis",
"Mitral Stenosis",
"Mitral Valve Prolapse",
"Pericardial Murmurs",
]
idx = int(np.argmax(preds))
confidence = float(preds[idx])
label = labels[idx]
gem_txt = None
if gemini_key:
gem_txt = query_gemini_rest("PCG", label, confidence, gemini_key)
return label, label, confidence, gem_txt
def pcg_to_features(file_obj, target_sr=16000, n_mels=128, n_frames=112):
with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp:
tmp.write(file_obj.read())
tmp_path = tmp.name
y, sr = librosa.load(tmp_path, sr=target_sr, mono=True)
mel = librosa.feature.melspectrogram(y=y, sr=sr, n_fft=512, hop_length=256, n_mels=n_mels)
logmel = librosa.power_to_db(mel, ref=np.max)
if logmel.shape[1] < n_frames:
pad_width = n_frames - logmel.shape[1]
pad = np.zeros((n_mels, pad_width))
logmel = np.hstack((logmel, pad))
else:
logmel = logmel[:, :n_frames]
feat = logmel.flatten().astype(np.float32)
return feat[np.newaxis, ...]
def analyze_emg_signal(file, model, gemini_key=""):
raw = load_uploaded_file(file, signal_type="EMG")
WINDOW = 1000
wins = []
if len(raw) < WINDOW:
pad = np.pad(raw, (0, WINDOW - len(raw)))
wins.append(((pad - pad.mean()) / (pad.std()+1e-6)).reshape(WINDOW, 1))
else:
for i in range(0, len(raw) - WINDOW + 1, WINDOW):
win = raw[i:i+WINDOW]
win = (win - win.mean()) / (win.std() + 1e-6)
wins.append(win.reshape(WINDOW, 1))
X = np.array(wins, dtype=np.float32)
preds = model.predict(X, verbose=0)
classes = np.argmax(preds, axis=1)
final = int(np.bincount(classes).argmax())
conf = float(preds[:, final].mean())
human = LABELS_EMG[final]
gemini_txt = None
if gemini_key:
gemini_txt = query_gemini_rest("EMG", human, conf, gemini_key)
return human, conf, gemini_txt
FEATURE_COLS = [
"rms_amplitude",
"peak_frequency",
"spectral_entropy",
"zero_crossing_rate",
"mean_frequency",
]
def vag_to_features(file_obj) -> np.ndarray:
df = pd.read_csv(file_obj)
x = df[FEATURE_COLS].iloc[0].values.astype(np.float32)
return x.reshape(1, -1)
def predict_vag_from_features(file_obj, model_bundle, gemini_key=""):
model = model_bundle["model"]
scaler = model_bundle["scaler"]
encoder = model_bundle["encoder"]
x = vag_to_features(file_obj)
x_s = scaler.transform(x)
prob = model.predict_proba(x_s)[0]
idx = int(np.argmax(prob))
conf = float(prob[idx])
label = encoder.inverse_transform([idx])[0].title()
gem_note = (
query_gemini_rest("VAG", label, conf, gemini_key)
if gemini_key else None
)
return label, label, conf, gem_note |